summaryrefslogtreecommitdiffstats
path: root/tools/include
diff options
context:
space:
mode:
authorDaniel Baumann <daniel.baumann@progress-linux.org>2024-04-11 08:27:49 +0000
committerDaniel Baumann <daniel.baumann@progress-linux.org>2024-04-11 08:27:49 +0000
commitace9429bb58fd418f0c81d4c2835699bddf6bde6 (patch)
treeb2d64bc10158fdd5497876388cd68142ca374ed3 /tools/include
parentInitial commit. (diff)
downloadlinux-ace9429bb58fd418f0c81d4c2835699bddf6bde6.tar.xz
linux-ace9429bb58fd418f0c81d4c2835699bddf6bde6.zip
Adding upstream version 6.6.15.upstream/6.6.15
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'tools/include')
-rw-r--r--tools/include/asm-generic/atomic-gcc.h95
-rw-r--r--tools/include/asm-generic/barrier.h40
-rw-r--r--tools/include/asm-generic/bitops.h31
-rw-r--r--tools/include/asm-generic/bitops/__ffs.h45
-rw-r--r--tools/include/asm-generic/bitops/__ffz.h12
-rw-r--r--tools/include/asm-generic/bitops/__fls.h44
-rw-r--r--tools/include/asm-generic/bitops/arch_hweight.h26
-rw-r--r--tools/include/asm-generic/bitops/atomic.h15
-rw-r--r--tools/include/asm-generic/bitops/const_hweight.h44
-rw-r--r--tools/include/asm-generic/bitops/fls.h42
-rw-r--r--tools/include/asm-generic/bitops/fls64.h37
-rw-r--r--tools/include/asm-generic/bitops/hweight.h8
-rw-r--r--tools/include/asm-generic/bitops/non-atomic.h115
-rw-r--r--tools/include/asm-generic/bitsperlong.h24
-rw-r--r--tools/include/asm-generic/hugetlb_encode.h37
-rw-r--r--tools/include/asm-generic/unaligned.h23
-rw-r--r--tools/include/asm/alternative.h9
-rw-r--r--tools/include/asm/atomic.h11
-rw-r--r--tools/include/asm/barrier.h63
-rw-r--r--tools/include/asm/bug.h46
-rw-r--r--tools/include/asm/export.h7
-rw-r--r--tools/include/asm/sections.h4
-rw-r--r--tools/include/linux/arm-smccc.h193
-rw-r--r--tools/include/linux/atomic.h15
-rw-r--r--tools/include/linux/bitfield.h176
-rw-r--r--tools/include/linux/bitmap.h152
-rw-r--r--tools/include/linux/bitops.h90
-rw-r--r--tools/include/linux/bits.h45
-rw-r--r--tools/include/linux/btf_ids.h208
-rw-r--r--tools/include/linux/bug.h11
-rw-r--r--tools/include/linux/build_bug.h91
-rw-r--r--tools/include/linux/cache.h10
-rw-r--r--tools/include/linux/compiler-gcc.h42
-rw-r--r--tools/include/linux/compiler.h211
-rw-r--r--tools/include/linux/compiler_types.h43
-rw-r--r--tools/include/linux/const.h14
-rw-r--r--tools/include/linux/coresight-pmu.h60
-rw-r--r--tools/include/linux/ctype.h82
-rw-r--r--tools/include/linux/debugfs.h5
-rw-r--r--tools/include/linux/delay.h4
-rw-r--r--tools/include/linux/err.h75
-rw-r--r--tools/include/linux/export.h7
-rw-r--r--tools/include/linux/filter.h341
-rw-r--r--tools/include/linux/find.h177
-rw-r--r--tools/include/linux/ftrace.h4
-rw-r--r--tools/include/linux/gfp.h13
-rw-r--r--tools/include/linux/gfp_types.h1
-rw-r--r--tools/include/linux/hash.h101
-rw-r--r--tools/include/linux/hashtable.h149
-rw-r--r--tools/include/linux/interrupt.h4
-rw-r--r--tools/include/linux/interval_tree_generic.h187
-rw-r--r--tools/include/linux/io.h5
-rw-r--r--tools/include/linux/jhash.h175
-rw-r--r--tools/include/linux/kallsyms.h34
-rw-r--r--tools/include/linux/kconfig.h67
-rw-r--r--tools/include/linux/kern_levels.h26
-rw-r--r--tools/include/linux/kernel.h108
-rw-r--r--tools/include/linux/linkage.h4
-rw-r--r--tools/include/linux/list.h783
-rw-r--r--tools/include/linux/list_sort.h14
-rw-r--r--tools/include/linux/log2.h175
-rw-r--r--tools/include/linux/math.h25
-rw-r--r--tools/include/linux/math64.h75
-rw-r--r--tools/include/linux/mm.h40
-rw-r--r--tools/include/linux/module.h12
-rw-r--r--tools/include/linux/mutex.h4
-rw-r--r--tools/include/linux/nmi.h0
-rw-r--r--tools/include/linux/numa.h16
-rw-r--r--tools/include/linux/objtool_types.h57
-rw-r--r--tools/include/linux/overflow.h144
-rw-r--r--tools/include/linux/pfn.h10
-rw-r--r--tools/include/linux/poison.h89
-rw-r--r--tools/include/linux/rbtree.h345
-rw-r--r--tools/include/linux/rbtree_augmented.h308
-rw-r--r--tools/include/linux/rcu.h25
-rw-r--r--tools/include/linux/refcount.h152
-rw-r--r--tools/include/linux/ring_buffer.h74
-rw-r--r--tools/include/linux/rwsem.h40
-rw-r--r--tools/include/linux/sched/clock.h4
-rw-r--r--tools/include/linux/sched/mm.h6
-rw-r--r--tools/include/linux/sched/task.h4
-rw-r--r--tools/include/linux/seq_file.h6
-rw-r--r--tools/include/linux/sizes.h48
-rw-r--r--tools/include/linux/slab.h48
-rw-r--r--tools/include/linux/spinlock.h40
-rw-r--r--tools/include/linux/static_call_types.h103
-rw-r--r--tools/include/linux/string.h50
-rw-r--r--tools/include/linux/stringify.h13
-rw-r--r--tools/include/linux/time64.h13
-rw-r--r--tools/include/linux/types.h101
-rw-r--r--tools/include/linux/unaligned/packed_struct.h47
-rw-r--r--tools/include/linux/zalloc.h12
-rw-r--r--tools/include/nolibc/.gitignore1
-rw-r--r--tools/include/nolibc/Makefile91
-rw-r--r--tools/include/nolibc/arch-aarch64.h157
-rw-r--r--tools/include/nolibc/arch-arm.h199
-rw-r--r--tools/include/nolibc/arch-i386.h180
-rw-r--r--tools/include/nolibc/arch-loongarch.h164
-rw-r--r--tools/include/nolibc/arch-mips.h195
-rw-r--r--tools/include/nolibc/arch-powerpc.h221
-rw-r--r--tools/include/nolibc/arch-riscv.h160
-rw-r--r--tools/include/nolibc/arch-s390.h186
-rw-r--r--tools/include/nolibc/arch-x86_64.h176
-rw-r--r--tools/include/nolibc/arch.h38
-rw-r--r--tools/include/nolibc/compiler.h25
-rw-r--r--tools/include/nolibc/crt.h62
-rw-r--r--tools/include/nolibc/ctype.h102
-rw-r--r--tools/include/nolibc/errno.h28
-rw-r--r--tools/include/nolibc/nolibc.h111
-rw-r--r--tools/include/nolibc/signal.h25
-rw-r--r--tools/include/nolibc/stackprotector.h51
-rw-r--r--tools/include/nolibc/std.h36
-rw-r--r--tools/include/nolibc/stdint.h113
-rw-r--r--tools/include/nolibc/stdio.h383
-rw-r--r--tools/include/nolibc/stdlib.h444
-rw-r--r--tools/include/nolibc/string.h294
-rw-r--r--tools/include/nolibc/sys.h1190
-rw-r--r--tools/include/nolibc/time.h31
-rw-r--r--tools/include/nolibc/types.h241
-rw-r--r--tools/include/nolibc/unistd.h68
-rw-r--r--tools/include/tools/be_byteshift.h71
-rw-r--r--tools/include/tools/config.h34
-rw-r--r--tools/include/tools/dis-asm-compat.h55
-rw-r--r--tools/include/tools/endian.h57
-rw-r--r--tools/include/tools/le_byteshift.h71
-rw-r--r--tools/include/tools/libc_compat.h20
-rw-r--r--tools/include/trace/events/lock.h4
-rw-r--r--tools/include/uapi/asm-generic/bitsperlong.h27
-rw-r--r--tools/include/uapi/asm-generic/bpf_perf_event.h9
-rw-r--r--tools/include/uapi/asm-generic/errno-base.h40
-rw-r--r--tools/include/uapi/asm-generic/errno.h123
-rw-r--r--tools/include/uapi/asm-generic/fcntl.h221
-rw-r--r--tools/include/uapi/asm-generic/ioctls.h121
-rw-r--r--tools/include/uapi/asm-generic/mman-common-tools.h23
-rw-r--r--tools/include/uapi/asm-generic/mman-common.h90
-rw-r--r--tools/include/uapi/asm-generic/mman.h22
-rw-r--r--tools/include/uapi/asm-generic/socket.h152
-rw-r--r--tools/include/uapi/asm-generic/unistd.h875
-rw-r--r--tools/include/uapi/asm/bitsperlong.h18
-rw-r--r--tools/include/uapi/asm/bpf_perf_event.h13
-rw-r--r--tools/include/uapi/asm/errno.h16
-rw-r--r--tools/include/uapi/drm/drm.h1326
-rw-r--r--tools/include/uapi/drm/i915_drm.h3848
-rw-r--r--tools/include/uapi/linux/bpf.h7319
-rw-r--r--tools/include/uapi/linux/bpf_common.h57
-rw-r--r--tools/include/uapi/linux/bpf_perf_event.h19
-rw-r--r--tools/include/uapi/linux/btf.h200
-rw-r--r--tools/include/uapi/linux/const.h36
-rw-r--r--tools/include/uapi/linux/erspan.h52
-rw-r--r--tools/include/uapi/linux/ethtool.h104
-rw-r--r--tools/include/uapi/linux/fadvise.h22
-rw-r--r--tools/include/uapi/linux/fcntl.h120
-rw-r--r--tools/include/uapi/linux/filter.h90
-rw-r--r--tools/include/uapi/linux/fs.h308
-rw-r--r--tools/include/uapi/linux/fscrypt.h196
-rw-r--r--tools/include/uapi/linux/hw_breakpoint.h25
-rw-r--r--tools/include/uapi/linux/if_link.h1284
-rw-r--r--tools/include/uapi/linux/if_tun.h114
-rw-r--r--tools/include/uapi/linux/if_xdp.h120
-rw-r--r--tools/include/uapi/linux/in.h333
-rw-r--r--tools/include/uapi/linux/kcmp.h28
-rw-r--r--tools/include/uapi/linux/kvm.h2252
-rw-r--r--tools/include/uapi/linux/mman.h58
-rw-r--r--tools/include/uapi/linux/mount.h140
-rw-r--r--tools/include/uapi/linux/netdev.h63
-rw-r--r--tools/include/uapi/linux/netlink.h252
-rw-r--r--tools/include/uapi/linux/openat2.h43
-rw-r--r--tools/include/uapi/linux/perf_event.h1449
-rw-r--r--tools/include/uapi/linux/pkt_cls.h612
-rw-r--r--tools/include/uapi/linux/pkt_sched.h1164
-rw-r--r--tools/include/uapi/linux/prctl.h309
-rw-r--r--tools/include/uapi/linux/sched.h148
-rw-r--r--tools/include/uapi/linux/seccomp.h157
-rw-r--r--tools/include/uapi/linux/seg6.h55
-rw-r--r--tools/include/uapi/linux/seg6_local.h80
-rw-r--r--tools/include/uapi/linux/stat.h194
-rw-r--r--tools/include/uapi/linux/stddef.h47
-rw-r--r--tools/include/uapi/linux/tc_act/tc_bpf.h30
-rw-r--r--tools/include/uapi/linux/tcp.h357
-rw-r--r--tools/include/uapi/linux/tls.h78
-rw-r--r--tools/include/uapi/linux/types.h23
-rw-r--r--tools/include/uapi/linux/usbdevice_fs.h231
-rw-r--r--tools/include/uapi/linux/vhost.h222
-rw-r--r--tools/include/uapi/sound/asound.h1249
-rw-r--r--tools/include/vdso/bits.h10
-rw-r--r--tools/include/vdso/const.h10
186 files changed, 38459 insertions, 0 deletions
diff --git a/tools/include/asm-generic/atomic-gcc.h b/tools/include/asm-generic/atomic-gcc.h
new file mode 100644
index 0000000000..9b3c528bab
--- /dev/null
+++ b/tools/include/asm-generic/atomic-gcc.h
@@ -0,0 +1,95 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __TOOLS_ASM_GENERIC_ATOMIC_H
+#define __TOOLS_ASM_GENERIC_ATOMIC_H
+
+#include <linux/compiler.h>
+#include <linux/types.h>
+#include <linux/bitops.h>
+
+/*
+ * Atomic operations that C can't guarantee us. Useful for
+ * resource counting etc..
+ *
+ * Excerpts obtained from the Linux kernel sources.
+ */
+
+#define ATOMIC_INIT(i) { (i) }
+
+/**
+ * atomic_read - read atomic variable
+ * @v: pointer of type atomic_t
+ *
+ * Atomically reads the value of @v.
+ */
+static inline int atomic_read(const atomic_t *v)
+{
+ return READ_ONCE((v)->counter);
+}
+
+/**
+ * atomic_set - set atomic variable
+ * @v: pointer of type atomic_t
+ * @i: required value
+ *
+ * Atomically sets the value of @v to @i.
+ */
+static inline void atomic_set(atomic_t *v, int i)
+{
+ v->counter = i;
+}
+
+/**
+ * atomic_inc - increment atomic variable
+ * @v: pointer of type atomic_t
+ *
+ * Atomically increments @v by 1.
+ */
+static inline void atomic_inc(atomic_t *v)
+{
+ __sync_add_and_fetch(&v->counter, 1);
+}
+
+/**
+ * atomic_dec_and_test - decrement and test
+ * @v: pointer of type atomic_t
+ *
+ * Atomically decrements @v by 1 and
+ * returns true if the result is 0, or false for all other
+ * cases.
+ */
+static inline int atomic_dec_and_test(atomic_t *v)
+{
+ return __sync_sub_and_fetch(&v->counter, 1) == 0;
+}
+
+#define cmpxchg(ptr, oldval, newval) \
+ __sync_val_compare_and_swap(ptr, oldval, newval)
+
+static inline int atomic_cmpxchg(atomic_t *v, int oldval, int newval)
+{
+ return cmpxchg(&(v)->counter, oldval, newval);
+}
+
+static inline int test_and_set_bit(long nr, unsigned long *addr)
+{
+ unsigned long mask = BIT_MASK(nr);
+ long old;
+
+ addr += BIT_WORD(nr);
+
+ old = __sync_fetch_and_or(addr, mask);
+ return !!(old & mask);
+}
+
+static inline int test_and_clear_bit(long nr, unsigned long *addr)
+{
+ unsigned long mask = BIT_MASK(nr);
+ long old;
+
+ addr += BIT_WORD(nr);
+
+ old = __sync_fetch_and_and(addr, ~mask);
+ return !!(old & mask);
+}
+
+#endif /* __TOOLS_ASM_GENERIC_ATOMIC_H */
diff --git a/tools/include/asm-generic/barrier.h b/tools/include/asm-generic/barrier.h
new file mode 100644
index 0000000000..6ef36e920e
--- /dev/null
+++ b/tools/include/asm-generic/barrier.h
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copied from the kernel sources to tools/perf/:
+ *
+ * Generic barrier definitions.
+ *
+ * It should be possible to use these on really simple architectures,
+ * but it serves more as a starting point for new ports.
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+#ifndef __TOOLS_LINUX_ASM_GENERIC_BARRIER_H
+#define __TOOLS_LINUX_ASM_GENERIC_BARRIER_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/compiler.h>
+
+/*
+ * Force strict CPU ordering. And yes, this is required on UP too when we're
+ * talking to devices.
+ *
+ * Fall back to compiler barriers if nothing better is provided.
+ */
+
+#ifndef mb
+#define mb() barrier()
+#endif
+
+#ifndef rmb
+#define rmb() mb()
+#endif
+
+#ifndef wmb
+#define wmb() mb()
+#endif
+
+#endif /* !__ASSEMBLY__ */
+#endif /* __TOOLS_LINUX_ASM_GENERIC_BARRIER_H */
diff --git a/tools/include/asm-generic/bitops.h b/tools/include/asm-generic/bitops.h
new file mode 100644
index 0000000000..9ab313e935
--- /dev/null
+++ b/tools/include/asm-generic/bitops.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __TOOLS_ASM_GENERIC_BITOPS_H
+#define __TOOLS_ASM_GENERIC_BITOPS_H
+
+/*
+ * tools/ copied this from include/asm-generic/bitops.h, bit by bit as it needed
+ * some functions.
+ *
+ * For the benefit of those who are trying to port Linux to another
+ * architecture, here are some C-language equivalents. You should
+ * recode these in the native assembly language, if at all possible.
+ *
+ * C language equivalents written by Theodore Ts'o, 9/26/92
+ */
+
+#include <asm-generic/bitops/__ffs.h>
+#include <asm-generic/bitops/__ffz.h>
+#include <asm-generic/bitops/fls.h>
+#include <asm-generic/bitops/__fls.h>
+#include <asm-generic/bitops/fls64.h>
+
+#ifndef _TOOLS_LINUX_BITOPS_H_
+#error only <linux/bitops.h> can be included directly
+#endif
+
+#include <asm-generic/bitops/hweight.h>
+
+#include <asm-generic/bitops/atomic.h>
+#include <asm-generic/bitops/non-atomic.h>
+
+#endif /* __TOOLS_ASM_GENERIC_BITOPS_H */
diff --git a/tools/include/asm-generic/bitops/__ffs.h b/tools/include/asm-generic/bitops/__ffs.h
new file mode 100644
index 0000000000..9d13105194
--- /dev/null
+++ b/tools/include/asm-generic/bitops/__ffs.h
@@ -0,0 +1,45 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TOOLS_LINUX_ASM_GENERIC_BITOPS___FFS_H_
+#define _TOOLS_LINUX_ASM_GENERIC_BITOPS___FFS_H_
+
+#include <asm/types.h>
+#include <asm/bitsperlong.h>
+
+/**
+ * __ffs - find first bit in word.
+ * @word: The word to search
+ *
+ * Undefined if no bit exists, so code should check against 0 first.
+ */
+static __always_inline unsigned long __ffs(unsigned long word)
+{
+ int num = 0;
+
+#if __BITS_PER_LONG == 64
+ if ((word & 0xffffffff) == 0) {
+ num += 32;
+ word >>= 32;
+ }
+#endif
+ if ((word & 0xffff) == 0) {
+ num += 16;
+ word >>= 16;
+ }
+ if ((word & 0xff) == 0) {
+ num += 8;
+ word >>= 8;
+ }
+ if ((word & 0xf) == 0) {
+ num += 4;
+ word >>= 4;
+ }
+ if ((word & 0x3) == 0) {
+ num += 2;
+ word >>= 2;
+ }
+ if ((word & 0x1) == 0)
+ num += 1;
+ return num;
+}
+
+#endif /* _TOOLS_LINUX_ASM_GENERIC_BITOPS___FFS_H_ */
diff --git a/tools/include/asm-generic/bitops/__ffz.h b/tools/include/asm-generic/bitops/__ffz.h
new file mode 100644
index 0000000000..6744bd4cdf
--- /dev/null
+++ b/tools/include/asm-generic/bitops/__ffz.h
@@ -0,0 +1,12 @@
+#ifndef _ASM_GENERIC_BITOPS_FFZ_H_
+#define _ASM_GENERIC_BITOPS_FFZ_H_
+
+/*
+ * ffz - find first zero in word.
+ * @word: The word to search
+ *
+ * Undefined if no zero exists, so code should check against ~0UL first.
+ */
+#define ffz(x) __ffs(~(x))
+
+#endif /* _ASM_GENERIC_BITOPS_FFZ_H_ */
diff --git a/tools/include/asm-generic/bitops/__fls.h b/tools/include/asm-generic/bitops/__fls.h
new file mode 100644
index 0000000000..03f721a8a2
--- /dev/null
+++ b/tools/include/asm-generic/bitops/__fls.h
@@ -0,0 +1,44 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_GENERIC_BITOPS___FLS_H_
+#define _ASM_GENERIC_BITOPS___FLS_H_
+
+#include <asm/types.h>
+
+/**
+ * __fls - find last (most-significant) set bit in a long word
+ * @word: the word to search
+ *
+ * Undefined if no set bit exists, so code should check against 0 first.
+ */
+static __always_inline unsigned long __fls(unsigned long word)
+{
+ int num = BITS_PER_LONG - 1;
+
+#if BITS_PER_LONG == 64
+ if (!(word & (~0ul << 32))) {
+ num -= 32;
+ word <<= 32;
+ }
+#endif
+ if (!(word & (~0ul << (BITS_PER_LONG-16)))) {
+ num -= 16;
+ word <<= 16;
+ }
+ if (!(word & (~0ul << (BITS_PER_LONG-8)))) {
+ num -= 8;
+ word <<= 8;
+ }
+ if (!(word & (~0ul << (BITS_PER_LONG-4)))) {
+ num -= 4;
+ word <<= 4;
+ }
+ if (!(word & (~0ul << (BITS_PER_LONG-2)))) {
+ num -= 2;
+ word <<= 2;
+ }
+ if (!(word & (~0ul << (BITS_PER_LONG-1))))
+ num -= 1;
+ return num;
+}
+
+#endif /* _ASM_GENERIC_BITOPS___FLS_H_ */
diff --git a/tools/include/asm-generic/bitops/arch_hweight.h b/tools/include/asm-generic/bitops/arch_hweight.h
new file mode 100644
index 0000000000..c2705e1d22
--- /dev/null
+++ b/tools/include/asm-generic/bitops/arch_hweight.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_GENERIC_BITOPS_ARCH_HWEIGHT_H_
+#define _ASM_GENERIC_BITOPS_ARCH_HWEIGHT_H_
+
+#include <asm/types.h>
+
+static inline unsigned int __arch_hweight32(unsigned int w)
+{
+ return __sw_hweight32(w);
+}
+
+static inline unsigned int __arch_hweight16(unsigned int w)
+{
+ return __sw_hweight16(w);
+}
+
+static inline unsigned int __arch_hweight8(unsigned int w)
+{
+ return __sw_hweight8(w);
+}
+
+static inline unsigned long __arch_hweight64(__u64 w)
+{
+ return __sw_hweight64(w);
+}
+#endif /* _ASM_GENERIC_BITOPS_HWEIGHT_H_ */
diff --git a/tools/include/asm-generic/bitops/atomic.h b/tools/include/asm-generic/bitops/atomic.h
new file mode 100644
index 0000000000..ab37a221b4
--- /dev/null
+++ b/tools/include/asm-generic/bitops/atomic.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TOOLS_LINUX_ASM_GENERIC_BITOPS_ATOMIC_H_
+#define _TOOLS_LINUX_ASM_GENERIC_BITOPS_ATOMIC_H_
+
+#include <asm/types.h>
+#include <asm/bitsperlong.h>
+
+/*
+ * Just alias the test versions, all of the compiler built-in atomics "fetch",
+ * and optimizing compile-time constants on x86 isn't worth the complexity.
+ */
+#define set_bit test_and_set_bit
+#define clear_bit test_and_clear_bit
+
+#endif /* _TOOLS_LINUX_ASM_GENERIC_BITOPS_ATOMIC_H_ */
diff --git a/tools/include/asm-generic/bitops/const_hweight.h b/tools/include/asm-generic/bitops/const_hweight.h
new file mode 100644
index 0000000000..149faeeeea
--- /dev/null
+++ b/tools/include/asm-generic/bitops/const_hweight.h
@@ -0,0 +1,44 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_GENERIC_BITOPS_CONST_HWEIGHT_H_
+#define _ASM_GENERIC_BITOPS_CONST_HWEIGHT_H_
+
+/*
+ * Compile time versions of __arch_hweightN()
+ */
+#define __const_hweight8(w) \
+ ((unsigned int) \
+ ((!!((w) & (1ULL << 0))) + \
+ (!!((w) & (1ULL << 1))) + \
+ (!!((w) & (1ULL << 2))) + \
+ (!!((w) & (1ULL << 3))) + \
+ (!!((w) & (1ULL << 4))) + \
+ (!!((w) & (1ULL << 5))) + \
+ (!!((w) & (1ULL << 6))) + \
+ (!!((w) & (1ULL << 7)))))
+
+#define __const_hweight16(w) (__const_hweight8(w) + __const_hweight8((w) >> 8 ))
+#define __const_hweight32(w) (__const_hweight16(w) + __const_hweight16((w) >> 16))
+#define __const_hweight64(w) (__const_hweight32(w) + __const_hweight32((w) >> 32))
+
+/*
+ * Generic interface.
+ */
+#define hweight8(w) (__builtin_constant_p(w) ? __const_hweight8(w) : __arch_hweight8(w))
+#define hweight16(w) (__builtin_constant_p(w) ? __const_hweight16(w) : __arch_hweight16(w))
+#define hweight32(w) (__builtin_constant_p(w) ? __const_hweight32(w) : __arch_hweight32(w))
+#define hweight64(w) (__builtin_constant_p(w) ? __const_hweight64(w) : __arch_hweight64(w))
+
+/*
+ * Interface for known constant arguments
+ */
+#define HWEIGHT8(w) (BUILD_BUG_ON_ZERO(!__builtin_constant_p(w)) + __const_hweight8(w))
+#define HWEIGHT16(w) (BUILD_BUG_ON_ZERO(!__builtin_constant_p(w)) + __const_hweight16(w))
+#define HWEIGHT32(w) (BUILD_BUG_ON_ZERO(!__builtin_constant_p(w)) + __const_hweight32(w))
+#define HWEIGHT64(w) (BUILD_BUG_ON_ZERO(!__builtin_constant_p(w)) + __const_hweight64(w))
+
+/*
+ * Type invariant interface to the compile time constant hweight functions.
+ */
+#define HWEIGHT(w) HWEIGHT64((u64)w)
+
+#endif /* _ASM_GENERIC_BITOPS_CONST_HWEIGHT_H_ */
diff --git a/tools/include/asm-generic/bitops/fls.h b/tools/include/asm-generic/bitops/fls.h
new file mode 100644
index 0000000000..b168bb10e1
--- /dev/null
+++ b/tools/include/asm-generic/bitops/fls.h
@@ -0,0 +1,42 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_GENERIC_BITOPS_FLS_H_
+#define _ASM_GENERIC_BITOPS_FLS_H_
+
+/**
+ * fls - find last (most-significant) bit set
+ * @x: the word to search
+ *
+ * This is defined the same way as ffs.
+ * Note fls(0) = 0, fls(1) = 1, fls(0x80000000) = 32.
+ */
+
+static __always_inline int fls(unsigned int x)
+{
+ int r = 32;
+
+ if (!x)
+ return 0;
+ if (!(x & 0xffff0000u)) {
+ x <<= 16;
+ r -= 16;
+ }
+ if (!(x & 0xff000000u)) {
+ x <<= 8;
+ r -= 8;
+ }
+ if (!(x & 0xf0000000u)) {
+ x <<= 4;
+ r -= 4;
+ }
+ if (!(x & 0xc0000000u)) {
+ x <<= 2;
+ r -= 2;
+ }
+ if (!(x & 0x80000000u)) {
+ x <<= 1;
+ r -= 1;
+ }
+ return r;
+}
+
+#endif /* _ASM_GENERIC_BITOPS_FLS_H_ */
diff --git a/tools/include/asm-generic/bitops/fls64.h b/tools/include/asm-generic/bitops/fls64.h
new file mode 100644
index 0000000000..866f2b2304
--- /dev/null
+++ b/tools/include/asm-generic/bitops/fls64.h
@@ -0,0 +1,37 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_GENERIC_BITOPS_FLS64_H_
+#define _ASM_GENERIC_BITOPS_FLS64_H_
+
+#include <asm/types.h>
+
+/**
+ * fls64 - find last set bit in a 64-bit word
+ * @x: the word to search
+ *
+ * This is defined in a similar way as the libc and compiler builtin
+ * ffsll, but returns the position of the most significant set bit.
+ *
+ * fls64(value) returns 0 if value is 0 or the position of the last
+ * set bit if value is nonzero. The last (most significant) bit is
+ * at position 64.
+ */
+#if BITS_PER_LONG == 32
+static __always_inline int fls64(__u64 x)
+{
+ __u32 h = x >> 32;
+ if (h)
+ return fls(h) + 32;
+ return fls(x);
+}
+#elif BITS_PER_LONG == 64
+static __always_inline int fls64(__u64 x)
+{
+ if (x == 0)
+ return 0;
+ return __fls(x) + 1;
+}
+#else
+#error BITS_PER_LONG not 32 or 64
+#endif
+
+#endif /* _ASM_GENERIC_BITOPS_FLS64_H_ */
diff --git a/tools/include/asm-generic/bitops/hweight.h b/tools/include/asm-generic/bitops/hweight.h
new file mode 100644
index 0000000000..3e681982bc
--- /dev/null
+++ b/tools/include/asm-generic/bitops/hweight.h
@@ -0,0 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TOOLS_LINUX_ASM_GENERIC_BITOPS_HWEIGHT_H_
+#define _TOOLS_LINUX_ASM_GENERIC_BITOPS_HWEIGHT_H_
+
+#include <asm-generic/bitops/arch_hweight.h>
+#include <asm-generic/bitops/const_hweight.h>
+
+#endif /* _TOOLS_LINUX_ASM_GENERIC_BITOPS_HWEIGHT_H_ */
diff --git a/tools/include/asm-generic/bitops/non-atomic.h b/tools/include/asm-generic/bitops/non-atomic.h
new file mode 100644
index 0000000000..0c472a8334
--- /dev/null
+++ b/tools/include/asm-generic/bitops/non-atomic.h
@@ -0,0 +1,115 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_GENERIC_BITOPS_NON_ATOMIC_H_
+#define _ASM_GENERIC_BITOPS_NON_ATOMIC_H_
+
+#include <linux/bits.h>
+
+/**
+ * ___set_bit - Set a bit in memory
+ * @nr: the bit to set
+ * @addr: the address to start counting from
+ *
+ * Unlike set_bit(), this function is non-atomic and may be reordered.
+ * If it's called on the same region of memory simultaneously, the effect
+ * may be that only one operation succeeds.
+ */
+static __always_inline void
+___set_bit(unsigned long nr, volatile unsigned long *addr)
+{
+ unsigned long mask = BIT_MASK(nr);
+ unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+
+ *p |= mask;
+}
+
+static __always_inline void
+___clear_bit(unsigned long nr, volatile unsigned long *addr)
+{
+ unsigned long mask = BIT_MASK(nr);
+ unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+
+ *p &= ~mask;
+}
+
+/**
+ * ___change_bit - Toggle a bit in memory
+ * @nr: the bit to change
+ * @addr: the address to start counting from
+ *
+ * Unlike change_bit(), this function is non-atomic and may be reordered.
+ * If it's called on the same region of memory simultaneously, the effect
+ * may be that only one operation succeeds.
+ */
+static __always_inline void
+___change_bit(unsigned long nr, volatile unsigned long *addr)
+{
+ unsigned long mask = BIT_MASK(nr);
+ unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+
+ *p ^= mask;
+}
+
+/**
+ * ___test_and_set_bit - Set a bit and return its old value
+ * @nr: Bit to set
+ * @addr: Address to count from
+ *
+ * This operation is non-atomic and can be reordered.
+ * If two examples of this operation race, one can appear to succeed
+ * but actually fail. You must protect multiple accesses with a lock.
+ */
+static __always_inline bool
+___test_and_set_bit(unsigned long nr, volatile unsigned long *addr)
+{
+ unsigned long mask = BIT_MASK(nr);
+ unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+ unsigned long old = *p;
+
+ *p = old | mask;
+ return (old & mask) != 0;
+}
+
+/**
+ * ___test_and_clear_bit - Clear a bit and return its old value
+ * @nr: Bit to clear
+ * @addr: Address to count from
+ *
+ * This operation is non-atomic and can be reordered.
+ * If two examples of this operation race, one can appear to succeed
+ * but actually fail. You must protect multiple accesses with a lock.
+ */
+static __always_inline bool
+___test_and_clear_bit(unsigned long nr, volatile unsigned long *addr)
+{
+ unsigned long mask = BIT_MASK(nr);
+ unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+ unsigned long old = *p;
+
+ *p = old & ~mask;
+ return (old & mask) != 0;
+}
+
+/* WARNING: non atomic and it can be reordered! */
+static __always_inline bool
+___test_and_change_bit(unsigned long nr, volatile unsigned long *addr)
+{
+ unsigned long mask = BIT_MASK(nr);
+ unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+ unsigned long old = *p;
+
+ *p = old ^ mask;
+ return (old & mask) != 0;
+}
+
+/**
+ * _test_bit - Determine whether a bit is set
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ */
+static __always_inline bool
+_test_bit(unsigned long nr, const volatile unsigned long *addr)
+{
+ return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
+}
+
+#endif /* _ASM_GENERIC_BITOPS_NON_ATOMIC_H_ */
diff --git a/tools/include/asm-generic/bitsperlong.h b/tools/include/asm-generic/bitsperlong.h
new file mode 100644
index 0000000000..2093d56ddd
--- /dev/null
+++ b/tools/include/asm-generic/bitsperlong.h
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_GENERIC_BITS_PER_LONG
+#define __ASM_GENERIC_BITS_PER_LONG
+
+#include <uapi/asm-generic/bitsperlong.h>
+
+#ifdef __SIZEOF_LONG__
+#define BITS_PER_LONG (__CHAR_BIT__ * __SIZEOF_LONG__)
+#else
+#define BITS_PER_LONG __WORDSIZE
+#endif
+
+#if BITS_PER_LONG != __BITS_PER_LONG
+#error Inconsistent word size. Check asm/bitsperlong.h
+#endif
+
+#ifndef BITS_PER_LONG_LONG
+#define BITS_PER_LONG_LONG 64
+#endif
+
+#define small_const_nbits(nbits) \
+ (__builtin_constant_p(nbits) && (nbits) <= BITS_PER_LONG && (nbits) > 0)
+
+#endif /* __ASM_GENERIC_BITS_PER_LONG */
diff --git a/tools/include/asm-generic/hugetlb_encode.h b/tools/include/asm-generic/hugetlb_encode.h
new file mode 100644
index 0000000000..de687009bf
--- /dev/null
+++ b/tools/include/asm-generic/hugetlb_encode.h
@@ -0,0 +1,37 @@
+#ifndef _ASM_GENERIC_HUGETLB_ENCODE_H_
+#define _ASM_GENERIC_HUGETLB_ENCODE_H_
+
+/*
+ * Several system calls take a flag to request "hugetlb" huge pages.
+ * Without further specification, these system calls will use the
+ * system's default huge page size. If a system supports multiple
+ * huge page sizes, the desired huge page size can be specified in
+ * bits [26:31] of the flag arguments. The value in these 6 bits
+ * will encode the log2 of the huge page size.
+ *
+ * The following definitions are associated with this huge page size
+ * encoding in flag arguments. System call specific header files
+ * that use this encoding should include this file. They can then
+ * provide definitions based on these with their own specific prefix.
+ * for example:
+ * #define MAP_HUGE_SHIFT HUGETLB_FLAG_ENCODE_SHIFT
+ */
+
+#define HUGETLB_FLAG_ENCODE_SHIFT 26
+#define HUGETLB_FLAG_ENCODE_MASK 0x3f
+
+#define HUGETLB_FLAG_ENCODE_16KB (14U << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_64KB (16U << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_512KB (19U << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_1MB (20U << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_2MB (21U << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_8MB (23U << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_16MB (24U << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_32MB (25U << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_256MB (28U << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_512MB (29U << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_1GB (30U << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_2GB (31U << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_16GB (34U << HUGETLB_FLAG_ENCODE_SHIFT)
+
+#endif /* _ASM_GENERIC_HUGETLB_ENCODE_H_ */
diff --git a/tools/include/asm-generic/unaligned.h b/tools/include/asm-generic/unaligned.h
new file mode 100644
index 0000000000..47387c6070
--- /dev/null
+++ b/tools/include/asm-generic/unaligned.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copied from the kernel sources to tools/perf/:
+ */
+
+#ifndef __TOOLS_LINUX_ASM_GENERIC_UNALIGNED_H
+#define __TOOLS_LINUX_ASM_GENERIC_UNALIGNED_H
+
+#define __get_unaligned_t(type, ptr) ({ \
+ const struct { type x; } __packed *__pptr = (typeof(__pptr))(ptr); \
+ __pptr->x; \
+})
+
+#define __put_unaligned_t(type, val, ptr) do { \
+ struct { type x; } __packed *__pptr = (typeof(__pptr))(ptr); \
+ __pptr->x = (val); \
+} while (0)
+
+#define get_unaligned(ptr) __get_unaligned_t(typeof(*(ptr)), (ptr))
+#define put_unaligned(val, ptr) __put_unaligned_t(typeof(*(ptr)), (val), (ptr))
+
+#endif /* __TOOLS_LINUX_ASM_GENERIC_UNALIGNED_H */
+
diff --git a/tools/include/asm/alternative.h b/tools/include/asm/alternative.h
new file mode 100644
index 0000000000..7ce02a2237
--- /dev/null
+++ b/tools/include/asm/alternative.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TOOLS_ASM_ALTERNATIVE_ASM_H
+#define _TOOLS_ASM_ALTERNATIVE_ASM_H
+
+/* Just disable it so we can build arch/x86/lib/memcpy_64.S for perf bench: */
+
+#define ALTERNATIVE #
+
+#endif
diff --git a/tools/include/asm/atomic.h b/tools/include/asm/atomic.h
new file mode 100644
index 0000000000..8c9bfffd41
--- /dev/null
+++ b/tools/include/asm/atomic.h
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __TOOLS_LINUX_ASM_ATOMIC_H
+#define __TOOLS_LINUX_ASM_ATOMIC_H
+
+#if defined(__i386__) || defined(__x86_64__)
+#include "../../arch/x86/include/asm/atomic.h"
+#else
+#include <asm-generic/atomic-gcc.h>
+#endif
+
+#endif /* __TOOLS_LINUX_ASM_ATOMIC_H */
diff --git a/tools/include/asm/barrier.h b/tools/include/asm/barrier.h
new file mode 100644
index 0000000000..8d378c57cb
--- /dev/null
+++ b/tools/include/asm/barrier.h
@@ -0,0 +1,63 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/compiler.h>
+#if defined(__i386__) || defined(__x86_64__)
+#include "../../arch/x86/include/asm/barrier.h"
+#elif defined(__arm__)
+#include "../../arch/arm/include/asm/barrier.h"
+#elif defined(__aarch64__)
+#include "../../arch/arm64/include/asm/barrier.h"
+#elif defined(__powerpc__)
+#include "../../arch/powerpc/include/asm/barrier.h"
+#elif defined(__s390__)
+#include "../../arch/s390/include/asm/barrier.h"
+#elif defined(__sh__)
+#include "../../arch/sh/include/asm/barrier.h"
+#elif defined(__sparc__)
+#include "../../arch/sparc/include/asm/barrier.h"
+#elif defined(__tile__)
+#include "../../arch/tile/include/asm/barrier.h"
+#elif defined(__alpha__)
+#include "../../arch/alpha/include/asm/barrier.h"
+#elif defined(__mips__)
+#include "../../arch/mips/include/asm/barrier.h"
+#elif defined(__ia64__)
+#include "../../arch/ia64/include/asm/barrier.h"
+#elif defined(__xtensa__)
+#include "../../arch/xtensa/include/asm/barrier.h"
+#else
+#include <asm-generic/barrier.h>
+#endif
+
+/*
+ * Generic fallback smp_*() definitions for archs that haven't
+ * been updated yet.
+ */
+
+#ifndef smp_rmb
+# define smp_rmb() rmb()
+#endif
+
+#ifndef smp_wmb
+# define smp_wmb() wmb()
+#endif
+
+#ifndef smp_mb
+# define smp_mb() mb()
+#endif
+
+#ifndef smp_store_release
+# define smp_store_release(p, v) \
+do { \
+ smp_mb(); \
+ WRITE_ONCE(*p, v); \
+} while (0)
+#endif
+
+#ifndef smp_load_acquire
+# define smp_load_acquire(p) \
+({ \
+ typeof(*p) ___p1 = READ_ONCE(*p); \
+ smp_mb(); \
+ ___p1; \
+})
+#endif
diff --git a/tools/include/asm/bug.h b/tools/include/asm/bug.h
new file mode 100644
index 0000000000..550223f0a6
--- /dev/null
+++ b/tools/include/asm/bug.h
@@ -0,0 +1,46 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TOOLS_ASM_BUG_H
+#define _TOOLS_ASM_BUG_H
+
+#include <linux/compiler.h>
+#include <stdio.h>
+
+#define __WARN_printf(arg...) do { fprintf(stderr, arg); } while (0)
+
+#define WARN(condition, format...) ({ \
+ int __ret_warn_on = !!(condition); \
+ if (unlikely(__ret_warn_on)) \
+ __WARN_printf(format); \
+ unlikely(__ret_warn_on); \
+})
+
+#define WARN_ON(condition) ({ \
+ int __ret_warn_on = !!(condition); \
+ if (unlikely(__ret_warn_on)) \
+ __WARN_printf("assertion failed at %s:%d\n", \
+ __FILE__, __LINE__); \
+ unlikely(__ret_warn_on); \
+})
+
+#define WARN_ON_ONCE(condition) ({ \
+ static int __warned; \
+ int __ret_warn_once = !!(condition); \
+ \
+ if (unlikely(__ret_warn_once && !__warned)) { \
+ __warned = true; \
+ WARN_ON(1); \
+ } \
+ unlikely(__ret_warn_once); \
+})
+
+#define WARN_ONCE(condition, format...) ({ \
+ static int __warned; \
+ int __ret_warn_once = !!(condition); \
+ \
+ if (unlikely(__ret_warn_once)) \
+ if (WARN(!__warned, format)) \
+ __warned = 1; \
+ unlikely(__ret_warn_once); \
+})
+
+#endif /* _TOOLS_ASM_BUG_H */
diff --git a/tools/include/asm/export.h b/tools/include/asm/export.h
new file mode 100644
index 0000000000..2cb1a0d830
--- /dev/null
+++ b/tools/include/asm/export.h
@@ -0,0 +1,7 @@
+#ifndef _TOOLS_ASM_EXPORT_H
+#define _TOOLS_ASM_EXPORT_H
+
+#define EXPORT_SYMBOL(x)
+#define EXPORT_SYMBOL_GPL(x)
+
+#endif /* _TOOLS_ASM_EXPORT_H */
diff --git a/tools/include/asm/sections.h b/tools/include/asm/sections.h
new file mode 100644
index 0000000000..a80643d7a7
--- /dev/null
+++ b/tools/include/asm/sections.h
@@ -0,0 +1,4 @@
+#ifndef __TOOLS_INCLUDE_LINUX_ASM_SECTIONS_H
+#define __TOOLS_INCLUDE_LINUX_ASM_SECTIONS_H
+
+#endif /* __TOOLS_INCLUDE_LINUX_ASM_SECTIONS_H */
diff --git a/tools/include/linux/arm-smccc.h b/tools/include/linux/arm-smccc.h
new file mode 100644
index 0000000000..63ce9bebcc
--- /dev/null
+++ b/tools/include/linux/arm-smccc.h
@@ -0,0 +1,193 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2015, Linaro Limited
+ */
+#ifndef __LINUX_ARM_SMCCC_H
+#define __LINUX_ARM_SMCCC_H
+
+#include <linux/const.h>
+
+/*
+ * This file provides common defines for ARM SMC Calling Convention as
+ * specified in
+ * https://developer.arm.com/docs/den0028/latest
+ *
+ * This code is up-to-date with version DEN 0028 C
+ */
+
+#define ARM_SMCCC_STD_CALL _AC(0,U)
+#define ARM_SMCCC_FAST_CALL _AC(1,U)
+#define ARM_SMCCC_TYPE_SHIFT 31
+
+#define ARM_SMCCC_SMC_32 0
+#define ARM_SMCCC_SMC_64 1
+#define ARM_SMCCC_CALL_CONV_SHIFT 30
+
+#define ARM_SMCCC_OWNER_MASK 0x3F
+#define ARM_SMCCC_OWNER_SHIFT 24
+
+#define ARM_SMCCC_FUNC_MASK 0xFFFF
+
+#define ARM_SMCCC_IS_FAST_CALL(smc_val) \
+ ((smc_val) & (ARM_SMCCC_FAST_CALL << ARM_SMCCC_TYPE_SHIFT))
+#define ARM_SMCCC_IS_64(smc_val) \
+ ((smc_val) & (ARM_SMCCC_SMC_64 << ARM_SMCCC_CALL_CONV_SHIFT))
+#define ARM_SMCCC_FUNC_NUM(smc_val) ((smc_val) & ARM_SMCCC_FUNC_MASK)
+#define ARM_SMCCC_OWNER_NUM(smc_val) \
+ (((smc_val) >> ARM_SMCCC_OWNER_SHIFT) & ARM_SMCCC_OWNER_MASK)
+
+#define ARM_SMCCC_CALL_VAL(type, calling_convention, owner, func_num) \
+ (((type) << ARM_SMCCC_TYPE_SHIFT) | \
+ ((calling_convention) << ARM_SMCCC_CALL_CONV_SHIFT) | \
+ (((owner) & ARM_SMCCC_OWNER_MASK) << ARM_SMCCC_OWNER_SHIFT) | \
+ ((func_num) & ARM_SMCCC_FUNC_MASK))
+
+#define ARM_SMCCC_OWNER_ARCH 0
+#define ARM_SMCCC_OWNER_CPU 1
+#define ARM_SMCCC_OWNER_SIP 2
+#define ARM_SMCCC_OWNER_OEM 3
+#define ARM_SMCCC_OWNER_STANDARD 4
+#define ARM_SMCCC_OWNER_STANDARD_HYP 5
+#define ARM_SMCCC_OWNER_VENDOR_HYP 6
+#define ARM_SMCCC_OWNER_TRUSTED_APP 48
+#define ARM_SMCCC_OWNER_TRUSTED_APP_END 49
+#define ARM_SMCCC_OWNER_TRUSTED_OS 50
+#define ARM_SMCCC_OWNER_TRUSTED_OS_END 63
+
+#define ARM_SMCCC_FUNC_QUERY_CALL_UID 0xff01
+
+#define ARM_SMCCC_QUIRK_NONE 0
+#define ARM_SMCCC_QUIRK_QCOM_A6 1 /* Save/restore register a6 */
+
+#define ARM_SMCCC_VERSION_1_0 0x10000
+#define ARM_SMCCC_VERSION_1_1 0x10001
+#define ARM_SMCCC_VERSION_1_2 0x10002
+#define ARM_SMCCC_VERSION_1_3 0x10003
+
+#define ARM_SMCCC_1_3_SVE_HINT 0x10000
+
+#define ARM_SMCCC_VERSION_FUNC_ID \
+ ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \
+ ARM_SMCCC_SMC_32, \
+ 0, 0)
+
+#define ARM_SMCCC_ARCH_FEATURES_FUNC_ID \
+ ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \
+ ARM_SMCCC_SMC_32, \
+ 0, 1)
+
+#define ARM_SMCCC_ARCH_SOC_ID \
+ ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \
+ ARM_SMCCC_SMC_32, \
+ 0, 2)
+
+#define ARM_SMCCC_ARCH_WORKAROUND_1 \
+ ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \
+ ARM_SMCCC_SMC_32, \
+ 0, 0x8000)
+
+#define ARM_SMCCC_ARCH_WORKAROUND_2 \
+ ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \
+ ARM_SMCCC_SMC_32, \
+ 0, 0x7fff)
+
+#define ARM_SMCCC_ARCH_WORKAROUND_3 \
+ ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \
+ ARM_SMCCC_SMC_32, \
+ 0, 0x3fff)
+
+#define ARM_SMCCC_VENDOR_HYP_CALL_UID_FUNC_ID \
+ ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \
+ ARM_SMCCC_SMC_32, \
+ ARM_SMCCC_OWNER_VENDOR_HYP, \
+ ARM_SMCCC_FUNC_QUERY_CALL_UID)
+
+/* KVM UID value: 28b46fb6-2ec5-11e9-a9ca-4b564d003a74 */
+#define ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_0 0xb66fb428U
+#define ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_1 0xe911c52eU
+#define ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_2 0x564bcaa9U
+#define ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_3 0x743a004dU
+
+/* KVM "vendor specific" services */
+#define ARM_SMCCC_KVM_FUNC_FEATURES 0
+#define ARM_SMCCC_KVM_FUNC_PTP 1
+#define ARM_SMCCC_KVM_FUNC_FEATURES_2 127
+#define ARM_SMCCC_KVM_NUM_FUNCS 128
+
+#define ARM_SMCCC_VENDOR_HYP_KVM_FEATURES_FUNC_ID \
+ ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \
+ ARM_SMCCC_SMC_32, \
+ ARM_SMCCC_OWNER_VENDOR_HYP, \
+ ARM_SMCCC_KVM_FUNC_FEATURES)
+
+#define SMCCC_ARCH_WORKAROUND_RET_UNAFFECTED 1
+
+/*
+ * ptp_kvm is a feature used for time sync between vm and host.
+ * ptp_kvm module in guest kernel will get service from host using
+ * this hypercall ID.
+ */
+#define ARM_SMCCC_VENDOR_HYP_KVM_PTP_FUNC_ID \
+ ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \
+ ARM_SMCCC_SMC_32, \
+ ARM_SMCCC_OWNER_VENDOR_HYP, \
+ ARM_SMCCC_KVM_FUNC_PTP)
+
+/* ptp_kvm counter type ID */
+#define KVM_PTP_VIRT_COUNTER 0
+#define KVM_PTP_PHYS_COUNTER 1
+
+/* Paravirtualised time calls (defined by ARM DEN0057A) */
+#define ARM_SMCCC_HV_PV_TIME_FEATURES \
+ ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \
+ ARM_SMCCC_SMC_64, \
+ ARM_SMCCC_OWNER_STANDARD_HYP, \
+ 0x20)
+
+#define ARM_SMCCC_HV_PV_TIME_ST \
+ ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \
+ ARM_SMCCC_SMC_64, \
+ ARM_SMCCC_OWNER_STANDARD_HYP, \
+ 0x21)
+
+/* TRNG entropy source calls (defined by ARM DEN0098) */
+#define ARM_SMCCC_TRNG_VERSION \
+ ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \
+ ARM_SMCCC_SMC_32, \
+ ARM_SMCCC_OWNER_STANDARD, \
+ 0x50)
+
+#define ARM_SMCCC_TRNG_FEATURES \
+ ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \
+ ARM_SMCCC_SMC_32, \
+ ARM_SMCCC_OWNER_STANDARD, \
+ 0x51)
+
+#define ARM_SMCCC_TRNG_GET_UUID \
+ ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \
+ ARM_SMCCC_SMC_32, \
+ ARM_SMCCC_OWNER_STANDARD, \
+ 0x52)
+
+#define ARM_SMCCC_TRNG_RND32 \
+ ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \
+ ARM_SMCCC_SMC_32, \
+ ARM_SMCCC_OWNER_STANDARD, \
+ 0x53)
+
+#define ARM_SMCCC_TRNG_RND64 \
+ ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \
+ ARM_SMCCC_SMC_64, \
+ ARM_SMCCC_OWNER_STANDARD, \
+ 0x53)
+
+/*
+ * Return codes defined in ARM DEN 0070A
+ * ARM DEN 0070A is now merged/consolidated into ARM DEN 0028 C
+ */
+#define SMCCC_RET_SUCCESS 0
+#define SMCCC_RET_NOT_SUPPORTED -1
+#define SMCCC_RET_NOT_REQUIRED -2
+#define SMCCC_RET_INVALID_PARAMETER -3
+
+#endif /*__LINUX_ARM_SMCCC_H*/
diff --git a/tools/include/linux/atomic.h b/tools/include/linux/atomic.h
new file mode 100644
index 0000000000..01907b3353
--- /dev/null
+++ b/tools/include/linux/atomic.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __TOOLS_LINUX_ATOMIC_H
+#define __TOOLS_LINUX_ATOMIC_H
+
+#include <asm/atomic.h>
+
+void atomic_long_set(atomic_long_t *v, long i);
+
+/* atomic_cmpxchg_relaxed */
+#ifndef atomic_cmpxchg_relaxed
+#define atomic_cmpxchg_relaxed atomic_cmpxchg
+#define atomic_cmpxchg_release atomic_cmpxchg
+#endif /* atomic_cmpxchg_relaxed */
+
+#endif /* __TOOLS_LINUX_ATOMIC_H */
diff --git a/tools/include/linux/bitfield.h b/tools/include/linux/bitfield.h
new file mode 100644
index 0000000000..6093fa6db2
--- /dev/null
+++ b/tools/include/linux/bitfield.h
@@ -0,0 +1,176 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2014 Felix Fietkau <nbd@nbd.name>
+ * Copyright (C) 2004 - 2009 Ivo van Doorn <IvDoorn@gmail.com>
+ */
+
+#ifndef _LINUX_BITFIELD_H
+#define _LINUX_BITFIELD_H
+
+#include <linux/build_bug.h>
+#include <asm/byteorder.h>
+
+/*
+ * Bitfield access macros
+ *
+ * FIELD_{GET,PREP} macros take as first parameter shifted mask
+ * from which they extract the base mask and shift amount.
+ * Mask must be a compilation time constant.
+ *
+ * Example:
+ *
+ * #define REG_FIELD_A GENMASK(6, 0)
+ * #define REG_FIELD_B BIT(7)
+ * #define REG_FIELD_C GENMASK(15, 8)
+ * #define REG_FIELD_D GENMASK(31, 16)
+ *
+ * Get:
+ * a = FIELD_GET(REG_FIELD_A, reg);
+ * b = FIELD_GET(REG_FIELD_B, reg);
+ *
+ * Set:
+ * reg = FIELD_PREP(REG_FIELD_A, 1) |
+ * FIELD_PREP(REG_FIELD_B, 0) |
+ * FIELD_PREP(REG_FIELD_C, c) |
+ * FIELD_PREP(REG_FIELD_D, 0x40);
+ *
+ * Modify:
+ * reg &= ~REG_FIELD_C;
+ * reg |= FIELD_PREP(REG_FIELD_C, c);
+ */
+
+#define __bf_shf(x) (__builtin_ffsll(x) - 1)
+
+#define __scalar_type_to_unsigned_cases(type) \
+ unsigned type: (unsigned type)0, \
+ signed type: (unsigned type)0
+
+#define __unsigned_scalar_typeof(x) typeof( \
+ _Generic((x), \
+ char: (unsigned char)0, \
+ __scalar_type_to_unsigned_cases(char), \
+ __scalar_type_to_unsigned_cases(short), \
+ __scalar_type_to_unsigned_cases(int), \
+ __scalar_type_to_unsigned_cases(long), \
+ __scalar_type_to_unsigned_cases(long long), \
+ default: (x)))
+
+#define __bf_cast_unsigned(type, x) ((__unsigned_scalar_typeof(type))(x))
+
+#define __BF_FIELD_CHECK(_mask, _reg, _val, _pfx) \
+ ({ \
+ BUILD_BUG_ON_MSG(!__builtin_constant_p(_mask), \
+ _pfx "mask is not constant"); \
+ BUILD_BUG_ON_MSG((_mask) == 0, _pfx "mask is zero"); \
+ BUILD_BUG_ON_MSG(__builtin_constant_p(_val) ? \
+ ~((_mask) >> __bf_shf(_mask)) & (_val) : 0, \
+ _pfx "value too large for the field"); \
+ BUILD_BUG_ON_MSG(__bf_cast_unsigned(_mask, _mask) > \
+ __bf_cast_unsigned(_reg, ~0ull), \
+ _pfx "type of reg too small for mask"); \
+ __BUILD_BUG_ON_NOT_POWER_OF_2((_mask) + \
+ (1ULL << __bf_shf(_mask))); \
+ })
+
+/**
+ * FIELD_MAX() - produce the maximum value representable by a field
+ * @_mask: shifted mask defining the field's length and position
+ *
+ * FIELD_MAX() returns the maximum value that can be held in the field
+ * specified by @_mask.
+ */
+#define FIELD_MAX(_mask) \
+ ({ \
+ __BF_FIELD_CHECK(_mask, 0ULL, 0ULL, "FIELD_MAX: "); \
+ (typeof(_mask))((_mask) >> __bf_shf(_mask)); \
+ })
+
+/**
+ * FIELD_FIT() - check if value fits in the field
+ * @_mask: shifted mask defining the field's length and position
+ * @_val: value to test against the field
+ *
+ * Return: true if @_val can fit inside @_mask, false if @_val is too big.
+ */
+#define FIELD_FIT(_mask, _val) \
+ ({ \
+ __BF_FIELD_CHECK(_mask, 0ULL, 0ULL, "FIELD_FIT: "); \
+ !((((typeof(_mask))_val) << __bf_shf(_mask)) & ~(_mask)); \
+ })
+
+/**
+ * FIELD_PREP() - prepare a bitfield element
+ * @_mask: shifted mask defining the field's length and position
+ * @_val: value to put in the field
+ *
+ * FIELD_PREP() masks and shifts up the value. The result should
+ * be combined with other fields of the bitfield using logical OR.
+ */
+#define FIELD_PREP(_mask, _val) \
+ ({ \
+ __BF_FIELD_CHECK(_mask, 0ULL, _val, "FIELD_PREP: "); \
+ ((typeof(_mask))(_val) << __bf_shf(_mask)) & (_mask); \
+ })
+
+/**
+ * FIELD_GET() - extract a bitfield element
+ * @_mask: shifted mask defining the field's length and position
+ * @_reg: value of entire bitfield
+ *
+ * FIELD_GET() extracts the field specified by @_mask from the
+ * bitfield passed in as @_reg by masking and shifting it down.
+ */
+#define FIELD_GET(_mask, _reg) \
+ ({ \
+ __BF_FIELD_CHECK(_mask, _reg, 0U, "FIELD_GET: "); \
+ (typeof(_mask))(((_reg) & (_mask)) >> __bf_shf(_mask)); \
+ })
+
+extern void __compiletime_error("value doesn't fit into mask")
+__field_overflow(void);
+extern void __compiletime_error("bad bitfield mask")
+__bad_mask(void);
+static __always_inline u64 field_multiplier(u64 field)
+{
+ if ((field | (field - 1)) & ((field | (field - 1)) + 1))
+ __bad_mask();
+ return field & -field;
+}
+static __always_inline u64 field_mask(u64 field)
+{
+ return field / field_multiplier(field);
+}
+#define field_max(field) ((typeof(field))field_mask(field))
+#define ____MAKE_OP(type,base,to,from) \
+static __always_inline __##type type##_encode_bits(base v, base field) \
+{ \
+ if (__builtin_constant_p(v) && (v & ~field_mask(field))) \
+ __field_overflow(); \
+ return to((v & field_mask(field)) * field_multiplier(field)); \
+} \
+static __always_inline __##type type##_replace_bits(__##type old, \
+ base val, base field) \
+{ \
+ return (old & ~to(field)) | type##_encode_bits(val, field); \
+} \
+static __always_inline void type##p_replace_bits(__##type *p, \
+ base val, base field) \
+{ \
+ *p = (*p & ~to(field)) | type##_encode_bits(val, field); \
+} \
+static __always_inline base type##_get_bits(__##type v, base field) \
+{ \
+ return (from(v) & field)/field_multiplier(field); \
+}
+#define __MAKE_OP(size) \
+ ____MAKE_OP(le##size,u##size,cpu_to_le##size,le##size##_to_cpu) \
+ ____MAKE_OP(be##size,u##size,cpu_to_be##size,be##size##_to_cpu) \
+ ____MAKE_OP(u##size,u##size,,)
+____MAKE_OP(u8,u8,,)
+__MAKE_OP(16)
+__MAKE_OP(32)
+__MAKE_OP(64)
+#undef __MAKE_OP
+#undef ____MAKE_OP
+
+#endif
diff --git a/tools/include/linux/bitmap.h b/tools/include/linux/bitmap.h
new file mode 100644
index 0000000000..f3566ea0f9
--- /dev/null
+++ b/tools/include/linux/bitmap.h
@@ -0,0 +1,152 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TOOLS_LINUX_BITMAP_H
+#define _TOOLS_LINUX_BITMAP_H
+
+#include <string.h>
+#include <linux/bitops.h>
+#include <linux/find.h>
+#include <stdlib.h>
+#include <linux/kernel.h>
+
+#define DECLARE_BITMAP(name,bits) \
+ unsigned long name[BITS_TO_LONGS(bits)]
+
+unsigned int __bitmap_weight(const unsigned long *bitmap, int bits);
+void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1,
+ const unsigned long *bitmap2, int bits);
+bool __bitmap_and(unsigned long *dst, const unsigned long *bitmap1,
+ const unsigned long *bitmap2, unsigned int bits);
+bool __bitmap_equal(const unsigned long *bitmap1,
+ const unsigned long *bitmap2, unsigned int bits);
+void bitmap_clear(unsigned long *map, unsigned int start, int len);
+bool __bitmap_intersects(const unsigned long *bitmap1,
+ const unsigned long *bitmap2, unsigned int bits);
+
+#define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) & (BITS_PER_LONG - 1)))
+#define BITMAP_LAST_WORD_MASK(nbits) (~0UL >> (-(nbits) & (BITS_PER_LONG - 1)))
+
+static inline void bitmap_zero(unsigned long *dst, unsigned int nbits)
+{
+ if (small_const_nbits(nbits))
+ *dst = 0UL;
+ else {
+ int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long);
+ memset(dst, 0, len);
+ }
+}
+
+static inline void bitmap_fill(unsigned long *dst, unsigned int nbits)
+{
+ unsigned int nlongs = BITS_TO_LONGS(nbits);
+ if (!small_const_nbits(nbits)) {
+ unsigned int len = (nlongs - 1) * sizeof(unsigned long);
+ memset(dst, 0xff, len);
+ }
+ dst[nlongs - 1] = BITMAP_LAST_WORD_MASK(nbits);
+}
+
+static inline bool bitmap_empty(const unsigned long *src, unsigned int nbits)
+{
+ if (small_const_nbits(nbits))
+ return ! (*src & BITMAP_LAST_WORD_MASK(nbits));
+
+ return find_first_bit(src, nbits) == nbits;
+}
+
+static inline bool bitmap_full(const unsigned long *src, unsigned int nbits)
+{
+ if (small_const_nbits(nbits))
+ return ! (~(*src) & BITMAP_LAST_WORD_MASK(nbits));
+
+ return find_first_zero_bit(src, nbits) == nbits;
+}
+
+static inline unsigned int bitmap_weight(const unsigned long *src, unsigned int nbits)
+{
+ if (small_const_nbits(nbits))
+ return hweight_long(*src & BITMAP_LAST_WORD_MASK(nbits));
+ return __bitmap_weight(src, nbits);
+}
+
+static inline void bitmap_or(unsigned long *dst, const unsigned long *src1,
+ const unsigned long *src2, unsigned int nbits)
+{
+ if (small_const_nbits(nbits))
+ *dst = *src1 | *src2;
+ else
+ __bitmap_or(dst, src1, src2, nbits);
+}
+
+/**
+ * bitmap_zalloc - Allocate bitmap
+ * @nbits: Number of bits
+ */
+static inline unsigned long *bitmap_zalloc(int nbits)
+{
+ return calloc(1, BITS_TO_LONGS(nbits) * sizeof(unsigned long));
+}
+
+/*
+ * bitmap_free - Free bitmap
+ * @bitmap: pointer to bitmap
+ */
+static inline void bitmap_free(unsigned long *bitmap)
+{
+ free(bitmap);
+}
+
+/*
+ * bitmap_scnprintf - print bitmap list into buffer
+ * @bitmap: bitmap
+ * @nbits: size of bitmap
+ * @buf: buffer to store output
+ * @size: size of @buf
+ */
+size_t bitmap_scnprintf(unsigned long *bitmap, unsigned int nbits,
+ char *buf, size_t size);
+
+/**
+ * bitmap_and - Do logical and on bitmaps
+ * @dst: resulting bitmap
+ * @src1: operand 1
+ * @src2: operand 2
+ * @nbits: size of bitmap
+ */
+static inline bool bitmap_and(unsigned long *dst, const unsigned long *src1,
+ const unsigned long *src2, unsigned int nbits)
+{
+ if (small_const_nbits(nbits))
+ return (*dst = *src1 & *src2 & BITMAP_LAST_WORD_MASK(nbits)) != 0;
+ return __bitmap_and(dst, src1, src2, nbits);
+}
+
+#ifdef __LITTLE_ENDIAN
+#define BITMAP_MEM_ALIGNMENT 8
+#else
+#define BITMAP_MEM_ALIGNMENT (8 * sizeof(unsigned long))
+#endif
+#define BITMAP_MEM_MASK (BITMAP_MEM_ALIGNMENT - 1)
+#define IS_ALIGNED(x, a) (((x) & ((typeof(x))(a) - 1)) == 0)
+
+static inline bool bitmap_equal(const unsigned long *src1,
+ const unsigned long *src2, unsigned int nbits)
+{
+ if (small_const_nbits(nbits))
+ return !((*src1 ^ *src2) & BITMAP_LAST_WORD_MASK(nbits));
+ if (__builtin_constant_p(nbits & BITMAP_MEM_MASK) &&
+ IS_ALIGNED(nbits, BITMAP_MEM_ALIGNMENT))
+ return !memcmp(src1, src2, nbits / 8);
+ return __bitmap_equal(src1, src2, nbits);
+}
+
+static inline bool bitmap_intersects(const unsigned long *src1,
+ const unsigned long *src2,
+ unsigned int nbits)
+{
+ if (small_const_nbits(nbits))
+ return ((*src1 & *src2) & BITMAP_LAST_WORD_MASK(nbits)) != 0;
+ else
+ return __bitmap_intersects(src1, src2, nbits);
+}
+
+#endif /* _TOOLS_LINUX_BITMAP_H */
diff --git a/tools/include/linux/bitops.h b/tools/include/linux/bitops.h
new file mode 100644
index 0000000000..f18683b95e
--- /dev/null
+++ b/tools/include/linux/bitops.h
@@ -0,0 +1,90 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TOOLS_LINUX_BITOPS_H_
+#define _TOOLS_LINUX_BITOPS_H_
+
+#include <asm/types.h>
+#include <limits.h>
+#ifndef __WORDSIZE
+#define __WORDSIZE (__SIZEOF_LONG__ * 8)
+#endif
+
+#ifndef BITS_PER_LONG
+# define BITS_PER_LONG __WORDSIZE
+#endif
+#include <linux/bits.h>
+#include <linux/compiler.h>
+
+#define BITS_PER_TYPE(type) (sizeof(type) * BITS_PER_BYTE)
+#define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_TYPE(long))
+#define BITS_TO_U64(nr) DIV_ROUND_UP(nr, BITS_PER_TYPE(u64))
+#define BITS_TO_U32(nr) DIV_ROUND_UP(nr, BITS_PER_TYPE(u32))
+#define BITS_TO_BYTES(nr) DIV_ROUND_UP(nr, BITS_PER_TYPE(char))
+
+extern unsigned int __sw_hweight8(unsigned int w);
+extern unsigned int __sw_hweight16(unsigned int w);
+extern unsigned int __sw_hweight32(unsigned int w);
+extern unsigned long __sw_hweight64(__u64 w);
+
+/*
+ * Defined here because those may be needed by architecture-specific static
+ * inlines.
+ */
+
+#define bitop(op, nr, addr) \
+ op(nr, addr)
+
+#define __set_bit(nr, addr) bitop(___set_bit, nr, addr)
+#define __clear_bit(nr, addr) bitop(___clear_bit, nr, addr)
+#define __change_bit(nr, addr) bitop(___change_bit, nr, addr)
+#define __test_and_set_bit(nr, addr) bitop(___test_and_set_bit, nr, addr)
+#define __test_and_clear_bit(nr, addr) bitop(___test_and_clear_bit, nr, addr)
+#define __test_and_change_bit(nr, addr) bitop(___test_and_change_bit, nr, addr)
+#define test_bit(nr, addr) bitop(_test_bit, nr, addr)
+
+/*
+ * Include this here because some architectures need generic_ffs/fls in
+ * scope
+ *
+ * XXX: this needs to be asm/bitops.h, when we get to per arch optimizations
+ */
+#include <asm-generic/bitops.h>
+
+#define for_each_set_bit(bit, addr, size) \
+ for ((bit) = find_first_bit((addr), (size)); \
+ (bit) < (size); \
+ (bit) = find_next_bit((addr), (size), (bit) + 1))
+
+#define for_each_clear_bit(bit, addr, size) \
+ for ((bit) = find_first_zero_bit((addr), (size)); \
+ (bit) < (size); \
+ (bit) = find_next_zero_bit((addr), (size), (bit) + 1))
+
+/* same as for_each_set_bit() but use bit as value to start with */
+#define for_each_set_bit_from(bit, addr, size) \
+ for ((bit) = find_next_bit((addr), (size), (bit)); \
+ (bit) < (size); \
+ (bit) = find_next_bit((addr), (size), (bit) + 1))
+
+static inline unsigned long hweight_long(unsigned long w)
+{
+ return sizeof(w) == 4 ? hweight32(w) : hweight64(w);
+}
+
+static inline unsigned fls_long(unsigned long l)
+{
+ if (sizeof(l) == 4)
+ return fls(l);
+ return fls64(l);
+}
+
+/**
+ * rol32 - rotate a 32-bit value left
+ * @word: value to rotate
+ * @shift: bits to roll
+ */
+static inline __u32 rol32(__u32 word, unsigned int shift)
+{
+ return (word << shift) | (word >> ((-shift) & 31));
+}
+
+#endif
diff --git a/tools/include/linux/bits.h b/tools/include/linux/bits.h
new file mode 100644
index 0000000000..7c0cf5031a
--- /dev/null
+++ b/tools/include/linux/bits.h
@@ -0,0 +1,45 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_BITS_H
+#define __LINUX_BITS_H
+
+#include <linux/const.h>
+#include <vdso/bits.h>
+#include <asm/bitsperlong.h>
+
+#define BIT_MASK(nr) (UL(1) << ((nr) % BITS_PER_LONG))
+#define BIT_WORD(nr) ((nr) / BITS_PER_LONG)
+#define BIT_ULL_MASK(nr) (ULL(1) << ((nr) % BITS_PER_LONG_LONG))
+#define BIT_ULL_WORD(nr) ((nr) / BITS_PER_LONG_LONG)
+#define BITS_PER_BYTE 8
+
+/*
+ * Create a contiguous bitmask starting at bit position @l and ending at
+ * position @h. For example
+ * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000.
+ */
+#if !defined(__ASSEMBLY__)
+#include <linux/build_bug.h>
+#define GENMASK_INPUT_CHECK(h, l) \
+ (BUILD_BUG_ON_ZERO(__builtin_choose_expr( \
+ __is_constexpr((l) > (h)), (l) > (h), 0)))
+#else
+/*
+ * BUILD_BUG_ON_ZERO is not available in h files included from asm files,
+ * disable the input check if that is the case.
+ */
+#define GENMASK_INPUT_CHECK(h, l) 0
+#endif
+
+#define __GENMASK(h, l) \
+ (((~UL(0)) - (UL(1) << (l)) + 1) & \
+ (~UL(0) >> (BITS_PER_LONG - 1 - (h))))
+#define GENMASK(h, l) \
+ (GENMASK_INPUT_CHECK(h, l) + __GENMASK(h, l))
+
+#define __GENMASK_ULL(h, l) \
+ (((~ULL(0)) - (ULL(1) << (l)) + 1) & \
+ (~ULL(0) >> (BITS_PER_LONG_LONG - 1 - (h))))
+#define GENMASK_ULL(h, l) \
+ (GENMASK_INPUT_CHECK(h, l) + __GENMASK_ULL(h, l))
+
+#endif /* __LINUX_BITS_H */
diff --git a/tools/include/linux/btf_ids.h b/tools/include/linux/btf_ids.h
new file mode 100644
index 0000000000..2f882d5cb3
--- /dev/null
+++ b/tools/include/linux/btf_ids.h
@@ -0,0 +1,208 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _LINUX_BTF_IDS_H
+#define _LINUX_BTF_IDS_H
+
+struct btf_id_set {
+ u32 cnt;
+ u32 ids[];
+};
+
+#ifdef CONFIG_DEBUG_INFO_BTF
+
+#include <linux/compiler.h> /* for __PASTE */
+
+/*
+ * Following macros help to define lists of BTF IDs placed
+ * in .BTF_ids section. They are initially filled with zeros
+ * (during compilation) and resolved later during the
+ * linking phase by resolve_btfids tool.
+ *
+ * Any change in list layout must be reflected in resolve_btfids
+ * tool logic.
+ */
+
+#define BTF_IDS_SECTION ".BTF_ids"
+
+#define ____BTF_ID(symbol) \
+asm( \
+".pushsection " BTF_IDS_SECTION ",\"a\"; \n" \
+".local " #symbol " ; \n" \
+".type " #symbol ", STT_OBJECT; \n" \
+".size " #symbol ", 4; \n" \
+#symbol ": \n" \
+".zero 4 \n" \
+".popsection; \n");
+
+#define __BTF_ID(symbol) \
+ ____BTF_ID(symbol)
+
+#define __ID(prefix) \
+ __PASTE(__PASTE(prefix, __COUNTER__), __LINE__)
+
+/*
+ * The BTF_ID defines unique symbol for each ID pointing
+ * to 4 zero bytes.
+ */
+#define BTF_ID(prefix, name) \
+ __BTF_ID(__ID(__BTF_ID__##prefix##__##name##__))
+
+/*
+ * The BTF_ID_LIST macro defines pure (unsorted) list
+ * of BTF IDs, with following layout:
+ *
+ * BTF_ID_LIST(list1)
+ * BTF_ID(type1, name1)
+ * BTF_ID(type2, name2)
+ *
+ * list1:
+ * __BTF_ID__type1__name1__1:
+ * .zero 4
+ * __BTF_ID__type2__name2__2:
+ * .zero 4
+ *
+ */
+#define __BTF_ID_LIST(name, scope) \
+asm( \
+".pushsection " BTF_IDS_SECTION ",\"a\"; \n" \
+"." #scope " " #name "; \n" \
+#name ":; \n" \
+".popsection; \n");
+
+#define BTF_ID_LIST(name) \
+__BTF_ID_LIST(name, local) \
+extern u32 name[];
+
+#define BTF_ID_LIST_GLOBAL(name, n) \
+__BTF_ID_LIST(name, globl)
+
+/* The BTF_ID_LIST_SINGLE macro defines a BTF_ID_LIST with
+ * a single entry.
+ */
+#define BTF_ID_LIST_SINGLE(name, prefix, typename) \
+ BTF_ID_LIST(name) \
+ BTF_ID(prefix, typename)
+#define BTF_ID_LIST_GLOBAL_SINGLE(name, prefix, typename) \
+ BTF_ID_LIST_GLOBAL(name, 1) \
+ BTF_ID(prefix, typename)
+
+/*
+ * The BTF_ID_UNUSED macro defines 4 zero bytes.
+ * It's used when we want to define 'unused' entry
+ * in BTF_ID_LIST, like:
+ *
+ * BTF_ID_LIST(bpf_skb_output_btf_ids)
+ * BTF_ID(struct, sk_buff)
+ * BTF_ID_UNUSED
+ * BTF_ID(struct, task_struct)
+ */
+
+#define BTF_ID_UNUSED \
+asm( \
+".pushsection " BTF_IDS_SECTION ",\"a\"; \n" \
+".zero 4 \n" \
+".popsection; \n");
+
+/*
+ * The BTF_SET_START/END macros pair defines sorted list of
+ * BTF IDs plus its members count, with following layout:
+ *
+ * BTF_SET_START(list)
+ * BTF_ID(type1, name1)
+ * BTF_ID(type2, name2)
+ * BTF_SET_END(list)
+ *
+ * __BTF_ID__set__list:
+ * .zero 4
+ * list:
+ * __BTF_ID__type1__name1__3:
+ * .zero 4
+ * __BTF_ID__type2__name2__4:
+ * .zero 4
+ *
+ */
+#define __BTF_SET_START(name, scope) \
+asm( \
+".pushsection " BTF_IDS_SECTION ",\"a\"; \n" \
+"." #scope " __BTF_ID__set__" #name "; \n" \
+"__BTF_ID__set__" #name ":; \n" \
+".zero 4 \n" \
+".popsection; \n");
+
+#define BTF_SET_START(name) \
+__BTF_ID_LIST(name, local) \
+__BTF_SET_START(name, local)
+
+#define BTF_SET_START_GLOBAL(name) \
+__BTF_ID_LIST(name, globl) \
+__BTF_SET_START(name, globl)
+
+#define BTF_SET_END(name) \
+asm( \
+".pushsection " BTF_IDS_SECTION ",\"a\"; \n" \
+".size __BTF_ID__set__" #name ", .-" #name " \n" \
+".popsection; \n"); \
+extern struct btf_id_set name;
+
+#else
+
+#define BTF_ID_LIST(name) static u32 __maybe_unused name[5];
+#define BTF_ID(prefix, name)
+#define BTF_ID_UNUSED
+#define BTF_ID_LIST_GLOBAL(name, n) u32 __maybe_unused name[n];
+#define BTF_ID_LIST_SINGLE(name, prefix, typename) static u32 __maybe_unused name[1];
+#define BTF_ID_LIST_GLOBAL_SINGLE(name, prefix, typename) u32 __maybe_unused name[1];
+#define BTF_SET_START(name) static struct btf_id_set __maybe_unused name = { 0 };
+#define BTF_SET_START_GLOBAL(name) static struct btf_id_set __maybe_unused name = { 0 };
+#define BTF_SET_END(name)
+
+#endif /* CONFIG_DEBUG_INFO_BTF */
+
+#ifdef CONFIG_NET
+/* Define a list of socket types which can be the argument for
+ * skc_to_*_sock() helpers. All these sockets should have
+ * sock_common as the first argument in its memory layout.
+ */
+#define BTF_SOCK_TYPE_xxx \
+ BTF_SOCK_TYPE(BTF_SOCK_TYPE_INET, inet_sock) \
+ BTF_SOCK_TYPE(BTF_SOCK_TYPE_INET_CONN, inet_connection_sock) \
+ BTF_SOCK_TYPE(BTF_SOCK_TYPE_INET_REQ, inet_request_sock) \
+ BTF_SOCK_TYPE(BTF_SOCK_TYPE_INET_TW, inet_timewait_sock) \
+ BTF_SOCK_TYPE(BTF_SOCK_TYPE_REQ, request_sock) \
+ BTF_SOCK_TYPE(BTF_SOCK_TYPE_SOCK, sock) \
+ BTF_SOCK_TYPE(BTF_SOCK_TYPE_SOCK_COMMON, sock_common) \
+ BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP, tcp_sock) \
+ BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP_REQ, tcp_request_sock) \
+ BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP_TW, tcp_timewait_sock) \
+ BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP6, tcp6_sock) \
+ BTF_SOCK_TYPE(BTF_SOCK_TYPE_UDP, udp_sock) \
+ BTF_SOCK_TYPE(BTF_SOCK_TYPE_UDP6, udp6_sock) \
+ BTF_SOCK_TYPE(BTF_SOCK_TYPE_UNIX, unix_sock) \
+ BTF_SOCK_TYPE(BTF_SOCK_TYPE_MPTCP, mptcp_sock) \
+ BTF_SOCK_TYPE(BTF_SOCK_TYPE_SOCKET, socket)
+
+enum {
+#define BTF_SOCK_TYPE(name, str) name,
+BTF_SOCK_TYPE_xxx
+#undef BTF_SOCK_TYPE
+MAX_BTF_SOCK_TYPE,
+};
+
+extern u32 btf_sock_ids[];
+#endif
+
+#define BTF_TRACING_TYPE_xxx \
+ BTF_TRACING_TYPE(BTF_TRACING_TYPE_TASK, task_struct) \
+ BTF_TRACING_TYPE(BTF_TRACING_TYPE_FILE, file) \
+ BTF_TRACING_TYPE(BTF_TRACING_TYPE_VMA, vm_area_struct)
+
+enum {
+#define BTF_TRACING_TYPE(name, type) name,
+BTF_TRACING_TYPE_xxx
+#undef BTF_TRACING_TYPE
+MAX_BTF_TRACING_TYPE,
+};
+
+extern u32 btf_tracing_ids[];
+
+#endif
diff --git a/tools/include/linux/bug.h b/tools/include/linux/bug.h
new file mode 100644
index 0000000000..85f80258a1
--- /dev/null
+++ b/tools/include/linux/bug.h
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TOOLS_PERF_LINUX_BUG_H
+#define _TOOLS_PERF_LINUX_BUG_H
+
+/* Force a compilation error if condition is true, but also produce a
+ result (of value 0 and type size_t), so the expression can be used
+ e.g. in a structure initializer (or where-ever else comma expressions
+ aren't permitted). */
+#define BUILD_BUG_ON_ZERO(e) (sizeof(struct { int:-!!(e); }))
+
+#endif /* _TOOLS_PERF_LINUX_BUG_H */
diff --git a/tools/include/linux/build_bug.h b/tools/include/linux/build_bug.h
new file mode 100644
index 0000000000..b4898ff085
--- /dev/null
+++ b/tools/include/linux/build_bug.h
@@ -0,0 +1,91 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_BUILD_BUG_H
+#define _LINUX_BUILD_BUG_H
+
+#include <linux/compiler.h>
+
+#ifdef __CHECKER__
+#define BUILD_BUG_ON_ZERO(e) (0)
+#else /* __CHECKER__ */
+/*
+ * Force a compilation error if condition is true, but also produce a
+ * result (of value 0 and type int), so the expression can be used
+ * e.g. in a structure initializer (or where-ever else comma expressions
+ * aren't permitted).
+ */
+#define BUILD_BUG_ON_ZERO(e) ((int)(sizeof(struct { int:(-!!(e)); })))
+#endif /* __CHECKER__ */
+
+/* Force a compilation error if a constant expression is not a power of 2 */
+#define __BUILD_BUG_ON_NOT_POWER_OF_2(n) \
+ BUILD_BUG_ON(((n) & ((n) - 1)) != 0)
+#define BUILD_BUG_ON_NOT_POWER_OF_2(n) \
+ BUILD_BUG_ON((n) == 0 || (((n) & ((n) - 1)) != 0))
+
+/*
+ * BUILD_BUG_ON_INVALID() permits the compiler to check the validity of the
+ * expression but avoids the generation of any code, even if that expression
+ * has side-effects.
+ */
+#define BUILD_BUG_ON_INVALID(e) ((void)(sizeof((__force long)(e))))
+
+/**
+ * BUILD_BUG_ON_MSG - break compile if a condition is true & emit supplied
+ * error message.
+ * @condition: the condition which the compiler should know is false.
+ *
+ * See BUILD_BUG_ON for description.
+ */
+#define BUILD_BUG_ON_MSG(cond, msg) compiletime_assert(!(cond), msg)
+
+/**
+ * BUILD_BUG_ON - break compile if a condition is true.
+ * @condition: the condition which the compiler should know is false.
+ *
+ * If you have some code which relies on certain constants being equal, or
+ * some other compile-time-evaluated condition, you should use BUILD_BUG_ON to
+ * detect if someone changes it.
+ */
+#define BUILD_BUG_ON(condition) \
+ BUILD_BUG_ON_MSG(condition, "BUILD_BUG_ON failed: " #condition)
+
+/**
+ * BUILD_BUG - break compile if used.
+ *
+ * If you have some code that you expect the compiler to eliminate at
+ * build time, you should use BUILD_BUG to detect if it is
+ * unexpectedly used.
+ */
+#define BUILD_BUG() BUILD_BUG_ON_MSG(1, "BUILD_BUG failed")
+
+/**
+ * static_assert - check integer constant expression at build time
+ *
+ * static_assert() is a wrapper for the C11 _Static_assert, with a
+ * little macro magic to make the message optional (defaulting to the
+ * stringification of the tested expression).
+ *
+ * Contrary to BUILD_BUG_ON(), static_assert() can be used at global
+ * scope, but requires the expression to be an integer constant
+ * expression (i.e., it is not enough that __builtin_constant_p() is
+ * true for expr).
+ *
+ * Also note that BUILD_BUG_ON() fails the build if the condition is
+ * true, while static_assert() fails the build if the expression is
+ * false.
+ */
+#ifndef static_assert
+#define static_assert(expr, ...) __static_assert(expr, ##__VA_ARGS__, #expr)
+#define __static_assert(expr, msg, ...) _Static_assert(expr, msg)
+#endif // static_assert
+
+
+/*
+ * Compile time check that field has an expected offset
+ */
+#define ASSERT_STRUCT_OFFSET(type, field, expected_offset) \
+ BUILD_BUG_ON_MSG(offsetof(type, field) != (expected_offset), \
+ "Offset of " #field " in " #type " has changed.")
+
+
+#endif /* _LINUX_BUILD_BUG_H */
diff --git a/tools/include/linux/cache.h b/tools/include/linux/cache.h
new file mode 100644
index 0000000000..9e9d585f0b
--- /dev/null
+++ b/tools/include/linux/cache.h
@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TOOLS_LINUX_CACHE_H
+#define _TOOLS_LINUX_CACHE_H
+
+#define L1_CACHE_SHIFT 5
+#define L1_CACHE_BYTES (1 << L1_CACHE_SHIFT)
+
+#define SMP_CACHE_BYTES L1_CACHE_BYTES
+
+#endif
diff --git a/tools/include/linux/compiler-gcc.h b/tools/include/linux/compiler-gcc.h
new file mode 100644
index 0000000000..62e7c901ac
--- /dev/null
+++ b/tools/include/linux/compiler-gcc.h
@@ -0,0 +1,42 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TOOLS_LINUX_COMPILER_H_
+#error "Please don't include <linux/compiler-gcc.h> directly, include <linux/compiler.h> instead."
+#endif
+
+/*
+ * Common definitions for all gcc versions go here.
+ */
+#ifndef GCC_VERSION
+#define GCC_VERSION (__GNUC__ * 10000 \
+ + __GNUC_MINOR__ * 100 \
+ + __GNUC_PATCHLEVEL__)
+#endif
+
+#if __has_attribute(__fallthrough__)
+# define fallthrough __attribute__((__fallthrough__))
+#else
+# define fallthrough do {} while (0) /* fallthrough */
+#endif
+
+#if __has_attribute(__error__)
+# define __compiletime_error(message) __attribute__((error(message)))
+#endif
+
+/* &a[0] degrades to a pointer: a different type from an array */
+#define __must_be_array(a) BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0]))
+
+#ifndef __pure
+#define __pure __attribute__((pure))
+#endif
+#define noinline __attribute__((noinline))
+#ifndef __packed
+#define __packed __attribute__((packed))
+#endif
+#ifndef __noreturn
+#define __noreturn __attribute__((noreturn))
+#endif
+#ifndef __aligned
+#define __aligned(x) __attribute__((aligned(x)))
+#endif
+#define __printf(a, b) __attribute__((format(printf, a, b)))
+#define __scanf(a, b) __attribute__((format(scanf, a, b)))
diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h
new file mode 100644
index 0000000000..1684216e82
--- /dev/null
+++ b/tools/include/linux/compiler.h
@@ -0,0 +1,211 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TOOLS_LINUX_COMPILER_H_
+#define _TOOLS_LINUX_COMPILER_H_
+
+#include <linux/compiler_types.h>
+
+#ifndef __compiletime_error
+# define __compiletime_error(message)
+#endif
+
+#ifdef __OPTIMIZE__
+# define __compiletime_assert(condition, msg, prefix, suffix) \
+ do { \
+ extern void prefix ## suffix(void) __compiletime_error(msg); \
+ if (!(condition)) \
+ prefix ## suffix(); \
+ } while (0)
+#else
+# define __compiletime_assert(condition, msg, prefix, suffix) do { } while (0)
+#endif
+
+#define _compiletime_assert(condition, msg, prefix, suffix) \
+ __compiletime_assert(condition, msg, prefix, suffix)
+
+/**
+ * compiletime_assert - break build and emit msg if condition is false
+ * @condition: a compile-time constant condition to check
+ * @msg: a message to emit if condition is false
+ *
+ * In tradition of POSIX assert, this macro will break the build if the
+ * supplied condition is *false*, emitting the supplied error message if the
+ * compiler has support to do so.
+ */
+#define compiletime_assert(condition, msg) \
+ _compiletime_assert(condition, msg, __compiletime_assert_, __COUNTER__)
+
+/* Optimization barrier */
+/* The "volatile" is due to gcc bugs */
+#define barrier() __asm__ __volatile__("": : :"memory")
+
+#ifndef __always_inline
+# define __always_inline inline __attribute__((always_inline))
+#endif
+
+#ifndef __always_unused
+#define __always_unused __attribute__((__unused__))
+#endif
+
+#ifndef __noreturn
+#define __noreturn __attribute__((__noreturn__))
+#endif
+
+#ifndef unreachable
+#define unreachable() __builtin_unreachable()
+#endif
+
+#ifndef noinline
+#define noinline
+#endif
+
+/* Are two types/vars the same type (ignoring qualifiers)? */
+#ifndef __same_type
+# define __same_type(a, b) __builtin_types_compatible_p(typeof(a), typeof(b))
+#endif
+
+#ifdef __ANDROID__
+/*
+ * FIXME: Big hammer to get rid of tons of:
+ * "warning: always_inline function might not be inlinable"
+ *
+ * At least on android-ndk-r12/platforms/android-24/arch-arm
+ */
+#undef __always_inline
+#define __always_inline inline
+#endif
+
+#define __user
+#define __rcu
+#define __read_mostly
+
+#ifndef __attribute_const__
+# define __attribute_const__
+#endif
+
+#ifndef __maybe_unused
+# define __maybe_unused __attribute__((unused))
+#endif
+
+#ifndef __used
+# define __used __attribute__((__unused__))
+#endif
+
+#ifndef __packed
+# define __packed __attribute__((__packed__))
+#endif
+
+#ifndef __force
+# define __force
+#endif
+
+#ifndef __weak
+# define __weak __attribute__((weak))
+#endif
+
+#ifndef likely
+# define likely(x) __builtin_expect(!!(x), 1)
+#endif
+
+#ifndef unlikely
+# define unlikely(x) __builtin_expect(!!(x), 0)
+#endif
+
+#ifndef __init
+# define __init
+#endif
+
+#include <linux/types.h>
+
+/*
+ * Following functions are taken from kernel sources and
+ * break aliasing rules in their original form.
+ *
+ * While kernel is compiled with -fno-strict-aliasing,
+ * perf uses -Wstrict-aliasing=3 which makes build fail
+ * under gcc 4.4.
+ *
+ * Using extra __may_alias__ type to allow aliasing
+ * in this case.
+ */
+typedef __u8 __attribute__((__may_alias__)) __u8_alias_t;
+typedef __u16 __attribute__((__may_alias__)) __u16_alias_t;
+typedef __u32 __attribute__((__may_alias__)) __u32_alias_t;
+typedef __u64 __attribute__((__may_alias__)) __u64_alias_t;
+
+static __always_inline void __read_once_size(const volatile void *p, void *res, int size)
+{
+ switch (size) {
+ case 1: *(__u8_alias_t *) res = *(volatile __u8_alias_t *) p; break;
+ case 2: *(__u16_alias_t *) res = *(volatile __u16_alias_t *) p; break;
+ case 4: *(__u32_alias_t *) res = *(volatile __u32_alias_t *) p; break;
+ case 8: *(__u64_alias_t *) res = *(volatile __u64_alias_t *) p; break;
+ default:
+ barrier();
+ __builtin_memcpy((void *)res, (const void *)p, size);
+ barrier();
+ }
+}
+
+static __always_inline void __write_once_size(volatile void *p, void *res, int size)
+{
+ switch (size) {
+ case 1: *(volatile __u8_alias_t *) p = *(__u8_alias_t *) res; break;
+ case 2: *(volatile __u16_alias_t *) p = *(__u16_alias_t *) res; break;
+ case 4: *(volatile __u32_alias_t *) p = *(__u32_alias_t *) res; break;
+ case 8: *(volatile __u64_alias_t *) p = *(__u64_alias_t *) res; break;
+ default:
+ barrier();
+ __builtin_memcpy((void *)p, (const void *)res, size);
+ barrier();
+ }
+}
+
+/*
+ * Prevent the compiler from merging or refetching reads or writes. The
+ * compiler is also forbidden from reordering successive instances of
+ * READ_ONCE and WRITE_ONCE, but only when the compiler is aware of some
+ * particular ordering. One way to make the compiler aware of ordering is to
+ * put the two invocations of READ_ONCE or WRITE_ONCE in different C
+ * statements.
+ *
+ * These two macros will also work on aggregate data types like structs or
+ * unions. If the size of the accessed data type exceeds the word size of
+ * the machine (e.g., 32 bits or 64 bits) READ_ONCE() and WRITE_ONCE() will
+ * fall back to memcpy and print a compile-time warning.
+ *
+ * Their two major use cases are: (1) Mediating communication between
+ * process-level code and irq/NMI handlers, all running on the same CPU,
+ * and (2) Ensuring that the compiler does not fold, spindle, or otherwise
+ * mutilate accesses that either do not require ordering or that interact
+ * with an explicit memory barrier or atomic instruction that provides the
+ * required ordering.
+ */
+
+#define READ_ONCE(x) \
+({ \
+ union { typeof(x) __val; char __c[1]; } __u = \
+ { .__c = { 0 } }; \
+ __read_once_size(&(x), __u.__c, sizeof(x)); \
+ __u.__val; \
+})
+
+#define WRITE_ONCE(x, val) \
+({ \
+ union { typeof(x) __val; char __c[1]; } __u = \
+ { .__val = (val) }; \
+ __write_once_size(&(x), __u.__c, sizeof(x)); \
+ __u.__val; \
+})
+
+
+/* Indirect macros required for expanded argument pasting, eg. __LINE__. */
+#define ___PASTE(a, b) a##b
+#define __PASTE(a, b) ___PASTE(a, b)
+
+#ifndef OPTIMIZER_HIDE_VAR
+/* Make the optimizer believe the variable can be manipulated arbitrarily. */
+#define OPTIMIZER_HIDE_VAR(var) \
+ __asm__ ("" : "=r" (var) : "0" (var))
+#endif
+
+#endif /* _TOOLS_LINUX_COMPILER_H */
diff --git a/tools/include/linux/compiler_types.h b/tools/include/linux/compiler_types.h
new file mode 100644
index 0000000000..1bdd834bdd
--- /dev/null
+++ b/tools/include/linux/compiler_types.h
@@ -0,0 +1,43 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_COMPILER_TYPES_H
+#define __LINUX_COMPILER_TYPES_H
+
+/* Builtins */
+
+/*
+ * __has_builtin is supported on gcc >= 10, clang >= 3 and icc >= 21.
+ * In the meantime, to support gcc < 10, we implement __has_builtin
+ * by hand.
+ */
+#ifndef __has_builtin
+#define __has_builtin(x) (0)
+#endif
+
+#ifdef __CHECKER__
+/* context/locking */
+# define __must_hold(x) __attribute__((context(x,1,1)))
+# define __acquires(x) __attribute__((context(x,0,1)))
+# define __releases(x) __attribute__((context(x,1,0)))
+# define __acquire(x) __context__(x,1)
+# define __release(x) __context__(x,-1)
+# define __cond_lock(x,c) ((c) ? ({ __acquire(x); 1; }) : 0)
+#else /* __CHECKER__ */
+/* context/locking */
+# define __must_hold(x)
+# define __acquires(x)
+# define __releases(x)
+# define __acquire(x) (void)0
+# define __release(x) (void)0
+# define __cond_lock(x,c) (c)
+#endif /* __CHECKER__ */
+
+/* Compiler specific macros. */
+#ifdef __GNUC__
+#include <linux/compiler-gcc.h>
+#endif
+
+#ifndef asm_volatile_goto
+#define asm_volatile_goto(x...) asm goto(x)
+#endif
+
+#endif /* __LINUX_COMPILER_TYPES_H */
diff --git a/tools/include/linux/const.h b/tools/include/linux/const.h
new file mode 100644
index 0000000000..435ddd72d2
--- /dev/null
+++ b/tools/include/linux/const.h
@@ -0,0 +1,14 @@
+#ifndef _LINUX_CONST_H
+#define _LINUX_CONST_H
+
+#include <vdso/const.h>
+
+/*
+ * This returns a constant expression while determining if an argument is
+ * a constant expression, most importantly without evaluating the argument.
+ * Glory to Martin Uecker <Martin.Uecker@med.uni-goettingen.de>
+ */
+#define __is_constexpr(x) \
+ (sizeof(int) == sizeof(*(8 ? ((void *)((long)(x) * 0l)) : (int *)8)))
+
+#endif /* _LINUX_CONST_H */
diff --git a/tools/include/linux/coresight-pmu.h b/tools/include/linux/coresight-pmu.h
new file mode 100644
index 0000000000..51ac441a37
--- /dev/null
+++ b/tools/include/linux/coresight-pmu.h
@@ -0,0 +1,60 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright(C) 2015 Linaro Limited. All rights reserved.
+ * Author: Mathieu Poirier <mathieu.poirier@linaro.org>
+ */
+
+#ifndef _LINUX_CORESIGHT_PMU_H
+#define _LINUX_CORESIGHT_PMU_H
+
+#include <linux/bits.h>
+
+#define CORESIGHT_ETM_PMU_NAME "cs_etm"
+
+/*
+ * The legacy Trace ID system based on fixed calculation from the cpu
+ * number. This has been replaced by drivers using a dynamic allocation
+ * system - but need to retain the legacy algorithm for backward comparibility
+ * in certain situations:-
+ * a) new perf running on older systems that generate the legacy mapping
+ * b) older tools that may not update at the same time as the kernel.
+ */
+#define CORESIGHT_LEGACY_CPU_TRACE_ID(cpu) (0x10 + (cpu * 2))
+
+/*
+ * Below are the definition of bit offsets for perf option, and works as
+ * arbitrary values for all ETM versions.
+ *
+ * Most of them are orignally from ETMv3.5/PTM's ETMCR config, therefore,
+ * ETMv3.5/PTM doesn't define ETMCR config bits with prefix "ETM3_" and
+ * directly use below macros as config bits.
+ */
+#define ETM_OPT_BRANCH_BROADCAST 8
+#define ETM_OPT_CYCACC 12
+#define ETM_OPT_CTXTID 14
+#define ETM_OPT_CTXTID2 15
+#define ETM_OPT_TS 28
+#define ETM_OPT_RETSTK 29
+
+/* ETMv4 CONFIGR programming bits for the ETM OPTs */
+#define ETM4_CFG_BIT_BB 3
+#define ETM4_CFG_BIT_CYCACC 4
+#define ETM4_CFG_BIT_CTXTID 6
+#define ETM4_CFG_BIT_VMID 7
+#define ETM4_CFG_BIT_TS 11
+#define ETM4_CFG_BIT_RETSTK 12
+#define ETM4_CFG_BIT_VMID_OPT 15
+
+/*
+ * Interpretation of the PERF_RECORD_AUX_OUTPUT_HW_ID payload.
+ * Used to associate a CPU with the CoreSight Trace ID.
+ * [07:00] - Trace ID - uses 8 bits to make value easy to read in file.
+ * [59:08] - Unused (SBZ)
+ * [63:60] - Version
+ */
+#define CS_AUX_HW_ID_TRACE_ID_MASK GENMASK_ULL(7, 0)
+#define CS_AUX_HW_ID_VERSION_MASK GENMASK_ULL(63, 60)
+
+#define CS_AUX_HW_ID_CURR_VERSION 0
+
+#endif
diff --git a/tools/include/linux/ctype.h b/tools/include/linux/ctype.h
new file mode 100644
index 0000000000..29ed3fe944
--- /dev/null
+++ b/tools/include/linux/ctype.h
@@ -0,0 +1,82 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_CTYPE_H
+#define _LINUX_CTYPE_H
+
+#include <linux/compiler.h>
+
+/*
+ * NOTE! This ctype does not handle EOF like the standard C
+ * library is required to.
+ */
+
+#define _U 0x01 /* upper */
+#define _L 0x02 /* lower */
+#define _D 0x04 /* digit */
+#define _C 0x08 /* cntrl */
+#define _P 0x10 /* punct */
+#define _S 0x20 /* white space (space/lf/tab) */
+#define _X 0x40 /* hex digit */
+#define _SP 0x80 /* hard space (0x20) */
+
+extern const unsigned char _ctype[];
+
+#define __ismask(x) (_ctype[(int)(unsigned char)(x)])
+
+#define isalnum(c) ((__ismask(c)&(_U|_L|_D)) != 0)
+#define isalpha(c) ((__ismask(c)&(_U|_L)) != 0)
+#define iscntrl(c) ((__ismask(c)&(_C)) != 0)
+#define isgraph(c) ((__ismask(c)&(_P|_U|_L|_D)) != 0)
+#define islower(c) ((__ismask(c)&(_L)) != 0)
+#define isprint(c) ((__ismask(c)&(_P|_U|_L|_D|_SP)) != 0)
+#define ispunct(c) ((__ismask(c)&(_P)) != 0)
+/* Note: isspace() must return false for %NUL-terminator */
+#define isspace(c) ((__ismask(c)&(_S)) != 0)
+#define isupper(c) ((__ismask(c)&(_U)) != 0)
+#define isxdigit(c) ((__ismask(c)&(_D|_X)) != 0)
+
+#define isascii(c) (((unsigned char)(c))<=0x7f)
+#define toascii(c) (((unsigned char)(c))&0x7f)
+
+#if __has_builtin(__builtin_isdigit)
+#define isdigit(c) __builtin_isdigit(c)
+#else
+static inline int __isdigit(int c)
+{
+ return '0' <= c && c <= '9';
+}
+#define isdigit(c) __isdigit(c)
+#endif
+
+static inline unsigned char __tolower(unsigned char c)
+{
+ if (isupper(c))
+ c -= 'A'-'a';
+ return c;
+}
+
+static inline unsigned char __toupper(unsigned char c)
+{
+ if (islower(c))
+ c -= 'a'-'A';
+ return c;
+}
+
+#define tolower(c) __tolower(c)
+#define toupper(c) __toupper(c)
+
+/*
+ * Fast implementation of tolower() for internal usage. Do not use in your
+ * code.
+ */
+static inline char _tolower(const char c)
+{
+ return c | 0x20;
+}
+
+/* Fast check for octal digit */
+static inline int isodigit(const char c)
+{
+ return c >= '0' && c <= '7';
+}
+
+#endif
diff --git a/tools/include/linux/debugfs.h b/tools/include/linux/debugfs.h
new file mode 100644
index 0000000000..4ba06140b1
--- /dev/null
+++ b/tools/include/linux/debugfs.h
@@ -0,0 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TOOLS_DEBUGFS_H
+#define _TOOLS_DEBUGFS_H
+
+#endif
diff --git a/tools/include/linux/delay.h b/tools/include/linux/delay.h
new file mode 100644
index 0000000000..55aa4173af
--- /dev/null
+++ b/tools/include/linux/delay.h
@@ -0,0 +1,4 @@
+#ifndef _TOOLS_INCLUDE_LINUX_DELAY_H
+#define _TOOLS_INCLUDE_LINUX_DELAY_H
+
+#endif /* _TOOLS_INCLUDE_LINUX_DELAY_H */
diff --git a/tools/include/linux/err.h b/tools/include/linux/err.h
new file mode 100644
index 0000000000..332b983ead
--- /dev/null
+++ b/tools/include/linux/err.h
@@ -0,0 +1,75 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __TOOLS_LINUX_ERR_H
+#define __TOOLS_LINUX_ERR_H
+
+#include <linux/compiler.h>
+#include <linux/types.h>
+
+#include <asm/errno.h>
+
+/*
+ * Original kernel header comment:
+ *
+ * Kernel pointers have redundant information, so we can use a
+ * scheme where we can return either an error code or a normal
+ * pointer with the same return value.
+ *
+ * This should be a per-architecture thing, to allow different
+ * error and pointer decisions.
+ *
+ * Userspace note:
+ * The same principle works for userspace, because 'error' pointers
+ * fall down to the unused hole far from user space, as described
+ * in Documentation/arch/x86/x86_64/mm.rst for x86_64 arch:
+ *
+ * 0000000000000000 - 00007fffffffffff (=47 bits) user space, different per mm hole caused by [48:63] sign extension
+ * ffffffffffe00000 - ffffffffffffffff (=2 MB) unused hole
+ *
+ * It should be the same case for other architectures, because
+ * this code is used in generic kernel code.
+ */
+#define MAX_ERRNO 4095
+
+#define IS_ERR_VALUE(x) unlikely((x) >= (unsigned long)-MAX_ERRNO)
+
+static inline void * __must_check ERR_PTR(long error_)
+{
+ return (void *) error_;
+}
+
+static inline long __must_check PTR_ERR(__force const void *ptr)
+{
+ return (long) ptr;
+}
+
+static inline bool __must_check IS_ERR(__force const void *ptr)
+{
+ return IS_ERR_VALUE((unsigned long)ptr);
+}
+
+static inline bool __must_check IS_ERR_OR_NULL(__force const void *ptr)
+{
+ return unlikely(!ptr) || IS_ERR_VALUE((unsigned long)ptr);
+}
+
+static inline int __must_check PTR_ERR_OR_ZERO(__force const void *ptr)
+{
+ if (IS_ERR(ptr))
+ return PTR_ERR(ptr);
+ else
+ return 0;
+}
+
+/**
+ * ERR_CAST - Explicitly cast an error-valued pointer to another pointer type
+ * @ptr: The pointer to cast.
+ *
+ * Explicitly cast an error-valued pointer to another pointer type in such a
+ * way as to make it clear that's what's going on.
+ */
+static inline void * __must_check ERR_CAST(__force const void *ptr)
+{
+ /* cast away the const */
+ return (void *) ptr;
+}
+#endif /* _LINUX_ERR_H */
diff --git a/tools/include/linux/export.h b/tools/include/linux/export.h
new file mode 100644
index 0000000000..acb6f4daa2
--- /dev/null
+++ b/tools/include/linux/export.h
@@ -0,0 +1,7 @@
+#ifndef _TOOLS_LINUX_EXPORT_H_
+#define _TOOLS_LINUX_EXPORT_H_
+
+#define EXPORT_SYMBOL(sym)
+#define EXPORT_SYMBOL_GPL(sym)
+
+#endif
diff --git a/tools/include/linux/filter.h b/tools/include/linux/filter.h
new file mode 100644
index 0000000000..736bdeccdf
--- /dev/null
+++ b/tools/include/linux/filter.h
@@ -0,0 +1,341 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Linux Socket Filter Data Structures
+ */
+#ifndef __TOOLS_LINUX_FILTER_H
+#define __TOOLS_LINUX_FILTER_H
+
+#include <linux/bpf.h>
+
+/* ArgX, context and stack frame pointer register positions. Note,
+ * Arg1, Arg2, Arg3, etc are used as argument mappings of function
+ * calls in BPF_CALL instruction.
+ */
+#define BPF_REG_ARG1 BPF_REG_1
+#define BPF_REG_ARG2 BPF_REG_2
+#define BPF_REG_ARG3 BPF_REG_3
+#define BPF_REG_ARG4 BPF_REG_4
+#define BPF_REG_ARG5 BPF_REG_5
+#define BPF_REG_CTX BPF_REG_6
+#define BPF_REG_FP BPF_REG_10
+
+/* Additional register mappings for converted user programs. */
+#define BPF_REG_A BPF_REG_0
+#define BPF_REG_X BPF_REG_7
+#define BPF_REG_TMP BPF_REG_8
+
+/* BPF program can access up to 512 bytes of stack space. */
+#define MAX_BPF_STACK 512
+
+/* Helper macros for filter block array initializers. */
+
+/* ALU ops on registers, bpf_add|sub|...: dst_reg += src_reg */
+
+#define BPF_ALU64_REG(OP, DST, SRC) \
+ ((struct bpf_insn) { \
+ .code = BPF_ALU64 | BPF_OP(OP) | BPF_X, \
+ .dst_reg = DST, \
+ .src_reg = SRC, \
+ .off = 0, \
+ .imm = 0 })
+
+#define BPF_ALU32_REG(OP, DST, SRC) \
+ ((struct bpf_insn) { \
+ .code = BPF_ALU | BPF_OP(OP) | BPF_X, \
+ .dst_reg = DST, \
+ .src_reg = SRC, \
+ .off = 0, \
+ .imm = 0 })
+
+/* ALU ops on immediates, bpf_add|sub|...: dst_reg += imm32 */
+
+#define BPF_ALU64_IMM(OP, DST, IMM) \
+ ((struct bpf_insn) { \
+ .code = BPF_ALU64 | BPF_OP(OP) | BPF_K, \
+ .dst_reg = DST, \
+ .src_reg = 0, \
+ .off = 0, \
+ .imm = IMM })
+
+#define BPF_ALU32_IMM(OP, DST, IMM) \
+ ((struct bpf_insn) { \
+ .code = BPF_ALU | BPF_OP(OP) | BPF_K, \
+ .dst_reg = DST, \
+ .src_reg = 0, \
+ .off = 0, \
+ .imm = IMM })
+
+/* Endianess conversion, cpu_to_{l,b}e(), {l,b}e_to_cpu() */
+
+#define BPF_ENDIAN(TYPE, DST, LEN) \
+ ((struct bpf_insn) { \
+ .code = BPF_ALU | BPF_END | BPF_SRC(TYPE), \
+ .dst_reg = DST, \
+ .src_reg = 0, \
+ .off = 0, \
+ .imm = LEN })
+
+/* Short form of mov, dst_reg = src_reg */
+
+#define BPF_MOV64_REG(DST, SRC) \
+ ((struct bpf_insn) { \
+ .code = BPF_ALU64 | BPF_MOV | BPF_X, \
+ .dst_reg = DST, \
+ .src_reg = SRC, \
+ .off = 0, \
+ .imm = 0 })
+
+#define BPF_MOV32_REG(DST, SRC) \
+ ((struct bpf_insn) { \
+ .code = BPF_ALU | BPF_MOV | BPF_X, \
+ .dst_reg = DST, \
+ .src_reg = SRC, \
+ .off = 0, \
+ .imm = 0 })
+
+/* Short form of mov, dst_reg = imm32 */
+
+#define BPF_MOV64_IMM(DST, IMM) \
+ ((struct bpf_insn) { \
+ .code = BPF_ALU64 | BPF_MOV | BPF_K, \
+ .dst_reg = DST, \
+ .src_reg = 0, \
+ .off = 0, \
+ .imm = IMM })
+
+#define BPF_MOV32_IMM(DST, IMM) \
+ ((struct bpf_insn) { \
+ .code = BPF_ALU | BPF_MOV | BPF_K, \
+ .dst_reg = DST, \
+ .src_reg = 0, \
+ .off = 0, \
+ .imm = IMM })
+
+/* Short form of mov based on type, BPF_X: dst_reg = src_reg, BPF_K: dst_reg = imm32 */
+
+#define BPF_MOV64_RAW(TYPE, DST, SRC, IMM) \
+ ((struct bpf_insn) { \
+ .code = BPF_ALU64 | BPF_MOV | BPF_SRC(TYPE), \
+ .dst_reg = DST, \
+ .src_reg = SRC, \
+ .off = 0, \
+ .imm = IMM })
+
+#define BPF_MOV32_RAW(TYPE, DST, SRC, IMM) \
+ ((struct bpf_insn) { \
+ .code = BPF_ALU | BPF_MOV | BPF_SRC(TYPE), \
+ .dst_reg = DST, \
+ .src_reg = SRC, \
+ .off = 0, \
+ .imm = IMM })
+
+/* Direct packet access, R0 = *(uint *) (skb->data + imm32) */
+
+#define BPF_LD_ABS(SIZE, IMM) \
+ ((struct bpf_insn) { \
+ .code = BPF_LD | BPF_SIZE(SIZE) | BPF_ABS, \
+ .dst_reg = 0, \
+ .src_reg = 0, \
+ .off = 0, \
+ .imm = IMM })
+
+/* Indirect packet access, R0 = *(uint *) (skb->data + src_reg + imm32) */
+
+#define BPF_LD_IND(SIZE, SRC, IMM) \
+ ((struct bpf_insn) { \
+ .code = BPF_LD | BPF_SIZE(SIZE) | BPF_IND, \
+ .dst_reg = 0, \
+ .src_reg = SRC, \
+ .off = 0, \
+ .imm = IMM })
+
+/* Memory load, dst_reg = *(uint *) (src_reg + off16) */
+
+#define BPF_LDX_MEM(SIZE, DST, SRC, OFF) \
+ ((struct bpf_insn) { \
+ .code = BPF_LDX | BPF_SIZE(SIZE) | BPF_MEM, \
+ .dst_reg = DST, \
+ .src_reg = SRC, \
+ .off = OFF, \
+ .imm = 0 })
+
+/* Memory store, *(uint *) (dst_reg + off16) = src_reg */
+
+#define BPF_STX_MEM(SIZE, DST, SRC, OFF) \
+ ((struct bpf_insn) { \
+ .code = BPF_STX | BPF_SIZE(SIZE) | BPF_MEM, \
+ .dst_reg = DST, \
+ .src_reg = SRC, \
+ .off = OFF, \
+ .imm = 0 })
+
+/*
+ * Atomic operations:
+ *
+ * BPF_ADD *(uint *) (dst_reg + off16) += src_reg
+ * BPF_AND *(uint *) (dst_reg + off16) &= src_reg
+ * BPF_OR *(uint *) (dst_reg + off16) |= src_reg
+ * BPF_XOR *(uint *) (dst_reg + off16) ^= src_reg
+ * BPF_ADD | BPF_FETCH src_reg = atomic_fetch_add(dst_reg + off16, src_reg);
+ * BPF_AND | BPF_FETCH src_reg = atomic_fetch_and(dst_reg + off16, src_reg);
+ * BPF_OR | BPF_FETCH src_reg = atomic_fetch_or(dst_reg + off16, src_reg);
+ * BPF_XOR | BPF_FETCH src_reg = atomic_fetch_xor(dst_reg + off16, src_reg);
+ * BPF_XCHG src_reg = atomic_xchg(dst_reg + off16, src_reg)
+ * BPF_CMPXCHG r0 = atomic_cmpxchg(dst_reg + off16, r0, src_reg)
+ */
+
+#define BPF_ATOMIC_OP(SIZE, OP, DST, SRC, OFF) \
+ ((struct bpf_insn) { \
+ .code = BPF_STX | BPF_SIZE(SIZE) | BPF_ATOMIC, \
+ .dst_reg = DST, \
+ .src_reg = SRC, \
+ .off = OFF, \
+ .imm = OP })
+
+/* Legacy alias */
+#define BPF_STX_XADD(SIZE, DST, SRC, OFF) BPF_ATOMIC_OP(SIZE, BPF_ADD, DST, SRC, OFF)
+
+/* Memory store, *(uint *) (dst_reg + off16) = imm32 */
+
+#define BPF_ST_MEM(SIZE, DST, OFF, IMM) \
+ ((struct bpf_insn) { \
+ .code = BPF_ST | BPF_SIZE(SIZE) | BPF_MEM, \
+ .dst_reg = DST, \
+ .src_reg = 0, \
+ .off = OFF, \
+ .imm = IMM })
+
+/* Conditional jumps against registers, if (dst_reg 'op' src_reg) goto pc + off16 */
+
+#define BPF_JMP_REG(OP, DST, SRC, OFF) \
+ ((struct bpf_insn) { \
+ .code = BPF_JMP | BPF_OP(OP) | BPF_X, \
+ .dst_reg = DST, \
+ .src_reg = SRC, \
+ .off = OFF, \
+ .imm = 0 })
+
+/* Like BPF_JMP_REG, but with 32-bit wide operands for comparison. */
+
+#define BPF_JMP32_REG(OP, DST, SRC, OFF) \
+ ((struct bpf_insn) { \
+ .code = BPF_JMP32 | BPF_OP(OP) | BPF_X, \
+ .dst_reg = DST, \
+ .src_reg = SRC, \
+ .off = OFF, \
+ .imm = 0 })
+
+/* Conditional jumps against immediates, if (dst_reg 'op' imm32) goto pc + off16 */
+
+#define BPF_JMP_IMM(OP, DST, IMM, OFF) \
+ ((struct bpf_insn) { \
+ .code = BPF_JMP | BPF_OP(OP) | BPF_K, \
+ .dst_reg = DST, \
+ .src_reg = 0, \
+ .off = OFF, \
+ .imm = IMM })
+
+/* Like BPF_JMP_IMM, but with 32-bit wide operands for comparison. */
+
+#define BPF_JMP32_IMM(OP, DST, IMM, OFF) \
+ ((struct bpf_insn) { \
+ .code = BPF_JMP32 | BPF_OP(OP) | BPF_K, \
+ .dst_reg = DST, \
+ .src_reg = 0, \
+ .off = OFF, \
+ .imm = IMM })
+
+/* Unconditional jumps, goto pc + off16 */
+
+#define BPF_JMP_A(OFF) \
+ ((struct bpf_insn) { \
+ .code = BPF_JMP | BPF_JA, \
+ .dst_reg = 0, \
+ .src_reg = 0, \
+ .off = OFF, \
+ .imm = 0 })
+
+/* Function call */
+
+#define BPF_EMIT_CALL(FUNC) \
+ ((struct bpf_insn) { \
+ .code = BPF_JMP | BPF_CALL, \
+ .dst_reg = 0, \
+ .src_reg = 0, \
+ .off = 0, \
+ .imm = ((FUNC) - BPF_FUNC_unspec) })
+
+/* Raw code statement block */
+
+#define BPF_RAW_INSN(CODE, DST, SRC, OFF, IMM) \
+ ((struct bpf_insn) { \
+ .code = CODE, \
+ .dst_reg = DST, \
+ .src_reg = SRC, \
+ .off = OFF, \
+ .imm = IMM })
+
+/* BPF_LD_IMM64 macro encodes single 'load 64-bit immediate' insn */
+
+#define BPF_LD_IMM64(DST, IMM) \
+ BPF_LD_IMM64_RAW(DST, 0, IMM)
+
+#define BPF_LD_IMM64_RAW(DST, SRC, IMM) \
+ ((struct bpf_insn) { \
+ .code = BPF_LD | BPF_DW | BPF_IMM, \
+ .dst_reg = DST, \
+ .src_reg = SRC, \
+ .off = 0, \
+ .imm = (__u32) (IMM) }), \
+ ((struct bpf_insn) { \
+ .code = 0, /* zero is reserved opcode */ \
+ .dst_reg = 0, \
+ .src_reg = 0, \
+ .off = 0, \
+ .imm = ((__u64) (IMM)) >> 32 })
+
+#define BPF_LD_IMM64_RAW_FULL(DST, SRC, OFF1, OFF2, IMM1, IMM2) \
+ ((struct bpf_insn) { \
+ .code = BPF_LD | BPF_DW | BPF_IMM, \
+ .dst_reg = DST, \
+ .src_reg = SRC, \
+ .off = OFF1, \
+ .imm = IMM1 }), \
+ ((struct bpf_insn) { \
+ .code = 0, /* zero is reserved opcode */ \
+ .dst_reg = 0, \
+ .src_reg = 0, \
+ .off = OFF2, \
+ .imm = IMM2 })
+
+/* pseudo BPF_LD_IMM64 insn used to refer to process-local map_fd */
+
+#define BPF_LD_MAP_FD(DST, MAP_FD) \
+ BPF_LD_IMM64_RAW_FULL(DST, BPF_PSEUDO_MAP_FD, 0, 0, \
+ MAP_FD, 0)
+
+#define BPF_LD_MAP_VALUE(DST, MAP_FD, VALUE_OFF) \
+ BPF_LD_IMM64_RAW_FULL(DST, BPF_PSEUDO_MAP_VALUE, 0, 0, \
+ MAP_FD, VALUE_OFF)
+
+/* Relative call */
+
+#define BPF_CALL_REL(TGT) \
+ ((struct bpf_insn) { \
+ .code = BPF_JMP | BPF_CALL, \
+ .dst_reg = 0, \
+ .src_reg = BPF_PSEUDO_CALL, \
+ .off = 0, \
+ .imm = TGT })
+
+/* Program exit */
+
+#define BPF_EXIT_INSN() \
+ ((struct bpf_insn) { \
+ .code = BPF_JMP | BPF_EXIT, \
+ .dst_reg = 0, \
+ .src_reg = 0, \
+ .off = 0, \
+ .imm = 0 })
+
+#endif /* __TOOLS_LINUX_FILTER_H */
diff --git a/tools/include/linux/find.h b/tools/include/linux/find.h
new file mode 100644
index 0000000000..38c0a542b0
--- /dev/null
+++ b/tools/include/linux/find.h
@@ -0,0 +1,177 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TOOLS_LINUX_FIND_H_
+#define _TOOLS_LINUX_FIND_H_
+
+#ifndef _TOOLS_LINUX_BITMAP_H
+#error tools: only <linux/bitmap.h> can be included directly
+#endif
+
+#include <linux/bitops.h>
+
+unsigned long _find_next_bit(const unsigned long *addr1, unsigned long nbits,
+ unsigned long start);
+unsigned long _find_next_and_bit(const unsigned long *addr1, const unsigned long *addr2,
+ unsigned long nbits, unsigned long start);
+unsigned long _find_next_zero_bit(const unsigned long *addr, unsigned long nbits,
+ unsigned long start);
+extern unsigned long _find_first_bit(const unsigned long *addr, unsigned long size);
+extern unsigned long _find_first_and_bit(const unsigned long *addr1,
+ const unsigned long *addr2, unsigned long size);
+extern unsigned long _find_first_zero_bit(const unsigned long *addr, unsigned long size);
+
+#ifndef find_next_bit
+/**
+ * find_next_bit - find the next set bit in a memory region
+ * @addr: The address to base the search on
+ * @size: The bitmap size in bits
+ * @offset: The bitnumber to start searching at
+ *
+ * Returns the bit number for the next set bit
+ * If no bits are set, returns @size.
+ */
+static inline
+unsigned long find_next_bit(const unsigned long *addr, unsigned long size,
+ unsigned long offset)
+{
+ if (small_const_nbits(size)) {
+ unsigned long val;
+
+ if (unlikely(offset >= size))
+ return size;
+
+ val = *addr & GENMASK(size - 1, offset);
+ return val ? __ffs(val) : size;
+ }
+
+ return _find_next_bit(addr, size, offset);
+}
+#endif
+
+#ifndef find_next_and_bit
+/**
+ * find_next_and_bit - find the next set bit in both memory regions
+ * @addr1: The first address to base the search on
+ * @addr2: The second address to base the search on
+ * @size: The bitmap size in bits
+ * @offset: The bitnumber to start searching at
+ *
+ * Returns the bit number for the next set bit
+ * If no bits are set, returns @size.
+ */
+static inline
+unsigned long find_next_and_bit(const unsigned long *addr1,
+ const unsigned long *addr2, unsigned long size,
+ unsigned long offset)
+{
+ if (small_const_nbits(size)) {
+ unsigned long val;
+
+ if (unlikely(offset >= size))
+ return size;
+
+ val = *addr1 & *addr2 & GENMASK(size - 1, offset);
+ return val ? __ffs(val) : size;
+ }
+
+ return _find_next_and_bit(addr1, addr2, size, offset);
+}
+#endif
+
+#ifndef find_next_zero_bit
+/**
+ * find_next_zero_bit - find the next cleared bit in a memory region
+ * @addr: The address to base the search on
+ * @size: The bitmap size in bits
+ * @offset: The bitnumber to start searching at
+ *
+ * Returns the bit number of the next zero bit
+ * If no bits are zero, returns @size.
+ */
+static inline
+unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size,
+ unsigned long offset)
+{
+ if (small_const_nbits(size)) {
+ unsigned long val;
+
+ if (unlikely(offset >= size))
+ return size;
+
+ val = *addr | ~GENMASK(size - 1, offset);
+ return val == ~0UL ? size : ffz(val);
+ }
+
+ return _find_next_zero_bit(addr, size, offset);
+}
+#endif
+
+#ifndef find_first_bit
+/**
+ * find_first_bit - find the first set bit in a memory region
+ * @addr: The address to start the search at
+ * @size: The maximum number of bits to search
+ *
+ * Returns the bit number of the first set bit.
+ * If no bits are set, returns @size.
+ */
+static inline
+unsigned long find_first_bit(const unsigned long *addr, unsigned long size)
+{
+ if (small_const_nbits(size)) {
+ unsigned long val = *addr & GENMASK(size - 1, 0);
+
+ return val ? __ffs(val) : size;
+ }
+
+ return _find_first_bit(addr, size);
+}
+#endif
+
+#ifndef find_first_and_bit
+/**
+ * find_first_and_bit - find the first set bit in both memory regions
+ * @addr1: The first address to base the search on
+ * @addr2: The second address to base the search on
+ * @size: The bitmap size in bits
+ *
+ * Returns the bit number for the next set bit
+ * If no bits are set, returns @size.
+ */
+static inline
+unsigned long find_first_and_bit(const unsigned long *addr1,
+ const unsigned long *addr2,
+ unsigned long size)
+{
+ if (small_const_nbits(size)) {
+ unsigned long val = *addr1 & *addr2 & GENMASK(size - 1, 0);
+
+ return val ? __ffs(val) : size;
+ }
+
+ return _find_first_and_bit(addr1, addr2, size);
+}
+#endif
+
+#ifndef find_first_zero_bit
+/**
+ * find_first_zero_bit - find the first cleared bit in a memory region
+ * @addr: The address to start the search at
+ * @size: The maximum number of bits to search
+ *
+ * Returns the bit number of the first cleared bit.
+ * If no bits are zero, returns @size.
+ */
+static inline
+unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size)
+{
+ if (small_const_nbits(size)) {
+ unsigned long val = *addr | ~GENMASK(size - 1, 0);
+
+ return val == ~0UL ? size : ffz(val);
+ }
+
+ return _find_first_zero_bit(addr, size);
+}
+#endif
+
+#endif /*__LINUX_FIND_H_ */
diff --git a/tools/include/linux/ftrace.h b/tools/include/linux/ftrace.h
new file mode 100644
index 0000000000..949f541ce1
--- /dev/null
+++ b/tools/include/linux/ftrace.h
@@ -0,0 +1,4 @@
+#ifndef _TOOLS_INCLUDE_LINUX_FTRACE_H
+#define _TOOLS_INCLUDE_LINUX_FTRACE_H
+
+#endif /* _TOOLS_INCLUDE_LINUX_FTRACE_H */
diff --git a/tools/include/linux/gfp.h b/tools/include/linux/gfp.h
new file mode 100644
index 0000000000..6a10ff5f5b
--- /dev/null
+++ b/tools/include/linux/gfp.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TOOLS_INCLUDE_LINUX_GFP_H
+#define _TOOLS_INCLUDE_LINUX_GFP_H
+
+#include <linux/types.h>
+#include <linux/gfp_types.h>
+
+static inline bool gfpflags_allow_blocking(const gfp_t gfp_flags)
+{
+ return !!(gfp_flags & __GFP_DIRECT_RECLAIM);
+}
+
+#endif /* _TOOLS_INCLUDE_LINUX_GFP_H */
diff --git a/tools/include/linux/gfp_types.h b/tools/include/linux/gfp_types.h
new file mode 100644
index 0000000000..5f9f1ed190
--- /dev/null
+++ b/tools/include/linux/gfp_types.h
@@ -0,0 +1 @@
+#include "../../../include/linux/gfp_types.h"
diff --git a/tools/include/linux/hash.h b/tools/include/linux/hash.h
new file mode 100644
index 0000000000..38edaa08f8
--- /dev/null
+++ b/tools/include/linux/hash.h
@@ -0,0 +1,101 @@
+#ifndef _LINUX_HASH_H
+#define _LINUX_HASH_H
+/* Fast hashing routine for ints, longs and pointers.
+ (C) 2002 Nadia Yvette Chambers, IBM */
+
+#include <asm/types.h>
+#include <linux/compiler.h>
+
+/*
+ * The "GOLDEN_RATIO_PRIME" is used in ifs/btrfs/brtfs_inode.h and
+ * fs/inode.c. It's not actually prime any more (the previous primes
+ * were actively bad for hashing), but the name remains.
+ */
+#if BITS_PER_LONG == 32
+#define GOLDEN_RATIO_PRIME GOLDEN_RATIO_32
+#define hash_long(val, bits) hash_32(val, bits)
+#elif BITS_PER_LONG == 64
+#define hash_long(val, bits) hash_64(val, bits)
+#define GOLDEN_RATIO_PRIME GOLDEN_RATIO_64
+#else
+#error Wordsize not 32 or 64
+#endif
+
+/*
+ * This hash multiplies the input by a large odd number and takes the
+ * high bits. Since multiplication propagates changes to the most
+ * significant end only, it is essential that the high bits of the
+ * product be used for the hash value.
+ *
+ * Chuck Lever verified the effectiveness of this technique:
+ * http://www.citi.umich.edu/techreports/reports/citi-tr-00-1.pdf
+ *
+ * Although a random odd number will do, it turns out that the golden
+ * ratio phi = (sqrt(5)-1)/2, or its negative, has particularly nice
+ * properties. (See Knuth vol 3, section 6.4, exercise 9.)
+ *
+ * These are the negative, (1 - phi) = phi**2 = (3 - sqrt(5))/2,
+ * which is very slightly easier to multiply by and makes no
+ * difference to the hash distribution.
+ */
+#define GOLDEN_RATIO_32 0x61C88647
+#define GOLDEN_RATIO_64 0x61C8864680B583EBull
+
+#ifdef CONFIG_HAVE_ARCH_HASH
+/* This header may use the GOLDEN_RATIO_xx constants */
+#include <asm/hash.h>
+#endif
+
+/*
+ * The _generic versions exist only so lib/test_hash.c can compare
+ * the arch-optimized versions with the generic.
+ *
+ * Note that if you change these, any <asm/hash.h> that aren't updated
+ * to match need to have their HAVE_ARCH_* define values updated so the
+ * self-test will not false-positive.
+ */
+#ifndef HAVE_ARCH__HASH_32
+#define __hash_32 __hash_32_generic
+#endif
+static inline u32 __hash_32_generic(u32 val)
+{
+ return val * GOLDEN_RATIO_32;
+}
+
+static inline u32 hash_32(u32 val, unsigned int bits)
+{
+ /* High bits are more random, so use them. */
+ return __hash_32(val) >> (32 - bits);
+}
+
+#ifndef HAVE_ARCH_HASH_64
+#define hash_64 hash_64_generic
+#endif
+static __always_inline u32 hash_64_generic(u64 val, unsigned int bits)
+{
+#if BITS_PER_LONG == 64
+ /* 64x64-bit multiply is efficient on all 64-bit processors */
+ return val * GOLDEN_RATIO_64 >> (64 - bits);
+#else
+ /* Hash 64 bits using only 32x32-bit multiply. */
+ return hash_32((u32)val ^ __hash_32(val >> 32), bits);
+#endif
+}
+
+static inline u32 hash_ptr(const void *ptr, unsigned int bits)
+{
+ return hash_long((unsigned long)ptr, bits);
+}
+
+/* This really should be called fold32_ptr; it does no hashing to speak of. */
+static inline u32 hash32_ptr(const void *ptr)
+{
+ unsigned long val = (unsigned long)ptr;
+
+#if BITS_PER_LONG == 64
+ val ^= (val >> 32);
+#endif
+ return (u32)val;
+}
+
+#endif /* _LINUX_HASH_H */
diff --git a/tools/include/linux/hashtable.h b/tools/include/linux/hashtable.h
new file mode 100644
index 0000000000..434dd5ac6d
--- /dev/null
+++ b/tools/include/linux/hashtable.h
@@ -0,0 +1,149 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Statically sized hash table implementation
+ * (C) 2012 Sasha Levin <levinsasha928@gmail.com>
+ */
+
+#ifndef _LINUX_HASHTABLE_H
+#define _LINUX_HASHTABLE_H
+
+#include <linux/list.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/bitops.h>
+#include <linux/hash.h>
+#include <linux/log2.h>
+
+#define DEFINE_HASHTABLE(name, bits) \
+ struct hlist_head name[1 << (bits)] = \
+ { [0 ... ((1 << (bits)) - 1)] = HLIST_HEAD_INIT }
+
+#define DECLARE_HASHTABLE(name, bits) \
+ struct hlist_head name[1 << (bits)]
+
+#define HASH_SIZE(name) (ARRAY_SIZE(name))
+#define HASH_BITS(name) ilog2(HASH_SIZE(name))
+
+/* Use hash_32 when possible to allow for fast 32bit hashing in 64bit kernels. */
+#define hash_min(val, bits) \
+ (sizeof(val) <= 4 ? hash_32(val, bits) : hash_long(val, bits))
+
+static inline void __hash_init(struct hlist_head *ht, unsigned int sz)
+{
+ unsigned int i;
+
+ for (i = 0; i < sz; i++)
+ INIT_HLIST_HEAD(&ht[i]);
+}
+
+/**
+ * hash_init - initialize a hash table
+ * @hashtable: hashtable to be initialized
+ *
+ * Calculates the size of the hashtable from the given parameter, otherwise
+ * same as hash_init_size.
+ *
+ * This has to be a macro since HASH_BITS() will not work on pointers since
+ * it calculates the size during preprocessing.
+ */
+#define hash_init(hashtable) __hash_init(hashtable, HASH_SIZE(hashtable))
+
+/**
+ * hash_add - add an object to a hashtable
+ * @hashtable: hashtable to add to
+ * @node: the &struct hlist_node of the object to be added
+ * @key: the key of the object to be added
+ */
+#define hash_add(hashtable, node, key) \
+ hlist_add_head(node, &hashtable[hash_min(key, HASH_BITS(hashtable))])
+
+/**
+ * hash_hashed - check whether an object is in any hashtable
+ * @node: the &struct hlist_node of the object to be checked
+ */
+static inline bool hash_hashed(struct hlist_node *node)
+{
+ return !hlist_unhashed(node);
+}
+
+static inline bool __hash_empty(struct hlist_head *ht, unsigned int sz)
+{
+ unsigned int i;
+
+ for (i = 0; i < sz; i++)
+ if (!hlist_empty(&ht[i]))
+ return false;
+
+ return true;
+}
+
+/**
+ * hash_empty - check whether a hashtable is empty
+ * @hashtable: hashtable to check
+ *
+ * This has to be a macro since HASH_BITS() will not work on pointers since
+ * it calculates the size during preprocessing.
+ */
+#define hash_empty(hashtable) __hash_empty(hashtable, HASH_SIZE(hashtable))
+
+/**
+ * hash_del - remove an object from a hashtable
+ * @node: &struct hlist_node of the object to remove
+ */
+static inline void hash_del(struct hlist_node *node)
+{
+ hlist_del_init(node);
+}
+
+/**
+ * hash_for_each - iterate over a hashtable
+ * @name: hashtable to iterate
+ * @bkt: integer to use as bucket loop cursor
+ * @obj: the type * to use as a loop cursor for each entry
+ * @member: the name of the hlist_node within the struct
+ */
+#define hash_for_each(name, bkt, obj, member) \
+ for ((bkt) = 0, obj = NULL; obj == NULL && (bkt) < HASH_SIZE(name);\
+ (bkt)++)\
+ hlist_for_each_entry(obj, &name[bkt], member)
+
+/**
+ * hash_for_each_safe - iterate over a hashtable safe against removal of
+ * hash entry
+ * @name: hashtable to iterate
+ * @bkt: integer to use as bucket loop cursor
+ * @tmp: a &struct used for temporary storage
+ * @obj: the type * to use as a loop cursor for each entry
+ * @member: the name of the hlist_node within the struct
+ */
+#define hash_for_each_safe(name, bkt, tmp, obj, member) \
+ for ((bkt) = 0, obj = NULL; obj == NULL && (bkt) < HASH_SIZE(name);\
+ (bkt)++)\
+ hlist_for_each_entry_safe(obj, tmp, &name[bkt], member)
+
+/**
+ * hash_for_each_possible - iterate over all possible objects hashing to the
+ * same bucket
+ * @name: hashtable to iterate
+ * @obj: the type * to use as a loop cursor for each entry
+ * @member: the name of the hlist_node within the struct
+ * @key: the key of the objects to iterate over
+ */
+#define hash_for_each_possible(name, obj, member, key) \
+ hlist_for_each_entry(obj, &name[hash_min(key, HASH_BITS(name))], member)
+
+/**
+ * hash_for_each_possible_safe - iterate over all possible objects hashing to the
+ * same bucket safe against removals
+ * @name: hashtable to iterate
+ * @obj: the type * to use as a loop cursor for each entry
+ * @tmp: a &struct used for temporary storage
+ * @member: the name of the hlist_node within the struct
+ * @key: the key of the objects to iterate over
+ */
+#define hash_for_each_possible_safe(name, obj, tmp, member, key) \
+ hlist_for_each_entry_safe(obj, tmp,\
+ &name[hash_min(key, HASH_BITS(name))], member)
+
+
+#endif
diff --git a/tools/include/linux/interrupt.h b/tools/include/linux/interrupt.h
new file mode 100644
index 0000000000..6be25bbdca
--- /dev/null
+++ b/tools/include/linux/interrupt.h
@@ -0,0 +1,4 @@
+#ifndef _TOOLS_INCLUDE_LINUX_INTERRUPT_H
+#define _TOOLS_INCLUDE_LINUX_INTERRUPT_H
+
+#endif /* _TOOLS_INCLUDE_LINUX_INTERRUPT_H */
diff --git a/tools/include/linux/interval_tree_generic.h b/tools/include/linux/interval_tree_generic.h
new file mode 100644
index 0000000000..aaa8a0767a
--- /dev/null
+++ b/tools/include/linux/interval_tree_generic.h
@@ -0,0 +1,187 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ Interval Trees
+ (C) 2012 Michel Lespinasse <walken@google.com>
+
+
+ include/linux/interval_tree_generic.h
+*/
+
+#include <linux/rbtree_augmented.h>
+
+/*
+ * Template for implementing interval trees
+ *
+ * ITSTRUCT: struct type of the interval tree nodes
+ * ITRB: name of struct rb_node field within ITSTRUCT
+ * ITTYPE: type of the interval endpoints
+ * ITSUBTREE: name of ITTYPE field within ITSTRUCT holding last-in-subtree
+ * ITSTART(n): start endpoint of ITSTRUCT node n
+ * ITLAST(n): last endpoint of ITSTRUCT node n
+ * ITSTATIC: 'static' or empty
+ * ITPREFIX: prefix to use for the inline tree definitions
+ *
+ * Note - before using this, please consider if generic version
+ * (interval_tree.h) would work for you...
+ */
+
+#define INTERVAL_TREE_DEFINE(ITSTRUCT, ITRB, ITTYPE, ITSUBTREE, \
+ ITSTART, ITLAST, ITSTATIC, ITPREFIX) \
+ \
+/* Callbacks for augmented rbtree insert and remove */ \
+ \
+RB_DECLARE_CALLBACKS_MAX(static, ITPREFIX ## _augment, \
+ ITSTRUCT, ITRB, ITTYPE, ITSUBTREE, ITLAST) \
+ \
+/* Insert / remove interval nodes from the tree */ \
+ \
+ITSTATIC void ITPREFIX ## _insert(ITSTRUCT *node, \
+ struct rb_root_cached *root) \
+{ \
+ struct rb_node **link = &root->rb_root.rb_node, *rb_parent = NULL; \
+ ITTYPE start = ITSTART(node), last = ITLAST(node); \
+ ITSTRUCT *parent; \
+ bool leftmost = true; \
+ \
+ while (*link) { \
+ rb_parent = *link; \
+ parent = rb_entry(rb_parent, ITSTRUCT, ITRB); \
+ if (parent->ITSUBTREE < last) \
+ parent->ITSUBTREE = last; \
+ if (start < ITSTART(parent)) \
+ link = &parent->ITRB.rb_left; \
+ else { \
+ link = &parent->ITRB.rb_right; \
+ leftmost = false; \
+ } \
+ } \
+ \
+ node->ITSUBTREE = last; \
+ rb_link_node(&node->ITRB, rb_parent, link); \
+ rb_insert_augmented_cached(&node->ITRB, root, \
+ leftmost, &ITPREFIX ## _augment); \
+} \
+ \
+ITSTATIC void ITPREFIX ## _remove(ITSTRUCT *node, \
+ struct rb_root_cached *root) \
+{ \
+ rb_erase_augmented_cached(&node->ITRB, root, &ITPREFIX ## _augment); \
+} \
+ \
+/* \
+ * Iterate over intervals intersecting [start;last] \
+ * \
+ * Note that a node's interval intersects [start;last] iff: \
+ * Cond1: ITSTART(node) <= last \
+ * and \
+ * Cond2: start <= ITLAST(node) \
+ */ \
+ \
+static ITSTRUCT * \
+ITPREFIX ## _subtree_search(ITSTRUCT *node, ITTYPE start, ITTYPE last) \
+{ \
+ while (true) { \
+ /* \
+ * Loop invariant: start <= node->ITSUBTREE \
+ * (Cond2 is satisfied by one of the subtree nodes) \
+ */ \
+ if (node->ITRB.rb_left) { \
+ ITSTRUCT *left = rb_entry(node->ITRB.rb_left, \
+ ITSTRUCT, ITRB); \
+ if (start <= left->ITSUBTREE) { \
+ /* \
+ * Some nodes in left subtree satisfy Cond2. \
+ * Iterate to find the leftmost such node N. \
+ * If it also satisfies Cond1, that's the \
+ * match we are looking for. Otherwise, there \
+ * is no matching interval as nodes to the \
+ * right of N can't satisfy Cond1 either. \
+ */ \
+ node = left; \
+ continue; \
+ } \
+ } \
+ if (ITSTART(node) <= last) { /* Cond1 */ \
+ if (start <= ITLAST(node)) /* Cond2 */ \
+ return node; /* node is leftmost match */ \
+ if (node->ITRB.rb_right) { \
+ node = rb_entry(node->ITRB.rb_right, \
+ ITSTRUCT, ITRB); \
+ if (start <= node->ITSUBTREE) \
+ continue; \
+ } \
+ } \
+ return NULL; /* No match */ \
+ } \
+} \
+ \
+ITSTATIC ITSTRUCT * \
+ITPREFIX ## _iter_first(struct rb_root_cached *root, \
+ ITTYPE start, ITTYPE last) \
+{ \
+ ITSTRUCT *node, *leftmost; \
+ \
+ if (!root->rb_root.rb_node) \
+ return NULL; \
+ \
+ /* \
+ * Fastpath range intersection/overlap between A: [a0, a1] and \
+ * B: [b0, b1] is given by: \
+ * \
+ * a0 <= b1 && b0 <= a1 \
+ * \
+ * ... where A holds the lock range and B holds the smallest \
+ * 'start' and largest 'last' in the tree. For the later, we \
+ * rely on the root node, which by augmented interval tree \
+ * property, holds the largest value in its last-in-subtree. \
+ * This allows mitigating some of the tree walk overhead for \
+ * for non-intersecting ranges, maintained and consulted in O(1). \
+ */ \
+ node = rb_entry(root->rb_root.rb_node, ITSTRUCT, ITRB); \
+ if (node->ITSUBTREE < start) \
+ return NULL; \
+ \
+ leftmost = rb_entry(root->rb_leftmost, ITSTRUCT, ITRB); \
+ if (ITSTART(leftmost) > last) \
+ return NULL; \
+ \
+ return ITPREFIX ## _subtree_search(node, start, last); \
+} \
+ \
+ITSTATIC ITSTRUCT * \
+ITPREFIX ## _iter_next(ITSTRUCT *node, ITTYPE start, ITTYPE last) \
+{ \
+ struct rb_node *rb = node->ITRB.rb_right, *prev; \
+ \
+ while (true) { \
+ /* \
+ * Loop invariants: \
+ * Cond1: ITSTART(node) <= last \
+ * rb == node->ITRB.rb_right \
+ * \
+ * First, search right subtree if suitable \
+ */ \
+ if (rb) { \
+ ITSTRUCT *right = rb_entry(rb, ITSTRUCT, ITRB); \
+ if (start <= right->ITSUBTREE) \
+ return ITPREFIX ## _subtree_search(right, \
+ start, last); \
+ } \
+ \
+ /* Move up the tree until we come from a node's left child */ \
+ do { \
+ rb = rb_parent(&node->ITRB); \
+ if (!rb) \
+ return NULL; \
+ prev = &node->ITRB; \
+ node = rb_entry(rb, ITSTRUCT, ITRB); \
+ rb = node->ITRB.rb_right; \
+ } while (prev == rb); \
+ \
+ /* Check if the node intersects [start;last] */ \
+ if (last < ITSTART(node)) /* !Cond1 */ \
+ return NULL; \
+ else if (start <= ITLAST(node)) /* Cond2 */ \
+ return node; \
+ } \
+}
diff --git a/tools/include/linux/io.h b/tools/include/linux/io.h
new file mode 100644
index 0000000000..e129871fe6
--- /dev/null
+++ b/tools/include/linux/io.h
@@ -0,0 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TOOLS_IO_H
+#define _TOOLS_IO_H
+
+#endif
diff --git a/tools/include/linux/jhash.h b/tools/include/linux/jhash.h
new file mode 100644
index 0000000000..af8d0fe1c6
--- /dev/null
+++ b/tools/include/linux/jhash.h
@@ -0,0 +1,175 @@
+#ifndef _LINUX_JHASH_H
+#define _LINUX_JHASH_H
+
+/* jhash.h: Jenkins hash support.
+ *
+ * Copyright (C) 2006. Bob Jenkins (bob_jenkins@burtleburtle.net)
+ *
+ * https://burtleburtle.net/bob/hash/
+ *
+ * These are the credits from Bob's sources:
+ *
+ * lookup3.c, by Bob Jenkins, May 2006, Public Domain.
+ *
+ * These are functions for producing 32-bit hashes for hash table lookup.
+ * hashword(), hashlittle(), hashlittle2(), hashbig(), mix(), and final()
+ * are externally useful functions. Routines to test the hash are included
+ * if SELF_TEST is defined. You can use this free for any purpose. It's in
+ * the public domain. It has no warranty.
+ *
+ * Copyright (C) 2009-2010 Jozsef Kadlecsik (kadlec@blackhole.kfki.hu)
+ *
+ * I've modified Bob's hash to be useful in the Linux kernel, and
+ * any bugs present are my fault.
+ * Jozsef
+ */
+#include <linux/bitops.h>
+#include <linux/unaligned/packed_struct.h>
+
+/* Best hash sizes are of power of two */
+#define jhash_size(n) ((u32)1<<(n))
+/* Mask the hash value, i.e (value & jhash_mask(n)) instead of (value % n) */
+#define jhash_mask(n) (jhash_size(n)-1)
+
+/* __jhash_mix -- mix 3 32-bit values reversibly. */
+#define __jhash_mix(a, b, c) \
+{ \
+ a -= c; a ^= rol32(c, 4); c += b; \
+ b -= a; b ^= rol32(a, 6); a += c; \
+ c -= b; c ^= rol32(b, 8); b += a; \
+ a -= c; a ^= rol32(c, 16); c += b; \
+ b -= a; b ^= rol32(a, 19); a += c; \
+ c -= b; c ^= rol32(b, 4); b += a; \
+}
+
+/* __jhash_final - final mixing of 3 32-bit values (a,b,c) into c */
+#define __jhash_final(a, b, c) \
+{ \
+ c ^= b; c -= rol32(b, 14); \
+ a ^= c; a -= rol32(c, 11); \
+ b ^= a; b -= rol32(a, 25); \
+ c ^= b; c -= rol32(b, 16); \
+ a ^= c; a -= rol32(c, 4); \
+ b ^= a; b -= rol32(a, 14); \
+ c ^= b; c -= rol32(b, 24); \
+}
+
+/* An arbitrary initial parameter */
+#define JHASH_INITVAL 0xdeadbeef
+
+/* jhash - hash an arbitrary key
+ * @k: sequence of bytes as key
+ * @length: the length of the key
+ * @initval: the previous hash, or an arbitray value
+ *
+ * The generic version, hashes an arbitrary sequence of bytes.
+ * No alignment or length assumptions are made about the input key.
+ *
+ * Returns the hash value of the key. The result depends on endianness.
+ */
+static inline u32 jhash(const void *key, u32 length, u32 initval)
+{
+ u32 a, b, c;
+ const u8 *k = key;
+
+ /* Set up the internal state */
+ a = b = c = JHASH_INITVAL + length + initval;
+
+ /* All but the last block: affect some 32 bits of (a,b,c) */
+ while (length > 12) {
+ a += __get_unaligned_cpu32(k);
+ b += __get_unaligned_cpu32(k + 4);
+ c += __get_unaligned_cpu32(k + 8);
+ __jhash_mix(a, b, c);
+ length -= 12;
+ k += 12;
+ }
+ /* Last block: affect all 32 bits of (c) */
+ /* All the case statements fall through */
+ switch (length) {
+ case 12: c += (u32)k[11]<<24;
+ case 11: c += (u32)k[10]<<16;
+ case 10: c += (u32)k[9]<<8;
+ case 9: c += k[8];
+ case 8: b += (u32)k[7]<<24;
+ case 7: b += (u32)k[6]<<16;
+ case 6: b += (u32)k[5]<<8;
+ case 5: b += k[4];
+ case 4: a += (u32)k[3]<<24;
+ case 3: a += (u32)k[2]<<16;
+ case 2: a += (u32)k[1]<<8;
+ case 1: a += k[0];
+ __jhash_final(a, b, c);
+ case 0: /* Nothing left to add */
+ break;
+ }
+
+ return c;
+}
+
+/* jhash2 - hash an array of u32's
+ * @k: the key which must be an array of u32's
+ * @length: the number of u32's in the key
+ * @initval: the previous hash, or an arbitray value
+ *
+ * Returns the hash value of the key.
+ */
+static inline u32 jhash2(const u32 *k, u32 length, u32 initval)
+{
+ u32 a, b, c;
+
+ /* Set up the internal state */
+ a = b = c = JHASH_INITVAL + (length<<2) + initval;
+
+ /* Handle most of the key */
+ while (length > 3) {
+ a += k[0];
+ b += k[1];
+ c += k[2];
+ __jhash_mix(a, b, c);
+ length -= 3;
+ k += 3;
+ }
+
+ /* Handle the last 3 u32's: all the case statements fall through */
+ switch (length) {
+ case 3: c += k[2];
+ case 2: b += k[1];
+ case 1: a += k[0];
+ __jhash_final(a, b, c);
+ case 0: /* Nothing left to add */
+ break;
+ }
+
+ return c;
+}
+
+
+/* __jhash_nwords - hash exactly 3, 2 or 1 word(s) */
+static inline u32 __jhash_nwords(u32 a, u32 b, u32 c, u32 initval)
+{
+ a += initval;
+ b += initval;
+ c += initval;
+
+ __jhash_final(a, b, c);
+
+ return c;
+}
+
+static inline u32 jhash_3words(u32 a, u32 b, u32 c, u32 initval)
+{
+ return __jhash_nwords(a, b, c, initval + JHASH_INITVAL + (3 << 2));
+}
+
+static inline u32 jhash_2words(u32 a, u32 b, u32 initval)
+{
+ return __jhash_nwords(a, b, 0, initval + JHASH_INITVAL + (2 << 2));
+}
+
+static inline u32 jhash_1word(u32 a, u32 initval)
+{
+ return __jhash_nwords(a, 0, 0, initval + JHASH_INITVAL + (1 << 2));
+}
+
+#endif /* _LINUX_JHASH_H */
diff --git a/tools/include/linux/kallsyms.h b/tools/include/linux/kallsyms.h
new file mode 100644
index 0000000000..5a37ccbec5
--- /dev/null
+++ b/tools/include/linux/kallsyms.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LIBLOCKDEP_LINUX_KALLSYMS_H_
+#define _LIBLOCKDEP_LINUX_KALLSYMS_H_
+
+#include <linux/kernel.h>
+#include <stdio.h>
+#include <unistd.h>
+
+#define KSYM_NAME_LEN 512
+
+struct module;
+
+static inline const char *kallsyms_lookup(unsigned long addr,
+ unsigned long *symbolsize,
+ unsigned long *offset,
+ char **modname, char *namebuf)
+{
+ return NULL;
+}
+
+#include <execinfo.h>
+#include <stdlib.h>
+static inline void print_ip_sym(const char *loglvl, unsigned long ip)
+{
+ char **name;
+
+ name = backtrace_symbols((void **)&ip, 1);
+
+ dprintf(STDOUT_FILENO, "%s\n", *name);
+
+ free(name);
+}
+
+#endif
diff --git a/tools/include/linux/kconfig.h b/tools/include/linux/kconfig.h
new file mode 100644
index 0000000000..13b86bd3b7
--- /dev/null
+++ b/tools/include/linux/kconfig.h
@@ -0,0 +1,67 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TOOLS_LINUX_KCONFIG_H
+#define _TOOLS_LINUX_KCONFIG_H
+
+/* CONFIG_CC_VERSION_TEXT (Do not delete this comment. See help in Kconfig) */
+
+#define __ARG_PLACEHOLDER_1 0,
+#define __take_second_arg(__ignored, val, ...) val
+
+/*
+ * The use of "&&" / "||" is limited in certain expressions.
+ * The following enable to calculate "and" / "or" with macro expansion only.
+ */
+#define __and(x, y) ___and(x, y)
+#define ___and(x, y) ____and(__ARG_PLACEHOLDER_##x, y)
+#define ____and(arg1_or_junk, y) __take_second_arg(arg1_or_junk y, 0)
+
+#define __or(x, y) ___or(x, y)
+#define ___or(x, y) ____or(__ARG_PLACEHOLDER_##x, y)
+#define ____or(arg1_or_junk, y) __take_second_arg(arg1_or_junk 1, y)
+
+/*
+ * Helper macros to use CONFIG_ options in C/CPP expressions. Note that
+ * these only work with boolean and tristate options.
+ */
+
+/*
+ * Getting something that works in C and CPP for an arg that may or may
+ * not be defined is tricky. Here, if we have "#define CONFIG_BOOGER 1"
+ * we match on the placeholder define, insert the "0," for arg1 and generate
+ * the triplet (0, 1, 0). Then the last step cherry picks the 2nd arg (a one).
+ * When CONFIG_BOOGER is not defined, we generate a (... 1, 0) pair, and when
+ * the last step cherry picks the 2nd arg, we get a zero.
+ */
+#define __is_defined(x) ___is_defined(x)
+#define ___is_defined(val) ____is_defined(__ARG_PLACEHOLDER_##val)
+#define ____is_defined(arg1_or_junk) __take_second_arg(arg1_or_junk 1, 0)
+
+/*
+ * IS_BUILTIN(CONFIG_FOO) evaluates to 1 if CONFIG_FOO is set to 'y', 0
+ * otherwise. For boolean options, this is equivalent to
+ * IS_ENABLED(CONFIG_FOO).
+ */
+#define IS_BUILTIN(option) __is_defined(option)
+
+/*
+ * IS_MODULE(CONFIG_FOO) evaluates to 1 if CONFIG_FOO is set to 'm', 0
+ * otherwise.
+ */
+#define IS_MODULE(option) __is_defined(option##_MODULE)
+
+/*
+ * IS_REACHABLE(CONFIG_FOO) evaluates to 1 if the currently compiled
+ * code can call a function defined in code compiled based on CONFIG_FOO.
+ * This is similar to IS_ENABLED(), but returns false when invoked from
+ * built-in code when CONFIG_FOO is set to 'm'.
+ */
+#define IS_REACHABLE(option) __or(IS_BUILTIN(option), \
+ __and(IS_MODULE(option), __is_defined(MODULE)))
+
+/*
+ * IS_ENABLED(CONFIG_FOO) evaluates to 1 if CONFIG_FOO is set to 'y' or 'm',
+ * 0 otherwise.
+ */
+#define IS_ENABLED(option) __or(IS_BUILTIN(option), IS_MODULE(option))
+
+#endif /* _TOOLS_LINUX_KCONFIG_H */
diff --git a/tools/include/linux/kern_levels.h b/tools/include/linux/kern_levels.h
new file mode 100644
index 0000000000..778ecb9844
--- /dev/null
+++ b/tools/include/linux/kern_levels.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __KERN_LEVELS_H__
+#define __KERN_LEVELS_H__
+
+#define KERN_SOH "" /* ASCII Start Of Header */
+#define KERN_SOH_ASCII ''
+
+#define KERN_EMERG KERN_SOH "" /* system is unusable */
+#define KERN_ALERT KERN_SOH "" /* action must be taken immediately */
+#define KERN_CRIT KERN_SOH "" /* critical conditions */
+#define KERN_ERR KERN_SOH "" /* error conditions */
+#define KERN_WARNING KERN_SOH "" /* warning conditions */
+#define KERN_NOTICE KERN_SOH "" /* normal but significant condition */
+#define KERN_INFO KERN_SOH "" /* informational */
+#define KERN_DEBUG KERN_SOH "" /* debug-level messages */
+
+#define KERN_DEFAULT KERN_SOH "" /* the default kernel loglevel */
+
+/*
+ * Annotation for a "continued" line of log printout (only done after a
+ * line that had no enclosing \n). Only to be used by core/arch code
+ * during early bootup (a continued line is not SMP-safe otherwise).
+ */
+#define KERN_CONT ""
+
+#endif
diff --git a/tools/include/linux/kernel.h b/tools/include/linux/kernel.h
new file mode 100644
index 0000000000..4b0673bf52
--- /dev/null
+++ b/tools/include/linux/kernel.h
@@ -0,0 +1,108 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __TOOLS_LINUX_KERNEL_H
+#define __TOOLS_LINUX_KERNEL_H
+
+#include <stdarg.h>
+#include <stddef.h>
+#include <assert.h>
+#include <linux/build_bug.h>
+#include <linux/compiler.h>
+#include <linux/math.h>
+#include <endian.h>
+#include <byteswap.h>
+
+#ifndef UINT_MAX
+#define UINT_MAX (~0U)
+#endif
+
+#define _RET_IP_ ((unsigned long)__builtin_return_address(0))
+
+#define PERF_ALIGN(x, a) __PERF_ALIGN_MASK(x, (typeof(x))(a)-1)
+#define __PERF_ALIGN_MASK(x, mask) (((x)+(mask))&~(mask))
+
+#ifndef offsetof
+#define offsetof(TYPE, MEMBER) ((size_t) &((TYPE *)0)->MEMBER)
+#endif
+
+#ifndef container_of
+/**
+ * container_of - cast a member of a structure out to the containing structure
+ * @ptr: the pointer to the member.
+ * @type: the type of the container struct this is embedded in.
+ * @member: the name of the member within the struct.
+ *
+ */
+#define container_of(ptr, type, member) ({ \
+ const typeof(((type *)0)->member) * __mptr = (ptr); \
+ (type *)((char *)__mptr - offsetof(type, member)); })
+#endif
+
+#ifndef max
+#define max(x, y) ({ \
+ typeof(x) _max1 = (x); \
+ typeof(y) _max2 = (y); \
+ (void) (&_max1 == &_max2); \
+ _max1 > _max2 ? _max1 : _max2; })
+#endif
+
+#ifndef min
+#define min(x, y) ({ \
+ typeof(x) _min1 = (x); \
+ typeof(y) _min2 = (y); \
+ (void) (&_min1 == &_min2); \
+ _min1 < _min2 ? _min1 : _min2; })
+#endif
+
+#define max_t(type, x, y) max((type)x, (type)y)
+#define min_t(type, x, y) min((type)x, (type)y)
+#define clamp(val, lo, hi) min((typeof(val))max(val, lo), hi)
+
+#ifndef BUG_ON
+#ifdef NDEBUG
+#define BUG_ON(cond) do { if (cond) {} } while (0)
+#else
+#define BUG_ON(cond) assert(!(cond))
+#endif
+#endif
+#define BUG() BUG_ON(1)
+
+#if __BYTE_ORDER == __BIG_ENDIAN
+#define cpu_to_le16 bswap_16
+#define cpu_to_le32 bswap_32
+#define cpu_to_le64 bswap_64
+#define le16_to_cpu bswap_16
+#define le32_to_cpu bswap_32
+#define le64_to_cpu bswap_64
+#define cpu_to_be16
+#define cpu_to_be32
+#define cpu_to_be64
+#define be16_to_cpu
+#define be32_to_cpu
+#define be64_to_cpu
+#else
+#define cpu_to_le16
+#define cpu_to_le32
+#define cpu_to_le64
+#define le16_to_cpu
+#define le32_to_cpu
+#define le64_to_cpu
+#define cpu_to_be16 bswap_16
+#define cpu_to_be32 bswap_32
+#define cpu_to_be64 bswap_64
+#define be16_to_cpu bswap_16
+#define be32_to_cpu bswap_32
+#define be64_to_cpu bswap_64
+#endif
+
+int vscnprintf(char *buf, size_t size, const char *fmt, va_list args);
+int scnprintf(char * buf, size_t size, const char * fmt, ...);
+int scnprintf_pad(char * buf, size_t size, const char * fmt, ...);
+
+#ifndef ARRAY_SIZE
+#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]) + __must_be_array(arr))
+#endif
+
+#define current_gfp_context(k) 0
+#define synchronize_rcu()
+
+#endif
diff --git a/tools/include/linux/linkage.h b/tools/include/linux/linkage.h
new file mode 100644
index 0000000000..bc763d5002
--- /dev/null
+++ b/tools/include/linux/linkage.h
@@ -0,0 +1,4 @@
+#ifndef _TOOLS_INCLUDE_LINUX_LINKAGE_H
+#define _TOOLS_INCLUDE_LINUX_LINKAGE_H
+
+#endif /* _TOOLS_INCLUDE_LINUX_LINKAGE_H */
diff --git a/tools/include/linux/list.h b/tools/include/linux/list.h
new file mode 100644
index 0000000000..a4dfb6a7cc
--- /dev/null
+++ b/tools/include/linux/list.h
@@ -0,0 +1,783 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __TOOLS_LINUX_LIST_H
+#define __TOOLS_LINUX_LIST_H
+
+#include <linux/types.h>
+#include <linux/poison.h>
+#include <linux/kernel.h>
+#include <linux/compiler.h>
+
+/*
+ * Simple doubly linked list implementation.
+ *
+ * Some of the internal functions ("__xxx") are useful when
+ * manipulating whole lists rather than single entries, as
+ * sometimes we already know the next/prev entries and we can
+ * generate better code by using them directly rather than
+ * using the generic single-entry routines.
+ */
+
+#define LIST_HEAD_INIT(name) { &(name), &(name) }
+
+#define LIST_HEAD(name) \
+ struct list_head name = LIST_HEAD_INIT(name)
+
+static inline void INIT_LIST_HEAD(struct list_head *list)
+{
+ list->next = list;
+ list->prev = list;
+}
+
+/*
+ * Insert a new entry between two known consecutive entries.
+ *
+ * This is only for internal list manipulation where we know
+ * the prev/next entries already!
+ */
+#ifndef CONFIG_DEBUG_LIST
+static inline void __list_add(struct list_head *new,
+ struct list_head *prev,
+ struct list_head *next)
+{
+ next->prev = new;
+ new->next = next;
+ new->prev = prev;
+ prev->next = new;
+}
+#else
+extern void __list_add(struct list_head *new,
+ struct list_head *prev,
+ struct list_head *next);
+#endif
+
+/**
+ * list_add - add a new entry
+ * @new: new entry to be added
+ * @head: list head to add it after
+ *
+ * Insert a new entry after the specified head.
+ * This is good for implementing stacks.
+ */
+static inline void list_add(struct list_head *new, struct list_head *head)
+{
+ __list_add(new, head, head->next);
+}
+
+
+/**
+ * list_add_tail - add a new entry
+ * @new: new entry to be added
+ * @head: list head to add it before
+ *
+ * Insert a new entry before the specified head.
+ * This is useful for implementing queues.
+ */
+static inline void list_add_tail(struct list_head *new, struct list_head *head)
+{
+ __list_add(new, head->prev, head);
+}
+
+/*
+ * Delete a list entry by making the prev/next entries
+ * point to each other.
+ *
+ * This is only for internal list manipulation where we know
+ * the prev/next entries already!
+ */
+static inline void __list_del(struct list_head * prev, struct list_head * next)
+{
+ next->prev = prev;
+ WRITE_ONCE(prev->next, next);
+}
+
+/**
+ * list_del - deletes entry from list.
+ * @entry: the element to delete from the list.
+ * Note: list_empty() on entry does not return true after this, the entry is
+ * in an undefined state.
+ */
+#ifndef CONFIG_DEBUG_LIST
+static inline void __list_del_entry(struct list_head *entry)
+{
+ __list_del(entry->prev, entry->next);
+}
+
+static inline void list_del(struct list_head *entry)
+{
+ __list_del(entry->prev, entry->next);
+ entry->next = LIST_POISON1;
+ entry->prev = LIST_POISON2;
+}
+#else
+extern void __list_del_entry(struct list_head *entry);
+extern void list_del(struct list_head *entry);
+#endif
+
+/**
+ * list_replace - replace old entry by new one
+ * @old : the element to be replaced
+ * @new : the new element to insert
+ *
+ * If @old was empty, it will be overwritten.
+ */
+static inline void list_replace(struct list_head *old,
+ struct list_head *new)
+{
+ new->next = old->next;
+ new->next->prev = new;
+ new->prev = old->prev;
+ new->prev->next = new;
+}
+
+static inline void list_replace_init(struct list_head *old,
+ struct list_head *new)
+{
+ list_replace(old, new);
+ INIT_LIST_HEAD(old);
+}
+
+/**
+ * list_del_init - deletes entry from list and reinitialize it.
+ * @entry: the element to delete from the list.
+ */
+static inline void list_del_init(struct list_head *entry)
+{
+ __list_del_entry(entry);
+ INIT_LIST_HEAD(entry);
+}
+
+/**
+ * list_move - delete from one list and add as another's head
+ * @list: the entry to move
+ * @head: the head that will precede our entry
+ */
+static inline void list_move(struct list_head *list, struct list_head *head)
+{
+ __list_del_entry(list);
+ list_add(list, head);
+}
+
+/**
+ * list_move_tail - delete from one list and add as another's tail
+ * @list: the entry to move
+ * @head: the head that will follow our entry
+ */
+static inline void list_move_tail(struct list_head *list,
+ struct list_head *head)
+{
+ __list_del_entry(list);
+ list_add_tail(list, head);
+}
+
+/**
+ * list_is_last - tests whether @list is the last entry in list @head
+ * @list: the entry to test
+ * @head: the head of the list
+ */
+static inline int list_is_last(const struct list_head *list,
+ const struct list_head *head)
+{
+ return list->next == head;
+}
+
+/**
+ * list_empty - tests whether a list is empty
+ * @head: the list to test.
+ */
+static inline int list_empty(const struct list_head *head)
+{
+ return head->next == head;
+}
+
+/**
+ * list_empty_careful - tests whether a list is empty and not being modified
+ * @head: the list to test
+ *
+ * Description:
+ * tests whether a list is empty _and_ checks that no other CPU might be
+ * in the process of modifying either member (next or prev)
+ *
+ * NOTE: using list_empty_careful() without synchronization
+ * can only be safe if the only activity that can happen
+ * to the list entry is list_del_init(). Eg. it cannot be used
+ * if another CPU could re-list_add() it.
+ */
+static inline int list_empty_careful(const struct list_head *head)
+{
+ struct list_head *next = head->next;
+ return (next == head) && (next == head->prev);
+}
+
+/**
+ * list_rotate_left - rotate the list to the left
+ * @head: the head of the list
+ */
+static inline void list_rotate_left(struct list_head *head)
+{
+ struct list_head *first;
+
+ if (!list_empty(head)) {
+ first = head->next;
+ list_move_tail(first, head);
+ }
+}
+
+/**
+ * list_is_singular - tests whether a list has just one entry.
+ * @head: the list to test.
+ */
+static inline int list_is_singular(const struct list_head *head)
+{
+ return !list_empty(head) && (head->next == head->prev);
+}
+
+static inline void __list_cut_position(struct list_head *list,
+ struct list_head *head, struct list_head *entry)
+{
+ struct list_head *new_first = entry->next;
+ list->next = head->next;
+ list->next->prev = list;
+ list->prev = entry;
+ entry->next = list;
+ head->next = new_first;
+ new_first->prev = head;
+}
+
+/**
+ * list_cut_position - cut a list into two
+ * @list: a new list to add all removed entries
+ * @head: a list with entries
+ * @entry: an entry within head, could be the head itself
+ * and if so we won't cut the list
+ *
+ * This helper moves the initial part of @head, up to and
+ * including @entry, from @head to @list. You should
+ * pass on @entry an element you know is on @head. @list
+ * should be an empty list or a list you do not care about
+ * losing its data.
+ *
+ */
+static inline void list_cut_position(struct list_head *list,
+ struct list_head *head, struct list_head *entry)
+{
+ if (list_empty(head))
+ return;
+ if (list_is_singular(head) &&
+ (head->next != entry && head != entry))
+ return;
+ if (entry == head)
+ INIT_LIST_HEAD(list);
+ else
+ __list_cut_position(list, head, entry);
+}
+
+static inline void __list_splice(const struct list_head *list,
+ struct list_head *prev,
+ struct list_head *next)
+{
+ struct list_head *first = list->next;
+ struct list_head *last = list->prev;
+
+ first->prev = prev;
+ prev->next = first;
+
+ last->next = next;
+ next->prev = last;
+}
+
+/**
+ * list_splice - join two lists, this is designed for stacks
+ * @list: the new list to add.
+ * @head: the place to add it in the first list.
+ */
+static inline void list_splice(const struct list_head *list,
+ struct list_head *head)
+{
+ if (!list_empty(list))
+ __list_splice(list, head, head->next);
+}
+
+/**
+ * list_splice_tail - join two lists, each list being a queue
+ * @list: the new list to add.
+ * @head: the place to add it in the first list.
+ */
+static inline void list_splice_tail(struct list_head *list,
+ struct list_head *head)
+{
+ if (!list_empty(list))
+ __list_splice(list, head->prev, head);
+}
+
+/**
+ * list_splice_init - join two lists and reinitialise the emptied list.
+ * @list: the new list to add.
+ * @head: the place to add it in the first list.
+ *
+ * The list at @list is reinitialised
+ */
+static inline void list_splice_init(struct list_head *list,
+ struct list_head *head)
+{
+ if (!list_empty(list)) {
+ __list_splice(list, head, head->next);
+ INIT_LIST_HEAD(list);
+ }
+}
+
+/**
+ * list_splice_tail_init - join two lists and reinitialise the emptied list
+ * @list: the new list to add.
+ * @head: the place to add it in the first list.
+ *
+ * Each of the lists is a queue.
+ * The list at @list is reinitialised
+ */
+static inline void list_splice_tail_init(struct list_head *list,
+ struct list_head *head)
+{
+ if (!list_empty(list)) {
+ __list_splice(list, head->prev, head);
+ INIT_LIST_HEAD(list);
+ }
+}
+
+/**
+ * list_entry - get the struct for this entry
+ * @ptr: the &struct list_head pointer.
+ * @type: the type of the struct this is embedded in.
+ * @member: the name of the list_head within the struct.
+ */
+#define list_entry(ptr, type, member) \
+ container_of(ptr, type, member)
+
+/**
+ * list_first_entry - get the first element from a list
+ * @ptr: the list head to take the element from.
+ * @type: the type of the struct this is embedded in.
+ * @member: the name of the list_head within the struct.
+ *
+ * Note, that list is expected to be not empty.
+ */
+#define list_first_entry(ptr, type, member) \
+ list_entry((ptr)->next, type, member)
+
+/**
+ * list_last_entry - get the last element from a list
+ * @ptr: the list head to take the element from.
+ * @type: the type of the struct this is embedded in.
+ * @member: the name of the list_head within the struct.
+ *
+ * Note, that list is expected to be not empty.
+ */
+#define list_last_entry(ptr, type, member) \
+ list_entry((ptr)->prev, type, member)
+
+/**
+ * list_first_entry_or_null - get the first element from a list
+ * @ptr: the list head to take the element from.
+ * @type: the type of the struct this is embedded in.
+ * @member: the name of the list_head within the struct.
+ *
+ * Note that if the list is empty, it returns NULL.
+ */
+#define list_first_entry_or_null(ptr, type, member) \
+ (!list_empty(ptr) ? list_first_entry(ptr, type, member) : NULL)
+
+/**
+ * list_last_entry_or_null - get the last element from a list
+ * @ptr: the list head to take the element from.
+ * @type: the type of the struct this is embedded in.
+ * @member: the name of the list_head within the struct.
+ *
+ * Note that if the list is empty, it returns NULL.
+ */
+#define list_last_entry_or_null(ptr, type, member) \
+ (!list_empty(ptr) ? list_last_entry(ptr, type, member) : NULL)
+
+/**
+ * list_next_entry - get the next element in list
+ * @pos: the type * to cursor
+ * @member: the name of the list_head within the struct.
+ */
+#define list_next_entry(pos, member) \
+ list_entry((pos)->member.next, typeof(*(pos)), member)
+
+/**
+ * list_prev_entry - get the prev element in list
+ * @pos: the type * to cursor
+ * @member: the name of the list_head within the struct.
+ */
+#define list_prev_entry(pos, member) \
+ list_entry((pos)->member.prev, typeof(*(pos)), member)
+
+/**
+ * list_for_each - iterate over a list
+ * @pos: the &struct list_head to use as a loop cursor.
+ * @head: the head for your list.
+ */
+#define list_for_each(pos, head) \
+ for (pos = (head)->next; pos != (head); pos = pos->next)
+
+/**
+ * list_for_each_prev - iterate over a list backwards
+ * @pos: the &struct list_head to use as a loop cursor.
+ * @head: the head for your list.
+ */
+#define list_for_each_prev(pos, head) \
+ for (pos = (head)->prev; pos != (head); pos = pos->prev)
+
+/**
+ * list_for_each_safe - iterate over a list safe against removal of list entry
+ * @pos: the &struct list_head to use as a loop cursor.
+ * @n: another &struct list_head to use as temporary storage
+ * @head: the head for your list.
+ */
+#define list_for_each_safe(pos, n, head) \
+ for (pos = (head)->next, n = pos->next; pos != (head); \
+ pos = n, n = pos->next)
+
+/**
+ * list_for_each_prev_safe - iterate over a list backwards safe against removal of list entry
+ * @pos: the &struct list_head to use as a loop cursor.
+ * @n: another &struct list_head to use as temporary storage
+ * @head: the head for your list.
+ */
+#define list_for_each_prev_safe(pos, n, head) \
+ for (pos = (head)->prev, n = pos->prev; \
+ pos != (head); \
+ pos = n, n = pos->prev)
+
+/**
+ * list_for_each_entry - iterate over list of given type
+ * @pos: the type * to use as a loop cursor.
+ * @head: the head for your list.
+ * @member: the name of the list_head within the struct.
+ */
+#define list_for_each_entry(pos, head, member) \
+ for (pos = list_first_entry(head, typeof(*pos), member); \
+ &pos->member != (head); \
+ pos = list_next_entry(pos, member))
+
+/**
+ * list_for_each_entry_reverse - iterate backwards over list of given type.
+ * @pos: the type * to use as a loop cursor.
+ * @head: the head for your list.
+ * @member: the name of the list_head within the struct.
+ */
+#define list_for_each_entry_reverse(pos, head, member) \
+ for (pos = list_last_entry(head, typeof(*pos), member); \
+ &pos->member != (head); \
+ pos = list_prev_entry(pos, member))
+
+/**
+ * list_prepare_entry - prepare a pos entry for use in list_for_each_entry_continue()
+ * @pos: the type * to use as a start point
+ * @head: the head of the list
+ * @member: the name of the list_head within the struct.
+ *
+ * Prepares a pos entry for use as a start point in list_for_each_entry_continue().
+ */
+#define list_prepare_entry(pos, head, member) \
+ ((pos) ? : list_entry(head, typeof(*pos), member))
+
+/**
+ * list_for_each_entry_continue - continue iteration over list of given type
+ * @pos: the type * to use as a loop cursor.
+ * @head: the head for your list.
+ * @member: the name of the list_head within the struct.
+ *
+ * Continue to iterate over list of given type, continuing after
+ * the current position.
+ */
+#define list_for_each_entry_continue(pos, head, member) \
+ for (pos = list_next_entry(pos, member); \
+ &pos->member != (head); \
+ pos = list_next_entry(pos, member))
+
+/**
+ * list_for_each_entry_continue_reverse - iterate backwards from the given point
+ * @pos: the type * to use as a loop cursor.
+ * @head: the head for your list.
+ * @member: the name of the list_head within the struct.
+ *
+ * Start to iterate over list of given type backwards, continuing after
+ * the current position.
+ */
+#define list_for_each_entry_continue_reverse(pos, head, member) \
+ for (pos = list_prev_entry(pos, member); \
+ &pos->member != (head); \
+ pos = list_prev_entry(pos, member))
+
+/**
+ * list_for_each_entry_from - iterate over list of given type from the current point
+ * @pos: the type * to use as a loop cursor.
+ * @head: the head for your list.
+ * @member: the name of the list_head within the struct.
+ *
+ * Iterate over list of given type, continuing from current position.
+ */
+#define list_for_each_entry_from(pos, head, member) \
+ for (; &pos->member != (head); \
+ pos = list_next_entry(pos, member))
+
+/**
+ * list_for_each_entry_safe - iterate over list of given type safe against removal of list entry
+ * @pos: the type * to use as a loop cursor.
+ * @n: another type * to use as temporary storage
+ * @head: the head for your list.
+ * @member: the name of the list_head within the struct.
+ */
+#define list_for_each_entry_safe(pos, n, head, member) \
+ for (pos = list_first_entry(head, typeof(*pos), member), \
+ n = list_next_entry(pos, member); \
+ &pos->member != (head); \
+ pos = n, n = list_next_entry(n, member))
+
+/**
+ * list_for_each_entry_safe_continue - continue list iteration safe against removal
+ * @pos: the type * to use as a loop cursor.
+ * @n: another type * to use as temporary storage
+ * @head: the head for your list.
+ * @member: the name of the list_head within the struct.
+ *
+ * Iterate over list of given type, continuing after current point,
+ * safe against removal of list entry.
+ */
+#define list_for_each_entry_safe_continue(pos, n, head, member) \
+ for (pos = list_next_entry(pos, member), \
+ n = list_next_entry(pos, member); \
+ &pos->member != (head); \
+ pos = n, n = list_next_entry(n, member))
+
+/**
+ * list_for_each_entry_safe_from - iterate over list from current point safe against removal
+ * @pos: the type * to use as a loop cursor.
+ * @n: another type * to use as temporary storage
+ * @head: the head for your list.
+ * @member: the name of the list_head within the struct.
+ *
+ * Iterate over list of given type from current point, safe against
+ * removal of list entry.
+ */
+#define list_for_each_entry_safe_from(pos, n, head, member) \
+ for (n = list_next_entry(pos, member); \
+ &pos->member != (head); \
+ pos = n, n = list_next_entry(n, member))
+
+/**
+ * list_for_each_entry_safe_reverse - iterate backwards over list safe against removal
+ * @pos: the type * to use as a loop cursor.
+ * @n: another type * to use as temporary storage
+ * @head: the head for your list.
+ * @member: the name of the list_head within the struct.
+ *
+ * Iterate backwards over list of given type, safe against removal
+ * of list entry.
+ */
+#define list_for_each_entry_safe_reverse(pos, n, head, member) \
+ for (pos = list_last_entry(head, typeof(*pos), member), \
+ n = list_prev_entry(pos, member); \
+ &pos->member != (head); \
+ pos = n, n = list_prev_entry(n, member))
+
+/**
+ * list_safe_reset_next - reset a stale list_for_each_entry_safe loop
+ * @pos: the loop cursor used in the list_for_each_entry_safe loop
+ * @n: temporary storage used in list_for_each_entry_safe
+ * @member: the name of the list_head within the struct.
+ *
+ * list_safe_reset_next is not safe to use in general if the list may be
+ * modified concurrently (eg. the lock is dropped in the loop body). An
+ * exception to this is if the cursor element (pos) is pinned in the list,
+ * and list_safe_reset_next is called after re-taking the lock and before
+ * completing the current iteration of the loop body.
+ */
+#define list_safe_reset_next(pos, n, member) \
+ n = list_next_entry(pos, member)
+
+/*
+ * Double linked lists with a single pointer list head.
+ * Mostly useful for hash tables where the two pointer list head is
+ * too wasteful.
+ * You lose the ability to access the tail in O(1).
+ */
+
+#define HLIST_HEAD_INIT { .first = NULL }
+#define HLIST_HEAD(name) struct hlist_head name = { .first = NULL }
+#define INIT_HLIST_HEAD(ptr) ((ptr)->first = NULL)
+static inline void INIT_HLIST_NODE(struct hlist_node *h)
+{
+ h->next = NULL;
+ h->pprev = NULL;
+}
+
+static inline int hlist_unhashed(const struct hlist_node *h)
+{
+ return !h->pprev;
+}
+
+static inline int hlist_empty(const struct hlist_head *h)
+{
+ return !h->first;
+}
+
+static inline void __hlist_del(struct hlist_node *n)
+{
+ struct hlist_node *next = n->next;
+ struct hlist_node **pprev = n->pprev;
+
+ WRITE_ONCE(*pprev, next);
+ if (next)
+ next->pprev = pprev;
+}
+
+static inline void hlist_del(struct hlist_node *n)
+{
+ __hlist_del(n);
+ n->next = LIST_POISON1;
+ n->pprev = LIST_POISON2;
+}
+
+static inline void hlist_del_init(struct hlist_node *n)
+{
+ if (!hlist_unhashed(n)) {
+ __hlist_del(n);
+ INIT_HLIST_NODE(n);
+ }
+}
+
+static inline void hlist_add_head(struct hlist_node *n, struct hlist_head *h)
+{
+ struct hlist_node *first = h->first;
+ n->next = first;
+ if (first)
+ first->pprev = &n->next;
+ h->first = n;
+ n->pprev = &h->first;
+}
+
+/* next must be != NULL */
+static inline void hlist_add_before(struct hlist_node *n,
+ struct hlist_node *next)
+{
+ n->pprev = next->pprev;
+ n->next = next;
+ next->pprev = &n->next;
+ *(n->pprev) = n;
+}
+
+static inline void hlist_add_behind(struct hlist_node *n,
+ struct hlist_node *prev)
+{
+ n->next = prev->next;
+ prev->next = n;
+ n->pprev = &prev->next;
+
+ if (n->next)
+ n->next->pprev = &n->next;
+}
+
+/* after that we'll appear to be on some hlist and hlist_del will work */
+static inline void hlist_add_fake(struct hlist_node *n)
+{
+ n->pprev = &n->next;
+}
+
+static inline bool hlist_fake(struct hlist_node *h)
+{
+ return h->pprev == &h->next;
+}
+
+/*
+ * Move a list from one list head to another. Fixup the pprev
+ * reference of the first entry if it exists.
+ */
+static inline void hlist_move_list(struct hlist_head *old,
+ struct hlist_head *new)
+{
+ new->first = old->first;
+ if (new->first)
+ new->first->pprev = &new->first;
+ old->first = NULL;
+}
+
+#define hlist_entry(ptr, type, member) container_of(ptr,type,member)
+
+#define hlist_for_each(pos, head) \
+ for (pos = (head)->first; pos ; pos = pos->next)
+
+#define hlist_for_each_safe(pos, n, head) \
+ for (pos = (head)->first; pos && ({ n = pos->next; 1; }); \
+ pos = n)
+
+#define hlist_entry_safe(ptr, type, member) \
+ ({ typeof(ptr) ____ptr = (ptr); \
+ ____ptr ? hlist_entry(____ptr, type, member) : NULL; \
+ })
+
+/**
+ * hlist_for_each_entry - iterate over list of given type
+ * @pos: the type * to use as a loop cursor.
+ * @head: the head for your list.
+ * @member: the name of the hlist_node within the struct.
+ */
+#define hlist_for_each_entry(pos, head, member) \
+ for (pos = hlist_entry_safe((head)->first, typeof(*(pos)), member);\
+ pos; \
+ pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member))
+
+/**
+ * hlist_for_each_entry_continue - iterate over a hlist continuing after current point
+ * @pos: the type * to use as a loop cursor.
+ * @member: the name of the hlist_node within the struct.
+ */
+#define hlist_for_each_entry_continue(pos, member) \
+ for (pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member);\
+ pos; \
+ pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member))
+
+/**
+ * hlist_for_each_entry_from - iterate over a hlist continuing from current point
+ * @pos: the type * to use as a loop cursor.
+ * @member: the name of the hlist_node within the struct.
+ */
+#define hlist_for_each_entry_from(pos, member) \
+ for (; pos; \
+ pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member))
+
+/**
+ * hlist_for_each_entry_safe - iterate over list of given type safe against removal of list entry
+ * @pos: the type * to use as a loop cursor.
+ * @n: another &struct hlist_node to use as temporary storage
+ * @head: the head for your list.
+ * @member: the name of the hlist_node within the struct.
+ */
+#define hlist_for_each_entry_safe(pos, n, head, member) \
+ for (pos = hlist_entry_safe((head)->first, typeof(*pos), member);\
+ pos && ({ n = pos->member.next; 1; }); \
+ pos = hlist_entry_safe(n, typeof(*pos), member))
+
+/**
+ * list_del_range - deletes range of entries from list.
+ * @begin: first element in the range to delete from the list.
+ * @end: last element in the range to delete from the list.
+ * Note: list_empty on the range of entries does not return true after this,
+ * the entries is in an undefined state.
+ */
+static inline void list_del_range(struct list_head *begin,
+ struct list_head *end)
+{
+ begin->prev->next = end->next;
+ end->next->prev = begin->prev;
+}
+
+/**
+ * list_for_each_from - iterate over a list from one of its nodes
+ * @pos: the &struct list_head to use as a loop cursor, from where to start
+ * @head: the head for your list.
+ */
+#define list_for_each_from(pos, head) \
+ for (; pos != (head); pos = pos->next)
+
+#endif /* __TOOLS_LINUX_LIST_H */
diff --git a/tools/include/linux/list_sort.h b/tools/include/linux/list_sort.h
new file mode 100644
index 0000000000..453105f74e
--- /dev/null
+++ b/tools/include/linux/list_sort.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_LIST_SORT_H
+#define _LINUX_LIST_SORT_H
+
+#include <linux/types.h>
+
+struct list_head;
+
+typedef int __attribute__((nonnull(2,3))) (*list_cmp_func_t)(void *,
+ const struct list_head *, const struct list_head *);
+
+__attribute__((nonnull(2,3)))
+void list_sort(void *priv, struct list_head *head, list_cmp_func_t cmp);
+#endif
diff --git a/tools/include/linux/log2.h b/tools/include/linux/log2.h
new file mode 100644
index 0000000000..e20a67d538
--- /dev/null
+++ b/tools/include/linux/log2.h
@@ -0,0 +1,175 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/* Integer base 2 logarithm calculation
+ *
+ * Copyright (C) 2006 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#ifndef _TOOLS_LINUX_LOG2_H
+#define _TOOLS_LINUX_LOG2_H
+
+#include <linux/bitops.h>
+#include <linux/types.h>
+
+/*
+ * non-constant log of base 2 calculators
+ * - the arch may override these in asm/bitops.h if they can be implemented
+ * more efficiently than using fls() and fls64()
+ * - the arch is not required to handle n==0 if implementing the fallback
+ */
+static inline __attribute__((const))
+int __ilog2_u32(u32 n)
+{
+ return fls(n) - 1;
+}
+
+static inline __attribute__((const))
+int __ilog2_u64(u64 n)
+{
+ return fls64(n) - 1;
+}
+
+/*
+ * Determine whether some value is a power of two, where zero is
+ * *not* considered a power of two.
+ */
+
+static inline __attribute__((const))
+bool is_power_of_2(unsigned long n)
+{
+ return (n != 0 && ((n & (n - 1)) == 0));
+}
+
+/*
+ * round up to nearest power of two
+ */
+static inline __attribute__((const))
+unsigned long __roundup_pow_of_two(unsigned long n)
+{
+ return 1UL << fls_long(n - 1);
+}
+
+/*
+ * round down to nearest power of two
+ */
+static inline __attribute__((const))
+unsigned long __rounddown_pow_of_two(unsigned long n)
+{
+ return 1UL << (fls_long(n) - 1);
+}
+
+/**
+ * ilog2 - log of base 2 of 32-bit or a 64-bit unsigned value
+ * @n - parameter
+ *
+ * constant-capable log of base 2 calculation
+ * - this can be used to initialise global variables from constant data, hence
+ * the massive ternary operator construction
+ *
+ * selects the appropriately-sized optimised version depending on sizeof(n)
+ */
+#define ilog2(n) \
+( \
+ __builtin_constant_p(n) ? ( \
+ (n) < 2 ? 0 : \
+ (n) & (1ULL << 63) ? 63 : \
+ (n) & (1ULL << 62) ? 62 : \
+ (n) & (1ULL << 61) ? 61 : \
+ (n) & (1ULL << 60) ? 60 : \
+ (n) & (1ULL << 59) ? 59 : \
+ (n) & (1ULL << 58) ? 58 : \
+ (n) & (1ULL << 57) ? 57 : \
+ (n) & (1ULL << 56) ? 56 : \
+ (n) & (1ULL << 55) ? 55 : \
+ (n) & (1ULL << 54) ? 54 : \
+ (n) & (1ULL << 53) ? 53 : \
+ (n) & (1ULL << 52) ? 52 : \
+ (n) & (1ULL << 51) ? 51 : \
+ (n) & (1ULL << 50) ? 50 : \
+ (n) & (1ULL << 49) ? 49 : \
+ (n) & (1ULL << 48) ? 48 : \
+ (n) & (1ULL << 47) ? 47 : \
+ (n) & (1ULL << 46) ? 46 : \
+ (n) & (1ULL << 45) ? 45 : \
+ (n) & (1ULL << 44) ? 44 : \
+ (n) & (1ULL << 43) ? 43 : \
+ (n) & (1ULL << 42) ? 42 : \
+ (n) & (1ULL << 41) ? 41 : \
+ (n) & (1ULL << 40) ? 40 : \
+ (n) & (1ULL << 39) ? 39 : \
+ (n) & (1ULL << 38) ? 38 : \
+ (n) & (1ULL << 37) ? 37 : \
+ (n) & (1ULL << 36) ? 36 : \
+ (n) & (1ULL << 35) ? 35 : \
+ (n) & (1ULL << 34) ? 34 : \
+ (n) & (1ULL << 33) ? 33 : \
+ (n) & (1ULL << 32) ? 32 : \
+ (n) & (1ULL << 31) ? 31 : \
+ (n) & (1ULL << 30) ? 30 : \
+ (n) & (1ULL << 29) ? 29 : \
+ (n) & (1ULL << 28) ? 28 : \
+ (n) & (1ULL << 27) ? 27 : \
+ (n) & (1ULL << 26) ? 26 : \
+ (n) & (1ULL << 25) ? 25 : \
+ (n) & (1ULL << 24) ? 24 : \
+ (n) & (1ULL << 23) ? 23 : \
+ (n) & (1ULL << 22) ? 22 : \
+ (n) & (1ULL << 21) ? 21 : \
+ (n) & (1ULL << 20) ? 20 : \
+ (n) & (1ULL << 19) ? 19 : \
+ (n) & (1ULL << 18) ? 18 : \
+ (n) & (1ULL << 17) ? 17 : \
+ (n) & (1ULL << 16) ? 16 : \
+ (n) & (1ULL << 15) ? 15 : \
+ (n) & (1ULL << 14) ? 14 : \
+ (n) & (1ULL << 13) ? 13 : \
+ (n) & (1ULL << 12) ? 12 : \
+ (n) & (1ULL << 11) ? 11 : \
+ (n) & (1ULL << 10) ? 10 : \
+ (n) & (1ULL << 9) ? 9 : \
+ (n) & (1ULL << 8) ? 8 : \
+ (n) & (1ULL << 7) ? 7 : \
+ (n) & (1ULL << 6) ? 6 : \
+ (n) & (1ULL << 5) ? 5 : \
+ (n) & (1ULL << 4) ? 4 : \
+ (n) & (1ULL << 3) ? 3 : \
+ (n) & (1ULL << 2) ? 2 : \
+ 1 ) : \
+ (sizeof(n) <= 4) ? \
+ __ilog2_u32(n) : \
+ __ilog2_u64(n) \
+ )
+
+/**
+ * roundup_pow_of_two - round the given value up to nearest power of two
+ * @n - parameter
+ *
+ * round the given value up to the nearest power of two
+ * - the result is undefined when n == 0
+ * - this can be used to initialise global variables from constant data
+ */
+#define roundup_pow_of_two(n) \
+( \
+ __builtin_constant_p(n) ? ( \
+ (n == 1) ? 1 : \
+ (1UL << (ilog2((n) - 1) + 1)) \
+ ) : \
+ __roundup_pow_of_two(n) \
+ )
+
+/**
+ * rounddown_pow_of_two - round the given value down to nearest power of two
+ * @n - parameter
+ *
+ * round the given value down to the nearest power of two
+ * - the result is undefined when n == 0
+ * - this can be used to initialise global variables from constant data
+ */
+#define rounddown_pow_of_two(n) \
+( \
+ __builtin_constant_p(n) ? ( \
+ (1UL << ilog2(n))) : \
+ __rounddown_pow_of_two(n) \
+ )
+
+#endif /* _TOOLS_LINUX_LOG2_H */
diff --git a/tools/include/linux/math.h b/tools/include/linux/math.h
new file mode 100644
index 0000000000..4e7af99ec9
--- /dev/null
+++ b/tools/include/linux/math.h
@@ -0,0 +1,25 @@
+#ifndef _TOOLS_MATH_H
+#define _TOOLS_MATH_H
+
+/*
+ * This looks more complex than it should be. But we need to
+ * get the type for the ~ right in round_down (it needs to be
+ * as wide as the result!), and we want to evaluate the macro
+ * arguments just once each.
+ */
+#define __round_mask(x, y) ((__typeof__(x))((y)-1))
+#define round_up(x, y) ((((x)-1) | __round_mask(x, y))+1)
+#define round_down(x, y) ((x) & ~__round_mask(x, y))
+
+#define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d))
+
+#ifndef roundup
+#define roundup(x, y) ( \
+{ \
+ const typeof(y) __y = y; \
+ (((x) + (__y - 1)) / __y) * __y; \
+} \
+)
+#endif
+
+#endif
diff --git a/tools/include/linux/math64.h b/tools/include/linux/math64.h
new file mode 100644
index 0000000000..4ad45d5943
--- /dev/null
+++ b/tools/include/linux/math64.h
@@ -0,0 +1,75 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_MATH64_H
+#define _LINUX_MATH64_H
+
+#include <linux/types.h>
+
+#ifdef __x86_64__
+static inline u64 mul_u64_u64_div64(u64 a, u64 b, u64 c)
+{
+ u64 q;
+
+ asm ("mulq %2; divq %3" : "=a" (q)
+ : "a" (a), "rm" (b), "rm" (c)
+ : "rdx");
+
+ return q;
+}
+#define mul_u64_u64_div64 mul_u64_u64_div64
+#endif
+
+#ifdef __SIZEOF_INT128__
+static inline u64 mul_u64_u32_shr(u64 a, u32 b, unsigned int shift)
+{
+ return (u64)(((unsigned __int128)a * b) >> shift);
+}
+
+#else
+
+#ifdef __i386__
+static inline u64 mul_u32_u32(u32 a, u32 b)
+{
+ u32 high, low;
+
+ asm ("mull %[b]" : "=a" (low), "=d" (high)
+ : [a] "a" (a), [b] "rm" (b) );
+
+ return low | ((u64)high) << 32;
+}
+#else
+static inline u64 mul_u32_u32(u32 a, u32 b)
+{
+ return (u64)a * b;
+}
+#endif
+
+static inline u64 mul_u64_u32_shr(u64 a, u32 b, unsigned int shift)
+{
+ u32 ah, al;
+ u64 ret;
+
+ al = a;
+ ah = a >> 32;
+
+ ret = mul_u32_u32(al, b) >> shift;
+ if (ah)
+ ret += mul_u32_u32(ah, b) << (32 - shift);
+
+ return ret;
+}
+
+#endif /* __SIZEOF_INT128__ */
+
+#ifndef mul_u64_u64_div64
+static inline u64 mul_u64_u64_div64(u64 a, u64 b, u64 c)
+{
+ u64 quot, rem;
+
+ quot = a / c;
+ rem = a % c;
+
+ return quot * b + (rem * b) / c;
+}
+#endif
+
+#endif /* _LINUX_MATH64_H */
diff --git a/tools/include/linux/mm.h b/tools/include/linux/mm.h
new file mode 100644
index 0000000000..f3c82ab5b1
--- /dev/null
+++ b/tools/include/linux/mm.h
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TOOLS_LINUX_MM_H
+#define _TOOLS_LINUX_MM_H
+
+#include <linux/mmzone.h>
+#include <uapi/linux/const.h>
+
+#define PAGE_SHIFT 12
+#define PAGE_SIZE (_AC(1, UL) << PAGE_SHIFT)
+#define PAGE_MASK (~(PAGE_SIZE - 1))
+
+#define PHYS_ADDR_MAX (~(phys_addr_t)0)
+
+#define ALIGN(x, a) __ALIGN_KERNEL((x), (a))
+#define ALIGN_DOWN(x, a) __ALIGN_KERNEL((x) - ((a) - 1), (a))
+
+#define PAGE_ALIGN(addr) ALIGN(addr, PAGE_SIZE)
+
+#define __va(x) ((void *)((unsigned long)(x)))
+#define __pa(x) ((unsigned long)(x))
+
+#define pfn_to_page(pfn) ((void *)((pfn) * PAGE_SIZE))
+
+#define phys_to_virt phys_to_virt
+static inline void *phys_to_virt(unsigned long address)
+{
+ return __va(address);
+}
+
+void reserve_bootmem_region(phys_addr_t start, phys_addr_t end, int nid);
+
+static inline void totalram_pages_inc(void)
+{
+}
+
+static inline void totalram_pages_add(long count)
+{
+}
+
+#endif
diff --git a/tools/include/linux/module.h b/tools/include/linux/module.h
new file mode 100644
index 0000000000..2c999abf68
--- /dev/null
+++ b/tools/include/linux/module.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LIBLOCKDEP_LINUX_MODULE_H_
+#define _LIBLOCKDEP_LINUX_MODULE_H_
+
+#define module_param(name, type, perm)
+
+static inline bool __is_module_percpu_address(unsigned long addr, unsigned long *can_addr)
+{
+ return false;
+}
+
+#endif
diff --git a/tools/include/linux/mutex.h b/tools/include/linux/mutex.h
new file mode 100644
index 0000000000..a8180d25f2
--- /dev/null
+++ b/tools/include/linux/mutex.h
@@ -0,0 +1,4 @@
+#ifndef _TOOLS_INCLUDE_LINUX_MUTEX_H
+#define _TOOLS_INCLUDE_LINUX_MUTEX_H
+
+#endif /* _TOOLS_INCLUDE_LINUX_MUTEX_H */
diff --git a/tools/include/linux/nmi.h b/tools/include/linux/nmi.h
new file mode 100644
index 0000000000..e69de29bb2
--- /dev/null
+++ b/tools/include/linux/nmi.h
diff --git a/tools/include/linux/numa.h b/tools/include/linux/numa.h
new file mode 100644
index 0000000000..110b0e5d0f
--- /dev/null
+++ b/tools/include/linux/numa.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_NUMA_H
+#define _LINUX_NUMA_H
+
+
+#ifdef CONFIG_NODES_SHIFT
+#define NODES_SHIFT CONFIG_NODES_SHIFT
+#else
+#define NODES_SHIFT 0
+#endif
+
+#define MAX_NUMNODES (1 << NODES_SHIFT)
+
+#define NUMA_NO_NODE (-1)
+
+#endif /* _LINUX_NUMA_H */
diff --git a/tools/include/linux/objtool_types.h b/tools/include/linux/objtool_types.h
new file mode 100644
index 0000000000..453a4f4ef3
--- /dev/null
+++ b/tools/include/linux/objtool_types.h
@@ -0,0 +1,57 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_OBJTOOL_TYPES_H
+#define _LINUX_OBJTOOL_TYPES_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/types.h>
+
+/*
+ * This struct is used by asm and inline asm code to manually annotate the
+ * location of registers on the stack.
+ */
+struct unwind_hint {
+ u32 ip;
+ s16 sp_offset;
+ u8 sp_reg;
+ u8 type;
+ u8 signal;
+};
+
+#endif /* __ASSEMBLY__ */
+
+/*
+ * UNWIND_HINT_TYPE_UNDEFINED: A blind spot in ORC coverage which can result in
+ * a truncated and unreliable stack unwind.
+ *
+ * UNWIND_HINT_TYPE_END_OF_STACK: The end of the kernel stack unwind before
+ * hitting user entry, boot code, or fork entry (when there are no pt_regs
+ * available).
+ *
+ * UNWIND_HINT_TYPE_CALL: Indicates that sp_reg+sp_offset resolves to PREV_SP
+ * (the caller's SP right before it made the call). Used for all callable
+ * functions, i.e. all C code and all callable asm functions.
+ *
+ * UNWIND_HINT_TYPE_REGS: Used in entry code to indicate that sp_reg+sp_offset
+ * points to a fully populated pt_regs from a syscall, interrupt, or exception.
+ *
+ * UNWIND_HINT_TYPE_REGS_PARTIAL: Used in entry code to indicate that
+ * sp_reg+sp_offset points to the iret return frame.
+ *
+ * UNWIND_HINT_TYPE_FUNC: Generate the unwind metadata of a callable function.
+ * Useful for code which doesn't have an ELF function annotation.
+ *
+ * UNWIND_HINT_TYPE_{SAVE,RESTORE}: Save the unwind metadata at a certain
+ * location so that it can be restored later.
+ */
+#define UNWIND_HINT_TYPE_UNDEFINED 0
+#define UNWIND_HINT_TYPE_END_OF_STACK 1
+#define UNWIND_HINT_TYPE_CALL 2
+#define UNWIND_HINT_TYPE_REGS 3
+#define UNWIND_HINT_TYPE_REGS_PARTIAL 4
+/* The below hint types don't have corresponding ORC types */
+#define UNWIND_HINT_TYPE_FUNC 5
+#define UNWIND_HINT_TYPE_SAVE 6
+#define UNWIND_HINT_TYPE_RESTORE 7
+
+#endif /* _LINUX_OBJTOOL_TYPES_H */
diff --git a/tools/include/linux/overflow.h b/tools/include/linux/overflow.h
new file mode 100644
index 0000000000..dcb0c1bf68
--- /dev/null
+++ b/tools/include/linux/overflow.h
@@ -0,0 +1,144 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
+#ifndef __LINUX_OVERFLOW_H
+#define __LINUX_OVERFLOW_H
+
+#include <linux/compiler.h>
+
+/*
+ * We need to compute the minimum and maximum values representable in a given
+ * type. These macros may also be useful elsewhere. It would seem more obvious
+ * to do something like:
+ *
+ * #define type_min(T) (T)(is_signed_type(T) ? (T)1 << (8*sizeof(T)-1) : 0)
+ * #define type_max(T) (T)(is_signed_type(T) ? ((T)1 << (8*sizeof(T)-1)) - 1 : ~(T)0)
+ *
+ * Unfortunately, the middle expressions, strictly speaking, have
+ * undefined behaviour, and at least some versions of gcc warn about
+ * the type_max expression (but not if -fsanitize=undefined is in
+ * effect; in that case, the warning is deferred to runtime...).
+ *
+ * The slightly excessive casting in type_min is to make sure the
+ * macros also produce sensible values for the exotic type _Bool. [The
+ * overflow checkers only almost work for _Bool, but that's
+ * a-feature-not-a-bug, since people shouldn't be doing arithmetic on
+ * _Bools. Besides, the gcc builtins don't allow _Bool* as third
+ * argument.]
+ *
+ * Idea stolen from
+ * https://mail-index.netbsd.org/tech-misc/2007/02/05/0000.html -
+ * credit to Christian Biere.
+ */
+#define is_signed_type(type) (((type)(-1)) < (type)1)
+#define __type_half_max(type) ((type)1 << (8*sizeof(type) - 1 - is_signed_type(type)))
+#define type_max(T) ((T)((__type_half_max(T) - 1) + __type_half_max(T)))
+#define type_min(T) ((T)((T)-type_max(T)-(T)1))
+
+/*
+ * For simplicity and code hygiene, the fallback code below insists on
+ * a, b and *d having the same type (similar to the min() and max()
+ * macros), whereas gcc's type-generic overflow checkers accept
+ * different types. Hence we don't just make check_add_overflow an
+ * alias for __builtin_add_overflow, but add type checks similar to
+ * below.
+ */
+#define check_add_overflow(a, b, d) ({ \
+ typeof(a) __a = (a); \
+ typeof(b) __b = (b); \
+ typeof(d) __d = (d); \
+ (void) (&__a == &__b); \
+ (void) (&__a == __d); \
+ __builtin_add_overflow(__a, __b, __d); \
+})
+
+#define check_sub_overflow(a, b, d) ({ \
+ typeof(a) __a = (a); \
+ typeof(b) __b = (b); \
+ typeof(d) __d = (d); \
+ (void) (&__a == &__b); \
+ (void) (&__a == __d); \
+ __builtin_sub_overflow(__a, __b, __d); \
+})
+
+#define check_mul_overflow(a, b, d) ({ \
+ typeof(a) __a = (a); \
+ typeof(b) __b = (b); \
+ typeof(d) __d = (d); \
+ (void) (&__a == &__b); \
+ (void) (&__a == __d); \
+ __builtin_mul_overflow(__a, __b, __d); \
+})
+
+/**
+ * array_size() - Calculate size of 2-dimensional array.
+ *
+ * @a: dimension one
+ * @b: dimension two
+ *
+ * Calculates size of 2-dimensional array: @a * @b.
+ *
+ * Returns: number of bytes needed to represent the array or SIZE_MAX on
+ * overflow.
+ */
+static inline __must_check size_t array_size(size_t a, size_t b)
+{
+ size_t bytes;
+
+ if (check_mul_overflow(a, b, &bytes))
+ return SIZE_MAX;
+
+ return bytes;
+}
+
+/**
+ * array3_size() - Calculate size of 3-dimensional array.
+ *
+ * @a: dimension one
+ * @b: dimension two
+ * @c: dimension three
+ *
+ * Calculates size of 3-dimensional array: @a * @b * @c.
+ *
+ * Returns: number of bytes needed to represent the array or SIZE_MAX on
+ * overflow.
+ */
+static inline __must_check size_t array3_size(size_t a, size_t b, size_t c)
+{
+ size_t bytes;
+
+ if (check_mul_overflow(a, b, &bytes))
+ return SIZE_MAX;
+ if (check_mul_overflow(bytes, c, &bytes))
+ return SIZE_MAX;
+
+ return bytes;
+}
+
+static inline __must_check size_t __ab_c_size(size_t n, size_t size, size_t c)
+{
+ size_t bytes;
+
+ if (check_mul_overflow(n, size, &bytes))
+ return SIZE_MAX;
+ if (check_add_overflow(bytes, c, &bytes))
+ return SIZE_MAX;
+
+ return bytes;
+}
+
+/**
+ * struct_size() - Calculate size of structure with trailing array.
+ * @p: Pointer to the structure.
+ * @member: Name of the array member.
+ * @n: Number of elements in the array.
+ *
+ * Calculates size of memory needed for structure @p followed by an
+ * array of @n @member elements.
+ *
+ * Return: number of bytes needed or SIZE_MAX on overflow.
+ */
+#define struct_size(p, member, n) \
+ __ab_c_size(n, \
+ sizeof(*(p)->member) + __must_be_array((p)->member),\
+ sizeof(*(p)))
+
+#endif /* __LINUX_OVERFLOW_H */
diff --git a/tools/include/linux/pfn.h b/tools/include/linux/pfn.h
new file mode 100644
index 0000000000..7512a58189
--- /dev/null
+++ b/tools/include/linux/pfn.h
@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TOOLS_LINUX_PFN_H_
+#define _TOOLS_LINUX_PFN_H_
+
+#include <linux/mm.h>
+
+#define PFN_UP(x) (((x) + PAGE_SIZE - 1) >> PAGE_SHIFT)
+#define PFN_DOWN(x) ((x) >> PAGE_SHIFT)
+#define PFN_PHYS(x) ((phys_addr_t)(x) << PAGE_SHIFT)
+#endif
diff --git a/tools/include/linux/poison.h b/tools/include/linux/poison.h
new file mode 100644
index 0000000000..2e6338ac5e
--- /dev/null
+++ b/tools/include/linux/poison.h
@@ -0,0 +1,89 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_POISON_H
+#define _LINUX_POISON_H
+
+/********** include/linux/list.h **********/
+
+/*
+ * Architectures might want to move the poison pointer offset
+ * into some well-recognized area such as 0xdead000000000000,
+ * that is also not mappable by user-space exploits:
+ */
+#ifdef CONFIG_ILLEGAL_POINTER_VALUE
+# define POISON_POINTER_DELTA _AC(CONFIG_ILLEGAL_POINTER_VALUE, UL)
+#else
+# define POISON_POINTER_DELTA 0
+#endif
+
+#ifdef __cplusplus
+#define LIST_POISON1 NULL
+#define LIST_POISON2 NULL
+#else
+/*
+ * These are non-NULL pointers that will result in page faults
+ * under normal circumstances, used to verify that nobody uses
+ * non-initialized list entries.
+ */
+#define LIST_POISON1 ((void *) 0x100 + POISON_POINTER_DELTA)
+#define LIST_POISON2 ((void *) 0x200 + POISON_POINTER_DELTA)
+#endif
+
+/********** include/linux/timer.h **********/
+/*
+ * Magic number "tsta" to indicate a static timer initializer
+ * for the object debugging code.
+ */
+#define TIMER_ENTRY_STATIC ((void *) 0x300 + POISON_POINTER_DELTA)
+
+/********** mm/page_poison.c **********/
+#define PAGE_POISON 0xaa
+
+/********** mm/page_alloc.c ************/
+
+#define TAIL_MAPPING ((void *) 0x400 + POISON_POINTER_DELTA)
+
+/********** mm/slab.c **********/
+/*
+ * Magic nums for obj red zoning.
+ * Placed in the first word before and the first word after an obj.
+ */
+#define RED_INACTIVE 0x09F911029D74E35BULL /* when obj is inactive */
+#define RED_ACTIVE 0xD84156C5635688C0ULL /* when obj is active */
+
+#define SLUB_RED_INACTIVE 0xbb
+#define SLUB_RED_ACTIVE 0xcc
+
+/* ...and for poisoning */
+#define POISON_INUSE 0x5a /* for use-uninitialised poisoning */
+#define POISON_FREE 0x6b /* for use-after-free poisoning */
+#define POISON_END 0xa5 /* end-byte of poisoning */
+
+/********** arch/$ARCH/mm/init.c **********/
+#define POISON_FREE_INITMEM 0xcc
+
+/********** arch/ia64/hp/common/sba_iommu.c **********/
+/*
+ * arch/ia64/hp/common/sba_iommu.c uses a 16-byte poison string with a
+ * value of "SBAIOMMU POISON\0" for spill-over poisoning.
+ */
+
+/********** fs/jbd/journal.c **********/
+#define JBD_POISON_FREE 0x5b
+#define JBD2_POISON_FREE 0x5c
+
+/********** drivers/base/dmapool.c **********/
+#define POOL_POISON_FREED 0xa7 /* !inuse */
+#define POOL_POISON_ALLOCATED 0xa9 /* !initted */
+
+/********** drivers/atm/ **********/
+#define ATM_POISON_FREE 0x12
+#define ATM_POISON 0xdeadbeef
+
+/********** kernel/mutexes **********/
+#define MUTEX_DEBUG_INIT 0x11
+#define MUTEX_DEBUG_FREE 0x22
+
+/********** security/ **********/
+#define KEY_DESTROY 0xbd
+
+#endif
diff --git a/tools/include/linux/rbtree.h b/tools/include/linux/rbtree.h
new file mode 100644
index 0000000000..2680f2edb8
--- /dev/null
+++ b/tools/include/linux/rbtree.h
@@ -0,0 +1,345 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ Red Black Trees
+ (C) 1999 Andrea Arcangeli <andrea@suse.de>
+
+
+ linux/include/linux/rbtree.h
+
+ To use rbtrees you'll have to implement your own insert and search cores.
+ This will avoid us to use callbacks and to drop drammatically performances.
+ I know it's not the cleaner way, but in C (not in C++) to get
+ performances and genericity...
+
+ See Documentation/core-api/rbtree.rst for documentation and samples.
+*/
+
+#ifndef __TOOLS_LINUX_PERF_RBTREE_H
+#define __TOOLS_LINUX_PERF_RBTREE_H
+
+#include <linux/kernel.h>
+#include <linux/stddef.h>
+
+struct rb_node {
+ unsigned long __rb_parent_color;
+ struct rb_node *rb_right;
+ struct rb_node *rb_left;
+} __attribute__((aligned(sizeof(long))));
+ /* The alignment might seem pointless, but allegedly CRIS needs it */
+
+struct rb_root {
+ struct rb_node *rb_node;
+};
+
+#define rb_parent(r) ((struct rb_node *)((r)->__rb_parent_color & ~3))
+
+#define RB_ROOT (struct rb_root) { NULL, }
+#define rb_entry(ptr, type, member) container_of(ptr, type, member)
+
+#define RB_EMPTY_ROOT(root) (READ_ONCE((root)->rb_node) == NULL)
+
+/* 'empty' nodes are nodes that are known not to be inserted in an rbtree */
+#define RB_EMPTY_NODE(node) \
+ ((node)->__rb_parent_color == (unsigned long)(node))
+#define RB_CLEAR_NODE(node) \
+ ((node)->__rb_parent_color = (unsigned long)(node))
+
+
+extern void rb_insert_color(struct rb_node *, struct rb_root *);
+extern void rb_erase(struct rb_node *, struct rb_root *);
+
+
+/* Find logical next and previous nodes in a tree */
+extern struct rb_node *rb_next(const struct rb_node *);
+extern struct rb_node *rb_prev(const struct rb_node *);
+extern struct rb_node *rb_first(const struct rb_root *);
+extern struct rb_node *rb_last(const struct rb_root *);
+
+/* Postorder iteration - always visit the parent after its children */
+extern struct rb_node *rb_first_postorder(const struct rb_root *);
+extern struct rb_node *rb_next_postorder(const struct rb_node *);
+
+/* Fast replacement of a single node without remove/rebalance/add/rebalance */
+extern void rb_replace_node(struct rb_node *victim, struct rb_node *new,
+ struct rb_root *root);
+
+static inline void rb_link_node(struct rb_node *node, struct rb_node *parent,
+ struct rb_node **rb_link)
+{
+ node->__rb_parent_color = (unsigned long)parent;
+ node->rb_left = node->rb_right = NULL;
+
+ *rb_link = node;
+}
+
+#define rb_entry_safe(ptr, type, member) \
+ ({ typeof(ptr) ____ptr = (ptr); \
+ ____ptr ? rb_entry(____ptr, type, member) : NULL; \
+ })
+
+/**
+ * rbtree_postorder_for_each_entry_safe - iterate in post-order over rb_root of
+ * given type allowing the backing memory of @pos to be invalidated
+ *
+ * @pos: the 'type *' to use as a loop cursor.
+ * @n: another 'type *' to use as temporary storage
+ * @root: 'rb_root *' of the rbtree.
+ * @field: the name of the rb_node field within 'type'.
+ *
+ * rbtree_postorder_for_each_entry_safe() provides a similar guarantee as
+ * list_for_each_entry_safe() and allows the iteration to continue independent
+ * of changes to @pos by the body of the loop.
+ *
+ * Note, however, that it cannot handle other modifications that re-order the
+ * rbtree it is iterating over. This includes calling rb_erase() on @pos, as
+ * rb_erase() may rebalance the tree, causing us to miss some nodes.
+ */
+#define rbtree_postorder_for_each_entry_safe(pos, n, root, field) \
+ for (pos = rb_entry_safe(rb_first_postorder(root), typeof(*pos), field); \
+ pos && ({ n = rb_entry_safe(rb_next_postorder(&pos->field), \
+ typeof(*pos), field); 1; }); \
+ pos = n)
+
+static inline void rb_erase_init(struct rb_node *n, struct rb_root *root)
+{
+ rb_erase(n, root);
+ RB_CLEAR_NODE(n);
+}
+
+/*
+ * Leftmost-cached rbtrees.
+ *
+ * We do not cache the rightmost node based on footprint
+ * size vs number of potential users that could benefit
+ * from O(1) rb_last(). Just not worth it, users that want
+ * this feature can always implement the logic explicitly.
+ * Furthermore, users that want to cache both pointers may
+ * find it a bit asymmetric, but that's ok.
+ */
+struct rb_root_cached {
+ struct rb_root rb_root;
+ struct rb_node *rb_leftmost;
+};
+
+#define RB_ROOT_CACHED (struct rb_root_cached) { {NULL, }, NULL }
+
+/* Same as rb_first(), but O(1) */
+#define rb_first_cached(root) (root)->rb_leftmost
+
+static inline void rb_insert_color_cached(struct rb_node *node,
+ struct rb_root_cached *root,
+ bool leftmost)
+{
+ if (leftmost)
+ root->rb_leftmost = node;
+ rb_insert_color(node, &root->rb_root);
+}
+
+static inline void rb_erase_cached(struct rb_node *node,
+ struct rb_root_cached *root)
+{
+ if (root->rb_leftmost == node)
+ root->rb_leftmost = rb_next(node);
+ rb_erase(node, &root->rb_root);
+}
+
+static inline void rb_replace_node_cached(struct rb_node *victim,
+ struct rb_node *new,
+ struct rb_root_cached *root)
+{
+ if (root->rb_leftmost == victim)
+ root->rb_leftmost = new;
+ rb_replace_node(victim, new, &root->rb_root);
+}
+
+/*
+ * The below helper functions use 2 operators with 3 different
+ * calling conventions. The operators are related like:
+ *
+ * comp(a->key,b) < 0 := less(a,b)
+ * comp(a->key,b) > 0 := less(b,a)
+ * comp(a->key,b) == 0 := !less(a,b) && !less(b,a)
+ *
+ * If these operators define a partial order on the elements we make no
+ * guarantee on which of the elements matching the key is found. See
+ * rb_find().
+ *
+ * The reason for this is to allow the find() interface without requiring an
+ * on-stack dummy object, which might not be feasible due to object size.
+ */
+
+/**
+ * rb_add_cached() - insert @node into the leftmost cached tree @tree
+ * @node: node to insert
+ * @tree: leftmost cached tree to insert @node into
+ * @less: operator defining the (partial) node order
+ */
+static __always_inline void
+rb_add_cached(struct rb_node *node, struct rb_root_cached *tree,
+ bool (*less)(struct rb_node *, const struct rb_node *))
+{
+ struct rb_node **link = &tree->rb_root.rb_node;
+ struct rb_node *parent = NULL;
+ bool leftmost = true;
+
+ while (*link) {
+ parent = *link;
+ if (less(node, parent)) {
+ link = &parent->rb_left;
+ } else {
+ link = &parent->rb_right;
+ leftmost = false;
+ }
+ }
+
+ rb_link_node(node, parent, link);
+ rb_insert_color_cached(node, tree, leftmost);
+}
+
+/**
+ * rb_add() - insert @node into @tree
+ * @node: node to insert
+ * @tree: tree to insert @node into
+ * @less: operator defining the (partial) node order
+ */
+static __always_inline void
+rb_add(struct rb_node *node, struct rb_root *tree,
+ bool (*less)(struct rb_node *, const struct rb_node *))
+{
+ struct rb_node **link = &tree->rb_node;
+ struct rb_node *parent = NULL;
+
+ while (*link) {
+ parent = *link;
+ if (less(node, parent))
+ link = &parent->rb_left;
+ else
+ link = &parent->rb_right;
+ }
+
+ rb_link_node(node, parent, link);
+ rb_insert_color(node, tree);
+}
+
+/**
+ * rb_find_add() - find equivalent @node in @tree, or add @node
+ * @node: node to look-for / insert
+ * @tree: tree to search / modify
+ * @cmp: operator defining the node order
+ *
+ * Returns the rb_node matching @node, or NULL when no match is found and @node
+ * is inserted.
+ */
+static __always_inline struct rb_node *
+rb_find_add(struct rb_node *node, struct rb_root *tree,
+ int (*cmp)(struct rb_node *, const struct rb_node *))
+{
+ struct rb_node **link = &tree->rb_node;
+ struct rb_node *parent = NULL;
+ int c;
+
+ while (*link) {
+ parent = *link;
+ c = cmp(node, parent);
+
+ if (c < 0)
+ link = &parent->rb_left;
+ else if (c > 0)
+ link = &parent->rb_right;
+ else
+ return parent;
+ }
+
+ rb_link_node(node, parent, link);
+ rb_insert_color(node, tree);
+ return NULL;
+}
+
+/**
+ * rb_find() - find @key in tree @tree
+ * @key: key to match
+ * @tree: tree to search
+ * @cmp: operator defining the node order
+ *
+ * Returns the rb_node matching @key or NULL.
+ */
+static __always_inline struct rb_node *
+rb_find(const void *key, const struct rb_root *tree,
+ int (*cmp)(const void *key, const struct rb_node *))
+{
+ struct rb_node *node = tree->rb_node;
+
+ while (node) {
+ int c = cmp(key, node);
+
+ if (c < 0)
+ node = node->rb_left;
+ else if (c > 0)
+ node = node->rb_right;
+ else
+ return node;
+ }
+
+ return NULL;
+}
+
+/**
+ * rb_find_first() - find the first @key in @tree
+ * @key: key to match
+ * @tree: tree to search
+ * @cmp: operator defining node order
+ *
+ * Returns the leftmost node matching @key, or NULL.
+ */
+static __always_inline struct rb_node *
+rb_find_first(const void *key, const struct rb_root *tree,
+ int (*cmp)(const void *key, const struct rb_node *))
+{
+ struct rb_node *node = tree->rb_node;
+ struct rb_node *match = NULL;
+
+ while (node) {
+ int c = cmp(key, node);
+
+ if (c <= 0) {
+ if (!c)
+ match = node;
+ node = node->rb_left;
+ } else if (c > 0) {
+ node = node->rb_right;
+ }
+ }
+
+ return match;
+}
+
+/**
+ * rb_next_match() - find the next @key in @tree
+ * @key: key to match
+ * @tree: tree to search
+ * @cmp: operator defining node order
+ *
+ * Returns the next node matching @key, or NULL.
+ */
+static __always_inline struct rb_node *
+rb_next_match(const void *key, struct rb_node *node,
+ int (*cmp)(const void *key, const struct rb_node *))
+{
+ node = rb_next(node);
+ if (node && cmp(key, node))
+ node = NULL;
+ return node;
+}
+
+/**
+ * rb_for_each() - iterates a subtree matching @key
+ * @node: iterator
+ * @key: key to match
+ * @tree: tree to search
+ * @cmp: operator defining node order
+ */
+#define rb_for_each(node, key, tree, cmp) \
+ for ((node) = rb_find_first((key), (tree), (cmp)); \
+ (node); (node) = rb_next_match((key), (node), (cmp)))
+
+#endif /* __TOOLS_LINUX_PERF_RBTREE_H */
diff --git a/tools/include/linux/rbtree_augmented.h b/tools/include/linux/rbtree_augmented.h
new file mode 100644
index 0000000000..570bb97944
--- /dev/null
+++ b/tools/include/linux/rbtree_augmented.h
@@ -0,0 +1,308 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ Red Black Trees
+ (C) 1999 Andrea Arcangeli <andrea@suse.de>
+ (C) 2002 David Woodhouse <dwmw2@infradead.org>
+ (C) 2012 Michel Lespinasse <walken@google.com>
+
+
+ tools/linux/include/linux/rbtree_augmented.h
+
+ Copied from:
+ linux/include/linux/rbtree_augmented.h
+*/
+
+#ifndef _TOOLS_LINUX_RBTREE_AUGMENTED_H
+#define _TOOLS_LINUX_RBTREE_AUGMENTED_H
+
+#include <linux/compiler.h>
+#include <linux/rbtree.h>
+
+/*
+ * Please note - only struct rb_augment_callbacks and the prototypes for
+ * rb_insert_augmented() and rb_erase_augmented() are intended to be public.
+ * The rest are implementation details you are not expected to depend on.
+ *
+ * See Documentation/core-api/rbtree.rst for documentation and samples.
+ */
+
+struct rb_augment_callbacks {
+ void (*propagate)(struct rb_node *node, struct rb_node *stop);
+ void (*copy)(struct rb_node *old, struct rb_node *new);
+ void (*rotate)(struct rb_node *old, struct rb_node *new);
+};
+
+extern void __rb_insert_augmented(struct rb_node *node, struct rb_root *root,
+ void (*augment_rotate)(struct rb_node *old, struct rb_node *new));
+
+/*
+ * Fixup the rbtree and update the augmented information when rebalancing.
+ *
+ * On insertion, the user must update the augmented information on the path
+ * leading to the inserted node, then call rb_link_node() as usual and
+ * rb_insert_augmented() instead of the usual rb_insert_color() call.
+ * If rb_insert_augmented() rebalances the rbtree, it will callback into
+ * a user provided function to update the augmented information on the
+ * affected subtrees.
+ */
+static inline void
+rb_insert_augmented(struct rb_node *node, struct rb_root *root,
+ const struct rb_augment_callbacks *augment)
+{
+ __rb_insert_augmented(node, root, augment->rotate);
+}
+
+static inline void
+rb_insert_augmented_cached(struct rb_node *node,
+ struct rb_root_cached *root, bool newleft,
+ const struct rb_augment_callbacks *augment)
+{
+ if (newleft)
+ root->rb_leftmost = node;
+ rb_insert_augmented(node, &root->rb_root, augment);
+}
+
+/*
+ * Template for declaring augmented rbtree callbacks (generic case)
+ *
+ * RBSTATIC: 'static' or empty
+ * RBNAME: name of the rb_augment_callbacks structure
+ * RBSTRUCT: struct type of the tree nodes
+ * RBFIELD: name of struct rb_node field within RBSTRUCT
+ * RBAUGMENTED: name of field within RBSTRUCT holding data for subtree
+ * RBCOMPUTE: name of function that recomputes the RBAUGMENTED data
+ */
+
+#define RB_DECLARE_CALLBACKS(RBSTATIC, RBNAME, \
+ RBSTRUCT, RBFIELD, RBAUGMENTED, RBCOMPUTE) \
+static inline void \
+RBNAME ## _propagate(struct rb_node *rb, struct rb_node *stop) \
+{ \
+ while (rb != stop) { \
+ RBSTRUCT *node = rb_entry(rb, RBSTRUCT, RBFIELD); \
+ if (RBCOMPUTE(node, true)) \
+ break; \
+ rb = rb_parent(&node->RBFIELD); \
+ } \
+} \
+static inline void \
+RBNAME ## _copy(struct rb_node *rb_old, struct rb_node *rb_new) \
+{ \
+ RBSTRUCT *old = rb_entry(rb_old, RBSTRUCT, RBFIELD); \
+ RBSTRUCT *new = rb_entry(rb_new, RBSTRUCT, RBFIELD); \
+ new->RBAUGMENTED = old->RBAUGMENTED; \
+} \
+static void \
+RBNAME ## _rotate(struct rb_node *rb_old, struct rb_node *rb_new) \
+{ \
+ RBSTRUCT *old = rb_entry(rb_old, RBSTRUCT, RBFIELD); \
+ RBSTRUCT *new = rb_entry(rb_new, RBSTRUCT, RBFIELD); \
+ new->RBAUGMENTED = old->RBAUGMENTED; \
+ RBCOMPUTE(old, false); \
+} \
+RBSTATIC const struct rb_augment_callbacks RBNAME = { \
+ .propagate = RBNAME ## _propagate, \
+ .copy = RBNAME ## _copy, \
+ .rotate = RBNAME ## _rotate \
+};
+
+/*
+ * Template for declaring augmented rbtree callbacks,
+ * computing RBAUGMENTED scalar as max(RBCOMPUTE(node)) for all subtree nodes.
+ *
+ * RBSTATIC: 'static' or empty
+ * RBNAME: name of the rb_augment_callbacks structure
+ * RBSTRUCT: struct type of the tree nodes
+ * RBFIELD: name of struct rb_node field within RBSTRUCT
+ * RBTYPE: type of the RBAUGMENTED field
+ * RBAUGMENTED: name of RBTYPE field within RBSTRUCT holding data for subtree
+ * RBCOMPUTE: name of function that returns the per-node RBTYPE scalar
+ */
+
+#define RB_DECLARE_CALLBACKS_MAX(RBSTATIC, RBNAME, RBSTRUCT, RBFIELD, \
+ RBTYPE, RBAUGMENTED, RBCOMPUTE) \
+static inline bool RBNAME ## _compute_max(RBSTRUCT *node, bool exit) \
+{ \
+ RBSTRUCT *child; \
+ RBTYPE max = RBCOMPUTE(node); \
+ if (node->RBFIELD.rb_left) { \
+ child = rb_entry(node->RBFIELD.rb_left, RBSTRUCT, RBFIELD); \
+ if (child->RBAUGMENTED > max) \
+ max = child->RBAUGMENTED; \
+ } \
+ if (node->RBFIELD.rb_right) { \
+ child = rb_entry(node->RBFIELD.rb_right, RBSTRUCT, RBFIELD); \
+ if (child->RBAUGMENTED > max) \
+ max = child->RBAUGMENTED; \
+ } \
+ if (exit && node->RBAUGMENTED == max) \
+ return true; \
+ node->RBAUGMENTED = max; \
+ return false; \
+} \
+RB_DECLARE_CALLBACKS(RBSTATIC, RBNAME, \
+ RBSTRUCT, RBFIELD, RBAUGMENTED, RBNAME ## _compute_max)
+
+
+#define RB_RED 0
+#define RB_BLACK 1
+
+#define __rb_parent(pc) ((struct rb_node *)(pc & ~3))
+
+#define __rb_color(pc) ((pc) & 1)
+#define __rb_is_black(pc) __rb_color(pc)
+#define __rb_is_red(pc) (!__rb_color(pc))
+#define rb_color(rb) __rb_color((rb)->__rb_parent_color)
+#define rb_is_red(rb) __rb_is_red((rb)->__rb_parent_color)
+#define rb_is_black(rb) __rb_is_black((rb)->__rb_parent_color)
+
+static inline void rb_set_parent(struct rb_node *rb, struct rb_node *p)
+{
+ rb->__rb_parent_color = rb_color(rb) | (unsigned long)p;
+}
+
+static inline void rb_set_parent_color(struct rb_node *rb,
+ struct rb_node *p, int color)
+{
+ rb->__rb_parent_color = (unsigned long)p | color;
+}
+
+static inline void
+__rb_change_child(struct rb_node *old, struct rb_node *new,
+ struct rb_node *parent, struct rb_root *root)
+{
+ if (parent) {
+ if (parent->rb_left == old)
+ WRITE_ONCE(parent->rb_left, new);
+ else
+ WRITE_ONCE(parent->rb_right, new);
+ } else
+ WRITE_ONCE(root->rb_node, new);
+}
+
+extern void __rb_erase_color(struct rb_node *parent, struct rb_root *root,
+ void (*augment_rotate)(struct rb_node *old, struct rb_node *new));
+
+static __always_inline struct rb_node *
+__rb_erase_augmented(struct rb_node *node, struct rb_root *root,
+ const struct rb_augment_callbacks *augment)
+{
+ struct rb_node *child = node->rb_right;
+ struct rb_node *tmp = node->rb_left;
+ struct rb_node *parent, *rebalance;
+ unsigned long pc;
+
+ if (!tmp) {
+ /*
+ * Case 1: node to erase has no more than 1 child (easy!)
+ *
+ * Note that if there is one child it must be red due to 5)
+ * and node must be black due to 4). We adjust colors locally
+ * so as to bypass __rb_erase_color() later on.
+ */
+ pc = node->__rb_parent_color;
+ parent = __rb_parent(pc);
+ __rb_change_child(node, child, parent, root);
+ if (child) {
+ child->__rb_parent_color = pc;
+ rebalance = NULL;
+ } else
+ rebalance = __rb_is_black(pc) ? parent : NULL;
+ tmp = parent;
+ } else if (!child) {
+ /* Still case 1, but this time the child is node->rb_left */
+ tmp->__rb_parent_color = pc = node->__rb_parent_color;
+ parent = __rb_parent(pc);
+ __rb_change_child(node, tmp, parent, root);
+ rebalance = NULL;
+ tmp = parent;
+ } else {
+ struct rb_node *successor = child, *child2;
+
+ tmp = child->rb_left;
+ if (!tmp) {
+ /*
+ * Case 2: node's successor is its right child
+ *
+ * (n) (s)
+ * / \ / \
+ * (x) (s) -> (x) (c)
+ * \
+ * (c)
+ */
+ parent = successor;
+ child2 = successor->rb_right;
+
+ augment->copy(node, successor);
+ } else {
+ /*
+ * Case 3: node's successor is leftmost under
+ * node's right child subtree
+ *
+ * (n) (s)
+ * / \ / \
+ * (x) (y) -> (x) (y)
+ * / /
+ * (p) (p)
+ * / /
+ * (s) (c)
+ * \
+ * (c)
+ */
+ do {
+ parent = successor;
+ successor = tmp;
+ tmp = tmp->rb_left;
+ } while (tmp);
+ child2 = successor->rb_right;
+ WRITE_ONCE(parent->rb_left, child2);
+ WRITE_ONCE(successor->rb_right, child);
+ rb_set_parent(child, successor);
+
+ augment->copy(node, successor);
+ augment->propagate(parent, successor);
+ }
+
+ tmp = node->rb_left;
+ WRITE_ONCE(successor->rb_left, tmp);
+ rb_set_parent(tmp, successor);
+
+ pc = node->__rb_parent_color;
+ tmp = __rb_parent(pc);
+ __rb_change_child(node, successor, tmp, root);
+
+ if (child2) {
+ successor->__rb_parent_color = pc;
+ rb_set_parent_color(child2, parent, RB_BLACK);
+ rebalance = NULL;
+ } else {
+ unsigned long pc2 = successor->__rb_parent_color;
+ successor->__rb_parent_color = pc;
+ rebalance = __rb_is_black(pc2) ? parent : NULL;
+ }
+ tmp = successor;
+ }
+
+ augment->propagate(tmp, NULL);
+ return rebalance;
+}
+
+static __always_inline void
+rb_erase_augmented(struct rb_node *node, struct rb_root *root,
+ const struct rb_augment_callbacks *augment)
+{
+ struct rb_node *rebalance = __rb_erase_augmented(node, root, augment);
+ if (rebalance)
+ __rb_erase_color(rebalance, root, augment->rotate);
+}
+
+static __always_inline void
+rb_erase_augmented_cached(struct rb_node *node, struct rb_root_cached *root,
+ const struct rb_augment_callbacks *augment)
+{
+ if (root->rb_leftmost == node)
+ root->rb_leftmost = rb_next(node);
+ rb_erase_augmented(node, &root->rb_root, augment);
+}
+
+#endif /* _TOOLS_LINUX_RBTREE_AUGMENTED_H */
diff --git a/tools/include/linux/rcu.h b/tools/include/linux/rcu.h
new file mode 100644
index 0000000000..9554d3fa54
--- /dev/null
+++ b/tools/include/linux/rcu.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LIBLOCKDEP_RCU_H_
+#define _LIBLOCKDEP_RCU_H_
+
+int rcu_scheduler_active;
+
+static inline int rcu_lockdep_current_cpu_online(void)
+{
+ return 1;
+}
+
+static inline int rcu_is_cpu_idle(void)
+{
+ return 1;
+}
+
+static inline bool rcu_is_watching(void)
+{
+ return false;
+}
+
+#define rcu_assign_pointer(p, v) do { (p) = (v); } while (0)
+#define RCU_INIT_POINTER(p, v) do { (p) = (v); } while (0)
+
+#endif
diff --git a/tools/include/linux/refcount.h b/tools/include/linux/refcount.h
new file mode 100644
index 0000000000..36cb29bc57
--- /dev/null
+++ b/tools/include/linux/refcount.h
@@ -0,0 +1,152 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TOOLS_LINUX_REFCOUNT_H
+#define _TOOLS_LINUX_REFCOUNT_H
+
+/*
+ * Variant of atomic_t specialized for reference counts.
+ *
+ * The interface matches the atomic_t interface (to aid in porting) but only
+ * provides the few functions one should use for reference counting.
+ *
+ * It differs in that the counter saturates at UINT_MAX and will not move once
+ * there. This avoids wrapping the counter and causing 'spurious'
+ * use-after-free issues.
+ *
+ * Memory ordering rules are slightly relaxed wrt regular atomic_t functions
+ * and provide only what is strictly required for refcounts.
+ *
+ * The increments are fully relaxed; these will not provide ordering. The
+ * rationale is that whatever is used to obtain the object we're increasing the
+ * reference count on will provide the ordering. For locked data structures,
+ * its the lock acquire, for RCU/lockless data structures its the dependent
+ * load.
+ *
+ * Do note that inc_not_zero() provides a control dependency which will order
+ * future stores against the inc, this ensures we'll never modify the object
+ * if we did not in fact acquire a reference.
+ *
+ * The decrements will provide release order, such that all the prior loads and
+ * stores will be issued before, it also provides a control dependency, which
+ * will order us against the subsequent free().
+ *
+ * The control dependency is against the load of the cmpxchg (ll/sc) that
+ * succeeded. This means the stores aren't fully ordered, but this is fine
+ * because the 1->0 transition indicates no concurrency.
+ *
+ * Note that the allocator is responsible for ordering things between free()
+ * and alloc().
+ *
+ */
+
+#include <linux/atomic.h>
+#include <linux/kernel.h>
+
+#ifdef NDEBUG
+#define REFCOUNT_WARN(cond, str) (void)(cond)
+#define __refcount_check
+#else
+#define REFCOUNT_WARN(cond, str) BUG_ON(cond)
+#define __refcount_check __must_check
+#endif
+
+typedef struct refcount_struct {
+ atomic_t refs;
+} refcount_t;
+
+#define REFCOUNT_INIT(n) { .refs = ATOMIC_INIT(n), }
+
+static inline void refcount_set(refcount_t *r, unsigned int n)
+{
+ atomic_set(&r->refs, n);
+}
+
+static inline unsigned int refcount_read(const refcount_t *r)
+{
+ return atomic_read(&r->refs);
+}
+
+/*
+ * Similar to atomic_inc_not_zero(), will saturate at UINT_MAX and WARN.
+ *
+ * Provides no memory ordering, it is assumed the caller has guaranteed the
+ * object memory to be stable (RCU, etc.). It does provide a control dependency
+ * and thereby orders future stores. See the comment on top.
+ */
+static inline __refcount_check
+bool refcount_inc_not_zero(refcount_t *r)
+{
+ unsigned int old, new, val = atomic_read(&r->refs);
+
+ for (;;) {
+ new = val + 1;
+
+ if (!val)
+ return false;
+
+ if (unlikely(!new))
+ return true;
+
+ old = atomic_cmpxchg_relaxed(&r->refs, val, new);
+ if (old == val)
+ break;
+
+ val = old;
+ }
+
+ REFCOUNT_WARN(new == UINT_MAX, "refcount_t: saturated; leaking memory.\n");
+
+ return true;
+}
+
+/*
+ * Similar to atomic_inc(), will saturate at UINT_MAX and WARN.
+ *
+ * Provides no memory ordering, it is assumed the caller already has a
+ * reference on the object, will WARN when this is not so.
+ */
+static inline void refcount_inc(refcount_t *r)
+{
+ REFCOUNT_WARN(!refcount_inc_not_zero(r), "refcount_t: increment on 0; use-after-free.\n");
+}
+
+/*
+ * Similar to atomic_dec_and_test(), it will WARN on underflow and fail to
+ * decrement when saturated at UINT_MAX.
+ *
+ * Provides release memory ordering, such that prior loads and stores are done
+ * before, and provides a control dependency such that free() must come after.
+ * See the comment on top.
+ */
+static inline __refcount_check
+bool refcount_sub_and_test(unsigned int i, refcount_t *r)
+{
+ unsigned int old, new, val = atomic_read(&r->refs);
+
+ for (;;) {
+ if (unlikely(val == UINT_MAX))
+ return false;
+
+ new = val - i;
+ if (new > val) {
+ REFCOUNT_WARN(new > val, "refcount_t: underflow; use-after-free.\n");
+ return false;
+ }
+
+ old = atomic_cmpxchg_release(&r->refs, val, new);
+ if (old == val)
+ break;
+
+ val = old;
+ }
+
+ return !new;
+}
+
+static inline __refcount_check
+bool refcount_dec_and_test(refcount_t *r)
+{
+ return refcount_sub_and_test(1, r);
+}
+
+
+#endif /* _ATOMIC_LINUX_REFCOUNT_H */
diff --git a/tools/include/linux/ring_buffer.h b/tools/include/linux/ring_buffer.h
new file mode 100644
index 0000000000..6c02617377
--- /dev/null
+++ b/tools/include/linux/ring_buffer.h
@@ -0,0 +1,74 @@
+#ifndef _TOOLS_LINUX_RING_BUFFER_H_
+#define _TOOLS_LINUX_RING_BUFFER_H_
+
+#include <asm/barrier.h>
+#include <linux/perf_event.h>
+
+/*
+ * Contract with kernel for walking the perf ring buffer from
+ * user space requires the following barrier pairing (quote
+ * from kernel/events/ring_buffer.c):
+ *
+ * Since the mmap() consumer (userspace) can run on a
+ * different CPU:
+ *
+ * kernel user
+ *
+ * if (LOAD ->data_tail) { LOAD ->data_head
+ * (A) smp_rmb() (C)
+ * STORE $data LOAD $data
+ * smp_wmb() (B) smp_mb() (D)
+ * STORE ->data_head STORE ->data_tail
+ * }
+ *
+ * Where A pairs with D, and B pairs with C.
+ *
+ * In our case A is a control dependency that separates the
+ * load of the ->data_tail and the stores of $data. In case
+ * ->data_tail indicates there is no room in the buffer to
+ * store $data we do not.
+ *
+ * D needs to be a full barrier since it separates the data
+ * READ from the tail WRITE.
+ *
+ * For B a WMB is sufficient since it separates two WRITEs,
+ * and for C an RMB is sufficient since it separates two READs.
+ *
+ * Note, instead of B, C, D we could also use smp_store_release()
+ * in B and D as well as smp_load_acquire() in C.
+ *
+ * However, this optimization does not make sense for all kernel
+ * supported architectures since for a fair number it would
+ * resolve into READ_ONCE() + smp_mb() pair for smp_load_acquire(),
+ * and smp_mb() + WRITE_ONCE() pair for smp_store_release().
+ *
+ * Thus for those smp_wmb() in B and smp_rmb() in C would still
+ * be less expensive. For the case of D this has either the same
+ * cost or is less expensive, for example, due to TSO x86 can
+ * avoid the CPU barrier entirely.
+ */
+
+static inline u64 ring_buffer_read_head(struct perf_event_mmap_page *base)
+{
+/*
+ * Architectures where smp_load_acquire() does not fallback to
+ * READ_ONCE() + smp_mb() pair.
+ */
+#if defined(__x86_64__) || defined(__aarch64__) || defined(__powerpc64__) || \
+ defined(__ia64__) || defined(__sparc__) && defined(__arch64__)
+ return smp_load_acquire(&base->data_head);
+#else
+ u64 head = READ_ONCE(base->data_head);
+
+ smp_rmb();
+ return head;
+#endif
+}
+
+static inline void ring_buffer_write_tail(struct perf_event_mmap_page *base,
+ u64 tail)
+{
+ smp_store_release(&base->data_tail, tail);
+}
+
+#endif /* _TOOLS_LINUX_RING_BUFFER_H_ */
diff --git a/tools/include/linux/rwsem.h b/tools/include/linux/rwsem.h
new file mode 100644
index 0000000000..83971b3cbf
--- /dev/null
+++ b/tools/include/linux/rwsem.h
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+#ifndef _TOOLS__RWSEM_H
+#define _TOOLS__RWSEM_H
+
+#include <pthread.h>
+
+struct rw_semaphore {
+ pthread_rwlock_t lock;
+};
+
+static inline int init_rwsem(struct rw_semaphore *sem)
+{
+ return pthread_rwlock_init(&sem->lock, NULL);
+}
+
+static inline int exit_rwsem(struct rw_semaphore *sem)
+{
+ return pthread_rwlock_destroy(&sem->lock);
+}
+
+static inline int down_read(struct rw_semaphore *sem)
+{
+ return pthread_rwlock_rdlock(&sem->lock);
+}
+
+static inline int up_read(struct rw_semaphore *sem)
+{
+ return pthread_rwlock_unlock(&sem->lock);
+}
+
+static inline int down_write(struct rw_semaphore *sem)
+{
+ return pthread_rwlock_wrlock(&sem->lock);
+}
+
+static inline int up_write(struct rw_semaphore *sem)
+{
+ return pthread_rwlock_unlock(&sem->lock);
+}
+#endif /* _TOOLS_RWSEM_H */
diff --git a/tools/include/linux/sched/clock.h b/tools/include/linux/sched/clock.h
new file mode 100644
index 0000000000..5837d17c41
--- /dev/null
+++ b/tools/include/linux/sched/clock.h
@@ -0,0 +1,4 @@
+#ifndef _TOOLS_PERF_LINUX_SCHED_CLOCK_H
+#define _TOOLS_PERF_LINUX_SCHED_CLOCK_H
+
+#endif /* _TOOLS_PERF_LINUX_SCHED_CLOCK_H */
diff --git a/tools/include/linux/sched/mm.h b/tools/include/linux/sched/mm.h
new file mode 100644
index 0000000000..967294b8ed
--- /dev/null
+++ b/tools/include/linux/sched/mm.h
@@ -0,0 +1,6 @@
+#ifndef _TOOLS_PERF_LINUX_SCHED_MM_H
+#define _TOOLS_PERF_LINUX_SCHED_MM_H
+
+#define might_alloc(gfp) do { } while (0)
+
+#endif /* _TOOLS_PERF_LINUX_SCHED_MM_H */
diff --git a/tools/include/linux/sched/task.h b/tools/include/linux/sched/task.h
new file mode 100644
index 0000000000..a97890eca1
--- /dev/null
+++ b/tools/include/linux/sched/task.h
@@ -0,0 +1,4 @@
+#ifndef _TOOLS_PERF_LINUX_SCHED_TASK_H
+#define _TOOLS_PERF_LINUX_SCHED_TASK_H
+
+#endif /* _TOOLS_PERF_LINUX_SCHED_TASK_H */
diff --git a/tools/include/linux/seq_file.h b/tools/include/linux/seq_file.h
new file mode 100644
index 0000000000..f6bc226af0
--- /dev/null
+++ b/tools/include/linux/seq_file.h
@@ -0,0 +1,6 @@
+#ifndef _TOOLS_INCLUDE_LINUX_SEQ_FILE_H
+#define _TOOLS_INCLUDE_LINUX_SEQ_FILE_H
+
+struct seq_file;
+
+#endif /* _TOOLS_INCLUDE_LINUX_SEQ_FILE_H */
diff --git a/tools/include/linux/sizes.h b/tools/include/linux/sizes.h
new file mode 100644
index 0000000000..1cbb4c4d01
--- /dev/null
+++ b/tools/include/linux/sizes.h
@@ -0,0 +1,48 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * include/linux/sizes.h
+ */
+#ifndef __LINUX_SIZES_H__
+#define __LINUX_SIZES_H__
+
+#include <linux/const.h>
+
+#define SZ_1 0x00000001
+#define SZ_2 0x00000002
+#define SZ_4 0x00000004
+#define SZ_8 0x00000008
+#define SZ_16 0x00000010
+#define SZ_32 0x00000020
+#define SZ_64 0x00000040
+#define SZ_128 0x00000080
+#define SZ_256 0x00000100
+#define SZ_512 0x00000200
+
+#define SZ_1K 0x00000400
+#define SZ_2K 0x00000800
+#define SZ_4K 0x00001000
+#define SZ_8K 0x00002000
+#define SZ_16K 0x00004000
+#define SZ_32K 0x00008000
+#define SZ_64K 0x00010000
+#define SZ_128K 0x00020000
+#define SZ_256K 0x00040000
+#define SZ_512K 0x00080000
+
+#define SZ_1M 0x00100000
+#define SZ_2M 0x00200000
+#define SZ_4M 0x00400000
+#define SZ_8M 0x00800000
+#define SZ_16M 0x01000000
+#define SZ_32M 0x02000000
+#define SZ_64M 0x04000000
+#define SZ_128M 0x08000000
+#define SZ_256M 0x10000000
+#define SZ_512M 0x20000000
+
+#define SZ_1G 0x40000000
+#define SZ_2G 0x80000000
+
+#define SZ_4G _AC(0x100000000, ULL)
+
+#endif /* __LINUX_SIZES_H__ */
diff --git a/tools/include/linux/slab.h b/tools/include/linux/slab.h
new file mode 100644
index 0000000000..311759ea25
--- /dev/null
+++ b/tools/include/linux/slab.h
@@ -0,0 +1,48 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TOOLS_SLAB_H
+#define _TOOLS_SLAB_H
+
+#include <linux/types.h>
+#include <linux/gfp.h>
+
+#define SLAB_PANIC 2
+#define SLAB_RECLAIM_ACCOUNT 0x00020000UL /* Objects are reclaimable */
+
+#define kzalloc_node(size, flags, node) kmalloc(size, flags)
+
+void *kmalloc(size_t size, gfp_t gfp);
+void kfree(void *p);
+
+bool slab_is_available(void);
+
+enum slab_state {
+ DOWN,
+ PARTIAL,
+ PARTIAL_NODE,
+ UP,
+ FULL
+};
+
+static inline void *kzalloc(size_t size, gfp_t gfp)
+{
+ return kmalloc(size, gfp | __GFP_ZERO);
+}
+
+struct list_lru;
+
+void *kmem_cache_alloc_lru(struct kmem_cache *cachep, struct list_lru *, int flags);
+static inline void *kmem_cache_alloc(struct kmem_cache *cachep, int flags)
+{
+ return kmem_cache_alloc_lru(cachep, NULL, flags);
+}
+void kmem_cache_free(struct kmem_cache *cachep, void *objp);
+
+struct kmem_cache *kmem_cache_create(const char *name, unsigned int size,
+ unsigned int align, unsigned int flags,
+ void (*ctor)(void *));
+
+void kmem_cache_free_bulk(struct kmem_cache *cachep, size_t size, void **list);
+int kmem_cache_alloc_bulk(struct kmem_cache *cachep, gfp_t gfp, size_t size,
+ void **list);
+
+#endif /* _TOOLS_SLAB_H */
diff --git a/tools/include/linux/spinlock.h b/tools/include/linux/spinlock.h
new file mode 100644
index 0000000000..622266b197
--- /dev/null
+++ b/tools/include/linux/spinlock.h
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_SPINLOCK_H_
+#define __LINUX_SPINLOCK_H_
+
+#include <pthread.h>
+#include <stdbool.h>
+
+#define spinlock_t pthread_mutex_t
+#define DEFINE_SPINLOCK(x) pthread_mutex_t x = PTHREAD_MUTEX_INITIALIZER
+#define __SPIN_LOCK_UNLOCKED(x) (pthread_mutex_t)PTHREAD_MUTEX_INITIALIZER
+#define spin_lock_init(x) pthread_mutex_init(x, NULL)
+
+#define spin_lock(x) pthread_mutex_lock(x)
+#define spin_unlock(x) pthread_mutex_unlock(x)
+#define spin_lock_bh(x) pthread_mutex_lock(x)
+#define spin_unlock_bh(x) pthread_mutex_unlock(x)
+#define spin_lock_irq(x) pthread_mutex_lock(x)
+#define spin_unlock_irq(x) pthread_mutex_unlock(x)
+#define spin_lock_irqsave(x, f) (void)f, pthread_mutex_lock(x)
+#define spin_unlock_irqrestore(x, f) (void)f, pthread_mutex_unlock(x)
+
+#define arch_spinlock_t pthread_mutex_t
+#define __ARCH_SPIN_LOCK_UNLOCKED PTHREAD_MUTEX_INITIALIZER
+
+static inline void arch_spin_lock(arch_spinlock_t *mutex)
+{
+ pthread_mutex_lock(mutex);
+}
+
+static inline void arch_spin_unlock(arch_spinlock_t *mutex)
+{
+ pthread_mutex_unlock(mutex);
+}
+
+static inline bool arch_spin_is_locked(arch_spinlock_t *mutex)
+{
+ return true;
+}
+
+#endif
diff --git a/tools/include/linux/static_call_types.h b/tools/include/linux/static_call_types.h
new file mode 100644
index 0000000000..5a00b8b2cf
--- /dev/null
+++ b/tools/include/linux/static_call_types.h
@@ -0,0 +1,103 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _STATIC_CALL_TYPES_H
+#define _STATIC_CALL_TYPES_H
+
+#include <linux/types.h>
+#include <linux/stringify.h>
+#include <linux/compiler.h>
+
+#define STATIC_CALL_KEY_PREFIX __SCK__
+#define STATIC_CALL_KEY_PREFIX_STR __stringify(STATIC_CALL_KEY_PREFIX)
+#define STATIC_CALL_KEY_PREFIX_LEN (sizeof(STATIC_CALL_KEY_PREFIX_STR) - 1)
+#define STATIC_CALL_KEY(name) __PASTE(STATIC_CALL_KEY_PREFIX, name)
+#define STATIC_CALL_KEY_STR(name) __stringify(STATIC_CALL_KEY(name))
+
+#define STATIC_CALL_TRAMP_PREFIX __SCT__
+#define STATIC_CALL_TRAMP_PREFIX_STR __stringify(STATIC_CALL_TRAMP_PREFIX)
+#define STATIC_CALL_TRAMP_PREFIX_LEN (sizeof(STATIC_CALL_TRAMP_PREFIX_STR) - 1)
+#define STATIC_CALL_TRAMP(name) __PASTE(STATIC_CALL_TRAMP_PREFIX, name)
+#define STATIC_CALL_TRAMP_STR(name) __stringify(STATIC_CALL_TRAMP(name))
+
+/*
+ * Flags in the low bits of static_call_site::key.
+ */
+#define STATIC_CALL_SITE_TAIL 1UL /* tail call */
+#define STATIC_CALL_SITE_INIT 2UL /* init section */
+#define STATIC_CALL_SITE_FLAGS 3UL
+
+/*
+ * The static call site table needs to be created by external tooling (objtool
+ * or a compiler plugin).
+ */
+struct static_call_site {
+ s32 addr;
+ s32 key;
+};
+
+#define DECLARE_STATIC_CALL(name, func) \
+ extern struct static_call_key STATIC_CALL_KEY(name); \
+ extern typeof(func) STATIC_CALL_TRAMP(name);
+
+#ifdef CONFIG_HAVE_STATIC_CALL
+
+#define __raw_static_call(name) (&STATIC_CALL_TRAMP(name))
+
+#ifdef CONFIG_HAVE_STATIC_CALL_INLINE
+
+/*
+ * __ADDRESSABLE() is used to ensure the key symbol doesn't get stripped from
+ * the symbol table so that objtool can reference it when it generates the
+ * .static_call_sites section.
+ */
+#define __STATIC_CALL_ADDRESSABLE(name) \
+ __ADDRESSABLE(STATIC_CALL_KEY(name))
+
+#define __static_call(name) \
+({ \
+ __STATIC_CALL_ADDRESSABLE(name); \
+ __raw_static_call(name); \
+})
+
+struct static_call_key {
+ void *func;
+ union {
+ /* bit 0: 0 = mods, 1 = sites */
+ unsigned long type;
+ struct static_call_mod *mods;
+ struct static_call_site *sites;
+ };
+};
+
+#else /* !CONFIG_HAVE_STATIC_CALL_INLINE */
+
+#define __STATIC_CALL_ADDRESSABLE(name)
+#define __static_call(name) __raw_static_call(name)
+
+struct static_call_key {
+ void *func;
+};
+
+#endif /* CONFIG_HAVE_STATIC_CALL_INLINE */
+
+#ifdef MODULE
+#define __STATIC_CALL_MOD_ADDRESSABLE(name)
+#define static_call_mod(name) __raw_static_call(name)
+#else
+#define __STATIC_CALL_MOD_ADDRESSABLE(name) __STATIC_CALL_ADDRESSABLE(name)
+#define static_call_mod(name) __static_call(name)
+#endif
+
+#define static_call(name) __static_call(name)
+
+#else
+
+struct static_call_key {
+ void *func;
+};
+
+#define static_call(name) \
+ ((typeof(STATIC_CALL_TRAMP(name))*)(STATIC_CALL_KEY(name).func))
+
+#endif /* CONFIG_HAVE_STATIC_CALL */
+
+#endif /* _STATIC_CALL_TYPES_H */
diff --git a/tools/include/linux/string.h b/tools/include/linux/string.h
new file mode 100644
index 0000000000..db5c99318c
--- /dev/null
+++ b/tools/include/linux/string.h
@@ -0,0 +1,50 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TOOLS_LINUX_STRING_H_
+#define _TOOLS_LINUX_STRING_H_
+
+#include <linux/types.h> /* for size_t */
+#include <string.h>
+
+void *memdup(const void *src, size_t len);
+
+char **argv_split(const char *str, int *argcp);
+void argv_free(char **argv);
+
+int strtobool(const char *s, bool *res);
+
+/*
+ * glibc based builds needs the extern while uClibc doesn't.
+ * However uClibc headers also define __GLIBC__ hence the hack below
+ */
+#if defined(__GLIBC__) && !defined(__UCLIBC__)
+// pragma diagnostic was introduced in gcc 4.6
+#if __GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 6)
+#pragma GCC diagnostic push
+#pragma GCC diagnostic ignored "-Wredundant-decls"
+#endif
+extern size_t strlcpy(char *dest, const char *src, size_t size);
+#if __GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 6)
+#pragma GCC diagnostic pop
+#endif
+#endif
+
+char *str_error_r(int errnum, char *buf, size_t buflen);
+
+char *strreplace(char *s, char old, char new);
+
+/**
+ * strstarts - does @str start with @prefix?
+ * @str: string to examine
+ * @prefix: prefix to look for.
+ */
+static inline bool strstarts(const char *str, const char *prefix)
+{
+ return strncmp(str, prefix, strlen(prefix)) == 0;
+}
+
+extern char * __must_check skip_spaces(const char *);
+
+extern char *strim(char *);
+
+extern void *memchr_inv(const void *start, int c, size_t bytes);
+#endif /* _TOOLS_LINUX_STRING_H_ */
diff --git a/tools/include/linux/stringify.h b/tools/include/linux/stringify.h
new file mode 100644
index 0000000000..60e2c187da
--- /dev/null
+++ b/tools/include/linux/stringify.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_STRINGIFY_H
+#define __LINUX_STRINGIFY_H
+
+/* Indirect stringification. Doing two levels allows the parameter to be a
+ * macro itself. For example, compile with -DFOO=bar, __stringify(FOO)
+ * converts to "bar".
+ */
+
+#define __stringify_1(x...) #x
+#define __stringify(x...) __stringify_1(x)
+
+#endif /* !__LINUX_STRINGIFY_H */
diff --git a/tools/include/linux/time64.h b/tools/include/linux/time64.h
new file mode 100644
index 0000000000..55fa644b95
--- /dev/null
+++ b/tools/include/linux/time64.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TOOLS_LINUX_TIME64_H
+#define _TOOLS_LINUX_TIME64_H
+
+#define MSEC_PER_SEC 1000L
+#define USEC_PER_MSEC 1000L
+#define NSEC_PER_USEC 1000L
+#define NSEC_PER_MSEC 1000000L
+#define USEC_PER_SEC 1000000L
+#define NSEC_PER_SEC 1000000000L
+#define FSEC_PER_SEC 1000000000000000LL
+
+#endif /* _LINUX_TIME64_H */
diff --git a/tools/include/linux/types.h b/tools/include/linux/types.h
new file mode 100644
index 0000000000..8519386acd
--- /dev/null
+++ b/tools/include/linux/types.h
@@ -0,0 +1,101 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TOOLS_LINUX_TYPES_H_
+#define _TOOLS_LINUX_TYPES_H_
+
+#include <stdbool.h>
+#include <stddef.h>
+#include <stdint.h>
+
+#ifndef __SANE_USERSPACE_TYPES__
+#define __SANE_USERSPACE_TYPES__ /* For PPC64, to get LL64 types */
+#endif
+
+#include <asm/types.h>
+#include <asm/posix_types.h>
+
+struct page;
+struct kmem_cache;
+
+typedef enum {
+ GFP_KERNEL,
+ GFP_ATOMIC,
+ __GFP_HIGHMEM,
+ __GFP_HIGH
+} gfp_t;
+
+/*
+ * We define u64 as uint64_t for every architecture
+ * so that we can print it with "%"PRIx64 without getting warnings.
+ *
+ * typedef __u64 u64;
+ * typedef __s64 s64;
+ */
+typedef uint64_t u64;
+typedef int64_t s64;
+
+typedef __u32 u32;
+typedef __s32 s32;
+
+typedef __u16 u16;
+typedef __s16 s16;
+
+typedef __u8 u8;
+typedef __s8 s8;
+
+#ifdef __CHECKER__
+#define __bitwise __attribute__((bitwise))
+#else
+#define __bitwise
+#endif
+
+#define __force
+/* This is defined in linux/compiler_types.h and is left for backward
+ * compatibility.
+ */
+#ifndef __user
+#define __user
+#endif
+#define __must_check
+#define __cold
+
+typedef __u16 __bitwise __le16;
+typedef __u16 __bitwise __be16;
+typedef __u32 __bitwise __le32;
+typedef __u32 __bitwise __be32;
+typedef __u64 __bitwise __le64;
+typedef __u64 __bitwise __be64;
+
+typedef __u16 __bitwise __sum16;
+typedef __u32 __bitwise __wsum;
+
+#ifdef CONFIG_PHYS_ADDR_T_64BIT
+typedef u64 phys_addr_t;
+#else
+typedef u32 phys_addr_t;
+#endif
+
+typedef struct {
+ int counter;
+} atomic_t;
+
+typedef struct {
+ long counter;
+} atomic_long_t;
+
+#ifndef __aligned_u64
+# define __aligned_u64 __u64 __attribute__((aligned(8)))
+#endif
+
+struct list_head {
+ struct list_head *next, *prev;
+};
+
+struct hlist_head {
+ struct hlist_node *first;
+};
+
+struct hlist_node {
+ struct hlist_node *next, **pprev;
+};
+
+#endif /* _TOOLS_LINUX_TYPES_H_ */
diff --git a/tools/include/linux/unaligned/packed_struct.h b/tools/include/linux/unaligned/packed_struct.h
new file mode 100644
index 0000000000..dbd93c7df2
--- /dev/null
+++ b/tools/include/linux/unaligned/packed_struct.h
@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_UNALIGNED_PACKED_STRUCT_H
+#define _LINUX_UNALIGNED_PACKED_STRUCT_H
+
+#include <linux/kernel.h>
+
+struct __una_u16 { u16 x; } __packed;
+struct __una_u32 { u32 x; } __packed;
+struct __una_u64 { u64 x; } __packed;
+
+static inline u16 __get_unaligned_cpu16(const void *p)
+{
+ const struct __una_u16 *ptr = (const struct __una_u16 *)p;
+ return ptr->x;
+}
+
+static inline u32 __get_unaligned_cpu32(const void *p)
+{
+ const struct __una_u32 *ptr = (const struct __una_u32 *)p;
+ return ptr->x;
+}
+
+static inline u64 __get_unaligned_cpu64(const void *p)
+{
+ const struct __una_u64 *ptr = (const struct __una_u64 *)p;
+ return ptr->x;
+}
+
+static inline void __put_unaligned_cpu16(u16 val, void *p)
+{
+ struct __una_u16 *ptr = (struct __una_u16 *)p;
+ ptr->x = val;
+}
+
+static inline void __put_unaligned_cpu32(u32 val, void *p)
+{
+ struct __una_u32 *ptr = (struct __una_u32 *)p;
+ ptr->x = val;
+}
+
+static inline void __put_unaligned_cpu64(u64 val, void *p)
+{
+ struct __una_u64 *ptr = (struct __una_u64 *)p;
+ ptr->x = val;
+}
+
+#endif /* _LINUX_UNALIGNED_PACKED_STRUCT_H */
diff --git a/tools/include/linux/zalloc.h b/tools/include/linux/zalloc.h
new file mode 100644
index 0000000000..81099c8404
--- /dev/null
+++ b/tools/include/linux/zalloc.h
@@ -0,0 +1,12 @@
+// SPDX-License-Identifier: LGPL-2.1
+#ifndef __TOOLS_LINUX_ZALLOC_H
+#define __TOOLS_LINUX_ZALLOC_H
+
+#include <stddef.h>
+
+void *zalloc(size_t size);
+void __zfree(void **ptr);
+
+#define zfree(ptr) __zfree((void **)(ptr))
+
+#endif // __TOOLS_LINUX_ZALLOC_H
diff --git a/tools/include/nolibc/.gitignore b/tools/include/nolibc/.gitignore
new file mode 100644
index 0000000000..dea22eaaed
--- /dev/null
+++ b/tools/include/nolibc/.gitignore
@@ -0,0 +1 @@
+sysroot
diff --git a/tools/include/nolibc/Makefile b/tools/include/nolibc/Makefile
new file mode 100644
index 0000000000..909b6eb500
--- /dev/null
+++ b/tools/include/nolibc/Makefile
@@ -0,0 +1,91 @@
+# SPDX-License-Identifier: GPL-2.0
+# Makefile for nolibc installation and tests
+include ../../scripts/Makefile.include
+
+# we're in ".../tools/include/nolibc"
+ifeq ($(srctree),)
+srctree := $(patsubst %/tools/include/,%,$(dir $(CURDIR)))
+endif
+
+# when run as make -C tools/ nolibc_<foo> the arch is not set
+ifeq ($(ARCH),)
+include $(srctree)/scripts/subarch.include
+ARCH = $(SUBARCH)
+endif
+
+# OUTPUT is only set when run from the main makefile, otherwise
+# it defaults to this nolibc directory.
+OUTPUT ?= $(CURDIR)/
+
+ifeq ($(V),1)
+Q=
+else
+Q=@
+endif
+
+nolibc_arch := $(patsubst arm64,aarch64,$(ARCH))
+arch_file := arch-$(nolibc_arch).h
+all_files := \
+ compiler.h \
+ crt.h \
+ ctype.h \
+ errno.h \
+ nolibc.h \
+ signal.h \
+ stackprotector.h \
+ std.h \
+ stdint.h \
+ stdlib.h \
+ string.h \
+ sys.h \
+ time.h \
+ types.h \
+ unistd.h \
+ stdio.h \
+
+
+# install all headers needed to support a bare-metal compiler
+all: headers
+
+install: help
+
+help:
+ @echo "Supported targets under nolibc:"
+ @echo " all call \"headers\""
+ @echo " clean clean the sysroot"
+ @echo " headers prepare a sysroot in tools/include/nolibc/sysroot"
+ @echo " headers_standalone like \"headers\", and also install kernel headers"
+ @echo " help this help"
+ @echo ""
+ @echo "These targets may also be called from tools as \"make nolibc_<target>\"."
+ @echo ""
+ @echo "Currently using the following variables:"
+ @echo " ARCH = $(ARCH)"
+ @echo " OUTPUT = $(OUTPUT)"
+ @echo ""
+
+# Note: when ARCH is "x86" we concatenate both x86_64 and i386
+headers:
+ $(Q)mkdir -p $(OUTPUT)sysroot
+ $(Q)mkdir -p $(OUTPUT)sysroot/include
+ $(Q)cp $(all_files) $(OUTPUT)sysroot/include/
+ $(Q)if [ "$(ARCH)" = "x86" ]; then \
+ sed -e \
+ 's,^#ifndef _NOLIBC_ARCH_X86_64_H,#if !defined(_NOLIBC_ARCH_X86_64_H) \&\& defined(__x86_64__),' \
+ arch-x86_64.h; \
+ sed -e \
+ 's,^#ifndef _NOLIBC_ARCH_I386_H,#if !defined(_NOLIBC_ARCH_I386_H) \&\& !defined(__x86_64__),' \
+ arch-i386.h; \
+ elif [ -e "$(arch_file)" ]; then \
+ cat $(arch_file); \
+ else \
+ echo "Fatal: architecture $(ARCH) not yet supported by nolibc." >&2; \
+ exit 1; \
+ fi > $(OUTPUT)sysroot/include/arch.h
+
+headers_standalone: headers
+ $(Q)$(MAKE) -C $(srctree) headers
+ $(Q)$(MAKE) -C $(srctree) headers_install INSTALL_HDR_PATH=$(OUTPUT)sysroot
+
+clean:
+ $(call QUIET_CLEAN, nolibc) rm -rf "$(OUTPUT)sysroot"
diff --git a/tools/include/nolibc/arch-aarch64.h b/tools/include/nolibc/arch-aarch64.h
new file mode 100644
index 0000000000..6c33c46848
--- /dev/null
+++ b/tools/include/nolibc/arch-aarch64.h
@@ -0,0 +1,157 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * AARCH64 specific definitions for NOLIBC
+ * Copyright (C) 2017-2022 Willy Tarreau <w@1wt.eu>
+ */
+
+#ifndef _NOLIBC_ARCH_AARCH64_H
+#define _NOLIBC_ARCH_AARCH64_H
+
+#include "compiler.h"
+#include "crt.h"
+
+/* Syscalls for AARCH64 :
+ * - registers are 64-bit
+ * - stack is 16-byte aligned
+ * - syscall number is passed in x8
+ * - arguments are in x0, x1, x2, x3, x4, x5
+ * - the system call is performed by calling svc 0
+ * - syscall return comes in x0.
+ * - the arguments are cast to long and assigned into the target registers
+ * which are then simply passed as registers to the asm code, so that we
+ * don't have to experience issues with register constraints.
+ *
+ * On aarch64, select() is not implemented so we have to use pselect6().
+ */
+#define __ARCH_WANT_SYS_PSELECT6
+
+#define my_syscall0(num) \
+({ \
+ register long _num __asm__ ("x8") = (num); \
+ register long _arg1 __asm__ ("x0"); \
+ \
+ __asm__ volatile ( \
+ "svc #0\n" \
+ : "=r"(_arg1) \
+ : "r"(_num) \
+ : "memory", "cc" \
+ ); \
+ _arg1; \
+})
+
+#define my_syscall1(num, arg1) \
+({ \
+ register long _num __asm__ ("x8") = (num); \
+ register long _arg1 __asm__ ("x0") = (long)(arg1); \
+ \
+ __asm__ volatile ( \
+ "svc #0\n" \
+ : "=r"(_arg1) \
+ : "r"(_arg1), \
+ "r"(_num) \
+ : "memory", "cc" \
+ ); \
+ _arg1; \
+})
+
+#define my_syscall2(num, arg1, arg2) \
+({ \
+ register long _num __asm__ ("x8") = (num); \
+ register long _arg1 __asm__ ("x0") = (long)(arg1); \
+ register long _arg2 __asm__ ("x1") = (long)(arg2); \
+ \
+ __asm__ volatile ( \
+ "svc #0\n" \
+ : "=r"(_arg1) \
+ : "r"(_arg1), "r"(_arg2), \
+ "r"(_num) \
+ : "memory", "cc" \
+ ); \
+ _arg1; \
+})
+
+#define my_syscall3(num, arg1, arg2, arg3) \
+({ \
+ register long _num __asm__ ("x8") = (num); \
+ register long _arg1 __asm__ ("x0") = (long)(arg1); \
+ register long _arg2 __asm__ ("x1") = (long)(arg2); \
+ register long _arg3 __asm__ ("x2") = (long)(arg3); \
+ \
+ __asm__ volatile ( \
+ "svc #0\n" \
+ : "=r"(_arg1) \
+ : "r"(_arg1), "r"(_arg2), "r"(_arg3), \
+ "r"(_num) \
+ : "memory", "cc" \
+ ); \
+ _arg1; \
+})
+
+#define my_syscall4(num, arg1, arg2, arg3, arg4) \
+({ \
+ register long _num __asm__ ("x8") = (num); \
+ register long _arg1 __asm__ ("x0") = (long)(arg1); \
+ register long _arg2 __asm__ ("x1") = (long)(arg2); \
+ register long _arg3 __asm__ ("x2") = (long)(arg3); \
+ register long _arg4 __asm__ ("x3") = (long)(arg4); \
+ \
+ __asm__ volatile ( \
+ "svc #0\n" \
+ : "=r"(_arg1) \
+ : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), \
+ "r"(_num) \
+ : "memory", "cc" \
+ ); \
+ _arg1; \
+})
+
+#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \
+({ \
+ register long _num __asm__ ("x8") = (num); \
+ register long _arg1 __asm__ ("x0") = (long)(arg1); \
+ register long _arg2 __asm__ ("x1") = (long)(arg2); \
+ register long _arg3 __asm__ ("x2") = (long)(arg3); \
+ register long _arg4 __asm__ ("x3") = (long)(arg4); \
+ register long _arg5 __asm__ ("x4") = (long)(arg5); \
+ \
+ __asm__ volatile ( \
+ "svc #0\n" \
+ : "=r" (_arg1) \
+ : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \
+ "r"(_num) \
+ : "memory", "cc" \
+ ); \
+ _arg1; \
+})
+
+#define my_syscall6(num, arg1, arg2, arg3, arg4, arg5, arg6) \
+({ \
+ register long _num __asm__ ("x8") = (num); \
+ register long _arg1 __asm__ ("x0") = (long)(arg1); \
+ register long _arg2 __asm__ ("x1") = (long)(arg2); \
+ register long _arg3 __asm__ ("x2") = (long)(arg3); \
+ register long _arg4 __asm__ ("x3") = (long)(arg4); \
+ register long _arg5 __asm__ ("x4") = (long)(arg5); \
+ register long _arg6 __asm__ ("x5") = (long)(arg6); \
+ \
+ __asm__ volatile ( \
+ "svc #0\n" \
+ : "=r" (_arg1) \
+ : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \
+ "r"(_arg6), "r"(_num) \
+ : "memory", "cc" \
+ ); \
+ _arg1; \
+})
+
+/* startup code */
+void __attribute__((weak, noreturn, optimize("Os", "omit-frame-pointer"))) __no_stack_protector _start(void)
+{
+ __asm__ volatile (
+ "mov x0, sp\n" /* save stack pointer to x0, as arg1 of _start_c */
+ "and sp, x0, -16\n" /* sp must be 16-byte aligned in the callee */
+ "bl _start_c\n" /* transfer to c runtime */
+ );
+ __builtin_unreachable();
+}
+#endif /* _NOLIBC_ARCH_AARCH64_H */
diff --git a/tools/include/nolibc/arch-arm.h b/tools/include/nolibc/arch-arm.h
new file mode 100644
index 0000000000..cae4afa7c1
--- /dev/null
+++ b/tools/include/nolibc/arch-arm.h
@@ -0,0 +1,199 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * ARM specific definitions for NOLIBC
+ * Copyright (C) 2017-2022 Willy Tarreau <w@1wt.eu>
+ */
+
+#ifndef _NOLIBC_ARCH_ARM_H
+#define _NOLIBC_ARCH_ARM_H
+
+#include "compiler.h"
+#include "crt.h"
+
+/* Syscalls for ARM in ARM or Thumb modes :
+ * - registers are 32-bit
+ * - stack is 8-byte aligned
+ * ( http://infocenter.arm.com/help/index.jsp?topic=/com.arm.doc.faqs/ka4127.html)
+ * - syscall number is passed in r7
+ * - arguments are in r0, r1, r2, r3, r4, r5
+ * - the system call is performed by calling svc #0
+ * - syscall return comes in r0.
+ * - only lr is clobbered.
+ * - the arguments are cast to long and assigned into the target registers
+ * which are then simply passed as registers to the asm code, so that we
+ * don't have to experience issues with register constraints.
+ * - the syscall number is always specified last in order to allow to force
+ * some registers before (gcc refuses a %-register at the last position).
+ * - in thumb mode without -fomit-frame-pointer, r7 is also used to store the
+ * frame pointer, and we cannot directly assign it as a register variable,
+ * nor can we clobber it. Instead we assign the r6 register and swap it
+ * with r7 before calling svc, and r6 is marked as clobbered.
+ * We're just using any regular register which we assign to r7 after saving
+ * it.
+ *
+ * Also, ARM supports the old_select syscall if newselect is not available
+ */
+#define __ARCH_WANT_SYS_OLD_SELECT
+
+#if (defined(__THUMBEB__) || defined(__THUMBEL__)) && \
+ !defined(NOLIBC_OMIT_FRAME_POINTER)
+/* swap r6,r7 needed in Thumb mode since we can't use nor clobber r7 */
+#define _NOLIBC_SYSCALL_REG "r6"
+#define _NOLIBC_THUMB_SET_R7 "eor r7, r6\neor r6, r7\neor r7, r6\n"
+#define _NOLIBC_THUMB_RESTORE_R7 "mov r7, r6\n"
+
+#else /* we're in ARM mode */
+/* in Arm mode we can directly use r7 */
+#define _NOLIBC_SYSCALL_REG "r7"
+#define _NOLIBC_THUMB_SET_R7 ""
+#define _NOLIBC_THUMB_RESTORE_R7 ""
+
+#endif /* end THUMB */
+
+#define my_syscall0(num) \
+({ \
+ register long _num __asm__(_NOLIBC_SYSCALL_REG) = (num); \
+ register long _arg1 __asm__ ("r0"); \
+ \
+ __asm__ volatile ( \
+ _NOLIBC_THUMB_SET_R7 \
+ "svc #0\n" \
+ _NOLIBC_THUMB_RESTORE_R7 \
+ : "=r"(_arg1), "=r"(_num) \
+ : "r"(_arg1), \
+ "r"(_num) \
+ : "memory", "cc", "lr" \
+ ); \
+ _arg1; \
+})
+
+#define my_syscall1(num, arg1) \
+({ \
+ register long _num __asm__(_NOLIBC_SYSCALL_REG) = (num); \
+ register long _arg1 __asm__ ("r0") = (long)(arg1); \
+ \
+ __asm__ volatile ( \
+ _NOLIBC_THUMB_SET_R7 \
+ "svc #0\n" \
+ _NOLIBC_THUMB_RESTORE_R7 \
+ : "=r"(_arg1), "=r" (_num) \
+ : "r"(_arg1), \
+ "r"(_num) \
+ : "memory", "cc", "lr" \
+ ); \
+ _arg1; \
+})
+
+#define my_syscall2(num, arg1, arg2) \
+({ \
+ register long _num __asm__(_NOLIBC_SYSCALL_REG) = (num); \
+ register long _arg1 __asm__ ("r0") = (long)(arg1); \
+ register long _arg2 __asm__ ("r1") = (long)(arg2); \
+ \
+ __asm__ volatile ( \
+ _NOLIBC_THUMB_SET_R7 \
+ "svc #0\n" \
+ _NOLIBC_THUMB_RESTORE_R7 \
+ : "=r"(_arg1), "=r" (_num) \
+ : "r"(_arg1), "r"(_arg2), \
+ "r"(_num) \
+ : "memory", "cc", "lr" \
+ ); \
+ _arg1; \
+})
+
+#define my_syscall3(num, arg1, arg2, arg3) \
+({ \
+ register long _num __asm__(_NOLIBC_SYSCALL_REG) = (num); \
+ register long _arg1 __asm__ ("r0") = (long)(arg1); \
+ register long _arg2 __asm__ ("r1") = (long)(arg2); \
+ register long _arg3 __asm__ ("r2") = (long)(arg3); \
+ \
+ __asm__ volatile ( \
+ _NOLIBC_THUMB_SET_R7 \
+ "svc #0\n" \
+ _NOLIBC_THUMB_RESTORE_R7 \
+ : "=r"(_arg1), "=r" (_num) \
+ : "r"(_arg1), "r"(_arg2), "r"(_arg3), \
+ "r"(_num) \
+ : "memory", "cc", "lr" \
+ ); \
+ _arg1; \
+})
+
+#define my_syscall4(num, arg1, arg2, arg3, arg4) \
+({ \
+ register long _num __asm__(_NOLIBC_SYSCALL_REG) = (num); \
+ register long _arg1 __asm__ ("r0") = (long)(arg1); \
+ register long _arg2 __asm__ ("r1") = (long)(arg2); \
+ register long _arg3 __asm__ ("r2") = (long)(arg3); \
+ register long _arg4 __asm__ ("r3") = (long)(arg4); \
+ \
+ __asm__ volatile ( \
+ _NOLIBC_THUMB_SET_R7 \
+ "svc #0\n" \
+ _NOLIBC_THUMB_RESTORE_R7 \
+ : "=r"(_arg1), "=r" (_num) \
+ : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), \
+ "r"(_num) \
+ : "memory", "cc", "lr" \
+ ); \
+ _arg1; \
+})
+
+#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \
+({ \
+ register long _num __asm__(_NOLIBC_SYSCALL_REG) = (num); \
+ register long _arg1 __asm__ ("r0") = (long)(arg1); \
+ register long _arg2 __asm__ ("r1") = (long)(arg2); \
+ register long _arg3 __asm__ ("r2") = (long)(arg3); \
+ register long _arg4 __asm__ ("r3") = (long)(arg4); \
+ register long _arg5 __asm__ ("r4") = (long)(arg5); \
+ \
+ __asm__ volatile ( \
+ _NOLIBC_THUMB_SET_R7 \
+ "svc #0\n" \
+ _NOLIBC_THUMB_RESTORE_R7 \
+ : "=r"(_arg1), "=r" (_num) \
+ : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \
+ "r"(_num) \
+ : "memory", "cc", "lr" \
+ ); \
+ _arg1; \
+})
+
+#define my_syscall6(num, arg1, arg2, arg3, arg4, arg5, arg6) \
+({ \
+ register long _num __asm__(_NOLIBC_SYSCALL_REG) = (num); \
+ register long _arg1 __asm__ ("r0") = (long)(arg1); \
+ register long _arg2 __asm__ ("r1") = (long)(arg2); \
+ register long _arg3 __asm__ ("r2") = (long)(arg3); \
+ register long _arg4 __asm__ ("r3") = (long)(arg4); \
+ register long _arg5 __asm__ ("r4") = (long)(arg5); \
+ register long _arg6 __asm__ ("r5") = (long)(arg6); \
+ \
+ __asm__ volatile ( \
+ _NOLIBC_THUMB_SET_R7 \
+ "svc #0\n" \
+ _NOLIBC_THUMB_RESTORE_R7 \
+ : "=r"(_arg1), "=r" (_num) \
+ : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \
+ "r"(_arg6), "r"(_num) \
+ : "memory", "cc", "lr" \
+ ); \
+ _arg1; \
+})
+
+/* startup code */
+void __attribute__((weak, noreturn, optimize("Os", "omit-frame-pointer"))) __no_stack_protector _start(void)
+{
+ __asm__ volatile (
+ "mov %r0, sp\n" /* save stack pointer to %r0, as arg1 of _start_c */
+ "and ip, %r0, #-8\n" /* sp must be 8-byte aligned in the callee */
+ "mov sp, ip\n"
+ "bl _start_c\n" /* transfer to c runtime */
+ );
+ __builtin_unreachable();
+}
+
+#endif /* _NOLIBC_ARCH_ARM_H */
diff --git a/tools/include/nolibc/arch-i386.h b/tools/include/nolibc/arch-i386.h
new file mode 100644
index 0000000000..28c26a00a7
--- /dev/null
+++ b/tools/include/nolibc/arch-i386.h
@@ -0,0 +1,180 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * i386 specific definitions for NOLIBC
+ * Copyright (C) 2017-2022 Willy Tarreau <w@1wt.eu>
+ */
+
+#ifndef _NOLIBC_ARCH_I386_H
+#define _NOLIBC_ARCH_I386_H
+
+#include "compiler.h"
+#include "crt.h"
+
+/* Syscalls for i386 :
+ * - mostly similar to x86_64
+ * - registers are 32-bit
+ * - syscall number is passed in eax
+ * - arguments are in ebx, ecx, edx, esi, edi, ebp respectively
+ * - all registers are preserved (except eax of course)
+ * - the system call is performed by calling int $0x80
+ * - syscall return comes in eax
+ * - the arguments are cast to long and assigned into the target registers
+ * which are then simply passed as registers to the asm code, so that we
+ * don't have to experience issues with register constraints.
+ * - the syscall number is always specified last in order to allow to force
+ * some registers before (gcc refuses a %-register at the last position).
+ *
+ * Also, i386 supports the old_select syscall if newselect is not available
+ */
+#define __ARCH_WANT_SYS_OLD_SELECT
+
+#define my_syscall0(num) \
+({ \
+ long _ret; \
+ register long _num __asm__ ("eax") = (num); \
+ \
+ __asm__ volatile ( \
+ "int $0x80\n" \
+ : "=a" (_ret) \
+ : "0"(_num) \
+ : "memory", "cc" \
+ ); \
+ _ret; \
+})
+
+#define my_syscall1(num, arg1) \
+({ \
+ long _ret; \
+ register long _num __asm__ ("eax") = (num); \
+ register long _arg1 __asm__ ("ebx") = (long)(arg1); \
+ \
+ __asm__ volatile ( \
+ "int $0x80\n" \
+ : "=a" (_ret) \
+ : "r"(_arg1), \
+ "0"(_num) \
+ : "memory", "cc" \
+ ); \
+ _ret; \
+})
+
+#define my_syscall2(num, arg1, arg2) \
+({ \
+ long _ret; \
+ register long _num __asm__ ("eax") = (num); \
+ register long _arg1 __asm__ ("ebx") = (long)(arg1); \
+ register long _arg2 __asm__ ("ecx") = (long)(arg2); \
+ \
+ __asm__ volatile ( \
+ "int $0x80\n" \
+ : "=a" (_ret) \
+ : "r"(_arg1), "r"(_arg2), \
+ "0"(_num) \
+ : "memory", "cc" \
+ ); \
+ _ret; \
+})
+
+#define my_syscall3(num, arg1, arg2, arg3) \
+({ \
+ long _ret; \
+ register long _num __asm__ ("eax") = (num); \
+ register long _arg1 __asm__ ("ebx") = (long)(arg1); \
+ register long _arg2 __asm__ ("ecx") = (long)(arg2); \
+ register long _arg3 __asm__ ("edx") = (long)(arg3); \
+ \
+ __asm__ volatile ( \
+ "int $0x80\n" \
+ : "=a" (_ret) \
+ : "r"(_arg1), "r"(_arg2), "r"(_arg3), \
+ "0"(_num) \
+ : "memory", "cc" \
+ ); \
+ _ret; \
+})
+
+#define my_syscall4(num, arg1, arg2, arg3, arg4) \
+({ \
+ long _ret; \
+ register long _num __asm__ ("eax") = (num); \
+ register long _arg1 __asm__ ("ebx") = (long)(arg1); \
+ register long _arg2 __asm__ ("ecx") = (long)(arg2); \
+ register long _arg3 __asm__ ("edx") = (long)(arg3); \
+ register long _arg4 __asm__ ("esi") = (long)(arg4); \
+ \
+ __asm__ volatile ( \
+ "int $0x80\n" \
+ : "=a" (_ret) \
+ : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), \
+ "0"(_num) \
+ : "memory", "cc" \
+ ); \
+ _ret; \
+})
+
+#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \
+({ \
+ long _ret; \
+ register long _num __asm__ ("eax") = (num); \
+ register long _arg1 __asm__ ("ebx") = (long)(arg1); \
+ register long _arg2 __asm__ ("ecx") = (long)(arg2); \
+ register long _arg3 __asm__ ("edx") = (long)(arg3); \
+ register long _arg4 __asm__ ("esi") = (long)(arg4); \
+ register long _arg5 __asm__ ("edi") = (long)(arg5); \
+ \
+ __asm__ volatile ( \
+ "int $0x80\n" \
+ : "=a" (_ret) \
+ : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \
+ "0"(_num) \
+ : "memory", "cc" \
+ ); \
+ _ret; \
+})
+
+#define my_syscall6(num, arg1, arg2, arg3, arg4, arg5, arg6) \
+({ \
+ long _eax = (long)(num); \
+ long _arg6 = (long)(arg6); /* Always in memory */ \
+ __asm__ volatile ( \
+ "pushl %[_arg6]\n\t" \
+ "pushl %%ebp\n\t" \
+ "movl 4(%%esp),%%ebp\n\t" \
+ "int $0x80\n\t" \
+ "popl %%ebp\n\t" \
+ "addl $4,%%esp\n\t" \
+ : "+a"(_eax) /* %eax */ \
+ : "b"(arg1), /* %ebx */ \
+ "c"(arg2), /* %ecx */ \
+ "d"(arg3), /* %edx */ \
+ "S"(arg4), /* %esi */ \
+ "D"(arg5), /* %edi */ \
+ [_arg6]"m"(_arg6) /* memory */ \
+ : "memory", "cc" \
+ ); \
+ _eax; \
+})
+
+/* startup code */
+/*
+ * i386 System V ABI mandates:
+ * 1) last pushed argument must be 16-byte aligned.
+ * 2) The deepest stack frame should be set to zero
+ *
+ */
+void __attribute__((weak, noreturn, optimize("Os", "omit-frame-pointer"))) __no_stack_protector _start(void)
+{
+ __asm__ volatile (
+ "xor %ebp, %ebp\n" /* zero the stack frame */
+ "mov %esp, %eax\n" /* save stack pointer to %eax, as arg1 of _start_c */
+ "add $12, %esp\n" /* avoid over-estimating after the 'and' & 'sub' below */
+ "and $-16, %esp\n" /* the %esp must be 16-byte aligned on 'call' */
+ "sub $12, %esp\n" /* sub 12 to keep it aligned after the push %eax */
+ "push %eax\n" /* push arg1 on stack to support plain stack modes too */
+ "call _start_c\n" /* transfer to c runtime */
+ "hlt\n" /* ensure it does not return */
+ );
+ __builtin_unreachable();
+}
+
+#endif /* _NOLIBC_ARCH_I386_H */
diff --git a/tools/include/nolibc/arch-loongarch.h b/tools/include/nolibc/arch-loongarch.h
new file mode 100644
index 0000000000..bf98f62201
--- /dev/null
+++ b/tools/include/nolibc/arch-loongarch.h
@@ -0,0 +1,164 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * LoongArch specific definitions for NOLIBC
+ * Copyright (C) 2023 Loongson Technology Corporation Limited
+ */
+
+#ifndef _NOLIBC_ARCH_LOONGARCH_H
+#define _NOLIBC_ARCH_LOONGARCH_H
+
+#include "compiler.h"
+#include "crt.h"
+
+/* Syscalls for LoongArch :
+ * - stack is 16-byte aligned
+ * - syscall number is passed in a7
+ * - arguments are in a0, a1, a2, a3, a4, a5
+ * - the system call is performed by calling "syscall 0"
+ * - syscall return comes in a0
+ * - the arguments are cast to long and assigned into the target
+ * registers which are then simply passed as registers to the asm code,
+ * so that we don't have to experience issues with register constraints.
+ *
+ * On LoongArch, select() is not implemented so we have to use pselect6().
+ */
+#define __ARCH_WANT_SYS_PSELECT6
+#define _NOLIBC_SYSCALL_CLOBBERLIST \
+ "memory", "$t0", "$t1", "$t2", "$t3", "$t4", "$t5", "$t6", "$t7", "$t8"
+
+#define my_syscall0(num) \
+({ \
+ register long _num __asm__ ("a7") = (num); \
+ register long _arg1 __asm__ ("a0"); \
+ \
+ __asm__ volatile ( \
+ "syscall 0\n" \
+ : "=r"(_arg1) \
+ : "r"(_num) \
+ : _NOLIBC_SYSCALL_CLOBBERLIST \
+ ); \
+ _arg1; \
+})
+
+#define my_syscall1(num, arg1) \
+({ \
+ register long _num __asm__ ("a7") = (num); \
+ register long _arg1 __asm__ ("a0") = (long)(arg1); \
+ \
+ __asm__ volatile ( \
+ "syscall 0\n" \
+ : "+r"(_arg1) \
+ : "r"(_num) \
+ : _NOLIBC_SYSCALL_CLOBBERLIST \
+ ); \
+ _arg1; \
+})
+
+#define my_syscall2(num, arg1, arg2) \
+({ \
+ register long _num __asm__ ("a7") = (num); \
+ register long _arg1 __asm__ ("a0") = (long)(arg1); \
+ register long _arg2 __asm__ ("a1") = (long)(arg2); \
+ \
+ __asm__ volatile ( \
+ "syscall 0\n" \
+ : "+r"(_arg1) \
+ : "r"(_arg2), \
+ "r"(_num) \
+ : _NOLIBC_SYSCALL_CLOBBERLIST \
+ ); \
+ _arg1; \
+})
+
+#define my_syscall3(num, arg1, arg2, arg3) \
+({ \
+ register long _num __asm__ ("a7") = (num); \
+ register long _arg1 __asm__ ("a0") = (long)(arg1); \
+ register long _arg2 __asm__ ("a1") = (long)(arg2); \
+ register long _arg3 __asm__ ("a2") = (long)(arg3); \
+ \
+ __asm__ volatile ( \
+ "syscall 0\n" \
+ : "+r"(_arg1) \
+ : "r"(_arg2), "r"(_arg3), \
+ "r"(_num) \
+ : _NOLIBC_SYSCALL_CLOBBERLIST \
+ ); \
+ _arg1; \
+})
+
+#define my_syscall4(num, arg1, arg2, arg3, arg4) \
+({ \
+ register long _num __asm__ ("a7") = (num); \
+ register long _arg1 __asm__ ("a0") = (long)(arg1); \
+ register long _arg2 __asm__ ("a1") = (long)(arg2); \
+ register long _arg3 __asm__ ("a2") = (long)(arg3); \
+ register long _arg4 __asm__ ("a3") = (long)(arg4); \
+ \
+ __asm__ volatile ( \
+ "syscall 0\n" \
+ : "+r"(_arg1) \
+ : "r"(_arg2), "r"(_arg3), "r"(_arg4), \
+ "r"(_num) \
+ : _NOLIBC_SYSCALL_CLOBBERLIST \
+ ); \
+ _arg1; \
+})
+
+#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \
+({ \
+ register long _num __asm__ ("a7") = (num); \
+ register long _arg1 __asm__ ("a0") = (long)(arg1); \
+ register long _arg2 __asm__ ("a1") = (long)(arg2); \
+ register long _arg3 __asm__ ("a2") = (long)(arg3); \
+ register long _arg4 __asm__ ("a3") = (long)(arg4); \
+ register long _arg5 __asm__ ("a4") = (long)(arg5); \
+ \
+ __asm__ volatile ( \
+ "syscall 0\n" \
+ : "+r"(_arg1) \
+ : "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \
+ "r"(_num) \
+ : _NOLIBC_SYSCALL_CLOBBERLIST \
+ ); \
+ _arg1; \
+})
+
+#define my_syscall6(num, arg1, arg2, arg3, arg4, arg5, arg6) \
+({ \
+ register long _num __asm__ ("a7") = (num); \
+ register long _arg1 __asm__ ("a0") = (long)(arg1); \
+ register long _arg2 __asm__ ("a1") = (long)(arg2); \
+ register long _arg3 __asm__ ("a2") = (long)(arg3); \
+ register long _arg4 __asm__ ("a3") = (long)(arg4); \
+ register long _arg5 __asm__ ("a4") = (long)(arg5); \
+ register long _arg6 __asm__ ("a5") = (long)(arg6); \
+ \
+ __asm__ volatile ( \
+ "syscall 0\n" \
+ : "+r"(_arg1) \
+ : "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), "r"(_arg6), \
+ "r"(_num) \
+ : _NOLIBC_SYSCALL_CLOBBERLIST \
+ ); \
+ _arg1; \
+})
+
+#if __loongarch_grlen == 32
+#define LONG_BSTRINS "bstrins.w"
+#else /* __loongarch_grlen == 64 */
+#define LONG_BSTRINS "bstrins.d"
+#endif
+
+/* startup code */
+void __attribute__((weak, noreturn, optimize("Os", "omit-frame-pointer"))) __no_stack_protector _start(void)
+{
+ __asm__ volatile (
+ "move $a0, $sp\n" /* save stack pointer to $a0, as arg1 of _start_c */
+ LONG_BSTRINS " $sp, $zero, 3, 0\n" /* $sp must be 16-byte aligned */
+ "bl _start_c\n" /* transfer to c runtime */
+ );
+ __builtin_unreachable();
+}
+
+#endif /* _NOLIBC_ARCH_LOONGARCH_H */
diff --git a/tools/include/nolibc/arch-mips.h b/tools/include/nolibc/arch-mips.h
new file mode 100644
index 0000000000..4ab6fa54be
--- /dev/null
+++ b/tools/include/nolibc/arch-mips.h
@@ -0,0 +1,195 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * MIPS specific definitions for NOLIBC
+ * Copyright (C) 2017-2022 Willy Tarreau <w@1wt.eu>
+ */
+
+#ifndef _NOLIBC_ARCH_MIPS_H
+#define _NOLIBC_ARCH_MIPS_H
+
+#include "compiler.h"
+#include "crt.h"
+
+/* Syscalls for MIPS ABI O32 :
+ * - WARNING! there's always a delayed slot!
+ * - WARNING again, the syntax is different, registers take a '$' and numbers
+ * do not.
+ * - registers are 32-bit
+ * - stack is 8-byte aligned
+ * - syscall number is passed in v0 (starts at 0xfa0).
+ * - arguments are in a0, a1, a2, a3, then the stack. The caller needs to
+ * leave some room in the stack for the callee to save a0..a3 if needed.
+ * - Many registers are clobbered, in fact only a0..a2 and s0..s8 are
+ * preserved. See: https://www.linux-mips.org/wiki/Syscall as well as
+ * scall32-o32.S in the kernel sources.
+ * - the system call is performed by calling "syscall"
+ * - syscall return comes in v0, and register a3 needs to be checked to know
+ * if an error occurred, in which case errno is in v0.
+ * - the arguments are cast to long and assigned into the target registers
+ * which are then simply passed as registers to the asm code, so that we
+ * don't have to experience issues with register constraints.
+ */
+
+#define _NOLIBC_SYSCALL_CLOBBERLIST \
+ "memory", "cc", "at", "v1", "hi", "lo", \
+ "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9"
+
+#define my_syscall0(num) \
+({ \
+ register long _num __asm__ ("v0") = (num); \
+ register long _arg4 __asm__ ("a3"); \
+ \
+ __asm__ volatile ( \
+ "addiu $sp, $sp, -32\n" \
+ "syscall\n" \
+ "addiu $sp, $sp, 32\n" \
+ : "=r"(_num), "=r"(_arg4) \
+ : "r"(_num) \
+ : _NOLIBC_SYSCALL_CLOBBERLIST \
+ ); \
+ _arg4 ? -_num : _num; \
+})
+
+#define my_syscall1(num, arg1) \
+({ \
+ register long _num __asm__ ("v0") = (num); \
+ register long _arg1 __asm__ ("a0") = (long)(arg1); \
+ register long _arg4 __asm__ ("a3"); \
+ \
+ __asm__ volatile ( \
+ "addiu $sp, $sp, -32\n" \
+ "syscall\n" \
+ "addiu $sp, $sp, 32\n" \
+ : "=r"(_num), "=r"(_arg4) \
+ : "0"(_num), \
+ "r"(_arg1) \
+ : _NOLIBC_SYSCALL_CLOBBERLIST \
+ ); \
+ _arg4 ? -_num : _num; \
+})
+
+#define my_syscall2(num, arg1, arg2) \
+({ \
+ register long _num __asm__ ("v0") = (num); \
+ register long _arg1 __asm__ ("a0") = (long)(arg1); \
+ register long _arg2 __asm__ ("a1") = (long)(arg2); \
+ register long _arg4 __asm__ ("a3"); \
+ \
+ __asm__ volatile ( \
+ "addiu $sp, $sp, -32\n" \
+ "syscall\n" \
+ "addiu $sp, $sp, 32\n" \
+ : "=r"(_num), "=r"(_arg4) \
+ : "0"(_num), \
+ "r"(_arg1), "r"(_arg2) \
+ : _NOLIBC_SYSCALL_CLOBBERLIST \
+ ); \
+ _arg4 ? -_num : _num; \
+})
+
+#define my_syscall3(num, arg1, arg2, arg3) \
+({ \
+ register long _num __asm__ ("v0") = (num); \
+ register long _arg1 __asm__ ("a0") = (long)(arg1); \
+ register long _arg2 __asm__ ("a1") = (long)(arg2); \
+ register long _arg3 __asm__ ("a2") = (long)(arg3); \
+ register long _arg4 __asm__ ("a3"); \
+ \
+ __asm__ volatile ( \
+ "addiu $sp, $sp, -32\n" \
+ "syscall\n" \
+ "addiu $sp, $sp, 32\n" \
+ : "=r"(_num), "=r"(_arg4) \
+ : "0"(_num), \
+ "r"(_arg1), "r"(_arg2), "r"(_arg3) \
+ : _NOLIBC_SYSCALL_CLOBBERLIST \
+ ); \
+ _arg4 ? -_num : _num; \
+})
+
+#define my_syscall4(num, arg1, arg2, arg3, arg4) \
+({ \
+ register long _num __asm__ ("v0") = (num); \
+ register long _arg1 __asm__ ("a0") = (long)(arg1); \
+ register long _arg2 __asm__ ("a1") = (long)(arg2); \
+ register long _arg3 __asm__ ("a2") = (long)(arg3); \
+ register long _arg4 __asm__ ("a3") = (long)(arg4); \
+ \
+ __asm__ volatile ( \
+ "addiu $sp, $sp, -32\n" \
+ "syscall\n" \
+ "addiu $sp, $sp, 32\n" \
+ : "=r" (_num), "=r"(_arg4) \
+ : "0"(_num), \
+ "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4) \
+ : _NOLIBC_SYSCALL_CLOBBERLIST \
+ ); \
+ _arg4 ? -_num : _num; \
+})
+
+#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \
+({ \
+ register long _num __asm__ ("v0") = (num); \
+ register long _arg1 __asm__ ("a0") = (long)(arg1); \
+ register long _arg2 __asm__ ("a1") = (long)(arg2); \
+ register long _arg3 __asm__ ("a2") = (long)(arg3); \
+ register long _arg4 __asm__ ("a3") = (long)(arg4); \
+ register long _arg5 = (long)(arg5); \
+ \
+ __asm__ volatile ( \
+ "addiu $sp, $sp, -32\n" \
+ "sw %7, 16($sp)\n" \
+ "syscall\n" \
+ "addiu $sp, $sp, 32\n" \
+ : "=r" (_num), "=r"(_arg4) \
+ : "0"(_num), \
+ "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5) \
+ : _NOLIBC_SYSCALL_CLOBBERLIST \
+ ); \
+ _arg4 ? -_num : _num; \
+})
+
+#define my_syscall6(num, arg1, arg2, arg3, arg4, arg5, arg6) \
+({ \
+ register long _num __asm__ ("v0") = (num); \
+ register long _arg1 __asm__ ("a0") = (long)(arg1); \
+ register long _arg2 __asm__ ("a1") = (long)(arg2); \
+ register long _arg3 __asm__ ("a2") = (long)(arg3); \
+ register long _arg4 __asm__ ("a3") = (long)(arg4); \
+ register long _arg5 = (long)(arg5); \
+ register long _arg6 = (long)(arg6); \
+ \
+ __asm__ volatile ( \
+ "addiu $sp, $sp, -32\n" \
+ "sw %7, 16($sp)\n" \
+ "sw %8, 20($sp)\n" \
+ "syscall\n" \
+ "addiu $sp, $sp, 32\n" \
+ : "=r" (_num), "=r"(_arg4) \
+ : "0"(_num), \
+ "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \
+ "r"(_arg6) \
+ : _NOLIBC_SYSCALL_CLOBBERLIST \
+ ); \
+ _arg4 ? -_num : _num; \
+})
+
+/* startup code, note that it's called __start on MIPS */
+void __attribute__((weak, noreturn, optimize("Os", "omit-frame-pointer"))) __no_stack_protector __start(void)
+{
+ __asm__ volatile (
+ ".set push\n"
+ ".set noreorder\n"
+ ".option pic0\n"
+ "move $a0, $sp\n" /* save stack pointer to $a0, as arg1 of _start_c */
+ "li $t0, -8\n"
+ "and $sp, $sp, $t0\n" /* $sp must be 8-byte aligned */
+ "addiu $sp, $sp, -16\n" /* the callee expects to save a0..a3 there */
+ "jal _start_c\n" /* transfer to c runtime */
+ " nop\n" /* delayed slot */
+ ".set pop\n"
+ );
+ __builtin_unreachable();
+}
+
+#endif /* _NOLIBC_ARCH_MIPS_H */
diff --git a/tools/include/nolibc/arch-powerpc.h b/tools/include/nolibc/arch-powerpc.h
new file mode 100644
index 0000000000..ac212e6185
--- /dev/null
+++ b/tools/include/nolibc/arch-powerpc.h
@@ -0,0 +1,221 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * PowerPC specific definitions for NOLIBC
+ * Copyright (C) 2023 Zhangjin Wu <falcon@tinylab.org>
+ */
+
+#ifndef _NOLIBC_ARCH_POWERPC_H
+#define _NOLIBC_ARCH_POWERPC_H
+
+#include "compiler.h"
+#include "crt.h"
+
+/* Syscalls for PowerPC :
+ * - stack is 16-byte aligned
+ * - syscall number is passed in r0
+ * - arguments are in r3, r4, r5, r6, r7, r8, r9
+ * - the system call is performed by calling "sc"
+ * - syscall return comes in r3, and the summary overflow bit is checked
+ * to know if an error occurred, in which case errno is in r3.
+ * - the arguments are cast to long and assigned into the target
+ * registers which are then simply passed as registers to the asm code,
+ * so that we don't have to experience issues with register constraints.
+ */
+
+#define _NOLIBC_SYSCALL_CLOBBERLIST \
+ "memory", "cr0", "r12", "r11", "r10", "r9"
+
+#define my_syscall0(num) \
+({ \
+ register long _ret __asm__ ("r3"); \
+ register long _num __asm__ ("r0") = (num); \
+ \
+ __asm__ volatile ( \
+ " sc\n" \
+ " bns+ 1f\n" \
+ " neg %0, %0\n" \
+ "1:\n" \
+ : "=r"(_ret), "+r"(_num) \
+ : \
+ : _NOLIBC_SYSCALL_CLOBBERLIST, "r8", "r7", "r6", "r5", "r4" \
+ ); \
+ _ret; \
+})
+
+#define my_syscall1(num, arg1) \
+({ \
+ register long _ret __asm__ ("r3"); \
+ register long _num __asm__ ("r0") = (num); \
+ register long _arg1 __asm__ ("r3") = (long)(arg1); \
+ \
+ __asm__ volatile ( \
+ " sc\n" \
+ " bns+ 1f\n" \
+ " neg %0, %0\n" \
+ "1:\n" \
+ : "=r"(_ret), "+r"(_num) \
+ : "0"(_arg1) \
+ : _NOLIBC_SYSCALL_CLOBBERLIST, "r8", "r7", "r6", "r5", "r4" \
+ ); \
+ _ret; \
+})
+
+
+#define my_syscall2(num, arg1, arg2) \
+({ \
+ register long _ret __asm__ ("r3"); \
+ register long _num __asm__ ("r0") = (num); \
+ register long _arg1 __asm__ ("r3") = (long)(arg1); \
+ register long _arg2 __asm__ ("r4") = (long)(arg2); \
+ \
+ __asm__ volatile ( \
+ " sc\n" \
+ " bns+ 1f\n" \
+ " neg %0, %0\n" \
+ "1:\n" \
+ : "=r"(_ret), "+r"(_num), "+r"(_arg2) \
+ : "0"(_arg1) \
+ : _NOLIBC_SYSCALL_CLOBBERLIST, "r8", "r7", "r6", "r5" \
+ ); \
+ _ret; \
+})
+
+
+#define my_syscall3(num, arg1, arg2, arg3) \
+({ \
+ register long _ret __asm__ ("r3"); \
+ register long _num __asm__ ("r0") = (num); \
+ register long _arg1 __asm__ ("r3") = (long)(arg1); \
+ register long _arg2 __asm__ ("r4") = (long)(arg2); \
+ register long _arg3 __asm__ ("r5") = (long)(arg3); \
+ \
+ __asm__ volatile ( \
+ " sc\n" \
+ " bns+ 1f\n" \
+ " neg %0, %0\n" \
+ "1:\n" \
+ : "=r"(_ret), "+r"(_num), "+r"(_arg2), "+r"(_arg3) \
+ : "0"(_arg1) \
+ : _NOLIBC_SYSCALL_CLOBBERLIST, "r8", "r7", "r6" \
+ ); \
+ _ret; \
+})
+
+
+#define my_syscall4(num, arg1, arg2, arg3, arg4) \
+({ \
+ register long _ret __asm__ ("r3"); \
+ register long _num __asm__ ("r0") = (num); \
+ register long _arg1 __asm__ ("r3") = (long)(arg1); \
+ register long _arg2 __asm__ ("r4") = (long)(arg2); \
+ register long _arg3 __asm__ ("r5") = (long)(arg3); \
+ register long _arg4 __asm__ ("r6") = (long)(arg4); \
+ \
+ __asm__ volatile ( \
+ " sc\n" \
+ " bns+ 1f\n" \
+ " neg %0, %0\n" \
+ "1:\n" \
+ : "=r"(_ret), "+r"(_num), "+r"(_arg2), "+r"(_arg3), \
+ "+r"(_arg4) \
+ : "0"(_arg1) \
+ : _NOLIBC_SYSCALL_CLOBBERLIST, "r8", "r7" \
+ ); \
+ _ret; \
+})
+
+
+#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \
+({ \
+ register long _ret __asm__ ("r3"); \
+ register long _num __asm__ ("r0") = (num); \
+ register long _arg1 __asm__ ("r3") = (long)(arg1); \
+ register long _arg2 __asm__ ("r4") = (long)(arg2); \
+ register long _arg3 __asm__ ("r5") = (long)(arg3); \
+ register long _arg4 __asm__ ("r6") = (long)(arg4); \
+ register long _arg5 __asm__ ("r7") = (long)(arg5); \
+ \
+ __asm__ volatile ( \
+ " sc\n" \
+ " bns+ 1f\n" \
+ " neg %0, %0\n" \
+ "1:\n" \
+ : "=r"(_ret), "+r"(_num), "+r"(_arg2), "+r"(_arg3), \
+ "+r"(_arg4), "+r"(_arg5) \
+ : "0"(_arg1) \
+ : _NOLIBC_SYSCALL_CLOBBERLIST, "r8" \
+ ); \
+ _ret; \
+})
+
+#define my_syscall6(num, arg1, arg2, arg3, arg4, arg5, arg6) \
+({ \
+ register long _ret __asm__ ("r3"); \
+ register long _num __asm__ ("r0") = (num); \
+ register long _arg1 __asm__ ("r3") = (long)(arg1); \
+ register long _arg2 __asm__ ("r4") = (long)(arg2); \
+ register long _arg3 __asm__ ("r5") = (long)(arg3); \
+ register long _arg4 __asm__ ("r6") = (long)(arg4); \
+ register long _arg5 __asm__ ("r7") = (long)(arg5); \
+ register long _arg6 __asm__ ("r8") = (long)(arg6); \
+ \
+ __asm__ volatile ( \
+ " sc\n" \
+ " bns+ 1f\n" \
+ " neg %0, %0\n" \
+ "1:\n" \
+ : "=r"(_ret), "+r"(_num), "+r"(_arg2), "+r"(_arg3), \
+ "+r"(_arg4), "+r"(_arg5), "+r"(_arg6) \
+ : "0"(_arg1) \
+ : _NOLIBC_SYSCALL_CLOBBERLIST \
+ ); \
+ _ret; \
+})
+
+#ifndef __powerpc64__
+/* FIXME: For 32-bit PowerPC, with newer gcc compilers (e.g. gcc 13.1.0),
+ * "omit-frame-pointer" fails with __attribute__((no_stack_protector)) but
+ * works with __attribute__((__optimize__("-fno-stack-protector")))
+ */
+#ifdef __no_stack_protector
+#undef __no_stack_protector
+#define __no_stack_protector __attribute__((__optimize__("-fno-stack-protector")))
+#endif
+#endif /* !__powerpc64__ */
+
+/* startup code */
+void __attribute__((weak, noreturn, optimize("Os", "omit-frame-pointer"))) __no_stack_protector _start(void)
+{
+#ifdef __powerpc64__
+#if _CALL_ELF == 2
+ /* with -mabi=elfv2, save TOC/GOT pointer to r2
+ * r12 is global entry pointer, we use it to compute TOC from r12
+ * https://www.llvm.org/devmtg/2014-04/PDFs/Talks/Euro-LLVM-2014-Weigand.pdf
+ * https://refspecs.linuxfoundation.org/ELF/ppc64/PPC-elf64abi.pdf
+ */
+ __asm__ volatile (
+ "addis 2, 12, .TOC. - _start@ha\n"
+ "addi 2, 2, .TOC. - _start@l\n"
+ );
+#endif /* _CALL_ELF == 2 */
+
+ __asm__ volatile (
+ "mr 3, 1\n" /* save stack pointer to r3, as arg1 of _start_c */
+ "clrrdi 1, 1, 4\n" /* align the stack to 16 bytes */
+ "li 0, 0\n" /* zero the frame pointer */
+ "stdu 1, -32(1)\n" /* the initial stack frame */
+ "bl _start_c\n" /* transfer to c runtime */
+ );
+#else
+ __asm__ volatile (
+ "mr 3, 1\n" /* save stack pointer to r3, as arg1 of _start_c */
+ "clrrwi 1, 1, 4\n" /* align the stack to 16 bytes */
+ "li 0, 0\n" /* zero the frame pointer */
+ "stwu 1, -16(1)\n" /* the initial stack frame */
+ "bl _start_c\n" /* transfer to c runtime */
+ );
+#endif
+ __builtin_unreachable();
+}
+
+#endif /* _NOLIBC_ARCH_POWERPC_H */
diff --git a/tools/include/nolibc/arch-riscv.h b/tools/include/nolibc/arch-riscv.h
new file mode 100644
index 0000000000..950cc2283f
--- /dev/null
+++ b/tools/include/nolibc/arch-riscv.h
@@ -0,0 +1,160 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * RISCV (32 and 64) specific definitions for NOLIBC
+ * Copyright (C) 2017-2022 Willy Tarreau <w@1wt.eu>
+ */
+
+#ifndef _NOLIBC_ARCH_RISCV_H
+#define _NOLIBC_ARCH_RISCV_H
+
+#include "compiler.h"
+#include "crt.h"
+
+/* Syscalls for RISCV :
+ * - stack is 16-byte aligned
+ * - syscall number is passed in a7
+ * - arguments are in a0, a1, a2, a3, a4, a5
+ * - the system call is performed by calling ecall
+ * - syscall return comes in a0
+ * - the arguments are cast to long and assigned into the target
+ * registers which are then simply passed as registers to the asm code,
+ * so that we don't have to experience issues with register constraints.
+ *
+ * On riscv, select() is not implemented so we have to use pselect6().
+ */
+#define __ARCH_WANT_SYS_PSELECT6
+
+#define my_syscall0(num) \
+({ \
+ register long _num __asm__ ("a7") = (num); \
+ register long _arg1 __asm__ ("a0"); \
+ \
+ __asm__ volatile ( \
+ "ecall\n\t" \
+ : "=r"(_arg1) \
+ : "r"(_num) \
+ : "memory", "cc" \
+ ); \
+ _arg1; \
+})
+
+#define my_syscall1(num, arg1) \
+({ \
+ register long _num __asm__ ("a7") = (num); \
+ register long _arg1 __asm__ ("a0") = (long)(arg1); \
+ \
+ __asm__ volatile ( \
+ "ecall\n" \
+ : "+r"(_arg1) \
+ : "r"(_num) \
+ : "memory", "cc" \
+ ); \
+ _arg1; \
+})
+
+#define my_syscall2(num, arg1, arg2) \
+({ \
+ register long _num __asm__ ("a7") = (num); \
+ register long _arg1 __asm__ ("a0") = (long)(arg1); \
+ register long _arg2 __asm__ ("a1") = (long)(arg2); \
+ \
+ __asm__ volatile ( \
+ "ecall\n" \
+ : "+r"(_arg1) \
+ : "r"(_arg2), \
+ "r"(_num) \
+ : "memory", "cc" \
+ ); \
+ _arg1; \
+})
+
+#define my_syscall3(num, arg1, arg2, arg3) \
+({ \
+ register long _num __asm__ ("a7") = (num); \
+ register long _arg1 __asm__ ("a0") = (long)(arg1); \
+ register long _arg2 __asm__ ("a1") = (long)(arg2); \
+ register long _arg3 __asm__ ("a2") = (long)(arg3); \
+ \
+ __asm__ volatile ( \
+ "ecall\n\t" \
+ : "+r"(_arg1) \
+ : "r"(_arg2), "r"(_arg3), \
+ "r"(_num) \
+ : "memory", "cc" \
+ ); \
+ _arg1; \
+})
+
+#define my_syscall4(num, arg1, arg2, arg3, arg4) \
+({ \
+ register long _num __asm__ ("a7") = (num); \
+ register long _arg1 __asm__ ("a0") = (long)(arg1); \
+ register long _arg2 __asm__ ("a1") = (long)(arg2); \
+ register long _arg3 __asm__ ("a2") = (long)(arg3); \
+ register long _arg4 __asm__ ("a3") = (long)(arg4); \
+ \
+ __asm__ volatile ( \
+ "ecall\n" \
+ : "+r"(_arg1) \
+ : "r"(_arg2), "r"(_arg3), "r"(_arg4), \
+ "r"(_num) \
+ : "memory", "cc" \
+ ); \
+ _arg1; \
+})
+
+#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \
+({ \
+ register long _num __asm__ ("a7") = (num); \
+ register long _arg1 __asm__ ("a0") = (long)(arg1); \
+ register long _arg2 __asm__ ("a1") = (long)(arg2); \
+ register long _arg3 __asm__ ("a2") = (long)(arg3); \
+ register long _arg4 __asm__ ("a3") = (long)(arg4); \
+ register long _arg5 __asm__ ("a4") = (long)(arg5); \
+ \
+ __asm__ volatile ( \
+ "ecall\n" \
+ : "+r"(_arg1) \
+ : "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \
+ "r"(_num) \
+ : "memory", "cc" \
+ ); \
+ _arg1; \
+})
+
+#define my_syscall6(num, arg1, arg2, arg3, arg4, arg5, arg6) \
+({ \
+ register long _num __asm__ ("a7") = (num); \
+ register long _arg1 __asm__ ("a0") = (long)(arg1); \
+ register long _arg2 __asm__ ("a1") = (long)(arg2); \
+ register long _arg3 __asm__ ("a2") = (long)(arg3); \
+ register long _arg4 __asm__ ("a3") = (long)(arg4); \
+ register long _arg5 __asm__ ("a4") = (long)(arg5); \
+ register long _arg6 __asm__ ("a5") = (long)(arg6); \
+ \
+ __asm__ volatile ( \
+ "ecall\n" \
+ : "+r"(_arg1) \
+ : "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), "r"(_arg6), \
+ "r"(_num) \
+ : "memory", "cc" \
+ ); \
+ _arg1; \
+})
+
+/* startup code */
+void __attribute__((weak, noreturn, optimize("Os", "omit-frame-pointer"))) __no_stack_protector _start(void)
+{
+ __asm__ volatile (
+ ".option push\n"
+ ".option norelax\n"
+ "lla gp, __global_pointer$\n"
+ ".option pop\n"
+ "mv a0, sp\n" /* save stack pointer to a0, as arg1 of _start_c */
+ "andi sp, a0, -16\n" /* sp must be 16-byte aligned */
+ "call _start_c\n" /* transfer to c runtime */
+ );
+ __builtin_unreachable();
+}
+
+#endif /* _NOLIBC_ARCH_RISCV_H */
diff --git a/tools/include/nolibc/arch-s390.h b/tools/include/nolibc/arch-s390.h
new file mode 100644
index 0000000000..5d60fd43f8
--- /dev/null
+++ b/tools/include/nolibc/arch-s390.h
@@ -0,0 +1,186 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * s390 specific definitions for NOLIBC
+ */
+
+#ifndef _NOLIBC_ARCH_S390_H
+#define _NOLIBC_ARCH_S390_H
+#include <asm/signal.h>
+#include <asm/unistd.h>
+
+#include "compiler.h"
+#include "crt.h"
+
+/* Syscalls for s390:
+ * - registers are 64-bit
+ * - syscall number is passed in r1
+ * - arguments are in r2-r7
+ * - the system call is performed by calling the svc instruction
+ * - syscall return value is in r2
+ * - r1 and r2 are clobbered, others are preserved.
+ *
+ * Link s390 ABI: https://github.com/IBM/s390x-abi
+ *
+ */
+
+#define my_syscall0(num) \
+({ \
+ register long _num __asm__ ("1") = (num); \
+ register long _rc __asm__ ("2"); \
+ \
+ __asm__ volatile ( \
+ "svc 0\n" \
+ : "=d"(_rc) \
+ : "d"(_num) \
+ : "memory", "cc" \
+ ); \
+ _rc; \
+})
+
+#define my_syscall1(num, arg1) \
+({ \
+ register long _num __asm__ ("1") = (num); \
+ register long _arg1 __asm__ ("2") = (long)(arg1); \
+ \
+ __asm__ volatile ( \
+ "svc 0\n" \
+ : "+d"(_arg1) \
+ : "d"(_num) \
+ : "memory", "cc" \
+ ); \
+ _arg1; \
+})
+
+#define my_syscall2(num, arg1, arg2) \
+({ \
+ register long _num __asm__ ("1") = (num); \
+ register long _arg1 __asm__ ("2") = (long)(arg1); \
+ register long _arg2 __asm__ ("3") = (long)(arg2); \
+ \
+ __asm__ volatile ( \
+ "svc 0\n" \
+ : "+d"(_arg1) \
+ : "d"(_arg2), "d"(_num) \
+ : "memory", "cc" \
+ ); \
+ _arg1; \
+})
+
+#define my_syscall3(num, arg1, arg2, arg3) \
+({ \
+ register long _num __asm__ ("1") = (num); \
+ register long _arg1 __asm__ ("2") = (long)(arg1); \
+ register long _arg2 __asm__ ("3") = (long)(arg2); \
+ register long _arg3 __asm__ ("4") = (long)(arg3); \
+ \
+ __asm__ volatile ( \
+ "svc 0\n" \
+ : "+d"(_arg1) \
+ : "d"(_arg2), "d"(_arg3), "d"(_num) \
+ : "memory", "cc" \
+ ); \
+ _arg1; \
+})
+
+#define my_syscall4(num, arg1, arg2, arg3, arg4) \
+({ \
+ register long _num __asm__ ("1") = (num); \
+ register long _arg1 __asm__ ("2") = (long)(arg1); \
+ register long _arg2 __asm__ ("3") = (long)(arg2); \
+ register long _arg3 __asm__ ("4") = (long)(arg3); \
+ register long _arg4 __asm__ ("5") = (long)(arg4); \
+ \
+ __asm__ volatile ( \
+ "svc 0\n" \
+ : "+d"(_arg1) \
+ : "d"(_arg2), "d"(_arg3), "d"(_arg4), "d"(_num) \
+ : "memory", "cc" \
+ ); \
+ _arg1; \
+})
+
+#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \
+({ \
+ register long _num __asm__ ("1") = (num); \
+ register long _arg1 __asm__ ("2") = (long)(arg1); \
+ register long _arg2 __asm__ ("3") = (long)(arg2); \
+ register long _arg3 __asm__ ("4") = (long)(arg3); \
+ register long _arg4 __asm__ ("5") = (long)(arg4); \
+ register long _arg5 __asm__ ("6") = (long)(arg5); \
+ \
+ __asm__ volatile ( \
+ "svc 0\n" \
+ : "+d"(_arg1) \
+ : "d"(_arg2), "d"(_arg3), "d"(_arg4), "d"(_arg5), \
+ "d"(_num) \
+ : "memory", "cc" \
+ ); \
+ _arg1; \
+})
+
+#define my_syscall6(num, arg1, arg2, arg3, arg4, arg5, arg6) \
+({ \
+ register long _num __asm__ ("1") = (num); \
+ register long _arg1 __asm__ ("2") = (long)(arg1); \
+ register long _arg2 __asm__ ("3") = (long)(arg2); \
+ register long _arg3 __asm__ ("4") = (long)(arg3); \
+ register long _arg4 __asm__ ("5") = (long)(arg4); \
+ register long _arg5 __asm__ ("6") = (long)(arg5); \
+ register long _arg6 __asm__ ("7") = (long)(arg6); \
+ \
+ __asm__ volatile ( \
+ "svc 0\n" \
+ : "+d"(_arg1) \
+ : "d"(_arg2), "d"(_arg3), "d"(_arg4), "d"(_arg5), \
+ "d"(_arg6), "d"(_num) \
+ : "memory", "cc" \
+ ); \
+ _arg1; \
+})
+
+/* startup code */
+void __attribute__((weak, noreturn, optimize("Os", "omit-frame-pointer"))) __no_stack_protector _start(void)
+{
+ __asm__ volatile (
+ "lgr %r2, %r15\n" /* save stack pointer to %r2, as arg1 of _start_c */
+ "aghi %r15, -160\n" /* allocate new stackframe */
+ "xc 0(8,%r15), 0(%r15)\n" /* clear backchain */
+ "brasl %r14, _start_c\n" /* transfer to c runtime */
+ );
+ __builtin_unreachable();
+}
+
+struct s390_mmap_arg_struct {
+ unsigned long addr;
+ unsigned long len;
+ unsigned long prot;
+ unsigned long flags;
+ unsigned long fd;
+ unsigned long offset;
+};
+
+static __attribute__((unused))
+void *sys_mmap(void *addr, size_t length, int prot, int flags, int fd,
+ off_t offset)
+{
+ struct s390_mmap_arg_struct args = {
+ .addr = (unsigned long)addr,
+ .len = (unsigned long)length,
+ .prot = prot,
+ .flags = flags,
+ .fd = fd,
+ .offset = (unsigned long)offset
+ };
+
+ return (void *)my_syscall1(__NR_mmap, &args);
+}
+#define sys_mmap sys_mmap
+
+static __attribute__((unused))
+pid_t sys_fork(void)
+{
+ return my_syscall5(__NR_clone, 0, SIGCHLD, 0, 0, 0);
+}
+#define sys_fork sys_fork
+
+#endif /* _NOLIBC_ARCH_S390_H */
diff --git a/tools/include/nolibc/arch-x86_64.h b/tools/include/nolibc/arch-x86_64.h
new file mode 100644
index 0000000000..e5ccb926c9
--- /dev/null
+++ b/tools/include/nolibc/arch-x86_64.h
@@ -0,0 +1,176 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * x86_64 specific definitions for NOLIBC
+ * Copyright (C) 2017-2022 Willy Tarreau <w@1wt.eu>
+ */
+
+#ifndef _NOLIBC_ARCH_X86_64_H
+#define _NOLIBC_ARCH_X86_64_H
+
+#include "compiler.h"
+#include "crt.h"
+
+/* Syscalls for x86_64 :
+ * - registers are 64-bit
+ * - syscall number is passed in rax
+ * - arguments are in rdi, rsi, rdx, r10, r8, r9 respectively
+ * - the system call is performed by calling the syscall instruction
+ * - syscall return comes in rax
+ * - rcx and r11 are clobbered, others are preserved.
+ * - the arguments are cast to long and assigned into the target registers
+ * which are then simply passed as registers to the asm code, so that we
+ * don't have to experience issues with register constraints.
+ * - the syscall number is always specified last in order to allow to force
+ * some registers before (gcc refuses a %-register at the last position).
+ * - see also x86-64 ABI section A.2 AMD64 Linux Kernel Conventions, A.2.1
+ * Calling Conventions.
+ *
+ * Link x86-64 ABI: https://gitlab.com/x86-psABIs/x86-64-ABI/-/wikis/home
+ *
+ */
+
+#define my_syscall0(num) \
+({ \
+ long _ret; \
+ register long _num __asm__ ("rax") = (num); \
+ \
+ __asm__ volatile ( \
+ "syscall\n" \
+ : "=a"(_ret) \
+ : "0"(_num) \
+ : "rcx", "r11", "memory", "cc" \
+ ); \
+ _ret; \
+})
+
+#define my_syscall1(num, arg1) \
+({ \
+ long _ret; \
+ register long _num __asm__ ("rax") = (num); \
+ register long _arg1 __asm__ ("rdi") = (long)(arg1); \
+ \
+ __asm__ volatile ( \
+ "syscall\n" \
+ : "=a"(_ret) \
+ : "r"(_arg1), \
+ "0"(_num) \
+ : "rcx", "r11", "memory", "cc" \
+ ); \
+ _ret; \
+})
+
+#define my_syscall2(num, arg1, arg2) \
+({ \
+ long _ret; \
+ register long _num __asm__ ("rax") = (num); \
+ register long _arg1 __asm__ ("rdi") = (long)(arg1); \
+ register long _arg2 __asm__ ("rsi") = (long)(arg2); \
+ \
+ __asm__ volatile ( \
+ "syscall\n" \
+ : "=a"(_ret) \
+ : "r"(_arg1), "r"(_arg2), \
+ "0"(_num) \
+ : "rcx", "r11", "memory", "cc" \
+ ); \
+ _ret; \
+})
+
+#define my_syscall3(num, arg1, arg2, arg3) \
+({ \
+ long _ret; \
+ register long _num __asm__ ("rax") = (num); \
+ register long _arg1 __asm__ ("rdi") = (long)(arg1); \
+ register long _arg2 __asm__ ("rsi") = (long)(arg2); \
+ register long _arg3 __asm__ ("rdx") = (long)(arg3); \
+ \
+ __asm__ volatile ( \
+ "syscall\n" \
+ : "=a"(_ret) \
+ : "r"(_arg1), "r"(_arg2), "r"(_arg3), \
+ "0"(_num) \
+ : "rcx", "r11", "memory", "cc" \
+ ); \
+ _ret; \
+})
+
+#define my_syscall4(num, arg1, arg2, arg3, arg4) \
+({ \
+ long _ret; \
+ register long _num __asm__ ("rax") = (num); \
+ register long _arg1 __asm__ ("rdi") = (long)(arg1); \
+ register long _arg2 __asm__ ("rsi") = (long)(arg2); \
+ register long _arg3 __asm__ ("rdx") = (long)(arg3); \
+ register long _arg4 __asm__ ("r10") = (long)(arg4); \
+ \
+ __asm__ volatile ( \
+ "syscall\n" \
+ : "=a"(_ret) \
+ : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), \
+ "0"(_num) \
+ : "rcx", "r11", "memory", "cc" \
+ ); \
+ _ret; \
+})
+
+#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \
+({ \
+ long _ret; \
+ register long _num __asm__ ("rax") = (num); \
+ register long _arg1 __asm__ ("rdi") = (long)(arg1); \
+ register long _arg2 __asm__ ("rsi") = (long)(arg2); \
+ register long _arg3 __asm__ ("rdx") = (long)(arg3); \
+ register long _arg4 __asm__ ("r10") = (long)(arg4); \
+ register long _arg5 __asm__ ("r8") = (long)(arg5); \
+ \
+ __asm__ volatile ( \
+ "syscall\n" \
+ : "=a"(_ret) \
+ : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \
+ "0"(_num) \
+ : "rcx", "r11", "memory", "cc" \
+ ); \
+ _ret; \
+})
+
+#define my_syscall6(num, arg1, arg2, arg3, arg4, arg5, arg6) \
+({ \
+ long _ret; \
+ register long _num __asm__ ("rax") = (num); \
+ register long _arg1 __asm__ ("rdi") = (long)(arg1); \
+ register long _arg2 __asm__ ("rsi") = (long)(arg2); \
+ register long _arg3 __asm__ ("rdx") = (long)(arg3); \
+ register long _arg4 __asm__ ("r10") = (long)(arg4); \
+ register long _arg5 __asm__ ("r8") = (long)(arg5); \
+ register long _arg6 __asm__ ("r9") = (long)(arg6); \
+ \
+ __asm__ volatile ( \
+ "syscall\n" \
+ : "=a"(_ret) \
+ : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \
+ "r"(_arg6), "0"(_num) \
+ : "rcx", "r11", "memory", "cc" \
+ ); \
+ _ret; \
+})
+
+/* startup code */
+/*
+ * x86-64 System V ABI mandates:
+ * 1) %rsp must be 16-byte aligned right before the function call.
+ * 2) The deepest stack frame should be zero (the %rbp).
+ *
+ */
+void __attribute__((weak, noreturn, optimize("Os", "omit-frame-pointer"))) __no_stack_protector _start(void)
+{
+ __asm__ volatile (
+ "xor %ebp, %ebp\n" /* zero the stack frame */
+ "mov %rsp, %rdi\n" /* save stack pointer to %rdi, as arg1 of _start_c */
+ "and $-16, %rsp\n" /* %rsp must be 16-byte aligned before call */
+ "call _start_c\n" /* transfer to c runtime */
+ "hlt\n" /* ensure it does not return */
+ );
+ __builtin_unreachable();
+}
+
+#endif /* _NOLIBC_ARCH_X86_64_H */
diff --git a/tools/include/nolibc/arch.h b/tools/include/nolibc/arch.h
new file mode 100644
index 0000000000..e276fb0680
--- /dev/null
+++ b/tools/include/nolibc/arch.h
@@ -0,0 +1,38 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * Copyright (C) 2017-2022 Willy Tarreau <w@1wt.eu>
+ */
+
+/* Below comes the architecture-specific code. For each architecture, we have
+ * the syscall declarations and the _start code definition. This is the only
+ * global part. On all architectures the kernel puts everything in the stack
+ * before jumping to _start just above us, without any return address (_start
+ * is not a function but an entry point). So at the stack pointer we find argc.
+ * Then argv[] begins, and ends at the first NULL. Then we have envp which
+ * starts and ends with a NULL as well. So envp=argv+argc+1.
+ */
+
+#ifndef _NOLIBC_ARCH_H
+#define _NOLIBC_ARCH_H
+
+#if defined(__x86_64__)
+#include "arch-x86_64.h"
+#elif defined(__i386__) || defined(__i486__) || defined(__i586__) || defined(__i686__)
+#include "arch-i386.h"
+#elif defined(__ARM_EABI__)
+#include "arch-arm.h"
+#elif defined(__aarch64__)
+#include "arch-aarch64.h"
+#elif defined(__mips__) && defined(_ABIO32)
+#include "arch-mips.h"
+#elif defined(__powerpc__)
+#include "arch-powerpc.h"
+#elif defined(__riscv)
+#include "arch-riscv.h"
+#elif defined(__s390x__)
+#include "arch-s390.h"
+#elif defined(__loongarch__)
+#include "arch-loongarch.h"
+#endif
+
+#endif /* _NOLIBC_ARCH_H */
diff --git a/tools/include/nolibc/compiler.h b/tools/include/nolibc/compiler.h
new file mode 100644
index 0000000000..beddc3665d
--- /dev/null
+++ b/tools/include/nolibc/compiler.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * NOLIBC compiler support header
+ * Copyright (C) 2023 Thomas Weißschuh <linux@weissschuh.net>
+ */
+#ifndef _NOLIBC_COMPILER_H
+#define _NOLIBC_COMPILER_H
+
+#if defined(__SSP__) || defined(__SSP_STRONG__) || defined(__SSP_ALL__) || defined(__SSP_EXPLICIT__)
+
+#define _NOLIBC_STACKPROTECTOR
+
+#endif /* defined(__SSP__) ... */
+
+#if defined(__has_attribute)
+# if __has_attribute(no_stack_protector)
+# define __no_stack_protector __attribute__((no_stack_protector))
+# else
+# define __no_stack_protector __attribute__((__optimize__("-fno-stack-protector")))
+# endif
+#else
+# define __no_stack_protector __attribute__((__optimize__("-fno-stack-protector")))
+#endif /* defined(__has_attribute) */
+
+#endif /* _NOLIBC_COMPILER_H */
diff --git a/tools/include/nolibc/crt.h b/tools/include/nolibc/crt.h
new file mode 100644
index 0000000000..a05655b4ce
--- /dev/null
+++ b/tools/include/nolibc/crt.h
@@ -0,0 +1,62 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * C Run Time support for NOLIBC
+ * Copyright (C) 2023 Zhangjin Wu <falcon@tinylab.org>
+ */
+
+#ifndef _NOLIBC_CRT_H
+#define _NOLIBC_CRT_H
+
+char **environ __attribute__((weak));
+const unsigned long *_auxv __attribute__((weak));
+
+static void __stack_chk_init(void);
+static void exit(int);
+
+__attribute__((weak))
+void _start_c(long *sp)
+{
+ long argc;
+ char **argv;
+ char **envp;
+ const unsigned long *auxv;
+ /* silence potential warning: conflicting types for 'main' */
+ int _nolibc_main(int, char **, char **) __asm__ ("main");
+
+ /* initialize stack protector */
+ __stack_chk_init();
+
+ /*
+ * sp : argc <-- argument count, required by main()
+ * argv: argv[0] <-- argument vector, required by main()
+ * argv[1]
+ * ...
+ * argv[argc-1]
+ * null
+ * environ: environ[0] <-- environment variables, required by main() and getenv()
+ * environ[1]
+ * ...
+ * null
+ * _auxv: _auxv[0] <-- auxiliary vector, required by getauxval()
+ * _auxv[1]
+ * ...
+ * null
+ */
+
+ /* assign argc and argv */
+ argc = *sp;
+ argv = (void *)(sp + 1);
+
+ /* find environ */
+ environ = envp = argv + argc + 1;
+
+ /* find _auxv */
+ for (auxv = (void *)envp; *auxv++;)
+ ;
+ _auxv = auxv;
+
+ /* go to application */
+ exit(_nolibc_main(argc, argv, envp));
+}
+
+#endif /* _NOLIBC_CRT_H */
diff --git a/tools/include/nolibc/ctype.h b/tools/include/nolibc/ctype.h
new file mode 100644
index 0000000000..6f90706d06
--- /dev/null
+++ b/tools/include/nolibc/ctype.h
@@ -0,0 +1,102 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * ctype function definitions for NOLIBC
+ * Copyright (C) 2017-2021 Willy Tarreau <w@1wt.eu>
+ */
+
+#ifndef _NOLIBC_CTYPE_H
+#define _NOLIBC_CTYPE_H
+
+#include "std.h"
+
+/*
+ * As much as possible, please keep functions alphabetically sorted.
+ */
+
+static __attribute__((unused))
+int isascii(int c)
+{
+ /* 0x00..0x7f */
+ return (unsigned int)c <= 0x7f;
+}
+
+static __attribute__((unused))
+int isblank(int c)
+{
+ return c == '\t' || c == ' ';
+}
+
+static __attribute__((unused))
+int iscntrl(int c)
+{
+ /* 0x00..0x1f, 0x7f */
+ return (unsigned int)c < 0x20 || c == 0x7f;
+}
+
+static __attribute__((unused))
+int isdigit(int c)
+{
+ return (unsigned int)(c - '0') < 10;
+}
+
+static __attribute__((unused))
+int isgraph(int c)
+{
+ /* 0x21..0x7e */
+ return (unsigned int)(c - 0x21) < 0x5e;
+}
+
+static __attribute__((unused))
+int islower(int c)
+{
+ return (unsigned int)(c - 'a') < 26;
+}
+
+static __attribute__((unused))
+int isprint(int c)
+{
+ /* 0x20..0x7e */
+ return (unsigned int)(c - 0x20) < 0x5f;
+}
+
+static __attribute__((unused))
+int isspace(int c)
+{
+ /* \t is 0x9, \n is 0xA, \v is 0xB, \f is 0xC, \r is 0xD */
+ return ((unsigned int)c == ' ') || (unsigned int)(c - 0x09) < 5;
+}
+
+static __attribute__((unused))
+int isupper(int c)
+{
+ return (unsigned int)(c - 'A') < 26;
+}
+
+static __attribute__((unused))
+int isxdigit(int c)
+{
+ return isdigit(c) || (unsigned int)(c - 'A') < 6 || (unsigned int)(c - 'a') < 6;
+}
+
+static __attribute__((unused))
+int isalpha(int c)
+{
+ return islower(c) || isupper(c);
+}
+
+static __attribute__((unused))
+int isalnum(int c)
+{
+ return isalpha(c) || isdigit(c);
+}
+
+static __attribute__((unused))
+int ispunct(int c)
+{
+ return isgraph(c) && !isalnum(c);
+}
+
+/* make sure to include all global symbols */
+#include "nolibc.h"
+
+#endif /* _NOLIBC_CTYPE_H */
diff --git a/tools/include/nolibc/errno.h b/tools/include/nolibc/errno.h
new file mode 100644
index 0000000000..a44486ff04
--- /dev/null
+++ b/tools/include/nolibc/errno.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * Minimal errno definitions for NOLIBC
+ * Copyright (C) 2017-2022 Willy Tarreau <w@1wt.eu>
+ */
+
+#ifndef _NOLIBC_ERRNO_H
+#define _NOLIBC_ERRNO_H
+
+#include <asm/errno.h>
+
+#ifndef NOLIBC_IGNORE_ERRNO
+#define SET_ERRNO(v) do { errno = (v); } while (0)
+int errno __attribute__((weak));
+#else
+#define SET_ERRNO(v) do { } while (0)
+#endif
+
+
+/* errno codes all ensure that they will not conflict with a valid pointer
+ * because they all correspond to the highest addressable memory page.
+ */
+#define MAX_ERRNO 4095
+
+/* make sure to include all global symbols */
+#include "nolibc.h"
+
+#endif /* _NOLIBC_ERRNO_H */
diff --git a/tools/include/nolibc/nolibc.h b/tools/include/nolibc/nolibc.h
new file mode 100644
index 0000000000..1f8d821000
--- /dev/null
+++ b/tools/include/nolibc/nolibc.h
@@ -0,0 +1,111 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/* nolibc.h
+ * Copyright (C) 2017-2018 Willy Tarreau <w@1wt.eu>
+ */
+
+/*
+ * This file is designed to be used as a libc alternative for minimal programs
+ * with very limited requirements. It consists of a small number of syscall and
+ * type definitions, and the minimal startup code needed to call main().
+ * All syscalls are declared as static functions so that they can be optimized
+ * away by the compiler when not used.
+ *
+ * Syscalls are split into 3 levels:
+ * - The lower level is the arch-specific syscall() definition, consisting in
+ * assembly code in compound expressions. These are called my_syscall0() to
+ * my_syscall6() depending on the number of arguments. All input arguments
+ * are castto a long stored in a register. These expressions always return
+ * the syscall's return value as a signed long value which is often either
+ * a pointer or the negated errno value.
+ *
+ * - The second level is mostly architecture-independent. It is made of
+ * static functions called sys_<name>() which rely on my_syscallN()
+ * depending on the syscall definition. These functions are responsible
+ * for exposing the appropriate types for the syscall arguments (int,
+ * pointers, etc) and for setting the appropriate return type (often int).
+ * A few of them are architecture-specific because the syscalls are not all
+ * mapped exactly the same among architectures. For example, some archs do
+ * not implement select() and need pselect6() instead, so the sys_select()
+ * function will have to abstract this.
+ *
+ * - The third level is the libc call definition. It exposes the lower raw
+ * sys_<name>() calls in a way that looks like what a libc usually does,
+ * takes care of specific input values, and of setting errno upon error.
+ * There can be minor variations compared to standard libc calls. For
+ * example the open() call always takes 3 args here.
+ *
+ * The errno variable is declared static and unused. This way it can be
+ * optimized away if not used. However this means that a program made of
+ * multiple C files may observe different errno values (one per C file). For
+ * the type of programs this project targets it usually is not a problem. The
+ * resulting program may even be reduced by defining the NOLIBC_IGNORE_ERRNO
+ * macro, in which case the errno value will never be assigned.
+ *
+ * Some stdint-like integer types are defined. These are valid on all currently
+ * supported architectures, because signs are enforced, ints are assumed to be
+ * 32 bits, longs the size of a pointer and long long 64 bits. If more
+ * architectures have to be supported, this may need to be adapted.
+ *
+ * Some macro definitions like the O_* values passed to open(), and some
+ * structures like the sys_stat struct depend on the architecture.
+ *
+ * The definitions start with the architecture-specific parts, which are picked
+ * based on what the compiler knows about the target architecture, and are
+ * completed with the generic code. Since it is the compiler which sets the
+ * target architecture, cross-compiling normally works out of the box without
+ * having to specify anything.
+ *
+ * Finally some very common libc-level functions are provided. It is the case
+ * for a few functions usually found in string.h, ctype.h, or stdlib.h.
+ *
+ * The nolibc.h file is only a convenient entry point which includes all other
+ * files. It also defines the NOLIBC macro, so that it is possible for a
+ * program to check this macro to know if it is being built against and decide
+ * to disable some features or simply not to include some standard libc files.
+ *
+ * A simple static executable may be built this way :
+ * $ gcc -fno-asynchronous-unwind-tables -fno-ident -s -Os -nostdlib \
+ * -static -include nolibc.h -o hello hello.c -lgcc
+ *
+ * Simple programs meant to be reasonably portable to various libc and using
+ * only a few common includes, may also be built by simply making the include
+ * path point to the nolibc directory:
+ * $ gcc -fno-asynchronous-unwind-tables -fno-ident -s -Os -nostdlib \
+ * -I../nolibc -o hello hello.c -lgcc
+ *
+ * The available standard (but limited) include files are:
+ * ctype.h, errno.h, signal.h, stdio.h, stdlib.h, string.h, time.h
+ *
+ * In addition, the following ones are expected to be provided by the compiler:
+ * float.h, stdarg.h, stddef.h
+ *
+ * The following ones which are part to the C standard are not provided:
+ * assert.h, locale.h, math.h, setjmp.h, limits.h
+ *
+ * A very useful calling convention table may be found here :
+ * http://man7.org/linux/man-pages/man2/syscall.2.html
+ *
+ * This doc is quite convenient though not necessarily up to date :
+ * https://w3challs.com/syscalls/
+ *
+ */
+#ifndef _NOLIBC_H
+#define _NOLIBC_H
+
+#include "std.h"
+#include "arch.h"
+#include "types.h"
+#include "sys.h"
+#include "ctype.h"
+#include "signal.h"
+#include "unistd.h"
+#include "stdio.h"
+#include "stdlib.h"
+#include "string.h"
+#include "time.h"
+#include "stackprotector.h"
+
+/* Used by programs to avoid std includes */
+#define NOLIBC
+
+#endif /* _NOLIBC_H */
diff --git a/tools/include/nolibc/signal.h b/tools/include/nolibc/signal.h
new file mode 100644
index 0000000000..137552216e
--- /dev/null
+++ b/tools/include/nolibc/signal.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * signal function definitions for NOLIBC
+ * Copyright (C) 2017-2022 Willy Tarreau <w@1wt.eu>
+ */
+
+#ifndef _NOLIBC_SIGNAL_H
+#define _NOLIBC_SIGNAL_H
+
+#include "std.h"
+#include "arch.h"
+#include "types.h"
+#include "sys.h"
+
+/* This one is not marked static as it's needed by libgcc for divide by zero */
+__attribute__((weak,unused,section(".text.nolibc_raise")))
+int raise(int signal)
+{
+ return sys_kill(sys_getpid(), signal);
+}
+
+/* make sure to include all global symbols */
+#include "nolibc.h"
+
+#endif /* _NOLIBC_SIGNAL_H */
diff --git a/tools/include/nolibc/stackprotector.h b/tools/include/nolibc/stackprotector.h
new file mode 100644
index 0000000000..13f1d0e603
--- /dev/null
+++ b/tools/include/nolibc/stackprotector.h
@@ -0,0 +1,51 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * Stack protector support for NOLIBC
+ * Copyright (C) 2023 Thomas Weißschuh <linux@weissschuh.net>
+ */
+
+#ifndef _NOLIBC_STACKPROTECTOR_H
+#define _NOLIBC_STACKPROTECTOR_H
+
+#include "compiler.h"
+
+#if defined(_NOLIBC_STACKPROTECTOR)
+
+#include "sys.h"
+#include "stdlib.h"
+
+/* The functions in this header are using raw syscall macros to avoid
+ * triggering stack protector errors themselves
+ */
+
+__attribute__((weak,noreturn,section(".text.nolibc_stack_chk")))
+void __stack_chk_fail(void)
+{
+ pid_t pid;
+ my_syscall3(__NR_write, STDERR_FILENO, "!!Stack smashing detected!!\n", 28);
+ pid = my_syscall0(__NR_getpid);
+ my_syscall2(__NR_kill, pid, SIGABRT);
+ for (;;);
+}
+
+__attribute__((weak,noreturn,section(".text.nolibc_stack_chk")))
+void __stack_chk_fail_local(void)
+{
+ __stack_chk_fail();
+}
+
+__attribute__((weak,section(".data.nolibc_stack_chk")))
+uintptr_t __stack_chk_guard;
+
+static __no_stack_protector void __stack_chk_init(void)
+{
+ my_syscall3(__NR_getrandom, &__stack_chk_guard, sizeof(__stack_chk_guard), 0);
+ /* a bit more randomness in case getrandom() fails, ensure the guard is never 0 */
+ if (__stack_chk_guard != (uintptr_t) &__stack_chk_guard)
+ __stack_chk_guard ^= (uintptr_t) &__stack_chk_guard;
+}
+#else /* !defined(_NOLIBC_STACKPROTECTOR) */
+static void __stack_chk_init(void) {}
+#endif /* defined(_NOLIBC_STACKPROTECTOR) */
+
+#endif /* _NOLIBC_STACKPROTECTOR_H */
diff --git a/tools/include/nolibc/std.h b/tools/include/nolibc/std.h
new file mode 100644
index 0000000000..933bc0be7e
--- /dev/null
+++ b/tools/include/nolibc/std.h
@@ -0,0 +1,36 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * Standard definitions and types for NOLIBC
+ * Copyright (C) 2017-2021 Willy Tarreau <w@1wt.eu>
+ */
+
+#ifndef _NOLIBC_STD_H
+#define _NOLIBC_STD_H
+
+/* Declare a few quite common macros and types that usually are in stdlib.h,
+ * stdint.h, ctype.h, unistd.h and a few other common locations. Please place
+ * integer type definitions and generic macros here, but avoid OS-specific and
+ * syscall-specific stuff, as this file is expected to be included very early.
+ */
+
+/* note: may already be defined */
+#ifndef NULL
+#define NULL ((void *)0)
+#endif
+
+#include "stdint.h"
+
+/* those are commonly provided by sys/types.h */
+typedef unsigned int dev_t;
+typedef unsigned long ino_t;
+typedef unsigned int mode_t;
+typedef signed int pid_t;
+typedef unsigned int uid_t;
+typedef unsigned int gid_t;
+typedef unsigned long nlink_t;
+typedef signed long off_t;
+typedef signed long blksize_t;
+typedef signed long blkcnt_t;
+typedef signed long time_t;
+
+#endif /* _NOLIBC_STD_H */
diff --git a/tools/include/nolibc/stdint.h b/tools/include/nolibc/stdint.h
new file mode 100644
index 0000000000..6665e272e2
--- /dev/null
+++ b/tools/include/nolibc/stdint.h
@@ -0,0 +1,113 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * Standard definitions and types for NOLIBC
+ * Copyright (C) 2023 Vincent Dagonneau <v@vda.io>
+ */
+
+#ifndef _NOLIBC_STDINT_H
+#define _NOLIBC_STDINT_H
+
+typedef unsigned char uint8_t;
+typedef signed char int8_t;
+typedef unsigned short uint16_t;
+typedef signed short int16_t;
+typedef unsigned int uint32_t;
+typedef signed int int32_t;
+typedef unsigned long long uint64_t;
+typedef signed long long int64_t;
+typedef __SIZE_TYPE__ size_t;
+typedef signed long ssize_t;
+typedef unsigned long uintptr_t;
+typedef signed long intptr_t;
+typedef signed long ptrdiff_t;
+
+typedef int8_t int_least8_t;
+typedef uint8_t uint_least8_t;
+typedef int16_t int_least16_t;
+typedef uint16_t uint_least16_t;
+typedef int32_t int_least32_t;
+typedef uint32_t uint_least32_t;
+typedef int64_t int_least64_t;
+typedef uint64_t uint_least64_t;
+
+typedef int8_t int_fast8_t;
+typedef uint8_t uint_fast8_t;
+typedef ssize_t int_fast16_t;
+typedef size_t uint_fast16_t;
+typedef ssize_t int_fast32_t;
+typedef size_t uint_fast32_t;
+typedef int64_t int_fast64_t;
+typedef uint64_t uint_fast64_t;
+
+typedef int64_t intmax_t;
+typedef uint64_t uintmax_t;
+
+/* limits of integral types */
+
+#define INT8_MIN (-128)
+#define INT16_MIN (-32767-1)
+#define INT32_MIN (-2147483647-1)
+#define INT64_MIN (-9223372036854775807LL-1)
+
+#define INT8_MAX (127)
+#define INT16_MAX (32767)
+#define INT32_MAX (2147483647)
+#define INT64_MAX (9223372036854775807LL)
+
+#define UINT8_MAX (255)
+#define UINT16_MAX (65535)
+#define UINT32_MAX (4294967295U)
+#define UINT64_MAX (18446744073709551615ULL)
+
+#define INT_LEAST8_MIN INT8_MIN
+#define INT_LEAST16_MIN INT16_MIN
+#define INT_LEAST32_MIN INT32_MIN
+#define INT_LEAST64_MIN INT64_MIN
+
+#define INT_LEAST8_MAX INT8_MAX
+#define INT_LEAST16_MAX INT16_MAX
+#define INT_LEAST32_MAX INT32_MAX
+#define INT_LEAST64_MAX INT64_MAX
+
+#define UINT_LEAST8_MAX UINT8_MAX
+#define UINT_LEAST16_MAX UINT16_MAX
+#define UINT_LEAST32_MAX UINT32_MAX
+#define UINT_LEAST64_MAX UINT64_MAX
+
+#define SIZE_MAX ((size_t)(__LONG_MAX__) * 2 + 1)
+#define INTPTR_MIN (-__LONG_MAX__ - 1)
+#define INTPTR_MAX __LONG_MAX__
+#define PTRDIFF_MIN INTPTR_MIN
+#define PTRDIFF_MAX INTPTR_MAX
+#define UINTPTR_MAX SIZE_MAX
+
+#define INT_FAST8_MIN INT8_MIN
+#define INT_FAST16_MIN INTPTR_MIN
+#define INT_FAST32_MIN INTPTR_MIN
+#define INT_FAST64_MIN INT64_MIN
+
+#define INT_FAST8_MAX INT8_MAX
+#define INT_FAST16_MAX INTPTR_MAX
+#define INT_FAST32_MAX INTPTR_MAX
+#define INT_FAST64_MAX INT64_MAX
+
+#define UINT_FAST8_MAX UINT8_MAX
+#define UINT_FAST16_MAX SIZE_MAX
+#define UINT_FAST32_MAX SIZE_MAX
+#define UINT_FAST64_MAX UINT64_MAX
+
+#ifndef INT_MIN
+#define INT_MIN (-__INT_MAX__ - 1)
+#endif
+#ifndef INT_MAX
+#define INT_MAX __INT_MAX__
+#endif
+
+#ifndef LONG_MIN
+#define LONG_MIN (-__LONG_MAX__ - 1)
+#endif
+#ifndef LONG_MAX
+#define LONG_MAX __LONG_MAX__
+#endif
+
+#endif /* _NOLIBC_STDINT_H */
diff --git a/tools/include/nolibc/stdio.h b/tools/include/nolibc/stdio.h
new file mode 100644
index 0000000000..cae402c11e
--- /dev/null
+++ b/tools/include/nolibc/stdio.h
@@ -0,0 +1,383 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * minimal stdio function definitions for NOLIBC
+ * Copyright (C) 2017-2021 Willy Tarreau <w@1wt.eu>
+ */
+
+#ifndef _NOLIBC_STDIO_H
+#define _NOLIBC_STDIO_H
+
+#include <stdarg.h>
+
+#include "std.h"
+#include "arch.h"
+#include "errno.h"
+#include "types.h"
+#include "sys.h"
+#include "stdlib.h"
+#include "string.h"
+
+#ifndef EOF
+#define EOF (-1)
+#endif
+
+/* Buffering mode used by setvbuf. */
+#define _IOFBF 0 /* Fully buffered. */
+#define _IOLBF 1 /* Line buffered. */
+#define _IONBF 2 /* No buffering. */
+
+/* just define FILE as a non-empty type. The value of the pointer gives
+ * the FD: FILE=~fd for fd>=0 or NULL for fd<0. This way positive FILE
+ * are immediately identified as abnormal entries (i.e. possible copies
+ * of valid pointers to something else).
+ */
+typedef struct FILE {
+ char dummy[1];
+} FILE;
+
+static __attribute__((unused)) FILE* const stdin = (FILE*)(intptr_t)~STDIN_FILENO;
+static __attribute__((unused)) FILE* const stdout = (FILE*)(intptr_t)~STDOUT_FILENO;
+static __attribute__((unused)) FILE* const stderr = (FILE*)(intptr_t)~STDERR_FILENO;
+
+/* provides a FILE* equivalent of fd. The mode is ignored. */
+static __attribute__((unused))
+FILE *fdopen(int fd, const char *mode __attribute__((unused)))
+{
+ if (fd < 0) {
+ SET_ERRNO(EBADF);
+ return NULL;
+ }
+ return (FILE*)(intptr_t)~fd;
+}
+
+/* provides the fd of stream. */
+static __attribute__((unused))
+int fileno(FILE *stream)
+{
+ intptr_t i = (intptr_t)stream;
+
+ if (i >= 0) {
+ SET_ERRNO(EBADF);
+ return -1;
+ }
+ return ~i;
+}
+
+/* flush a stream. */
+static __attribute__((unused))
+int fflush(FILE *stream)
+{
+ intptr_t i = (intptr_t)stream;
+
+ /* NULL is valid here. */
+ if (i > 0) {
+ SET_ERRNO(EBADF);
+ return -1;
+ }
+
+ /* Don't do anything, nolibc does not support buffering. */
+ return 0;
+}
+
+/* flush a stream. */
+static __attribute__((unused))
+int fclose(FILE *stream)
+{
+ intptr_t i = (intptr_t)stream;
+
+ if (i >= 0) {
+ SET_ERRNO(EBADF);
+ return -1;
+ }
+
+ if (close(~i))
+ return EOF;
+
+ return 0;
+}
+
+/* getc(), fgetc(), getchar() */
+
+#define getc(stream) fgetc(stream)
+
+static __attribute__((unused))
+int fgetc(FILE* stream)
+{
+ unsigned char ch;
+
+ if (read(fileno(stream), &ch, 1) <= 0)
+ return EOF;
+ return ch;
+}
+
+static __attribute__((unused))
+int getchar(void)
+{
+ return fgetc(stdin);
+}
+
+
+/* putc(), fputc(), putchar() */
+
+#define putc(c, stream) fputc(c, stream)
+
+static __attribute__((unused))
+int fputc(int c, FILE* stream)
+{
+ unsigned char ch = c;
+
+ if (write(fileno(stream), &ch, 1) <= 0)
+ return EOF;
+ return ch;
+}
+
+static __attribute__((unused))
+int putchar(int c)
+{
+ return fputc(c, stdout);
+}
+
+
+/* fwrite(), puts(), fputs(). Note that puts() emits '\n' but not fputs(). */
+
+/* internal fwrite()-like function which only takes a size and returns 0 on
+ * success or EOF on error. It automatically retries on short writes.
+ */
+static __attribute__((unused))
+int _fwrite(const void *buf, size_t size, FILE *stream)
+{
+ ssize_t ret;
+ int fd = fileno(stream);
+
+ while (size) {
+ ret = write(fd, buf, size);
+ if (ret <= 0)
+ return EOF;
+ size -= ret;
+ buf += ret;
+ }
+ return 0;
+}
+
+static __attribute__((unused))
+size_t fwrite(const void *s, size_t size, size_t nmemb, FILE *stream)
+{
+ size_t written;
+
+ for (written = 0; written < nmemb; written++) {
+ if (_fwrite(s, size, stream) != 0)
+ break;
+ s += size;
+ }
+ return written;
+}
+
+static __attribute__((unused))
+int fputs(const char *s, FILE *stream)
+{
+ return _fwrite(s, strlen(s), stream);
+}
+
+static __attribute__((unused))
+int puts(const char *s)
+{
+ if (fputs(s, stdout) == EOF)
+ return EOF;
+ return putchar('\n');
+}
+
+
+/* fgets() */
+static __attribute__((unused))
+char *fgets(char *s, int size, FILE *stream)
+{
+ int ofs;
+ int c;
+
+ for (ofs = 0; ofs + 1 < size;) {
+ c = fgetc(stream);
+ if (c == EOF)
+ break;
+ s[ofs++] = c;
+ if (c == '\n')
+ break;
+ }
+ if (ofs < size)
+ s[ofs] = 0;
+ return ofs ? s : NULL;
+}
+
+
+/* minimal vfprintf(). It supports the following formats:
+ * - %[l*]{d,u,c,x,p}
+ * - %s
+ * - unknown modifiers are ignored.
+ */
+static __attribute__((unused))
+int vfprintf(FILE *stream, const char *fmt, va_list args)
+{
+ char escape, lpref, c;
+ unsigned long long v;
+ unsigned int written;
+ size_t len, ofs;
+ char tmpbuf[21];
+ const char *outstr;
+
+ written = ofs = escape = lpref = 0;
+ while (1) {
+ c = fmt[ofs++];
+
+ if (escape) {
+ /* we're in an escape sequence, ofs == 1 */
+ escape = 0;
+ if (c == 'c' || c == 'd' || c == 'u' || c == 'x' || c == 'p') {
+ char *out = tmpbuf;
+
+ if (c == 'p')
+ v = va_arg(args, unsigned long);
+ else if (lpref) {
+ if (lpref > 1)
+ v = va_arg(args, unsigned long long);
+ else
+ v = va_arg(args, unsigned long);
+ } else
+ v = va_arg(args, unsigned int);
+
+ if (c == 'd') {
+ /* sign-extend the value */
+ if (lpref == 0)
+ v = (long long)(int)v;
+ else if (lpref == 1)
+ v = (long long)(long)v;
+ }
+
+ switch (c) {
+ case 'c':
+ out[0] = v;
+ out[1] = 0;
+ break;
+ case 'd':
+ i64toa_r(v, out);
+ break;
+ case 'u':
+ u64toa_r(v, out);
+ break;
+ case 'p':
+ *(out++) = '0';
+ *(out++) = 'x';
+ /* fall through */
+ default: /* 'x' and 'p' above */
+ u64toh_r(v, out);
+ break;
+ }
+ outstr = tmpbuf;
+ }
+ else if (c == 's') {
+ outstr = va_arg(args, char *);
+ if (!outstr)
+ outstr="(null)";
+ }
+ else if (c == '%') {
+ /* queue it verbatim */
+ continue;
+ }
+ else {
+ /* modifiers or final 0 */
+ if (c == 'l') {
+ /* long format prefix, maintain the escape */
+ lpref++;
+ }
+ escape = 1;
+ goto do_escape;
+ }
+ len = strlen(outstr);
+ goto flush_str;
+ }
+
+ /* not an escape sequence */
+ if (c == 0 || c == '%') {
+ /* flush pending data on escape or end */
+ escape = 1;
+ lpref = 0;
+ outstr = fmt;
+ len = ofs - 1;
+ flush_str:
+ if (_fwrite(outstr, len, stream) != 0)
+ break;
+
+ written += len;
+ do_escape:
+ if (c == 0)
+ break;
+ fmt += ofs;
+ ofs = 0;
+ continue;
+ }
+
+ /* literal char, just queue it */
+ }
+ return written;
+}
+
+static __attribute__((unused))
+int vprintf(const char *fmt, va_list args)
+{
+ return vfprintf(stdout, fmt, args);
+}
+
+static __attribute__((unused, format(printf, 2, 3)))
+int fprintf(FILE *stream, const char *fmt, ...)
+{
+ va_list args;
+ int ret;
+
+ va_start(args, fmt);
+ ret = vfprintf(stream, fmt, args);
+ va_end(args);
+ return ret;
+}
+
+static __attribute__((unused, format(printf, 1, 2)))
+int printf(const char *fmt, ...)
+{
+ va_list args;
+ int ret;
+
+ va_start(args, fmt);
+ ret = vfprintf(stdout, fmt, args);
+ va_end(args);
+ return ret;
+}
+
+static __attribute__((unused))
+void perror(const char *msg)
+{
+ fprintf(stderr, "%s%serrno=%d\n", (msg && *msg) ? msg : "", (msg && *msg) ? ": " : "", errno);
+}
+
+static __attribute__((unused))
+int setvbuf(FILE *stream __attribute__((unused)),
+ char *buf __attribute__((unused)),
+ int mode,
+ size_t size __attribute__((unused)))
+{
+ /*
+ * nolibc does not support buffering so this is a nop. Just check mode
+ * is valid as required by the spec.
+ */
+ switch (mode) {
+ case _IOFBF:
+ case _IOLBF:
+ case _IONBF:
+ break;
+ default:
+ return EOF;
+ }
+
+ return 0;
+}
+
+/* make sure to include all global symbols */
+#include "nolibc.h"
+
+#endif /* _NOLIBC_STDIO_H */
diff --git a/tools/include/nolibc/stdlib.h b/tools/include/nolibc/stdlib.h
new file mode 100644
index 0000000000..bacfd35c51
--- /dev/null
+++ b/tools/include/nolibc/stdlib.h
@@ -0,0 +1,444 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * stdlib function definitions for NOLIBC
+ * Copyright (C) 2017-2021 Willy Tarreau <w@1wt.eu>
+ */
+
+#ifndef _NOLIBC_STDLIB_H
+#define _NOLIBC_STDLIB_H
+
+#include "std.h"
+#include "arch.h"
+#include "types.h"
+#include "sys.h"
+#include "string.h"
+#include <linux/auxvec.h>
+
+struct nolibc_heap {
+ size_t len;
+ char user_p[] __attribute__((__aligned__));
+};
+
+/* Buffer used to store int-to-ASCII conversions. Will only be implemented if
+ * any of the related functions is implemented. The area is large enough to
+ * store "18446744073709551615" or "-9223372036854775808" and the final zero.
+ */
+static __attribute__((unused)) char itoa_buffer[21];
+
+/*
+ * As much as possible, please keep functions alphabetically sorted.
+ */
+
+/* must be exported, as it's used by libgcc for various divide functions */
+__attribute__((weak,unused,noreturn,section(".text.nolibc_abort")))
+void abort(void)
+{
+ sys_kill(sys_getpid(), SIGABRT);
+ for (;;);
+}
+
+static __attribute__((unused))
+long atol(const char *s)
+{
+ unsigned long ret = 0;
+ unsigned long d;
+ int neg = 0;
+
+ if (*s == '-') {
+ neg = 1;
+ s++;
+ }
+
+ while (1) {
+ d = (*s++) - '0';
+ if (d > 9)
+ break;
+ ret *= 10;
+ ret += d;
+ }
+
+ return neg ? -ret : ret;
+}
+
+static __attribute__((unused))
+int atoi(const char *s)
+{
+ return atol(s);
+}
+
+static __attribute__((unused))
+void free(void *ptr)
+{
+ struct nolibc_heap *heap;
+
+ if (!ptr)
+ return;
+
+ heap = container_of(ptr, struct nolibc_heap, user_p);
+ munmap(heap, heap->len);
+}
+
+/* getenv() tries to find the environment variable named <name> in the
+ * environment array pointed to by global variable "environ" which must be
+ * declared as a char **, and must be terminated by a NULL (it is recommended
+ * to set this variable to the "envp" argument of main()). If the requested
+ * environment variable exists its value is returned otherwise NULL is
+ * returned.
+ */
+static __attribute__((unused))
+char *getenv(const char *name)
+{
+ int idx, i;
+
+ if (environ) {
+ for (idx = 0; environ[idx]; idx++) {
+ for (i = 0; name[i] && name[i] == environ[idx][i];)
+ i++;
+ if (!name[i] && environ[idx][i] == '=')
+ return &environ[idx][i+1];
+ }
+ }
+ return NULL;
+}
+
+static __attribute__((unused))
+unsigned long getauxval(unsigned long type)
+{
+ const unsigned long *auxv = _auxv;
+ unsigned long ret;
+
+ if (!auxv)
+ return 0;
+
+ while (1) {
+ if (!auxv[0] && !auxv[1]) {
+ ret = 0;
+ break;
+ }
+
+ if (auxv[0] == type) {
+ ret = auxv[1];
+ break;
+ }
+
+ auxv += 2;
+ }
+
+ return ret;
+}
+
+static __attribute__((unused))
+void *malloc(size_t len)
+{
+ struct nolibc_heap *heap;
+
+ /* Always allocate memory with size multiple of 4096. */
+ len = sizeof(*heap) + len;
+ len = (len + 4095UL) & -4096UL;
+ heap = mmap(NULL, len, PROT_READ|PROT_WRITE, MAP_ANONYMOUS|MAP_PRIVATE,
+ -1, 0);
+ if (__builtin_expect(heap == MAP_FAILED, 0))
+ return NULL;
+
+ heap->len = len;
+ return heap->user_p;
+}
+
+static __attribute__((unused))
+void *calloc(size_t size, size_t nmemb)
+{
+ size_t x = size * nmemb;
+
+ if (__builtin_expect(size && ((x / size) != nmemb), 0)) {
+ SET_ERRNO(ENOMEM);
+ return NULL;
+ }
+
+ /*
+ * No need to zero the heap, the MAP_ANONYMOUS in malloc()
+ * already does it.
+ */
+ return malloc(x);
+}
+
+static __attribute__((unused))
+void *realloc(void *old_ptr, size_t new_size)
+{
+ struct nolibc_heap *heap;
+ size_t user_p_len;
+ void *ret;
+
+ if (!old_ptr)
+ return malloc(new_size);
+
+ heap = container_of(old_ptr, struct nolibc_heap, user_p);
+ user_p_len = heap->len - sizeof(*heap);
+ /*
+ * Don't realloc() if @user_p_len >= @new_size, this block of
+ * memory is still enough to handle the @new_size. Just return
+ * the same pointer.
+ */
+ if (user_p_len >= new_size)
+ return old_ptr;
+
+ ret = malloc(new_size);
+ if (__builtin_expect(!ret, 0))
+ return NULL;
+
+ memcpy(ret, heap->user_p, heap->len);
+ munmap(heap, heap->len);
+ return ret;
+}
+
+/* Converts the unsigned long integer <in> to its hex representation into
+ * buffer <buffer>, which must be long enough to store the number and the
+ * trailing zero (17 bytes for "ffffffffffffffff" or 9 for "ffffffff"). The
+ * buffer is filled from the first byte, and the number of characters emitted
+ * (not counting the trailing zero) is returned. The function is constructed
+ * in a way to optimize the code size and avoid any divide that could add a
+ * dependency on large external functions.
+ */
+static __attribute__((unused))
+int utoh_r(unsigned long in, char *buffer)
+{
+ signed char pos = (~0UL > 0xfffffffful) ? 60 : 28;
+ int digits = 0;
+ int dig;
+
+ do {
+ dig = in >> pos;
+ in -= (uint64_t)dig << pos;
+ pos -= 4;
+ if (dig || digits || pos < 0) {
+ if (dig > 9)
+ dig += 'a' - '0' - 10;
+ buffer[digits++] = '0' + dig;
+ }
+ } while (pos >= 0);
+
+ buffer[digits] = 0;
+ return digits;
+}
+
+/* converts unsigned long <in> to an hex string using the static itoa_buffer
+ * and returns the pointer to that string.
+ */
+static __inline__ __attribute__((unused))
+char *utoh(unsigned long in)
+{
+ utoh_r(in, itoa_buffer);
+ return itoa_buffer;
+}
+
+/* Converts the unsigned long integer <in> to its string representation into
+ * buffer <buffer>, which must be long enough to store the number and the
+ * trailing zero (21 bytes for 18446744073709551615 in 64-bit, 11 for
+ * 4294967295 in 32-bit). The buffer is filled from the first byte, and the
+ * number of characters emitted (not counting the trailing zero) is returned.
+ * The function is constructed in a way to optimize the code size and avoid
+ * any divide that could add a dependency on large external functions.
+ */
+static __attribute__((unused))
+int utoa_r(unsigned long in, char *buffer)
+{
+ unsigned long lim;
+ int digits = 0;
+ int pos = (~0UL > 0xfffffffful) ? 19 : 9;
+ int dig;
+
+ do {
+ for (dig = 0, lim = 1; dig < pos; dig++)
+ lim *= 10;
+
+ if (digits || in >= lim || !pos) {
+ for (dig = 0; in >= lim; dig++)
+ in -= lim;
+ buffer[digits++] = '0' + dig;
+ }
+ } while (pos--);
+
+ buffer[digits] = 0;
+ return digits;
+}
+
+/* Converts the signed long integer <in> to its string representation into
+ * buffer <buffer>, which must be long enough to store the number and the
+ * trailing zero (21 bytes for -9223372036854775808 in 64-bit, 12 for
+ * -2147483648 in 32-bit). The buffer is filled from the first byte, and the
+ * number of characters emitted (not counting the trailing zero) is returned.
+ */
+static __attribute__((unused))
+int itoa_r(long in, char *buffer)
+{
+ char *ptr = buffer;
+ int len = 0;
+
+ if (in < 0) {
+ in = -in;
+ *(ptr++) = '-';
+ len++;
+ }
+ len += utoa_r(in, ptr);
+ return len;
+}
+
+/* for historical compatibility, same as above but returns the pointer to the
+ * buffer.
+ */
+static __inline__ __attribute__((unused))
+char *ltoa_r(long in, char *buffer)
+{
+ itoa_r(in, buffer);
+ return buffer;
+}
+
+/* converts long integer <in> to a string using the static itoa_buffer and
+ * returns the pointer to that string.
+ */
+static __inline__ __attribute__((unused))
+char *itoa(long in)
+{
+ itoa_r(in, itoa_buffer);
+ return itoa_buffer;
+}
+
+/* converts long integer <in> to a string using the static itoa_buffer and
+ * returns the pointer to that string. Same as above, for compatibility.
+ */
+static __inline__ __attribute__((unused))
+char *ltoa(long in)
+{
+ itoa_r(in, itoa_buffer);
+ return itoa_buffer;
+}
+
+/* converts unsigned long integer <in> to a string using the static itoa_buffer
+ * and returns the pointer to that string.
+ */
+static __inline__ __attribute__((unused))
+char *utoa(unsigned long in)
+{
+ utoa_r(in, itoa_buffer);
+ return itoa_buffer;
+}
+
+/* Converts the unsigned 64-bit integer <in> to its hex representation into
+ * buffer <buffer>, which must be long enough to store the number and the
+ * trailing zero (17 bytes for "ffffffffffffffff"). The buffer is filled from
+ * the first byte, and the number of characters emitted (not counting the
+ * trailing zero) is returned. The function is constructed in a way to optimize
+ * the code size and avoid any divide that could add a dependency on large
+ * external functions.
+ */
+static __attribute__((unused))
+int u64toh_r(uint64_t in, char *buffer)
+{
+ signed char pos = 60;
+ int digits = 0;
+ int dig;
+
+ do {
+ if (sizeof(long) >= 8) {
+ dig = (in >> pos) & 0xF;
+ } else {
+ /* 32-bit platforms: avoid a 64-bit shift */
+ uint32_t d = (pos >= 32) ? (in >> 32) : in;
+ dig = (d >> (pos & 31)) & 0xF;
+ }
+ if (dig > 9)
+ dig += 'a' - '0' - 10;
+ pos -= 4;
+ if (dig || digits || pos < 0)
+ buffer[digits++] = '0' + dig;
+ } while (pos >= 0);
+
+ buffer[digits] = 0;
+ return digits;
+}
+
+/* converts uint64_t <in> to an hex string using the static itoa_buffer and
+ * returns the pointer to that string.
+ */
+static __inline__ __attribute__((unused))
+char *u64toh(uint64_t in)
+{
+ u64toh_r(in, itoa_buffer);
+ return itoa_buffer;
+}
+
+/* Converts the unsigned 64-bit integer <in> to its string representation into
+ * buffer <buffer>, which must be long enough to store the number and the
+ * trailing zero (21 bytes for 18446744073709551615). The buffer is filled from
+ * the first byte, and the number of characters emitted (not counting the
+ * trailing zero) is returned. The function is constructed in a way to optimize
+ * the code size and avoid any divide that could add a dependency on large
+ * external functions.
+ */
+static __attribute__((unused))
+int u64toa_r(uint64_t in, char *buffer)
+{
+ unsigned long long lim;
+ int digits = 0;
+ int pos = 19; /* start with the highest possible digit */
+ int dig;
+
+ do {
+ for (dig = 0, lim = 1; dig < pos; dig++)
+ lim *= 10;
+
+ if (digits || in >= lim || !pos) {
+ for (dig = 0; in >= lim; dig++)
+ in -= lim;
+ buffer[digits++] = '0' + dig;
+ }
+ } while (pos--);
+
+ buffer[digits] = 0;
+ return digits;
+}
+
+/* Converts the signed 64-bit integer <in> to its string representation into
+ * buffer <buffer>, which must be long enough to store the number and the
+ * trailing zero (21 bytes for -9223372036854775808). The buffer is filled from
+ * the first byte, and the number of characters emitted (not counting the
+ * trailing zero) is returned.
+ */
+static __attribute__((unused))
+int i64toa_r(int64_t in, char *buffer)
+{
+ char *ptr = buffer;
+ int len = 0;
+
+ if (in < 0) {
+ in = -in;
+ *(ptr++) = '-';
+ len++;
+ }
+ len += u64toa_r(in, ptr);
+ return len;
+}
+
+/* converts int64_t <in> to a string using the static itoa_buffer and returns
+ * the pointer to that string.
+ */
+static __inline__ __attribute__((unused))
+char *i64toa(int64_t in)
+{
+ i64toa_r(in, itoa_buffer);
+ return itoa_buffer;
+}
+
+/* converts uint64_t <in> to a string using the static itoa_buffer and returns
+ * the pointer to that string.
+ */
+static __inline__ __attribute__((unused))
+char *u64toa(uint64_t in)
+{
+ u64toa_r(in, itoa_buffer);
+ return itoa_buffer;
+}
+
+/* make sure to include all global symbols */
+#include "nolibc.h"
+
+#endif /* _NOLIBC_STDLIB_H */
diff --git a/tools/include/nolibc/string.h b/tools/include/nolibc/string.h
new file mode 100644
index 0000000000..0c2e06c7c4
--- /dev/null
+++ b/tools/include/nolibc/string.h
@@ -0,0 +1,294 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * string function definitions for NOLIBC
+ * Copyright (C) 2017-2021 Willy Tarreau <w@1wt.eu>
+ */
+
+#ifndef _NOLIBC_STRING_H
+#define _NOLIBC_STRING_H
+
+#include "std.h"
+
+static void *malloc(size_t len);
+
+/*
+ * As much as possible, please keep functions alphabetically sorted.
+ */
+
+static __attribute__((unused))
+int memcmp(const void *s1, const void *s2, size_t n)
+{
+ size_t ofs = 0;
+ int c1 = 0;
+
+ while (ofs < n && !(c1 = ((unsigned char *)s1)[ofs] - ((unsigned char *)s2)[ofs])) {
+ ofs++;
+ }
+ return c1;
+}
+
+static __attribute__((unused))
+void *_nolibc_memcpy_up(void *dst, const void *src, size_t len)
+{
+ size_t pos = 0;
+
+ while (pos < len) {
+ ((char *)dst)[pos] = ((const char *)src)[pos];
+ pos++;
+ }
+ return dst;
+}
+
+static __attribute__((unused))
+void *_nolibc_memcpy_down(void *dst, const void *src, size_t len)
+{
+ while (len) {
+ len--;
+ ((char *)dst)[len] = ((const char *)src)[len];
+ }
+ return dst;
+}
+
+/* might be ignored by the compiler without -ffreestanding, then found as
+ * missing.
+ */
+__attribute__((weak,unused,section(".text.nolibc_memmove")))
+void *memmove(void *dst, const void *src, size_t len)
+{
+ size_t dir, pos;
+
+ pos = len;
+ dir = -1;
+
+ if (dst < src) {
+ pos = -1;
+ dir = 1;
+ }
+
+ while (len) {
+ pos += dir;
+ ((char *)dst)[pos] = ((const char *)src)[pos];
+ len--;
+ }
+ return dst;
+}
+
+/* must be exported, as it's used by libgcc on ARM */
+__attribute__((weak,unused,section(".text.nolibc_memcpy")))
+void *memcpy(void *dst, const void *src, size_t len)
+{
+ return _nolibc_memcpy_up(dst, src, len);
+}
+
+/* might be ignored by the compiler without -ffreestanding, then found as
+ * missing.
+ */
+__attribute__((weak,unused,section(".text.nolibc_memset")))
+void *memset(void *dst, int b, size_t len)
+{
+ char *p = dst;
+
+ while (len--) {
+ /* prevent gcc from recognizing memset() here */
+ __asm__ volatile("");
+ *(p++) = b;
+ }
+ return dst;
+}
+
+static __attribute__((unused))
+char *strchr(const char *s, int c)
+{
+ while (*s) {
+ if (*s == (char)c)
+ return (char *)s;
+ s++;
+ }
+ return NULL;
+}
+
+static __attribute__((unused))
+int strcmp(const char *a, const char *b)
+{
+ unsigned int c;
+ int diff;
+
+ while (!(diff = (unsigned char)*a++ - (c = (unsigned char)*b++)) && c)
+ ;
+ return diff;
+}
+
+static __attribute__((unused))
+char *strcpy(char *dst, const char *src)
+{
+ char *ret = dst;
+
+ while ((*dst++ = *src++));
+ return ret;
+}
+
+/* this function is only used with arguments that are not constants or when
+ * it's not known because optimizations are disabled. Note that gcc 12
+ * recognizes an strlen() pattern and replaces it with a jump to strlen(),
+ * thus itself, hence the asm() statement below that's meant to disable this
+ * confusing practice.
+ */
+static __attribute__((unused))
+size_t strlen(const char *str)
+{
+ size_t len;
+
+ for (len = 0; str[len]; len++)
+ __asm__("");
+ return len;
+}
+
+/* do not trust __builtin_constant_p() at -O0, as clang will emit a test and
+ * the two branches, then will rely on an external definition of strlen().
+ */
+#if defined(__OPTIMIZE__)
+#define nolibc_strlen(x) strlen(x)
+#define strlen(str) ({ \
+ __builtin_constant_p((str)) ? \
+ __builtin_strlen((str)) : \
+ nolibc_strlen((str)); \
+})
+#endif
+
+static __attribute__((unused))
+size_t strnlen(const char *str, size_t maxlen)
+{
+ size_t len;
+
+ for (len = 0; (len < maxlen) && str[len]; len++);
+ return len;
+}
+
+static __attribute__((unused))
+char *strdup(const char *str)
+{
+ size_t len;
+ char *ret;
+
+ len = strlen(str);
+ ret = malloc(len + 1);
+ if (__builtin_expect(ret != NULL, 1))
+ memcpy(ret, str, len + 1);
+
+ return ret;
+}
+
+static __attribute__((unused))
+char *strndup(const char *str, size_t maxlen)
+{
+ size_t len;
+ char *ret;
+
+ len = strnlen(str, maxlen);
+ ret = malloc(len + 1);
+ if (__builtin_expect(ret != NULL, 1)) {
+ memcpy(ret, str, len);
+ ret[len] = '\0';
+ }
+
+ return ret;
+}
+
+static __attribute__((unused))
+size_t strlcat(char *dst, const char *src, size_t size)
+{
+ size_t len;
+ char c;
+
+ for (len = 0; dst[len]; len++)
+ ;
+
+ for (;;) {
+ c = *src;
+ if (len < size)
+ dst[len] = c;
+ if (!c)
+ break;
+ len++;
+ src++;
+ }
+
+ return len;
+}
+
+static __attribute__((unused))
+size_t strlcpy(char *dst, const char *src, size_t size)
+{
+ size_t len;
+ char c;
+
+ for (len = 0;;) {
+ c = src[len];
+ if (len < size)
+ dst[len] = c;
+ if (!c)
+ break;
+ len++;
+ }
+ return len;
+}
+
+static __attribute__((unused))
+char *strncat(char *dst, const char *src, size_t size)
+{
+ char *orig = dst;
+
+ while (*dst)
+ dst++;
+
+ while (size && (*dst = *src)) {
+ src++;
+ dst++;
+ size--;
+ }
+
+ *dst = 0;
+ return orig;
+}
+
+static __attribute__((unused))
+int strncmp(const char *a, const char *b, size_t size)
+{
+ unsigned int c;
+ int diff = 0;
+
+ while (size-- &&
+ !(diff = (unsigned char)*a++ - (c = (unsigned char)*b++)) && c)
+ ;
+
+ return diff;
+}
+
+static __attribute__((unused))
+char *strncpy(char *dst, const char *src, size_t size)
+{
+ size_t len;
+
+ for (len = 0; len < size; len++)
+ if ((dst[len] = *src))
+ src++;
+ return dst;
+}
+
+static __attribute__((unused))
+char *strrchr(const char *s, int c)
+{
+ const char *ret = NULL;
+
+ while (*s) {
+ if (*s == (char)c)
+ ret = s;
+ s++;
+ }
+ return (char *)ret;
+}
+
+/* make sure to include all global symbols */
+#include "nolibc.h"
+
+#endif /* _NOLIBC_STRING_H */
diff --git a/tools/include/nolibc/sys.h b/tools/include/nolibc/sys.h
new file mode 100644
index 0000000000..fdb6bd6c0e
--- /dev/null
+++ b/tools/include/nolibc/sys.h
@@ -0,0 +1,1190 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * Syscall definitions for NOLIBC (those in man(2))
+ * Copyright (C) 2017-2021 Willy Tarreau <w@1wt.eu>
+ */
+
+#ifndef _NOLIBC_SYS_H
+#define _NOLIBC_SYS_H
+
+#include <stdarg.h>
+#include "std.h"
+
+/* system includes */
+#include <asm/unistd.h>
+#include <asm/signal.h> /* for SIGCHLD */
+#include <asm/ioctls.h>
+#include <asm/mman.h>
+#include <linux/fs.h>
+#include <linux/loop.h>
+#include <linux/time.h>
+#include <linux/auxvec.h>
+#include <linux/fcntl.h> /* for O_* and AT_* */
+#include <linux/stat.h> /* for statx() */
+#include <linux/prctl.h>
+
+#include "arch.h"
+#include "errno.h"
+#include "types.h"
+
+
+/* Syscall return helper: takes the syscall value in argument and checks for an
+ * error in it. This may only be used with signed returns (int or long), but
+ * not with pointers. An error is any value < 0. When an error is encountered,
+ * -ret is set into errno and -1 is returned. Otherwise the returned value is
+ * passed as-is with its type preserved.
+ */
+
+#define __sysret(arg) \
+({ \
+ __typeof__(arg) __sysret_arg = (arg); \
+ (__sysret_arg < 0) /* error ? */ \
+ ? (({ SET_ERRNO(-__sysret_arg); }), -1) /* ret -1 with errno = -arg */ \
+ : __sysret_arg; /* return original value */ \
+})
+
+
+/* Functions in this file only describe syscalls. They're declared static so
+ * that the compiler usually decides to inline them while still being allowed
+ * to pass a pointer to one of their instances. Each syscall exists in two
+ * versions:
+ * - the "internal" ones, which matches the raw syscall interface at the
+ * kernel level, which may sometimes slightly differ from the documented
+ * libc-level ones. For example most of them return either a valid value
+ * or -errno. All of these are prefixed with "sys_". They may be called
+ * by non-portable applications if desired.
+ *
+ * - the "exported" ones, whose interface must closely match the one
+ * documented in man(2), that applications are supposed to expect. These
+ * ones rely on the internal ones, and set errno.
+ *
+ * Each syscall will be defined with the two functions, sorted in alphabetical
+ * order applied to the exported names.
+ *
+ * In case of doubt about the relevance of a function here, only those which
+ * set errno should be defined here. Wrappers like those appearing in man(3)
+ * should not be placed here.
+ */
+
+
+/*
+ * int brk(void *addr);
+ * void *sbrk(intptr_t inc)
+ */
+
+static __attribute__((unused))
+void *sys_brk(void *addr)
+{
+ return (void *)my_syscall1(__NR_brk, addr);
+}
+
+static __attribute__((unused))
+int brk(void *addr)
+{
+ void *ret = sys_brk(addr);
+
+ if (!ret) {
+ SET_ERRNO(ENOMEM);
+ return -1;
+ }
+ return 0;
+}
+
+static __attribute__((unused))
+void *sbrk(intptr_t inc)
+{
+ /* first call to find current end */
+ void *ret = sys_brk(0);
+
+ if (ret && sys_brk(ret + inc) == ret + inc)
+ return ret + inc;
+
+ SET_ERRNO(ENOMEM);
+ return (void *)-1;
+}
+
+
+/*
+ * int chdir(const char *path);
+ */
+
+static __attribute__((unused))
+int sys_chdir(const char *path)
+{
+ return my_syscall1(__NR_chdir, path);
+}
+
+static __attribute__((unused))
+int chdir(const char *path)
+{
+ return __sysret(sys_chdir(path));
+}
+
+
+/*
+ * int chmod(const char *path, mode_t mode);
+ */
+
+static __attribute__((unused))
+int sys_chmod(const char *path, mode_t mode)
+{
+#ifdef __NR_fchmodat
+ return my_syscall4(__NR_fchmodat, AT_FDCWD, path, mode, 0);
+#elif defined(__NR_chmod)
+ return my_syscall2(__NR_chmod, path, mode);
+#else
+ return -ENOSYS;
+#endif
+}
+
+static __attribute__((unused))
+int chmod(const char *path, mode_t mode)
+{
+ return __sysret(sys_chmod(path, mode));
+}
+
+
+/*
+ * int chown(const char *path, uid_t owner, gid_t group);
+ */
+
+static __attribute__((unused))
+int sys_chown(const char *path, uid_t owner, gid_t group)
+{
+#ifdef __NR_fchownat
+ return my_syscall5(__NR_fchownat, AT_FDCWD, path, owner, group, 0);
+#elif defined(__NR_chown)
+ return my_syscall3(__NR_chown, path, owner, group);
+#else
+ return -ENOSYS;
+#endif
+}
+
+static __attribute__((unused))
+int chown(const char *path, uid_t owner, gid_t group)
+{
+ return __sysret(sys_chown(path, owner, group));
+}
+
+
+/*
+ * int chroot(const char *path);
+ */
+
+static __attribute__((unused))
+int sys_chroot(const char *path)
+{
+ return my_syscall1(__NR_chroot, path);
+}
+
+static __attribute__((unused))
+int chroot(const char *path)
+{
+ return __sysret(sys_chroot(path));
+}
+
+
+/*
+ * int close(int fd);
+ */
+
+static __attribute__((unused))
+int sys_close(int fd)
+{
+ return my_syscall1(__NR_close, fd);
+}
+
+static __attribute__((unused))
+int close(int fd)
+{
+ return __sysret(sys_close(fd));
+}
+
+
+/*
+ * int dup(int fd);
+ */
+
+static __attribute__((unused))
+int sys_dup(int fd)
+{
+ return my_syscall1(__NR_dup, fd);
+}
+
+static __attribute__((unused))
+int dup(int fd)
+{
+ return __sysret(sys_dup(fd));
+}
+
+
+/*
+ * int dup2(int old, int new);
+ */
+
+static __attribute__((unused))
+int sys_dup2(int old, int new)
+{
+#ifdef __NR_dup3
+ return my_syscall3(__NR_dup3, old, new, 0);
+#elif defined(__NR_dup2)
+ return my_syscall2(__NR_dup2, old, new);
+#else
+ return -ENOSYS;
+#endif
+}
+
+static __attribute__((unused))
+int dup2(int old, int new)
+{
+ return __sysret(sys_dup2(old, new));
+}
+
+
+/*
+ * int dup3(int old, int new, int flags);
+ */
+
+#ifdef __NR_dup3
+static __attribute__((unused))
+int sys_dup3(int old, int new, int flags)
+{
+ return my_syscall3(__NR_dup3, old, new, flags);
+}
+
+static __attribute__((unused))
+int dup3(int old, int new, int flags)
+{
+ return __sysret(sys_dup3(old, new, flags));
+}
+#endif
+
+
+/*
+ * int execve(const char *filename, char *const argv[], char *const envp[]);
+ */
+
+static __attribute__((unused))
+int sys_execve(const char *filename, char *const argv[], char *const envp[])
+{
+ return my_syscall3(__NR_execve, filename, argv, envp);
+}
+
+static __attribute__((unused))
+int execve(const char *filename, char *const argv[], char *const envp[])
+{
+ return __sysret(sys_execve(filename, argv, envp));
+}
+
+
+/*
+ * void exit(int status);
+ */
+
+static __attribute__((noreturn,unused))
+void sys_exit(int status)
+{
+ my_syscall1(__NR_exit, status & 255);
+ while(1); /* shut the "noreturn" warnings. */
+}
+
+static __attribute__((noreturn,unused))
+void exit(int status)
+{
+ sys_exit(status);
+}
+
+
+/*
+ * pid_t fork(void);
+ */
+
+#ifndef sys_fork
+static __attribute__((unused))
+pid_t sys_fork(void)
+{
+#ifdef __NR_clone
+ /* note: some archs only have clone() and not fork(). Different archs
+ * have a different API, but most archs have the flags on first arg and
+ * will not use the rest with no other flag.
+ */
+ return my_syscall5(__NR_clone, SIGCHLD, 0, 0, 0, 0);
+#elif defined(__NR_fork)
+ return my_syscall0(__NR_fork);
+#else
+ return -ENOSYS;
+#endif
+}
+#endif
+
+static __attribute__((unused))
+pid_t fork(void)
+{
+ return __sysret(sys_fork());
+}
+
+
+/*
+ * int fsync(int fd);
+ */
+
+static __attribute__((unused))
+int sys_fsync(int fd)
+{
+ return my_syscall1(__NR_fsync, fd);
+}
+
+static __attribute__((unused))
+int fsync(int fd)
+{
+ return __sysret(sys_fsync(fd));
+}
+
+
+/*
+ * int getdents64(int fd, struct linux_dirent64 *dirp, int count);
+ */
+
+static __attribute__((unused))
+int sys_getdents64(int fd, struct linux_dirent64 *dirp, int count)
+{
+ return my_syscall3(__NR_getdents64, fd, dirp, count);
+}
+
+static __attribute__((unused))
+int getdents64(int fd, struct linux_dirent64 *dirp, int count)
+{
+ return __sysret(sys_getdents64(fd, dirp, count));
+}
+
+
+/*
+ * uid_t geteuid(void);
+ */
+
+static __attribute__((unused))
+uid_t sys_geteuid(void)
+{
+#ifdef __NR_geteuid32
+ return my_syscall0(__NR_geteuid32);
+#else
+ return my_syscall0(__NR_geteuid);
+#endif
+}
+
+static __attribute__((unused))
+uid_t geteuid(void)
+{
+ return sys_geteuid();
+}
+
+
+/*
+ * pid_t getpgid(pid_t pid);
+ */
+
+static __attribute__((unused))
+pid_t sys_getpgid(pid_t pid)
+{
+ return my_syscall1(__NR_getpgid, pid);
+}
+
+static __attribute__((unused))
+pid_t getpgid(pid_t pid)
+{
+ return __sysret(sys_getpgid(pid));
+}
+
+
+/*
+ * pid_t getpgrp(void);
+ */
+
+static __attribute__((unused))
+pid_t sys_getpgrp(void)
+{
+ return sys_getpgid(0);
+}
+
+static __attribute__((unused))
+pid_t getpgrp(void)
+{
+ return sys_getpgrp();
+}
+
+
+/*
+ * pid_t getpid(void);
+ */
+
+static __attribute__((unused))
+pid_t sys_getpid(void)
+{
+ return my_syscall0(__NR_getpid);
+}
+
+static __attribute__((unused))
+pid_t getpid(void)
+{
+ return sys_getpid();
+}
+
+
+/*
+ * pid_t getppid(void);
+ */
+
+static __attribute__((unused))
+pid_t sys_getppid(void)
+{
+ return my_syscall0(__NR_getppid);
+}
+
+static __attribute__((unused))
+pid_t getppid(void)
+{
+ return sys_getppid();
+}
+
+
+/*
+ * pid_t gettid(void);
+ */
+
+static __attribute__((unused))
+pid_t sys_gettid(void)
+{
+ return my_syscall0(__NR_gettid);
+}
+
+static __attribute__((unused))
+pid_t gettid(void)
+{
+ return sys_gettid();
+}
+
+static unsigned long getauxval(unsigned long key);
+
+/*
+ * int getpagesize(void);
+ */
+
+static __attribute__((unused))
+int getpagesize(void)
+{
+ return __sysret((int)getauxval(AT_PAGESZ) ?: -ENOENT);
+}
+
+
+/*
+ * int gettimeofday(struct timeval *tv, struct timezone *tz);
+ */
+
+static __attribute__((unused))
+int sys_gettimeofday(struct timeval *tv, struct timezone *tz)
+{
+#ifdef __NR_gettimeofday
+ return my_syscall2(__NR_gettimeofday, tv, tz);
+#else
+ return -ENOSYS;
+#endif
+}
+
+static __attribute__((unused))
+int gettimeofday(struct timeval *tv, struct timezone *tz)
+{
+ return __sysret(sys_gettimeofday(tv, tz));
+}
+
+
+/*
+ * uid_t getuid(void);
+ */
+
+static __attribute__((unused))
+uid_t sys_getuid(void)
+{
+#ifdef __NR_getuid32
+ return my_syscall0(__NR_getuid32);
+#else
+ return my_syscall0(__NR_getuid);
+#endif
+}
+
+static __attribute__((unused))
+uid_t getuid(void)
+{
+ return sys_getuid();
+}
+
+
+/*
+ * int ioctl(int fd, unsigned long req, void *value);
+ */
+
+static __attribute__((unused))
+int sys_ioctl(int fd, unsigned long req, void *value)
+{
+ return my_syscall3(__NR_ioctl, fd, req, value);
+}
+
+static __attribute__((unused))
+int ioctl(int fd, unsigned long req, void *value)
+{
+ return __sysret(sys_ioctl(fd, req, value));
+}
+
+/*
+ * int kill(pid_t pid, int signal);
+ */
+
+static __attribute__((unused))
+int sys_kill(pid_t pid, int signal)
+{
+ return my_syscall2(__NR_kill, pid, signal);
+}
+
+static __attribute__((unused))
+int kill(pid_t pid, int signal)
+{
+ return __sysret(sys_kill(pid, signal));
+}
+
+
+/*
+ * int link(const char *old, const char *new);
+ */
+
+static __attribute__((unused))
+int sys_link(const char *old, const char *new)
+{
+#ifdef __NR_linkat
+ return my_syscall5(__NR_linkat, AT_FDCWD, old, AT_FDCWD, new, 0);
+#elif defined(__NR_link)
+ return my_syscall2(__NR_link, old, new);
+#else
+ return -ENOSYS;
+#endif
+}
+
+static __attribute__((unused))
+int link(const char *old, const char *new)
+{
+ return __sysret(sys_link(old, new));
+}
+
+
+/*
+ * off_t lseek(int fd, off_t offset, int whence);
+ */
+
+static __attribute__((unused))
+off_t sys_lseek(int fd, off_t offset, int whence)
+{
+#ifdef __NR_lseek
+ return my_syscall3(__NR_lseek, fd, offset, whence);
+#else
+ return -ENOSYS;
+#endif
+}
+
+static __attribute__((unused))
+off_t lseek(int fd, off_t offset, int whence)
+{
+ return __sysret(sys_lseek(fd, offset, whence));
+}
+
+
+/*
+ * int mkdir(const char *path, mode_t mode);
+ */
+
+static __attribute__((unused))
+int sys_mkdir(const char *path, mode_t mode)
+{
+#ifdef __NR_mkdirat
+ return my_syscall3(__NR_mkdirat, AT_FDCWD, path, mode);
+#elif defined(__NR_mkdir)
+ return my_syscall2(__NR_mkdir, path, mode);
+#else
+ return -ENOSYS;
+#endif
+}
+
+static __attribute__((unused))
+int mkdir(const char *path, mode_t mode)
+{
+ return __sysret(sys_mkdir(path, mode));
+}
+
+/*
+ * int rmdir(const char *path);
+ */
+
+static __attribute__((unused))
+int sys_rmdir(const char *path)
+{
+#ifdef __NR_rmdir
+ return my_syscall1(__NR_rmdir, path);
+#elif defined(__NR_unlinkat)
+ return my_syscall3(__NR_unlinkat, AT_FDCWD, path, AT_REMOVEDIR);
+#else
+ return -ENOSYS;
+#endif
+}
+
+static __attribute__((unused))
+int rmdir(const char *path)
+{
+ return __sysret(sys_rmdir(path));
+}
+
+
+/*
+ * int mknod(const char *path, mode_t mode, dev_t dev);
+ */
+
+static __attribute__((unused))
+long sys_mknod(const char *path, mode_t mode, dev_t dev)
+{
+#ifdef __NR_mknodat
+ return my_syscall4(__NR_mknodat, AT_FDCWD, path, mode, dev);
+#elif defined(__NR_mknod)
+ return my_syscall3(__NR_mknod, path, mode, dev);
+#else
+ return -ENOSYS;
+#endif
+}
+
+static __attribute__((unused))
+int mknod(const char *path, mode_t mode, dev_t dev)
+{
+ return __sysret(sys_mknod(path, mode, dev));
+}
+
+#ifndef sys_mmap
+static __attribute__((unused))
+void *sys_mmap(void *addr, size_t length, int prot, int flags, int fd,
+ off_t offset)
+{
+ int n;
+
+#if defined(__NR_mmap2)
+ n = __NR_mmap2;
+ offset >>= 12;
+#else
+ n = __NR_mmap;
+#endif
+
+ return (void *)my_syscall6(n, addr, length, prot, flags, fd, offset);
+}
+#endif
+
+/* Note that on Linux, MAP_FAILED is -1 so we can use the generic __sysret()
+ * which returns -1 upon error and still satisfy user land that checks for
+ * MAP_FAILED.
+ */
+
+static __attribute__((unused))
+void *mmap(void *addr, size_t length, int prot, int flags, int fd, off_t offset)
+{
+ void *ret = sys_mmap(addr, length, prot, flags, fd, offset);
+
+ if ((unsigned long)ret >= -4095UL) {
+ SET_ERRNO(-(long)ret);
+ ret = MAP_FAILED;
+ }
+ return ret;
+}
+
+static __attribute__((unused))
+int sys_munmap(void *addr, size_t length)
+{
+ return my_syscall2(__NR_munmap, addr, length);
+}
+
+static __attribute__((unused))
+int munmap(void *addr, size_t length)
+{
+ return __sysret(sys_munmap(addr, length));
+}
+
+/*
+ * int mount(const char *source, const char *target,
+ * const char *fstype, unsigned long flags,
+ * const void *data);
+ */
+static __attribute__((unused))
+int sys_mount(const char *src, const char *tgt, const char *fst,
+ unsigned long flags, const void *data)
+{
+ return my_syscall5(__NR_mount, src, tgt, fst, flags, data);
+}
+
+static __attribute__((unused))
+int mount(const char *src, const char *tgt,
+ const char *fst, unsigned long flags,
+ const void *data)
+{
+ return __sysret(sys_mount(src, tgt, fst, flags, data));
+}
+
+
+/*
+ * int open(const char *path, int flags[, mode_t mode]);
+ */
+
+static __attribute__((unused))
+int sys_open(const char *path, int flags, mode_t mode)
+{
+#ifdef __NR_openat
+ return my_syscall4(__NR_openat, AT_FDCWD, path, flags, mode);
+#elif defined(__NR_open)
+ return my_syscall3(__NR_open, path, flags, mode);
+#else
+ return -ENOSYS;
+#endif
+}
+
+static __attribute__((unused))
+int open(const char *path, int flags, ...)
+{
+ mode_t mode = 0;
+
+ if (flags & O_CREAT) {
+ va_list args;
+
+ va_start(args, flags);
+ mode = va_arg(args, int);
+ va_end(args);
+ }
+
+ return __sysret(sys_open(path, flags, mode));
+}
+
+
+/*
+ * int pipe2(int pipefd[2], int flags);
+ * int pipe(int pipefd[2]);
+ */
+
+static __attribute__((unused))
+int sys_pipe2(int pipefd[2], int flags)
+{
+ return my_syscall2(__NR_pipe2, pipefd, flags);
+}
+
+static __attribute__((unused))
+int pipe2(int pipefd[2], int flags)
+{
+ return __sysret(sys_pipe2(pipefd, flags));
+}
+
+static __attribute__((unused))
+int pipe(int pipefd[2])
+{
+ return pipe2(pipefd, 0);
+}
+
+
+/*
+ * int prctl(int option, unsigned long arg2, unsigned long arg3,
+ * unsigned long arg4, unsigned long arg5);
+ */
+
+static __attribute__((unused))
+int sys_prctl(int option, unsigned long arg2, unsigned long arg3,
+ unsigned long arg4, unsigned long arg5)
+{
+ return my_syscall5(__NR_prctl, option, arg2, arg3, arg4, arg5);
+}
+
+static __attribute__((unused))
+int prctl(int option, unsigned long arg2, unsigned long arg3,
+ unsigned long arg4, unsigned long arg5)
+{
+ return __sysret(sys_prctl(option, arg2, arg3, arg4, arg5));
+}
+
+
+/*
+ * int pivot_root(const char *new, const char *old);
+ */
+
+static __attribute__((unused))
+int sys_pivot_root(const char *new, const char *old)
+{
+ return my_syscall2(__NR_pivot_root, new, old);
+}
+
+static __attribute__((unused))
+int pivot_root(const char *new, const char *old)
+{
+ return __sysret(sys_pivot_root(new, old));
+}
+
+
+/*
+ * int poll(struct pollfd *fds, int nfds, int timeout);
+ */
+
+static __attribute__((unused))
+int sys_poll(struct pollfd *fds, int nfds, int timeout)
+{
+#if defined(__NR_ppoll)
+ struct timespec t;
+
+ if (timeout >= 0) {
+ t.tv_sec = timeout / 1000;
+ t.tv_nsec = (timeout % 1000) * 1000000;
+ }
+ return my_syscall5(__NR_ppoll, fds, nfds, (timeout >= 0) ? &t : NULL, NULL, 0);
+#elif defined(__NR_poll)
+ return my_syscall3(__NR_poll, fds, nfds, timeout);
+#else
+ return -ENOSYS;
+#endif
+}
+
+static __attribute__((unused))
+int poll(struct pollfd *fds, int nfds, int timeout)
+{
+ return __sysret(sys_poll(fds, nfds, timeout));
+}
+
+
+/*
+ * ssize_t read(int fd, void *buf, size_t count);
+ */
+
+static __attribute__((unused))
+ssize_t sys_read(int fd, void *buf, size_t count)
+{
+ return my_syscall3(__NR_read, fd, buf, count);
+}
+
+static __attribute__((unused))
+ssize_t read(int fd, void *buf, size_t count)
+{
+ return __sysret(sys_read(fd, buf, count));
+}
+
+
+/*
+ * int reboot(int cmd);
+ * <cmd> is among LINUX_REBOOT_CMD_*
+ */
+
+static __attribute__((unused))
+ssize_t sys_reboot(int magic1, int magic2, int cmd, void *arg)
+{
+ return my_syscall4(__NR_reboot, magic1, magic2, cmd, arg);
+}
+
+static __attribute__((unused))
+int reboot(int cmd)
+{
+ return __sysret(sys_reboot(LINUX_REBOOT_MAGIC1, LINUX_REBOOT_MAGIC2, cmd, 0));
+}
+
+
+/*
+ * int sched_yield(void);
+ */
+
+static __attribute__((unused))
+int sys_sched_yield(void)
+{
+ return my_syscall0(__NR_sched_yield);
+}
+
+static __attribute__((unused))
+int sched_yield(void)
+{
+ return __sysret(sys_sched_yield());
+}
+
+
+/*
+ * int select(int nfds, fd_set *read_fds, fd_set *write_fds,
+ * fd_set *except_fds, struct timeval *timeout);
+ */
+
+static __attribute__((unused))
+int sys_select(int nfds, fd_set *rfds, fd_set *wfds, fd_set *efds, struct timeval *timeout)
+{
+#if defined(__ARCH_WANT_SYS_OLD_SELECT) && !defined(__NR__newselect)
+ struct sel_arg_struct {
+ unsigned long n;
+ fd_set *r, *w, *e;
+ struct timeval *t;
+ } arg = { .n = nfds, .r = rfds, .w = wfds, .e = efds, .t = timeout };
+ return my_syscall1(__NR_select, &arg);
+#elif defined(__ARCH_WANT_SYS_PSELECT6) && defined(__NR_pselect6)
+ struct timespec t;
+
+ if (timeout) {
+ t.tv_sec = timeout->tv_sec;
+ t.tv_nsec = timeout->tv_usec * 1000;
+ }
+ return my_syscall6(__NR_pselect6, nfds, rfds, wfds, efds, timeout ? &t : NULL, NULL);
+#elif defined(__NR__newselect) || defined(__NR_select)
+#ifndef __NR__newselect
+#define __NR__newselect __NR_select
+#endif
+ return my_syscall5(__NR__newselect, nfds, rfds, wfds, efds, timeout);
+#else
+ return -ENOSYS;
+#endif
+}
+
+static __attribute__((unused))
+int select(int nfds, fd_set *rfds, fd_set *wfds, fd_set *efds, struct timeval *timeout)
+{
+ return __sysret(sys_select(nfds, rfds, wfds, efds, timeout));
+}
+
+
+/*
+ * int setpgid(pid_t pid, pid_t pgid);
+ */
+
+static __attribute__((unused))
+int sys_setpgid(pid_t pid, pid_t pgid)
+{
+ return my_syscall2(__NR_setpgid, pid, pgid);
+}
+
+static __attribute__((unused))
+int setpgid(pid_t pid, pid_t pgid)
+{
+ return __sysret(sys_setpgid(pid, pgid));
+}
+
+
+/*
+ * pid_t setsid(void);
+ */
+
+static __attribute__((unused))
+pid_t sys_setsid(void)
+{
+ return my_syscall0(__NR_setsid);
+}
+
+static __attribute__((unused))
+pid_t setsid(void)
+{
+ return __sysret(sys_setsid());
+}
+
+/*
+ * int statx(int fd, const char *path, int flags, unsigned int mask, struct statx *buf);
+ * int stat(const char *path, struct stat *buf);
+ */
+
+static __attribute__((unused))
+int sys_statx(int fd, const char *path, int flags, unsigned int mask, struct statx *buf)
+{
+#ifdef __NR_statx
+ return my_syscall5(__NR_statx, fd, path, flags, mask, buf);
+#else
+ return -ENOSYS;
+#endif
+}
+
+static __attribute__((unused))
+int statx(int fd, const char *path, int flags, unsigned int mask, struct statx *buf)
+{
+ return __sysret(sys_statx(fd, path, flags, mask, buf));
+}
+
+
+static __attribute__((unused))
+int stat(const char *path, struct stat *buf)
+{
+ struct statx statx;
+ long ret;
+
+ ret = __sysret(sys_statx(AT_FDCWD, path, AT_NO_AUTOMOUNT, STATX_BASIC_STATS, &statx));
+ if (ret == -1)
+ return ret;
+
+ buf->st_dev = ((statx.stx_dev_minor & 0xff)
+ | (statx.stx_dev_major << 8)
+ | ((statx.stx_dev_minor & ~0xff) << 12));
+ buf->st_ino = statx.stx_ino;
+ buf->st_mode = statx.stx_mode;
+ buf->st_nlink = statx.stx_nlink;
+ buf->st_uid = statx.stx_uid;
+ buf->st_gid = statx.stx_gid;
+ buf->st_rdev = ((statx.stx_rdev_minor & 0xff)
+ | (statx.stx_rdev_major << 8)
+ | ((statx.stx_rdev_minor & ~0xff) << 12));
+ buf->st_size = statx.stx_size;
+ buf->st_blksize = statx.stx_blksize;
+ buf->st_blocks = statx.stx_blocks;
+ buf->st_atim.tv_sec = statx.stx_atime.tv_sec;
+ buf->st_atim.tv_nsec = statx.stx_atime.tv_nsec;
+ buf->st_mtim.tv_sec = statx.stx_mtime.tv_sec;
+ buf->st_mtim.tv_nsec = statx.stx_mtime.tv_nsec;
+ buf->st_ctim.tv_sec = statx.stx_ctime.tv_sec;
+ buf->st_ctim.tv_nsec = statx.stx_ctime.tv_nsec;
+
+ return 0;
+}
+
+
+/*
+ * int symlink(const char *old, const char *new);
+ */
+
+static __attribute__((unused))
+int sys_symlink(const char *old, const char *new)
+{
+#ifdef __NR_symlinkat
+ return my_syscall3(__NR_symlinkat, old, AT_FDCWD, new);
+#elif defined(__NR_symlink)
+ return my_syscall2(__NR_symlink, old, new);
+#else
+ return -ENOSYS;
+#endif
+}
+
+static __attribute__((unused))
+int symlink(const char *old, const char *new)
+{
+ return __sysret(sys_symlink(old, new));
+}
+
+
+/*
+ * mode_t umask(mode_t mode);
+ */
+
+static __attribute__((unused))
+mode_t sys_umask(mode_t mode)
+{
+ return my_syscall1(__NR_umask, mode);
+}
+
+static __attribute__((unused))
+mode_t umask(mode_t mode)
+{
+ return sys_umask(mode);
+}
+
+
+/*
+ * int umount2(const char *path, int flags);
+ */
+
+static __attribute__((unused))
+int sys_umount2(const char *path, int flags)
+{
+ return my_syscall2(__NR_umount2, path, flags);
+}
+
+static __attribute__((unused))
+int umount2(const char *path, int flags)
+{
+ return __sysret(sys_umount2(path, flags));
+}
+
+
+/*
+ * int unlink(const char *path);
+ */
+
+static __attribute__((unused))
+int sys_unlink(const char *path)
+{
+#ifdef __NR_unlinkat
+ return my_syscall3(__NR_unlinkat, AT_FDCWD, path, 0);
+#elif defined(__NR_unlink)
+ return my_syscall1(__NR_unlink, path);
+#else
+ return -ENOSYS;
+#endif
+}
+
+static __attribute__((unused))
+int unlink(const char *path)
+{
+ return __sysret(sys_unlink(path));
+}
+
+
+/*
+ * pid_t wait(int *status);
+ * pid_t wait4(pid_t pid, int *status, int options, struct rusage *rusage);
+ * pid_t waitpid(pid_t pid, int *status, int options);
+ */
+
+static __attribute__((unused))
+pid_t sys_wait4(pid_t pid, int *status, int options, struct rusage *rusage)
+{
+#ifdef __NR_wait4
+ return my_syscall4(__NR_wait4, pid, status, options, rusage);
+#else
+ return -ENOSYS;
+#endif
+}
+
+static __attribute__((unused))
+pid_t wait(int *status)
+{
+ return __sysret(sys_wait4(-1, status, 0, NULL));
+}
+
+static __attribute__((unused))
+pid_t wait4(pid_t pid, int *status, int options, struct rusage *rusage)
+{
+ return __sysret(sys_wait4(pid, status, options, rusage));
+}
+
+
+static __attribute__((unused))
+pid_t waitpid(pid_t pid, int *status, int options)
+{
+ return __sysret(sys_wait4(pid, status, options, NULL));
+}
+
+
+/*
+ * ssize_t write(int fd, const void *buf, size_t count);
+ */
+
+static __attribute__((unused))
+ssize_t sys_write(int fd, const void *buf, size_t count)
+{
+ return my_syscall3(__NR_write, fd, buf, count);
+}
+
+static __attribute__((unused))
+ssize_t write(int fd, const void *buf, size_t count)
+{
+ return __sysret(sys_write(fd, buf, count));
+}
+
+
+/*
+ * int memfd_create(const char *name, unsigned int flags);
+ */
+
+static __attribute__((unused))
+int sys_memfd_create(const char *name, unsigned int flags)
+{
+ return my_syscall2(__NR_memfd_create, name, flags);
+}
+
+static __attribute__((unused))
+int memfd_create(const char *name, unsigned int flags)
+{
+ return __sysret(sys_memfd_create(name, flags));
+}
+
+/* make sure to include all global symbols */
+#include "nolibc.h"
+
+#endif /* _NOLIBC_SYS_H */
diff --git a/tools/include/nolibc/time.h b/tools/include/nolibc/time.h
new file mode 100644
index 0000000000..84655361b9
--- /dev/null
+++ b/tools/include/nolibc/time.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * time function definitions for NOLIBC
+ * Copyright (C) 2017-2022 Willy Tarreau <w@1wt.eu>
+ */
+
+#ifndef _NOLIBC_TIME_H
+#define _NOLIBC_TIME_H
+
+#include "std.h"
+#include "arch.h"
+#include "types.h"
+#include "sys.h"
+
+static __attribute__((unused))
+time_t time(time_t *tptr)
+{
+ struct timeval tv;
+
+ /* note, cannot fail here */
+ sys_gettimeofday(&tv, NULL);
+
+ if (tptr)
+ *tptr = tv.tv_sec;
+ return tv.tv_sec;
+}
+
+/* make sure to include all global symbols */
+#include "nolibc.h"
+
+#endif /* _NOLIBC_TIME_H */
diff --git a/tools/include/nolibc/types.h b/tools/include/nolibc/types.h
new file mode 100644
index 0000000000..8cfc4c860f
--- /dev/null
+++ b/tools/include/nolibc/types.h
@@ -0,0 +1,241 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * Special types used by various syscalls for NOLIBC
+ * Copyright (C) 2017-2021 Willy Tarreau <w@1wt.eu>
+ */
+
+#ifndef _NOLIBC_TYPES_H
+#define _NOLIBC_TYPES_H
+
+#include "std.h"
+#include <linux/mman.h>
+#include <linux/reboot.h> /* for LINUX_REBOOT_* */
+#include <linux/stat.h>
+#include <linux/time.h>
+
+
+/* Only the generic macros and types may be defined here. The arch-specific
+ * ones such as the O_RDONLY and related macros used by fcntl() and open()
+ * must not be defined here.
+ */
+
+/* stat flags (WARNING, octal here). We need to check for an existing
+ * definition because linux/stat.h may omit to define those if it finds
+ * that any glibc header was already included.
+ */
+#if !defined(S_IFMT)
+#define S_IFDIR 0040000
+#define S_IFCHR 0020000
+#define S_IFBLK 0060000
+#define S_IFREG 0100000
+#define S_IFIFO 0010000
+#define S_IFLNK 0120000
+#define S_IFSOCK 0140000
+#define S_IFMT 0170000
+
+#define S_ISDIR(mode) (((mode) & S_IFMT) == S_IFDIR)
+#define S_ISCHR(mode) (((mode) & S_IFMT) == S_IFCHR)
+#define S_ISBLK(mode) (((mode) & S_IFMT) == S_IFBLK)
+#define S_ISREG(mode) (((mode) & S_IFMT) == S_IFREG)
+#define S_ISFIFO(mode) (((mode) & S_IFMT) == S_IFIFO)
+#define S_ISLNK(mode) (((mode) & S_IFMT) == S_IFLNK)
+#define S_ISSOCK(mode) (((mode) & 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
+
+/* dirent types */
+#define DT_UNKNOWN 0x0
+#define DT_FIFO 0x1
+#define DT_CHR 0x2
+#define DT_DIR 0x4
+#define DT_BLK 0x6
+#define DT_REG 0x8
+#define DT_LNK 0xa
+#define DT_SOCK 0xc
+
+/* commonly an fd_set represents 256 FDs */
+#ifndef FD_SETSIZE
+#define FD_SETSIZE 256
+#endif
+
+/* PATH_MAX and MAXPATHLEN are often used and found with plenty of different
+ * values.
+ */
+#ifndef PATH_MAX
+#define PATH_MAX 4096
+#endif
+
+#ifndef MAXPATHLEN
+#define MAXPATHLEN (PATH_MAX)
+#endif
+
+/* flags for mmap */
+#ifndef MAP_FAILED
+#define MAP_FAILED ((void *)-1)
+#endif
+
+/* whence values for lseek() */
+#define SEEK_SET 0
+#define SEEK_CUR 1
+#define SEEK_END 2
+
+/* flags for reboot */
+#define RB_AUTOBOOT LINUX_REBOOT_CMD_RESTART
+#define RB_HALT_SYSTEM LINUX_REBOOT_CMD_HALT
+#define RB_ENABLE_CAD LINUX_REBOOT_CMD_CAD_ON
+#define RB_DISABLE_CAD LINUX_REBOOT_CMD_CAD_OFF
+#define RB_POWER_OFF LINUX_REBOOT_CMD_POWER_OFF
+#define RB_SW_SUSPEND LINUX_REBOOT_CMD_SW_SUSPEND
+#define RB_KEXEC LINUX_REBOOT_CMD_KEXEC
+
+/* Macros used on waitpid()'s return status */
+#define WEXITSTATUS(status) (((status) & 0xff00) >> 8)
+#define WIFEXITED(status) (((status) & 0x7f) == 0)
+#define WTERMSIG(status) ((status) & 0x7f)
+#define WIFSIGNALED(status) ((status) - 1 < 0xff)
+
+/* waitpid() flags */
+#define WNOHANG 1
+
+/* standard exit() codes */
+#define EXIT_SUCCESS 0
+#define EXIT_FAILURE 1
+
+#define FD_SETIDXMASK (8 * sizeof(unsigned long))
+#define FD_SETBITMASK (8 * sizeof(unsigned long)-1)
+
+/* for select() */
+typedef struct {
+ unsigned long fds[(FD_SETSIZE + FD_SETBITMASK) / FD_SETIDXMASK];
+} fd_set;
+
+#define FD_CLR(fd, set) do { \
+ fd_set *__set = (set); \
+ int __fd = (fd); \
+ if (__fd >= 0) \
+ __set->fds[__fd / FD_SETIDXMASK] &= \
+ ~(1U << (__fd & FX_SETBITMASK)); \
+ } while (0)
+
+#define FD_SET(fd, set) do { \
+ fd_set *__set = (set); \
+ int __fd = (fd); \
+ if (__fd >= 0) \
+ __set->fds[__fd / FD_SETIDXMASK] |= \
+ 1 << (__fd & FD_SETBITMASK); \
+ } while (0)
+
+#define FD_ISSET(fd, set) ({ \
+ fd_set *__set = (set); \
+ int __fd = (fd); \
+ int __r = 0; \
+ if (__fd >= 0) \
+ __r = !!(__set->fds[__fd / FD_SETIDXMASK] & \
+1U << (__fd & FD_SET_BITMASK)); \
+ __r; \
+ })
+
+#define FD_ZERO(set) do { \
+ fd_set *__set = (set); \
+ int __idx; \
+ int __size = (FD_SETSIZE+FD_SETBITMASK) / FD_SETIDXMASK;\
+ for (__idx = 0; __idx < __size; __idx++) \
+ __set->fds[__idx] = 0; \
+ } while (0)
+
+/* for poll() */
+#define POLLIN 0x0001
+#define POLLPRI 0x0002
+#define POLLOUT 0x0004
+#define POLLERR 0x0008
+#define POLLHUP 0x0010
+#define POLLNVAL 0x0020
+
+struct pollfd {
+ int fd;
+ short int events;
+ short int revents;
+};
+
+/* for getdents64() */
+struct linux_dirent64 {
+ uint64_t d_ino;
+ int64_t d_off;
+ unsigned short d_reclen;
+ unsigned char d_type;
+ char d_name[];
+};
+
+/* needed by wait4() */
+struct rusage {
+ struct timeval ru_utime;
+ struct timeval ru_stime;
+ long ru_maxrss;
+ long ru_ixrss;
+ long ru_idrss;
+ long ru_isrss;
+ long ru_minflt;
+ long ru_majflt;
+ long ru_nswap;
+ long ru_inblock;
+ long ru_oublock;
+ long ru_msgsnd;
+ long ru_msgrcv;
+ long ru_nsignals;
+ long ru_nvcsw;
+ long ru_nivcsw;
+};
+
+/* The format of the struct as returned by the libc to the application, which
+ * significantly differs from the format returned by the stat() syscall flavours.
+ */
+struct stat {
+ dev_t st_dev; /* ID of device containing file */
+ ino_t st_ino; /* inode number */
+ mode_t st_mode; /* protection */
+ nlink_t st_nlink; /* number of hard links */
+ uid_t st_uid; /* user ID of owner */
+ gid_t st_gid; /* group ID of owner */
+ dev_t st_rdev; /* device ID (if special file) */
+ off_t st_size; /* total size, in bytes */
+ blksize_t st_blksize; /* blocksize for file system I/O */
+ blkcnt_t st_blocks; /* number of 512B blocks allocated */
+ union { time_t st_atime; struct timespec st_atim; }; /* time of last access */
+ union { time_t st_mtime; struct timespec st_mtim; }; /* time of last modification */
+ union { time_t st_ctime; struct timespec st_ctim; }; /* time of last status change */
+};
+
+/* WARNING, it only deals with the 4096 first majors and 256 first minors */
+#define makedev(major, minor) ((dev_t)((((major) & 0xfff) << 8) | ((minor) & 0xff)))
+#define major(dev) ((unsigned int)(((dev) >> 8) & 0xfff))
+#define minor(dev) ((unsigned int)(((dev) & 0xff))
+
+#ifndef offsetof
+#define offsetof(TYPE, FIELD) ((size_t) &((TYPE *)0)->FIELD)
+#endif
+
+#ifndef container_of
+#define container_of(PTR, TYPE, FIELD) ({ \
+ __typeof__(((TYPE *)0)->FIELD) *__FIELD_PTR = (PTR); \
+ (TYPE *)((char *) __FIELD_PTR - offsetof(TYPE, FIELD)); \
+})
+#endif
+
+/* make sure to include all global symbols */
+#include "nolibc.h"
+
+#endif /* _NOLIBC_TYPES_H */
diff --git a/tools/include/nolibc/unistd.h b/tools/include/nolibc/unistd.h
new file mode 100644
index 0000000000..e38f3660c0
--- /dev/null
+++ b/tools/include/nolibc/unistd.h
@@ -0,0 +1,68 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * unistd function definitions for NOLIBC
+ * Copyright (C) 2017-2022 Willy Tarreau <w@1wt.eu>
+ */
+
+#ifndef _NOLIBC_UNISTD_H
+#define _NOLIBC_UNISTD_H
+
+#include "std.h"
+#include "arch.h"
+#include "types.h"
+#include "sys.h"
+
+
+#define STDIN_FILENO 0
+#define STDOUT_FILENO 1
+#define STDERR_FILENO 2
+
+
+static __attribute__((unused))
+int msleep(unsigned int msecs)
+{
+ struct timeval my_timeval = { msecs / 1000, (msecs % 1000) * 1000 };
+
+ if (sys_select(0, 0, 0, 0, &my_timeval) < 0)
+ return (my_timeval.tv_sec * 1000) +
+ (my_timeval.tv_usec / 1000) +
+ !!(my_timeval.tv_usec % 1000);
+ else
+ return 0;
+}
+
+static __attribute__((unused))
+unsigned int sleep(unsigned int seconds)
+{
+ struct timeval my_timeval = { seconds, 0 };
+
+ if (sys_select(0, 0, 0, 0, &my_timeval) < 0)
+ return my_timeval.tv_sec + !!my_timeval.tv_usec;
+ else
+ return 0;
+}
+
+static __attribute__((unused))
+int usleep(unsigned int usecs)
+{
+ struct timeval my_timeval = { usecs / 1000000, usecs % 1000000 };
+
+ return sys_select(0, 0, 0, 0, &my_timeval);
+}
+
+static __attribute__((unused))
+int tcsetpgrp(int fd, pid_t pid)
+{
+ return ioctl(fd, TIOCSPGRP, &pid);
+}
+
+#define __syscall_narg(_0, _1, _2, _3, _4, _5, _6, N, ...) N
+#define _syscall_narg(...) __syscall_narg(__VA_ARGS__, 6, 5, 4, 3, 2, 1, 0)
+#define _syscall(N, ...) __sysret(my_syscall##N(__VA_ARGS__))
+#define _syscall_n(N, ...) _syscall(N, __VA_ARGS__)
+#define syscall(...) _syscall_n(_syscall_narg(__VA_ARGS__), ##__VA_ARGS__)
+
+/* make sure to include all global symbols */
+#include "nolibc.h"
+
+#endif /* _NOLIBC_UNISTD_H */
diff --git a/tools/include/tools/be_byteshift.h b/tools/include/tools/be_byteshift.h
new file mode 100644
index 0000000000..f7d1d16989
--- /dev/null
+++ b/tools/include/tools/be_byteshift.h
@@ -0,0 +1,71 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TOOLS_BE_BYTESHIFT_H
+#define _TOOLS_BE_BYTESHIFT_H
+
+#include <stdint.h>
+
+static inline uint16_t __get_unaligned_be16(const uint8_t *p)
+{
+ return p[0] << 8 | p[1];
+}
+
+static inline uint32_t __get_unaligned_be32(const uint8_t *p)
+{
+ return p[0] << 24 | p[1] << 16 | p[2] << 8 | p[3];
+}
+
+static inline uint64_t __get_unaligned_be64(const uint8_t *p)
+{
+ return (uint64_t)__get_unaligned_be32(p) << 32 |
+ __get_unaligned_be32(p + 4);
+}
+
+static inline void __put_unaligned_be16(uint16_t val, uint8_t *p)
+{
+ *p++ = val >> 8;
+ *p++ = val;
+}
+
+static inline void __put_unaligned_be32(uint32_t val, uint8_t *p)
+{
+ __put_unaligned_be16(val >> 16, p);
+ __put_unaligned_be16(val, p + 2);
+}
+
+static inline void __put_unaligned_be64(uint64_t val, uint8_t *p)
+{
+ __put_unaligned_be32(val >> 32, p);
+ __put_unaligned_be32(val, p + 4);
+}
+
+static inline uint16_t get_unaligned_be16(const void *p)
+{
+ return __get_unaligned_be16((const uint8_t *)p);
+}
+
+static inline uint32_t get_unaligned_be32(const void *p)
+{
+ return __get_unaligned_be32((const uint8_t *)p);
+}
+
+static inline uint64_t get_unaligned_be64(const void *p)
+{
+ return __get_unaligned_be64((const uint8_t *)p);
+}
+
+static inline void put_unaligned_be16(uint16_t val, void *p)
+{
+ __put_unaligned_be16(val, p);
+}
+
+static inline void put_unaligned_be32(uint32_t val, void *p)
+{
+ __put_unaligned_be32(val, p);
+}
+
+static inline void put_unaligned_be64(uint64_t val, void *p)
+{
+ __put_unaligned_be64(val, p);
+}
+
+#endif /* _TOOLS_BE_BYTESHIFT_H */
diff --git a/tools/include/tools/config.h b/tools/include/tools/config.h
new file mode 100644
index 0000000000..08ade7df81
--- /dev/null
+++ b/tools/include/tools/config.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TOOLS_CONFIG_H
+#define _TOOLS_CONFIG_H
+
+/* Subset of include/linux/kconfig.h */
+
+#define __ARG_PLACEHOLDER_1 0,
+#define __take_second_arg(__ignored, val, ...) val
+
+/*
+ * Helper macros to use CONFIG_ options in C/CPP expressions. Note that
+ * these only work with boolean and tristate options.
+ */
+
+/*
+ * Getting something that works in C and CPP for an arg that may or may
+ * not be defined is tricky. Here, if we have "#define CONFIG_BOOGER 1"
+ * we match on the placeholder define, insert the "0," for arg1 and generate
+ * the triplet (0, 1, 0). Then the last step cherry picks the 2nd arg (a one).
+ * When CONFIG_BOOGER is not defined, we generate a (... 1, 0) pair, and when
+ * the last step cherry picks the 2nd arg, we get a zero.
+ */
+#define __is_defined(x) ___is_defined(x)
+#define ___is_defined(val) ____is_defined(__ARG_PLACEHOLDER_##val)
+#define ____is_defined(arg1_or_junk) __take_second_arg(arg1_or_junk 1, 0)
+
+/*
+ * IS_BUILTIN(CONFIG_FOO) evaluates to 1 if CONFIG_FOO is set to 'y', 0
+ * otherwise. For boolean options, this is equivalent to
+ * IS_ENABLED(CONFIG_FOO).
+ */
+#define IS_BUILTIN(option) __is_defined(option)
+
+#endif /* _TOOLS_CONFIG_H */
diff --git a/tools/include/tools/dis-asm-compat.h b/tools/include/tools/dis-asm-compat.h
new file mode 100644
index 0000000000..70f331e23e
--- /dev/null
+++ b/tools/include/tools/dis-asm-compat.h
@@ -0,0 +1,55 @@
+/* SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause */
+#ifndef _TOOLS_DIS_ASM_COMPAT_H
+#define _TOOLS_DIS_ASM_COMPAT_H
+
+#include <stdio.h>
+#include <dis-asm.h>
+
+/* define types for older binutils version, to centralize ifdef'ery a bit */
+#ifndef DISASM_INIT_STYLED
+enum disassembler_style {DISASSEMBLER_STYLE_NOT_EMPTY};
+typedef int (*fprintf_styled_ftype) (void *, enum disassembler_style, const char*, ...);
+#endif
+
+/*
+ * Trivial fprintf wrapper to be used as the fprintf_styled_func argument to
+ * init_disassemble_info_compat() when normal fprintf suffices.
+ */
+static inline int fprintf_styled(void *out,
+ enum disassembler_style style,
+ const char *fmt, ...)
+{
+ va_list args;
+ int r;
+
+ (void)style;
+
+ va_start(args, fmt);
+ r = vfprintf(out, fmt, args);
+ va_end(args);
+
+ return r;
+}
+
+/*
+ * Wrapper for init_disassemble_info() that hides version
+ * differences. Depending on binutils version and architecture either
+ * fprintf_func or fprintf_styled_func will be called.
+ */
+static inline void init_disassemble_info_compat(struct disassemble_info *info,
+ void *stream,
+ fprintf_ftype unstyled_func,
+ fprintf_styled_ftype styled_func)
+{
+#ifdef DISASM_INIT_STYLED
+ init_disassemble_info(info, stream,
+ unstyled_func,
+ styled_func);
+#else
+ (void)styled_func;
+ init_disassemble_info(info, stream,
+ unstyled_func);
+#endif
+}
+
+#endif /* _TOOLS_DIS_ASM_COMPAT_H */
diff --git a/tools/include/tools/endian.h b/tools/include/tools/endian.h
new file mode 100644
index 0000000000..c67888fd42
--- /dev/null
+++ b/tools/include/tools/endian.h
@@ -0,0 +1,57 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TOOLS_ENDIAN_H
+#define _TOOLS_ENDIAN_H
+
+#include <byteswap.h>
+
+#if __BYTE_ORDER == __LITTLE_ENDIAN
+
+#ifndef htole16
+#define htole16(x) (x)
+#endif
+#ifndef htole32
+#define htole32(x) (x)
+#endif
+#ifndef htole64
+#define htole64(x) (x)
+#endif
+
+#ifndef le16toh
+#define le16toh(x) (x)
+#endif
+
+#ifndef le32toh
+#define le32toh(x) (x)
+#endif
+
+#ifndef le64toh
+#define le64toh(x) (x)
+#endif
+
+#else /* __BYTE_ORDER */
+
+#ifndef htole16
+#define htole16(x) __bswap_16(x)
+#endif
+#ifndef htole32
+#define htole32(x) __bswap_32(x)
+#endif
+#ifndef htole64
+#define htole64(x) __bswap_64(x)
+#endif
+
+#ifndef le16toh
+#define le16toh(x) __bswap_16(x)
+#endif
+
+#ifndef le32toh
+#define le32toh(x) __bswap_32(x)
+#endif
+
+#ifndef le64toh
+#define le64toh(x) __bswap_64(x)
+#endif
+
+#endif
+
+#endif /* _TOOLS_ENDIAN_H */
diff --git a/tools/include/tools/le_byteshift.h b/tools/include/tools/le_byteshift.h
new file mode 100644
index 0000000000..dc8565f397
--- /dev/null
+++ b/tools/include/tools/le_byteshift.h
@@ -0,0 +1,71 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TOOLS_LE_BYTESHIFT_H
+#define _TOOLS_LE_BYTESHIFT_H
+
+#include <stdint.h>
+
+static inline uint16_t __get_unaligned_le16(const uint8_t *p)
+{
+ return p[0] | p[1] << 8;
+}
+
+static inline uint32_t __get_unaligned_le32(const uint8_t *p)
+{
+ return p[0] | p[1] << 8 | p[2] << 16 | p[3] << 24;
+}
+
+static inline uint64_t __get_unaligned_le64(const uint8_t *p)
+{
+ return (uint64_t)__get_unaligned_le32(p + 4) << 32 |
+ __get_unaligned_le32(p);
+}
+
+static inline void __put_unaligned_le16(uint16_t val, uint8_t *p)
+{
+ *p++ = val;
+ *p++ = val >> 8;
+}
+
+static inline void __put_unaligned_le32(uint32_t val, uint8_t *p)
+{
+ __put_unaligned_le16(val >> 16, p + 2);
+ __put_unaligned_le16(val, p);
+}
+
+static inline void __put_unaligned_le64(uint64_t val, uint8_t *p)
+{
+ __put_unaligned_le32(val >> 32, p + 4);
+ __put_unaligned_le32(val, p);
+}
+
+static inline uint16_t get_unaligned_le16(const void *p)
+{
+ return __get_unaligned_le16((const uint8_t *)p);
+}
+
+static inline uint32_t get_unaligned_le32(const void *p)
+{
+ return __get_unaligned_le32((const uint8_t *)p);
+}
+
+static inline uint64_t get_unaligned_le64(const void *p)
+{
+ return __get_unaligned_le64((const uint8_t *)p);
+}
+
+static inline void put_unaligned_le16(uint16_t val, void *p)
+{
+ __put_unaligned_le16(val, p);
+}
+
+static inline void put_unaligned_le32(uint32_t val, void *p)
+{
+ __put_unaligned_le32(val, p);
+}
+
+static inline void put_unaligned_le64(uint64_t val, void *p)
+{
+ __put_unaligned_le64(val, p);
+}
+
+#endif /* _TOOLS_LE_BYTESHIFT_H */
diff --git a/tools/include/tools/libc_compat.h b/tools/include/tools/libc_compat.h
new file mode 100644
index 0000000000..e907ba6f15
--- /dev/null
+++ b/tools/include/tools/libc_compat.h
@@ -0,0 +1,20 @@
+// SPDX-License-Identifier: (LGPL-2.0+ OR BSD-2-Clause)
+/* Copyright (C) 2018 Netronome Systems, Inc. */
+
+#ifndef __TOOLS_LIBC_COMPAT_H
+#define __TOOLS_LIBC_COMPAT_H
+
+#include <stdlib.h>
+#include <linux/overflow.h>
+
+#ifdef COMPAT_NEED_REALLOCARRAY
+static inline void *reallocarray(void *ptr, size_t nmemb, size_t size)
+{
+ size_t bytes;
+
+ if (unlikely(check_mul_overflow(nmemb, size, &bytes)))
+ return NULL;
+ return realloc(ptr, bytes);
+}
+#endif
+#endif
diff --git a/tools/include/trace/events/lock.h b/tools/include/trace/events/lock.h
new file mode 100644
index 0000000000..5b15fd5ee1
--- /dev/null
+++ b/tools/include/trace/events/lock.h
@@ -0,0 +1,4 @@
+#ifndef _TOOLS_INCLUDE_TRACE_EVENTS_LOCK_H
+#define _TOOLS_INCLUDE_TRACE_EVENTS_LOCK_H
+
+#endif /* _TOOLS_INCLUDE_TRACE_EVENTS_LOCK_H */
diff --git a/tools/include/uapi/asm-generic/bitsperlong.h b/tools/include/uapi/asm-generic/bitsperlong.h
new file mode 100644
index 0000000000..352cb81947
--- /dev/null
+++ b/tools/include/uapi/asm-generic/bitsperlong.h
@@ -0,0 +1,27 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI__ASM_GENERIC_BITS_PER_LONG
+#define _UAPI__ASM_GENERIC_BITS_PER_LONG
+
+#ifndef __BITS_PER_LONG
+/*
+ * In order to keep safe and avoid regression, only unify uapi
+ * bitsperlong.h for some archs which are using newer toolchains
+ * that have the definitions of __CHAR_BIT__ and __SIZEOF_LONG__.
+ * See the following link for more info:
+ * https://lore.kernel.org/linux-arch/b9624545-2c80-49a1-ac3c-39264a591f7b@app.fastmail.com/
+ */
+#if defined(__CHAR_BIT__) && defined(__SIZEOF_LONG__)
+#define __BITS_PER_LONG (__CHAR_BIT__ * __SIZEOF_LONG__)
+#else
+/*
+ * There seems to be no way of detecting this automatically from user
+ * space, so 64 bit architectures should override this in their
+ * bitsperlong.h. In particular, an architecture that supports
+ * both 32 and 64 bit user space must not rely on CONFIG_64BIT
+ * to decide it, but rather check a compiler provided macro.
+ */
+#define __BITS_PER_LONG 32
+#endif
+#endif
+
+#endif /* _UAPI__ASM_GENERIC_BITS_PER_LONG */
diff --git a/tools/include/uapi/asm-generic/bpf_perf_event.h b/tools/include/uapi/asm-generic/bpf_perf_event.h
new file mode 100644
index 0000000000..53815d2cd0
--- /dev/null
+++ b/tools/include/uapi/asm-generic/bpf_perf_event.h
@@ -0,0 +1,9 @@
+#ifndef _UAPI__ASM_GENERIC_BPF_PERF_EVENT_H__
+#define _UAPI__ASM_GENERIC_BPF_PERF_EVENT_H__
+
+#include <linux/ptrace.h>
+
+/* Export kernel pt_regs structure */
+typedef struct pt_regs bpf_user_pt_regs_t;
+
+#endif /* _UAPI__ASM_GENERIC_BPF_PERF_EVENT_H__ */
diff --git a/tools/include/uapi/asm-generic/errno-base.h b/tools/include/uapi/asm-generic/errno-base.h
new file mode 100644
index 0000000000..9653140bff
--- /dev/null
+++ b/tools/include/uapi/asm-generic/errno-base.h
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _ASM_GENERIC_ERRNO_BASE_H
+#define _ASM_GENERIC_ERRNO_BASE_H
+
+#define EPERM 1 /* Operation not permitted */
+#define ENOENT 2 /* No such file or directory */
+#define ESRCH 3 /* No such process */
+#define EINTR 4 /* Interrupted system call */
+#define EIO 5 /* I/O error */
+#define ENXIO 6 /* No such device or address */
+#define E2BIG 7 /* Argument list too long */
+#define ENOEXEC 8 /* Exec format error */
+#define EBADF 9 /* Bad file number */
+#define ECHILD 10 /* No child processes */
+#define EAGAIN 11 /* Try again */
+#define ENOMEM 12 /* Out of memory */
+#define EACCES 13 /* Permission denied */
+#define EFAULT 14 /* Bad address */
+#define ENOTBLK 15 /* Block device required */
+#define EBUSY 16 /* Device or resource busy */
+#define EEXIST 17 /* File exists */
+#define EXDEV 18 /* Cross-device link */
+#define ENODEV 19 /* No such device */
+#define ENOTDIR 20 /* Not a directory */
+#define EISDIR 21 /* Is a directory */
+#define EINVAL 22 /* Invalid argument */
+#define ENFILE 23 /* File table overflow */
+#define EMFILE 24 /* Too many open files */
+#define ENOTTY 25 /* Not a typewriter */
+#define ETXTBSY 26 /* Text file busy */
+#define EFBIG 27 /* File too large */
+#define ENOSPC 28 /* No space left on device */
+#define ESPIPE 29 /* Illegal seek */
+#define EROFS 30 /* Read-only file system */
+#define EMLINK 31 /* Too many links */
+#define EPIPE 32 /* Broken pipe */
+#define EDOM 33 /* Math argument out of domain of func */
+#define ERANGE 34 /* Math result not representable */
+
+#endif
diff --git a/tools/include/uapi/asm-generic/errno.h b/tools/include/uapi/asm-generic/errno.h
new file mode 100644
index 0000000000..cf9c51ac49
--- /dev/null
+++ b/tools/include/uapi/asm-generic/errno.h
@@ -0,0 +1,123 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _ASM_GENERIC_ERRNO_H
+#define _ASM_GENERIC_ERRNO_H
+
+#include <asm-generic/errno-base.h>
+
+#define EDEADLK 35 /* Resource deadlock would occur */
+#define ENAMETOOLONG 36 /* File name too long */
+#define ENOLCK 37 /* No record locks available */
+
+/*
+ * This error code is special: arch syscall entry code will return
+ * -ENOSYS if users try to call a syscall that doesn't exist. To keep
+ * failures of syscalls that really do exist distinguishable from
+ * failures due to attempts to use a nonexistent syscall, syscall
+ * implementations should refrain from returning -ENOSYS.
+ */
+#define ENOSYS 38 /* Invalid system call number */
+
+#define ENOTEMPTY 39 /* Directory not empty */
+#define ELOOP 40 /* Too many symbolic links encountered */
+#define EWOULDBLOCK EAGAIN /* Operation would block */
+#define ENOMSG 42 /* No message of desired type */
+#define EIDRM 43 /* Identifier removed */
+#define ECHRNG 44 /* Channel number out of range */
+#define EL2NSYNC 45 /* Level 2 not synchronized */
+#define EL3HLT 46 /* Level 3 halted */
+#define EL3RST 47 /* Level 3 reset */
+#define ELNRNG 48 /* Link number out of range */
+#define EUNATCH 49 /* Protocol driver not attached */
+#define ENOCSI 50 /* No CSI structure available */
+#define EL2HLT 51 /* Level 2 halted */
+#define EBADE 52 /* Invalid exchange */
+#define EBADR 53 /* Invalid request descriptor */
+#define EXFULL 54 /* Exchange full */
+#define ENOANO 55 /* No anode */
+#define EBADRQC 56 /* Invalid request code */
+#define EBADSLT 57 /* Invalid slot */
+
+#define EDEADLOCK EDEADLK
+
+#define EBFONT 59 /* Bad font file format */
+#define ENOSTR 60 /* Device not a stream */
+#define ENODATA 61 /* No data available */
+#define ETIME 62 /* Timer expired */
+#define ENOSR 63 /* Out of streams resources */
+#define ENONET 64 /* Machine is not on the network */
+#define ENOPKG 65 /* Package not installed */
+#define EREMOTE 66 /* Object is remote */
+#define ENOLINK 67 /* Link has been severed */
+#define EADV 68 /* Advertise error */
+#define ESRMNT 69 /* Srmount error */
+#define ECOMM 70 /* Communication error on send */
+#define EPROTO 71 /* Protocol error */
+#define EMULTIHOP 72 /* Multihop attempted */
+#define EDOTDOT 73 /* RFS specific error */
+#define EBADMSG 74 /* Not a data message */
+#define EOVERFLOW 75 /* Value too large for defined data type */
+#define ENOTUNIQ 76 /* Name not unique on network */
+#define EBADFD 77 /* File descriptor in bad state */
+#define EREMCHG 78 /* Remote address changed */
+#define ELIBACC 79 /* Can not access a needed shared library */
+#define ELIBBAD 80 /* Accessing a corrupted shared library */
+#define ELIBSCN 81 /* .lib section in a.out corrupted */
+#define ELIBMAX 82 /* Attempting to link in too many shared libraries */
+#define ELIBEXEC 83 /* Cannot exec a shared library directly */
+#define EILSEQ 84 /* Illegal byte sequence */
+#define ERESTART 85 /* Interrupted system call should be restarted */
+#define ESTRPIPE 86 /* Streams pipe error */
+#define EUSERS 87 /* Too many users */
+#define ENOTSOCK 88 /* Socket operation on non-socket */
+#define EDESTADDRREQ 89 /* Destination address required */
+#define EMSGSIZE 90 /* Message too long */
+#define EPROTOTYPE 91 /* Protocol wrong type for socket */
+#define ENOPROTOOPT 92 /* Protocol not available */
+#define EPROTONOSUPPORT 93 /* Protocol not supported */
+#define ESOCKTNOSUPPORT 94 /* Socket type not supported */
+#define EOPNOTSUPP 95 /* Operation not supported on transport endpoint */
+#define EPFNOSUPPORT 96 /* Protocol family not supported */
+#define EAFNOSUPPORT 97 /* Address family not supported by protocol */
+#define EADDRINUSE 98 /* Address already in use */
+#define EADDRNOTAVAIL 99 /* Cannot assign requested address */
+#define ENETDOWN 100 /* Network is down */
+#define ENETUNREACH 101 /* Network is unreachable */
+#define ENETRESET 102 /* Network dropped connection because of reset */
+#define ECONNABORTED 103 /* Software caused connection abort */
+#define ECONNRESET 104 /* Connection reset by peer */
+#define ENOBUFS 105 /* No buffer space available */
+#define EISCONN 106 /* Transport endpoint is already connected */
+#define ENOTCONN 107 /* Transport endpoint is not connected */
+#define ESHUTDOWN 108 /* Cannot send after transport endpoint shutdown */
+#define ETOOMANYREFS 109 /* Too many references: cannot splice */
+#define ETIMEDOUT 110 /* Connection timed out */
+#define ECONNREFUSED 111 /* Connection refused */
+#define EHOSTDOWN 112 /* Host is down */
+#define EHOSTUNREACH 113 /* No route to host */
+#define EALREADY 114 /* Operation already in progress */
+#define EINPROGRESS 115 /* Operation now in progress */
+#define ESTALE 116 /* Stale file handle */
+#define EUCLEAN 117 /* Structure needs cleaning */
+#define ENOTNAM 118 /* Not a XENIX named type file */
+#define ENAVAIL 119 /* No XENIX semaphores available */
+#define EISNAM 120 /* Is a named type file */
+#define EREMOTEIO 121 /* Remote I/O error */
+#define EDQUOT 122 /* Quota exceeded */
+
+#define ENOMEDIUM 123 /* No medium found */
+#define EMEDIUMTYPE 124 /* Wrong medium type */
+#define ECANCELED 125 /* Operation Canceled */
+#define ENOKEY 126 /* Required key not available */
+#define EKEYEXPIRED 127 /* Key has expired */
+#define EKEYREVOKED 128 /* Key has been revoked */
+#define EKEYREJECTED 129 /* Key was rejected by service */
+
+/* for robust mutexes */
+#define EOWNERDEAD 130 /* Owner died */
+#define ENOTRECOVERABLE 131 /* State not recoverable */
+
+#define ERFKILL 132 /* Operation not possible due to RF-kill */
+
+#define EHWPOISON 133 /* Memory page has hardware error */
+
+#endif
diff --git a/tools/include/uapi/asm-generic/fcntl.h b/tools/include/uapi/asm-generic/fcntl.h
new file mode 100644
index 0000000000..1c7a0f6632
--- /dev/null
+++ b/tools/include/uapi/asm-generic/fcntl.h
@@ -0,0 +1,221 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _ASM_GENERIC_FCNTL_H
+#define _ASM_GENERIC_FCNTL_H
+
+#include <linux/types.h>
+
+/*
+ * FMODE_EXEC is 0x20
+ * FMODE_NONOTIFY is 0x4000000
+ * These cannot be used by userspace O_* until internal and external open
+ * flags are split.
+ * -Eric Paris
+ */
+
+/*
+ * When introducing new O_* bits, please check its uniqueness in fcntl_init().
+ */
+
+#define O_ACCMODE 00000003
+#define O_RDONLY 00000000
+#define O_WRONLY 00000001
+#define O_RDWR 00000002
+#ifndef O_CREAT
+#define O_CREAT 00000100 /* not fcntl */
+#endif
+#ifndef O_EXCL
+#define O_EXCL 00000200 /* not fcntl */
+#endif
+#ifndef O_NOCTTY
+#define O_NOCTTY 00000400 /* not fcntl */
+#endif
+#ifndef O_TRUNC
+#define O_TRUNC 00001000 /* not fcntl */
+#endif
+#ifndef O_APPEND
+#define O_APPEND 00002000
+#endif
+#ifndef O_NONBLOCK
+#define O_NONBLOCK 00004000
+#endif
+#ifndef O_DSYNC
+#define O_DSYNC 00010000 /* used to be O_SYNC, see below */
+#endif
+#ifndef FASYNC
+#define FASYNC 00020000 /* fcntl, for BSD compatibility */
+#endif
+#ifndef O_DIRECT
+#define O_DIRECT 00040000 /* direct disk access hint */
+#endif
+#ifndef O_LARGEFILE
+#define O_LARGEFILE 00100000
+#endif
+#ifndef O_DIRECTORY
+#define O_DIRECTORY 00200000 /* must be a directory */
+#endif
+#ifndef O_NOFOLLOW
+#define O_NOFOLLOW 00400000 /* don't follow links */
+#endif
+#ifndef O_NOATIME
+#define O_NOATIME 01000000
+#endif
+#ifndef O_CLOEXEC
+#define O_CLOEXEC 02000000 /* set close_on_exec */
+#endif
+
+/*
+ * Before Linux 2.6.33 only O_DSYNC semantics were implemented, but using
+ * the O_SYNC flag. We continue to use the existing numerical value
+ * for O_DSYNC semantics now, but using the correct symbolic name for it.
+ * This new value is used to request true Posix O_SYNC semantics. It is
+ * defined in this strange way to make sure applications compiled against
+ * new headers get at least O_DSYNC semantics on older kernels.
+ *
+ * This has the nice side-effect that we can simply test for O_DSYNC
+ * wherever we do not care if O_DSYNC or O_SYNC is used.
+ *
+ * Note: __O_SYNC must never be used directly.
+ */
+#ifndef O_SYNC
+#define __O_SYNC 04000000
+#define O_SYNC (__O_SYNC|O_DSYNC)
+#endif
+
+#ifndef O_PATH
+#define O_PATH 010000000
+#endif
+
+#ifndef __O_TMPFILE
+#define __O_TMPFILE 020000000
+#endif
+
+/* a horrid kludge trying to make sure that this will fail on old kernels */
+#define O_TMPFILE (__O_TMPFILE | O_DIRECTORY)
+
+#ifndef O_NDELAY
+#define O_NDELAY O_NONBLOCK
+#endif
+
+#define F_DUPFD 0 /* dup */
+#define F_GETFD 1 /* get close_on_exec */
+#define F_SETFD 2 /* set/clear close_on_exec */
+#define F_GETFL 3 /* get file->f_flags */
+#define F_SETFL 4 /* set file->f_flags */
+#ifndef F_GETLK
+#define F_GETLK 5
+#define F_SETLK 6
+#define F_SETLKW 7
+#endif
+#ifndef F_SETOWN
+#define F_SETOWN 8 /* for sockets. */
+#define F_GETOWN 9 /* for sockets. */
+#endif
+#ifndef F_SETSIG
+#define F_SETSIG 10 /* for sockets. */
+#define F_GETSIG 11 /* for sockets. */
+#endif
+
+#if __BITS_PER_LONG == 32 || defined(__KERNEL__)
+#ifndef F_GETLK64
+#define F_GETLK64 12 /* using 'struct flock64' */
+#define F_SETLK64 13
+#define F_SETLKW64 14
+#endif
+#endif /* __BITS_PER_LONG == 32 || defined(__KERNEL__) */
+
+#ifndef F_SETOWN_EX
+#define F_SETOWN_EX 15
+#define F_GETOWN_EX 16
+#endif
+
+#ifndef F_GETOWNER_UIDS
+#define F_GETOWNER_UIDS 17
+#endif
+
+/*
+ * Open File Description Locks
+ *
+ * Usually record locks held by a process are released on *any* close and are
+ * not inherited across a fork().
+ *
+ * These cmd values will set locks that conflict with process-associated
+ * record locks, but are "owned" by the open file description, not the
+ * process. This means that they are inherited across fork() like BSD (flock)
+ * locks, and they are only released automatically when the last reference to
+ * the open file against which they were acquired is put.
+ */
+#define F_OFD_GETLK 36
+#define F_OFD_SETLK 37
+#define F_OFD_SETLKW 38
+
+#define F_OWNER_TID 0
+#define F_OWNER_PID 1
+#define F_OWNER_PGRP 2
+
+struct f_owner_ex {
+ int type;
+ __kernel_pid_t pid;
+};
+
+/* for F_[GET|SET]FL */
+#define FD_CLOEXEC 1 /* actually anything with low bit set goes */
+
+/* for posix fcntl() and lockf() */
+#ifndef F_RDLCK
+#define F_RDLCK 0
+#define F_WRLCK 1
+#define F_UNLCK 2
+#endif
+
+/* for old implementation of bsd flock () */
+#ifndef F_EXLCK
+#define F_EXLCK 4 /* or 3 */
+#define F_SHLCK 8 /* or 4 */
+#endif
+
+/* operations for bsd flock(), also used by the kernel implementation */
+#define LOCK_SH 1 /* shared lock */
+#define LOCK_EX 2 /* exclusive lock */
+#define LOCK_NB 4 /* or'd with one of the above to prevent
+ blocking */
+#define LOCK_UN 8 /* remove lock */
+
+/*
+ * LOCK_MAND support has been removed from the kernel. We leave the symbols
+ * here to not break legacy builds, but these should not be used in new code.
+ */
+#define LOCK_MAND 32 /* This is a mandatory flock ... */
+#define LOCK_READ 64 /* which allows concurrent read operations */
+#define LOCK_WRITE 128 /* which allows concurrent write operations */
+#define LOCK_RW 192 /* which allows concurrent read & write ops */
+
+#define F_LINUX_SPECIFIC_BASE 1024
+
+#ifndef HAVE_ARCH_STRUCT_FLOCK
+struct flock {
+ short l_type;
+ short l_whence;
+ __kernel_off_t l_start;
+ __kernel_off_t l_len;
+ __kernel_pid_t l_pid;
+#ifdef __ARCH_FLOCK_EXTRA_SYSID
+ __ARCH_FLOCK_EXTRA_SYSID
+#endif
+#ifdef __ARCH_FLOCK_PAD
+ __ARCH_FLOCK_PAD
+#endif
+};
+
+struct flock64 {
+ short l_type;
+ short l_whence;
+ __kernel_loff_t l_start;
+ __kernel_loff_t l_len;
+ __kernel_pid_t l_pid;
+#ifdef __ARCH_FLOCK64_PAD
+ __ARCH_FLOCK64_PAD
+#endif
+};
+#endif /* HAVE_ARCH_STRUCT_FLOCK */
+
+#endif /* _ASM_GENERIC_FCNTL_H */
diff --git a/tools/include/uapi/asm-generic/ioctls.h b/tools/include/uapi/asm-generic/ioctls.h
new file mode 100644
index 0000000000..cdc9f4ca8c
--- /dev/null
+++ b/tools/include/uapi/asm-generic/ioctls.h
@@ -0,0 +1,121 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __ASM_GENERIC_IOCTLS_H
+#define __ASM_GENERIC_IOCTLS_H
+
+#include <linux/ioctl.h>
+
+/*
+ * These are the most common definitions for tty ioctl numbers.
+ * Most of them do not use the recommended _IOC(), but there is
+ * probably some source code out there hardcoding the number,
+ * so we might as well use them for all new platforms.
+ *
+ * The architectures that use different values here typically
+ * try to be compatible with some Unix variants for the same
+ * architecture.
+ */
+
+/* 0x54 is just a magic number to make these relatively unique ('T') */
+
+#define TCGETS 0x5401
+#define TCSETS 0x5402
+#define TCSETSW 0x5403
+#define TCSETSF 0x5404
+#define TCGETA 0x5405
+#define TCSETA 0x5406
+#define TCSETAW 0x5407
+#define TCSETAF 0x5408
+#define TCSBRK 0x5409
+#define TCXONC 0x540A
+#define TCFLSH 0x540B
+#define TIOCEXCL 0x540C
+#define TIOCNXCL 0x540D
+#define TIOCSCTTY 0x540E
+#define TIOCGPGRP 0x540F
+#define TIOCSPGRP 0x5410
+#define TIOCOUTQ 0x5411
+#define TIOCSTI 0x5412
+#define TIOCGWINSZ 0x5413
+#define TIOCSWINSZ 0x5414
+#define TIOCMGET 0x5415
+#define TIOCMBIS 0x5416
+#define TIOCMBIC 0x5417
+#define TIOCMSET 0x5418
+#define TIOCGSOFTCAR 0x5419
+#define TIOCSSOFTCAR 0x541A
+#define FIONREAD 0x541B
+#define TIOCINQ FIONREAD
+#define TIOCLINUX 0x541C
+#define TIOCCONS 0x541D
+#define TIOCGSERIAL 0x541E
+#define TIOCSSERIAL 0x541F
+#define TIOCPKT 0x5420
+#define FIONBIO 0x5421
+#define TIOCNOTTY 0x5422
+#define TIOCSETD 0x5423
+#define TIOCGETD 0x5424
+#define TCSBRKP 0x5425 /* Needed for POSIX tcsendbreak() */
+#define TIOCSBRK 0x5427 /* BSD compatibility */
+#define TIOCCBRK 0x5428 /* BSD compatibility */
+#define TIOCGSID 0x5429 /* Return the session ID of FD */
+#define TCGETS2 _IOR('T', 0x2A, struct termios2)
+#define TCSETS2 _IOW('T', 0x2B, struct termios2)
+#define TCSETSW2 _IOW('T', 0x2C, struct termios2)
+#define TCSETSF2 _IOW('T', 0x2D, struct termios2)
+#define TIOCGRS485 0x542E
+#ifndef TIOCSRS485
+#define TIOCSRS485 0x542F
+#endif
+#define TIOCGPTN _IOR('T', 0x30, unsigned int) /* Get Pty Number (of pty-mux device) */
+#define TIOCSPTLCK _IOW('T', 0x31, int) /* Lock/unlock Pty */
+#define TIOCGDEV _IOR('T', 0x32, unsigned int) /* Get primary device node of /dev/console */
+#define TCGETX 0x5432 /* SYS5 TCGETX compatibility */
+#define TCSETX 0x5433
+#define TCSETXF 0x5434
+#define TCSETXW 0x5435
+#define TIOCSIG _IOW('T', 0x36, int) /* pty: generate signal */
+#define TIOCVHANGUP 0x5437
+#define TIOCGPKT _IOR('T', 0x38, int) /* Get packet mode state */
+#define TIOCGPTLCK _IOR('T', 0x39, int) /* Get Pty lock state */
+#define TIOCGEXCL _IOR('T', 0x40, int) /* Get exclusive mode state */
+#define TIOCGPTPEER _IO('T', 0x41) /* Safely open the slave */
+#define TIOCGISO7816 _IOR('T', 0x42, struct serial_iso7816)
+#define TIOCSISO7816 _IOWR('T', 0x43, struct serial_iso7816)
+
+#define FIONCLEX 0x5450
+#define FIOCLEX 0x5451
+#define FIOASYNC 0x5452
+#define TIOCSERCONFIG 0x5453
+#define TIOCSERGWILD 0x5454
+#define TIOCSERSWILD 0x5455
+#define TIOCGLCKTRMIOS 0x5456
+#define TIOCSLCKTRMIOS 0x5457
+#define TIOCSERGSTRUCT 0x5458 /* For debugging only */
+#define TIOCSERGETLSR 0x5459 /* Get line status register */
+#define TIOCSERGETMULTI 0x545A /* Get multiport config */
+#define TIOCSERSETMULTI 0x545B /* Set multiport config */
+
+#define TIOCMIWAIT 0x545C /* wait for a change on serial input line(s) */
+#define TIOCGICOUNT 0x545D /* read serial port inline interrupt counts */
+
+/*
+ * Some arches already define FIOQSIZE due to a historical
+ * conflict with a Hayes modem-specific ioctl value.
+ */
+#ifndef FIOQSIZE
+# define FIOQSIZE 0x5460
+#endif
+
+/* Used for packet mode */
+#define TIOCPKT_DATA 0
+#define TIOCPKT_FLUSHREAD 1
+#define TIOCPKT_FLUSHWRITE 2
+#define TIOCPKT_STOP 4
+#define TIOCPKT_START 8
+#define TIOCPKT_NOSTOP 16
+#define TIOCPKT_DOSTOP 32
+#define TIOCPKT_IOCTL 64
+
+#define TIOCSER_TEMT 0x01 /* Transmitter physically empty */
+
+#endif /* __ASM_GENERIC_IOCTLS_H */
diff --git a/tools/include/uapi/asm-generic/mman-common-tools.h b/tools/include/uapi/asm-generic/mman-common-tools.h
new file mode 100644
index 0000000000..af7d0d3a31
--- /dev/null
+++ b/tools/include/uapi/asm-generic/mman-common-tools.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __ASM_GENERIC_MMAN_COMMON_TOOLS_ONLY_H
+#define __ASM_GENERIC_MMAN_COMMON_TOOLS_ONLY_H
+
+#include <asm-generic/mman-common.h>
+
+/* We need this because we need to have tools/include/uapi/ included in the tools
+ * header search path to get access to stuff that is not yet in the system's
+ * copy of the files in that directory, but since this cset:
+ *
+ * 746c9398f5ac ("arch: move common mmap flags to linux/mman.h")
+ *
+ * We end up making sys/mman.h, that is in the system headers, to not find the
+ * MAP_SHARED and MAP_PRIVATE defines because they are not anymore in our copy
+ * of asm-generic/mman-common.h. So we define them here and include this header
+ * from each of the per arch mman.h headers.
+ */
+#ifndef MAP_SHARED
+#define MAP_SHARED 0x01 /* Share changes */
+#define MAP_PRIVATE 0x02 /* Changes are private */
+#define MAP_SHARED_VALIDATE 0x03 /* share + validate extension flags */
+#endif
+#endif // __ASM_GENERIC_MMAN_COMMON_TOOLS_ONLY_H
diff --git a/tools/include/uapi/asm-generic/mman-common.h b/tools/include/uapi/asm-generic/mman-common.h
new file mode 100644
index 0000000000..6ce1f1ceb4
--- /dev/null
+++ b/tools/include/uapi/asm-generic/mman-common.h
@@ -0,0 +1,90 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __ASM_GENERIC_MMAN_COMMON_H
+#define __ASM_GENERIC_MMAN_COMMON_H
+
+/*
+ Author: Michael S. Tsirkin <mst@mellanox.co.il>, Mellanox Technologies Ltd.
+ Based on: asm-xxx/mman.h
+*/
+
+#define PROT_READ 0x1 /* page can be read */
+#define PROT_WRITE 0x2 /* page can be written */
+#define PROT_EXEC 0x4 /* page can be executed */
+#define PROT_SEM 0x8 /* page may be used for atomic ops */
+/* 0x10 reserved for arch-specific use */
+/* 0x20 reserved for arch-specific use */
+#define PROT_NONE 0x0 /* page can not be accessed */
+#define PROT_GROWSDOWN 0x01000000 /* mprotect flag: extend change to start of growsdown vma */
+#define PROT_GROWSUP 0x02000000 /* mprotect flag: extend change to end of growsup vma */
+
+/* 0x01 - 0x03 are defined in linux/mman.h */
+#define MAP_TYPE 0x0f /* Mask for type of mapping */
+#define MAP_FIXED 0x10 /* Interpret addr exactly */
+#define MAP_ANONYMOUS 0x20 /* don't use a file */
+
+/* 0x0100 - 0x4000 flags are defined in asm-generic/mman.h */
+#define MAP_POPULATE 0x008000 /* populate (prefault) pagetables */
+#define MAP_NONBLOCK 0x010000 /* do not block on IO */
+#define MAP_STACK 0x020000 /* give out an address that is best suited for process/thread stacks */
+#define MAP_HUGETLB 0x040000 /* create a huge page mapping */
+#define MAP_SYNC 0x080000 /* perform synchronous page faults for the mapping */
+#define MAP_FIXED_NOREPLACE 0x100000 /* MAP_FIXED which doesn't unmap underlying mapping */
+
+#define MAP_UNINITIALIZED 0x4000000 /* For anonymous mmap, memory could be
+ * uninitialized */
+
+/*
+ * Flags for mlock
+ */
+#define MLOCK_ONFAULT 0x01 /* Lock pages in range after they are faulted in, do not prefault */
+
+#define MS_ASYNC 1 /* sync memory asynchronously */
+#define MS_INVALIDATE 2 /* invalidate the caches */
+#define MS_SYNC 4 /* synchronous memory sync */
+
+#define MADV_NORMAL 0 /* no further special treatment */
+#define MADV_RANDOM 1 /* expect random page references */
+#define MADV_SEQUENTIAL 2 /* expect sequential page references */
+#define MADV_WILLNEED 3 /* will need these pages */
+#define MADV_DONTNEED 4 /* don't need these pages */
+
+/* common parameters: try to keep these consistent across architectures */
+#define MADV_FREE 8 /* free pages only if memory pressure */
+#define MADV_REMOVE 9 /* remove these pages & resources */
+#define MADV_DONTFORK 10 /* don't inherit across fork */
+#define MADV_DOFORK 11 /* do inherit across fork */
+#define MADV_HWPOISON 100 /* poison a page for testing */
+#define MADV_SOFT_OFFLINE 101 /* soft offline page for testing */
+
+#define MADV_MERGEABLE 12 /* KSM may merge identical pages */
+#define MADV_UNMERGEABLE 13 /* KSM may not merge identical pages */
+
+#define MADV_HUGEPAGE 14 /* Worth backing with hugepages */
+#define MADV_NOHUGEPAGE 15 /* Not worth backing with hugepages */
+
+#define MADV_DONTDUMP 16 /* Explicity exclude from the core dump,
+ overrides the coredump filter bits */
+#define MADV_DODUMP 17 /* Clear the MADV_DONTDUMP flag */
+
+#define MADV_WIPEONFORK 18 /* Zero memory on fork, child only */
+#define MADV_KEEPONFORK 19 /* Undo MADV_WIPEONFORK */
+
+#define MADV_COLD 20 /* deactivate these pages */
+#define MADV_PAGEOUT 21 /* reclaim these pages */
+
+#define MADV_POPULATE_READ 22 /* populate (prefault) page tables readable */
+#define MADV_POPULATE_WRITE 23 /* populate (prefault) page tables writable */
+
+#define MADV_DONTNEED_LOCKED 24 /* like DONTNEED, but drop locked pages too */
+
+#define MADV_COLLAPSE 25 /* Synchronous hugepage collapse */
+
+/* compatibility flags */
+#define MAP_FILE 0
+
+#define PKEY_DISABLE_ACCESS 0x1
+#define PKEY_DISABLE_WRITE 0x2
+#define PKEY_ACCESS_MASK (PKEY_DISABLE_ACCESS |\
+ PKEY_DISABLE_WRITE)
+
+#endif /* __ASM_GENERIC_MMAN_COMMON_H */
diff --git a/tools/include/uapi/asm-generic/mman.h b/tools/include/uapi/asm-generic/mman.h
new file mode 100644
index 0000000000..406f7718f9
--- /dev/null
+++ b/tools/include/uapi/asm-generic/mman.h
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __ASM_GENERIC_MMAN_H
+#define __ASM_GENERIC_MMAN_H
+
+#include <asm-generic/mman-common-tools.h>
+
+#define MAP_GROWSDOWN 0x0100 /* stack-like segment */
+#define MAP_DENYWRITE 0x0800 /* ETXTBSY */
+#define MAP_EXECUTABLE 0x1000 /* mark it as an executable */
+#define MAP_LOCKED 0x2000 /* pages are locked */
+#define MAP_NORESERVE 0x4000 /* don't check for reservations */
+
+/*
+ * Bits [26:31] are reserved, see asm-generic/hugetlb_encode.h
+ * for MAP_HUGETLB usage
+ */
+
+#define MCL_CURRENT 1 /* lock all current mappings */
+#define MCL_FUTURE 2 /* lock all future mappings */
+#define MCL_ONFAULT 4 /* lock all pages that are faulted in */
+
+#endif /* __ASM_GENERIC_MMAN_H */
diff --git a/tools/include/uapi/asm-generic/socket.h b/tools/include/uapi/asm-generic/socket.h
new file mode 100644
index 0000000000..54d9c8bf7c
--- /dev/null
+++ b/tools/include/uapi/asm-generic/socket.h
@@ -0,0 +1,152 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __ASM_GENERIC_SOCKET_H
+#define __ASM_GENERIC_SOCKET_H
+
+#include <linux/posix_types.h>
+#include <asm/sockios.h>
+
+/* For setsockopt(2) */
+#define SOL_SOCKET 1
+
+#define SO_DEBUG 1
+#define SO_REUSEADDR 2
+#define SO_TYPE 3
+#define SO_ERROR 4
+#define SO_DONTROUTE 5
+#define SO_BROADCAST 6
+#define SO_SNDBUF 7
+#define SO_RCVBUF 8
+#define SO_SNDBUFFORCE 32
+#define SO_RCVBUFFORCE 33
+#define SO_KEEPALIVE 9
+#define SO_OOBINLINE 10
+#define SO_NO_CHECK 11
+#define SO_PRIORITY 12
+#define SO_LINGER 13
+#define SO_BSDCOMPAT 14
+#define SO_REUSEPORT 15
+#ifndef SO_PASSCRED /* powerpc only differs in these */
+#define SO_PASSCRED 16
+#define SO_PEERCRED 17
+#define SO_RCVLOWAT 18
+#define SO_SNDLOWAT 19
+#define SO_RCVTIMEO_OLD 20
+#define SO_SNDTIMEO_OLD 21
+#endif
+
+/* Security levels - as per NRL IPv6 - don't actually do anything */
+#define SO_SECURITY_AUTHENTICATION 22
+#define SO_SECURITY_ENCRYPTION_TRANSPORT 23
+#define SO_SECURITY_ENCRYPTION_NETWORK 24
+
+#define SO_BINDTODEVICE 25
+
+/* Socket filtering */
+#define SO_ATTACH_FILTER 26
+#define SO_DETACH_FILTER 27
+#define SO_GET_FILTER SO_ATTACH_FILTER
+
+#define SO_PEERNAME 28
+
+#define SO_ACCEPTCONN 30
+
+#define SO_PEERSEC 31
+#define SO_PASSSEC 34
+
+#define SO_MARK 36
+
+#define SO_PROTOCOL 38
+#define SO_DOMAIN 39
+
+#define SO_RXQ_OVFL 40
+
+#define SO_WIFI_STATUS 41
+#define SCM_WIFI_STATUS SO_WIFI_STATUS
+#define SO_PEEK_OFF 42
+
+/* Instruct lower device to use last 4-bytes of skb data as FCS */
+#define SO_NOFCS 43
+
+#define SO_LOCK_FILTER 44
+
+#define SO_SELECT_ERR_QUEUE 45
+
+#define SO_BUSY_POLL 46
+
+#define SO_MAX_PACING_RATE 47
+
+#define SO_BPF_EXTENSIONS 48
+
+#define SO_INCOMING_CPU 49
+
+#define SO_ATTACH_BPF 50
+#define SO_DETACH_BPF SO_DETACH_FILTER
+
+#define SO_ATTACH_REUSEPORT_CBPF 51
+#define SO_ATTACH_REUSEPORT_EBPF 52
+
+#define SO_CNX_ADVICE 53
+
+#define SCM_TIMESTAMPING_OPT_STATS 54
+
+#define SO_MEMINFO 55
+
+#define SO_INCOMING_NAPI_ID 56
+
+#define SO_COOKIE 57
+
+#define SCM_TIMESTAMPING_PKTINFO 58
+
+#define SO_PEERGROUPS 59
+
+#define SO_ZEROCOPY 60
+
+#define SO_TXTIME 61
+#define SCM_TXTIME SO_TXTIME
+
+#define SO_BINDTOIFINDEX 62
+
+#define SO_TIMESTAMP_OLD 29
+#define SO_TIMESTAMPNS_OLD 35
+#define SO_TIMESTAMPING_OLD 37
+
+#define SO_TIMESTAMP_NEW 63
+#define SO_TIMESTAMPNS_NEW 64
+#define SO_TIMESTAMPING_NEW 65
+
+#define SO_RCVTIMEO_NEW 66
+#define SO_SNDTIMEO_NEW 67
+
+#define SO_DETACH_REUSEPORT_BPF 68
+
+#define SO_RCVMARK 75
+
+#define SO_PASSPIDFD 76
+#define SO_PEERPIDFD 77
+
+#if !defined(__KERNEL__)
+
+#if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__))
+/* on 64-bit and x32, avoid the ?: operator */
+#define SO_TIMESTAMP SO_TIMESTAMP_OLD
+#define SO_TIMESTAMPNS SO_TIMESTAMPNS_OLD
+#define SO_TIMESTAMPING SO_TIMESTAMPING_OLD
+
+#define SO_RCVTIMEO SO_RCVTIMEO_OLD
+#define SO_SNDTIMEO SO_SNDTIMEO_OLD
+#else
+#define SO_TIMESTAMP (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMP_OLD : SO_TIMESTAMP_NEW)
+#define SO_TIMESTAMPNS (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMPNS_OLD : SO_TIMESTAMPNS_NEW)
+#define SO_TIMESTAMPING (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMPING_OLD : SO_TIMESTAMPING_NEW)
+
+#define SO_RCVTIMEO (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_RCVTIMEO_OLD : SO_RCVTIMEO_NEW)
+#define SO_SNDTIMEO (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_SNDTIMEO_OLD : SO_SNDTIMEO_NEW)
+#endif
+
+#define SCM_TIMESTAMP SO_TIMESTAMP
+#define SCM_TIMESTAMPNS SO_TIMESTAMPNS
+#define SCM_TIMESTAMPING SO_TIMESTAMPING
+
+#endif
+
+#endif /* __ASM_GENERIC_SOCKET_H */
diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
new file mode 100644
index 0000000000..abe087c53b
--- /dev/null
+++ b/tools/include/uapi/asm-generic/unistd.h
@@ -0,0 +1,875 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#include <asm/bitsperlong.h>
+
+/*
+ * This file contains the system call numbers, based on the
+ * layout of the x86-64 architecture, which embeds the
+ * pointer to the syscall in the table.
+ *
+ * As a basic principle, no duplication of functionality
+ * should be added, e.g. we don't use lseek when llseek
+ * is present. New architectures should use this file
+ * and implement the less feature-full calls in user space.
+ */
+
+#ifndef __SYSCALL
+#define __SYSCALL(x, y)
+#endif
+
+#if __BITS_PER_LONG == 32 || defined(__SYSCALL_COMPAT)
+#define __SC_3264(_nr, _32, _64) __SYSCALL(_nr, _32)
+#else
+#define __SC_3264(_nr, _32, _64) __SYSCALL(_nr, _64)
+#endif
+
+#ifdef __SYSCALL_COMPAT
+#define __SC_COMP(_nr, _sys, _comp) __SYSCALL(_nr, _comp)
+#define __SC_COMP_3264(_nr, _32, _64, _comp) __SYSCALL(_nr, _comp)
+#else
+#define __SC_COMP(_nr, _sys, _comp) __SYSCALL(_nr, _sys)
+#define __SC_COMP_3264(_nr, _32, _64, _comp) __SC_3264(_nr, _32, _64)
+#endif
+
+#define __NR_io_setup 0
+__SC_COMP(__NR_io_setup, sys_io_setup, compat_sys_io_setup)
+#define __NR_io_destroy 1
+__SYSCALL(__NR_io_destroy, sys_io_destroy)
+#define __NR_io_submit 2
+__SC_COMP(__NR_io_submit, sys_io_submit, compat_sys_io_submit)
+#define __NR_io_cancel 3
+__SYSCALL(__NR_io_cancel, sys_io_cancel)
+
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
+#define __NR_io_getevents 4
+__SC_3264(__NR_io_getevents, sys_io_getevents_time32, sys_io_getevents)
+#endif
+
+#define __NR_setxattr 5
+__SYSCALL(__NR_setxattr, sys_setxattr)
+#define __NR_lsetxattr 6
+__SYSCALL(__NR_lsetxattr, sys_lsetxattr)
+#define __NR_fsetxattr 7
+__SYSCALL(__NR_fsetxattr, sys_fsetxattr)
+#define __NR_getxattr 8
+__SYSCALL(__NR_getxattr, sys_getxattr)
+#define __NR_lgetxattr 9
+__SYSCALL(__NR_lgetxattr, sys_lgetxattr)
+#define __NR_fgetxattr 10
+__SYSCALL(__NR_fgetxattr, sys_fgetxattr)
+#define __NR_listxattr 11
+__SYSCALL(__NR_listxattr, sys_listxattr)
+#define __NR_llistxattr 12
+__SYSCALL(__NR_llistxattr, sys_llistxattr)
+#define __NR_flistxattr 13
+__SYSCALL(__NR_flistxattr, sys_flistxattr)
+#define __NR_removexattr 14
+__SYSCALL(__NR_removexattr, sys_removexattr)
+#define __NR_lremovexattr 15
+__SYSCALL(__NR_lremovexattr, sys_lremovexattr)
+#define __NR_fremovexattr 16
+__SYSCALL(__NR_fremovexattr, sys_fremovexattr)
+#define __NR_getcwd 17
+__SYSCALL(__NR_getcwd, sys_getcwd)
+#define __NR_lookup_dcookie 18
+__SC_COMP(__NR_lookup_dcookie, sys_lookup_dcookie, compat_sys_lookup_dcookie)
+#define __NR_eventfd2 19
+__SYSCALL(__NR_eventfd2, sys_eventfd2)
+#define __NR_epoll_create1 20
+__SYSCALL(__NR_epoll_create1, sys_epoll_create1)
+#define __NR_epoll_ctl 21
+__SYSCALL(__NR_epoll_ctl, sys_epoll_ctl)
+#define __NR_epoll_pwait 22
+__SC_COMP(__NR_epoll_pwait, sys_epoll_pwait, compat_sys_epoll_pwait)
+#define __NR_dup 23
+__SYSCALL(__NR_dup, sys_dup)
+#define __NR_dup3 24
+__SYSCALL(__NR_dup3, sys_dup3)
+#define __NR3264_fcntl 25
+__SC_COMP_3264(__NR3264_fcntl, sys_fcntl64, sys_fcntl, compat_sys_fcntl64)
+#define __NR_inotify_init1 26
+__SYSCALL(__NR_inotify_init1, sys_inotify_init1)
+#define __NR_inotify_add_watch 27
+__SYSCALL(__NR_inotify_add_watch, sys_inotify_add_watch)
+#define __NR_inotify_rm_watch 28
+__SYSCALL(__NR_inotify_rm_watch, sys_inotify_rm_watch)
+#define __NR_ioctl 29
+__SC_COMP(__NR_ioctl, sys_ioctl, compat_sys_ioctl)
+#define __NR_ioprio_set 30
+__SYSCALL(__NR_ioprio_set, sys_ioprio_set)
+#define __NR_ioprio_get 31
+__SYSCALL(__NR_ioprio_get, sys_ioprio_get)
+#define __NR_flock 32
+__SYSCALL(__NR_flock, sys_flock)
+#define __NR_mknodat 33
+__SYSCALL(__NR_mknodat, sys_mknodat)
+#define __NR_mkdirat 34
+__SYSCALL(__NR_mkdirat, sys_mkdirat)
+#define __NR_unlinkat 35
+__SYSCALL(__NR_unlinkat, sys_unlinkat)
+#define __NR_symlinkat 36
+__SYSCALL(__NR_symlinkat, sys_symlinkat)
+#define __NR_linkat 37
+__SYSCALL(__NR_linkat, sys_linkat)
+
+#ifdef __ARCH_WANT_RENAMEAT
+/* renameat is superseded with flags by renameat2 */
+#define __NR_renameat 38
+__SYSCALL(__NR_renameat, sys_renameat)
+#endif /* __ARCH_WANT_RENAMEAT */
+
+#define __NR_umount2 39
+__SYSCALL(__NR_umount2, sys_umount)
+#define __NR_mount 40
+__SYSCALL(__NR_mount, sys_mount)
+#define __NR_pivot_root 41
+__SYSCALL(__NR_pivot_root, sys_pivot_root)
+#define __NR_nfsservctl 42
+__SYSCALL(__NR_nfsservctl, sys_ni_syscall)
+#define __NR3264_statfs 43
+__SC_COMP_3264(__NR3264_statfs, sys_statfs64, sys_statfs, \
+ compat_sys_statfs64)
+#define __NR3264_fstatfs 44
+__SC_COMP_3264(__NR3264_fstatfs, sys_fstatfs64, sys_fstatfs, \
+ compat_sys_fstatfs64)
+#define __NR3264_truncate 45
+__SC_COMP_3264(__NR3264_truncate, sys_truncate64, sys_truncate, \
+ compat_sys_truncate64)
+#define __NR3264_ftruncate 46
+__SC_COMP_3264(__NR3264_ftruncate, sys_ftruncate64, sys_ftruncate, \
+ compat_sys_ftruncate64)
+#define __NR_fallocate 47
+__SC_COMP(__NR_fallocate, sys_fallocate, compat_sys_fallocate)
+#define __NR_faccessat 48
+__SYSCALL(__NR_faccessat, sys_faccessat)
+#define __NR_chdir 49
+__SYSCALL(__NR_chdir, sys_chdir)
+#define __NR_fchdir 50
+__SYSCALL(__NR_fchdir, sys_fchdir)
+#define __NR_chroot 51
+__SYSCALL(__NR_chroot, sys_chroot)
+#define __NR_fchmod 52
+__SYSCALL(__NR_fchmod, sys_fchmod)
+#define __NR_fchmodat 53
+__SYSCALL(__NR_fchmodat, sys_fchmodat)
+#define __NR_fchownat 54
+__SYSCALL(__NR_fchownat, sys_fchownat)
+#define __NR_fchown 55
+__SYSCALL(__NR_fchown, sys_fchown)
+#define __NR_openat 56
+__SYSCALL(__NR_openat, sys_openat)
+#define __NR_close 57
+__SYSCALL(__NR_close, sys_close)
+#define __NR_vhangup 58
+__SYSCALL(__NR_vhangup, sys_vhangup)
+#define __NR_pipe2 59
+__SYSCALL(__NR_pipe2, sys_pipe2)
+#define __NR_quotactl 60
+__SYSCALL(__NR_quotactl, sys_quotactl)
+#define __NR_getdents64 61
+__SYSCALL(__NR_getdents64, sys_getdents64)
+#define __NR3264_lseek 62
+__SC_3264(__NR3264_lseek, sys_llseek, sys_lseek)
+#define __NR_read 63
+__SYSCALL(__NR_read, sys_read)
+#define __NR_write 64
+__SYSCALL(__NR_write, sys_write)
+#define __NR_readv 65
+__SC_COMP(__NR_readv, sys_readv, sys_readv)
+#define __NR_writev 66
+__SC_COMP(__NR_writev, sys_writev, sys_writev)
+#define __NR_pread64 67
+__SC_COMP(__NR_pread64, sys_pread64, compat_sys_pread64)
+#define __NR_pwrite64 68
+__SC_COMP(__NR_pwrite64, sys_pwrite64, compat_sys_pwrite64)
+#define __NR_preadv 69
+__SC_COMP(__NR_preadv, sys_preadv, compat_sys_preadv)
+#define __NR_pwritev 70
+__SC_COMP(__NR_pwritev, sys_pwritev, compat_sys_pwritev)
+#define __NR3264_sendfile 71
+__SYSCALL(__NR3264_sendfile, sys_sendfile64)
+
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
+#define __NR_pselect6 72
+__SC_COMP_3264(__NR_pselect6, sys_pselect6_time32, sys_pselect6, compat_sys_pselect6_time32)
+#define __NR_ppoll 73
+__SC_COMP_3264(__NR_ppoll, sys_ppoll_time32, sys_ppoll, compat_sys_ppoll_time32)
+#endif
+
+#define __NR_signalfd4 74
+__SC_COMP(__NR_signalfd4, sys_signalfd4, compat_sys_signalfd4)
+#define __NR_vmsplice 75
+__SYSCALL(__NR_vmsplice, sys_vmsplice)
+#define __NR_splice 76
+__SYSCALL(__NR_splice, sys_splice)
+#define __NR_tee 77
+__SYSCALL(__NR_tee, sys_tee)
+#define __NR_readlinkat 78
+__SYSCALL(__NR_readlinkat, sys_readlinkat)
+
+#if defined(__ARCH_WANT_NEW_STAT) || defined(__ARCH_WANT_STAT64)
+#define __NR3264_fstatat 79
+__SC_3264(__NR3264_fstatat, sys_fstatat64, sys_newfstatat)
+#define __NR3264_fstat 80
+__SC_3264(__NR3264_fstat, sys_fstat64, sys_newfstat)
+#endif
+
+#define __NR_sync 81
+__SYSCALL(__NR_sync, sys_sync)
+#define __NR_fsync 82
+__SYSCALL(__NR_fsync, sys_fsync)
+#define __NR_fdatasync 83
+__SYSCALL(__NR_fdatasync, sys_fdatasync)
+
+#ifdef __ARCH_WANT_SYNC_FILE_RANGE2
+#define __NR_sync_file_range2 84
+__SC_COMP(__NR_sync_file_range2, sys_sync_file_range2, \
+ compat_sys_sync_file_range2)
+#else
+#define __NR_sync_file_range 84
+__SC_COMP(__NR_sync_file_range, sys_sync_file_range, \
+ compat_sys_sync_file_range)
+#endif
+
+#define __NR_timerfd_create 85
+__SYSCALL(__NR_timerfd_create, sys_timerfd_create)
+
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
+#define __NR_timerfd_settime 86
+__SC_3264(__NR_timerfd_settime, sys_timerfd_settime32, \
+ sys_timerfd_settime)
+#define __NR_timerfd_gettime 87
+__SC_3264(__NR_timerfd_gettime, sys_timerfd_gettime32, \
+ sys_timerfd_gettime)
+#endif
+
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
+#define __NR_utimensat 88
+__SC_3264(__NR_utimensat, sys_utimensat_time32, sys_utimensat)
+#endif
+
+#define __NR_acct 89
+__SYSCALL(__NR_acct, sys_acct)
+#define __NR_capget 90
+__SYSCALL(__NR_capget, sys_capget)
+#define __NR_capset 91
+__SYSCALL(__NR_capset, sys_capset)
+#define __NR_personality 92
+__SYSCALL(__NR_personality, sys_personality)
+#define __NR_exit 93
+__SYSCALL(__NR_exit, sys_exit)
+#define __NR_exit_group 94
+__SYSCALL(__NR_exit_group, sys_exit_group)
+#define __NR_waitid 95
+__SC_COMP(__NR_waitid, sys_waitid, compat_sys_waitid)
+#define __NR_set_tid_address 96
+__SYSCALL(__NR_set_tid_address, sys_set_tid_address)
+#define __NR_unshare 97
+__SYSCALL(__NR_unshare, sys_unshare)
+
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
+#define __NR_futex 98
+__SC_3264(__NR_futex, sys_futex_time32, sys_futex)
+#endif
+
+#define __NR_set_robust_list 99
+__SC_COMP(__NR_set_robust_list, sys_set_robust_list, \
+ compat_sys_set_robust_list)
+#define __NR_get_robust_list 100
+__SC_COMP(__NR_get_robust_list, sys_get_robust_list, \
+ compat_sys_get_robust_list)
+
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
+#define __NR_nanosleep 101
+__SC_3264(__NR_nanosleep, sys_nanosleep_time32, sys_nanosleep)
+#endif
+
+#define __NR_getitimer 102
+__SC_COMP(__NR_getitimer, sys_getitimer, compat_sys_getitimer)
+#define __NR_setitimer 103
+__SC_COMP(__NR_setitimer, sys_setitimer, compat_sys_setitimer)
+#define __NR_kexec_load 104
+__SC_COMP(__NR_kexec_load, sys_kexec_load, compat_sys_kexec_load)
+#define __NR_init_module 105
+__SYSCALL(__NR_init_module, sys_init_module)
+#define __NR_delete_module 106
+__SYSCALL(__NR_delete_module, sys_delete_module)
+#define __NR_timer_create 107
+__SC_COMP(__NR_timer_create, sys_timer_create, compat_sys_timer_create)
+
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
+#define __NR_timer_gettime 108
+__SC_3264(__NR_timer_gettime, sys_timer_gettime32, sys_timer_gettime)
+#endif
+
+#define __NR_timer_getoverrun 109
+__SYSCALL(__NR_timer_getoverrun, sys_timer_getoverrun)
+
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
+#define __NR_timer_settime 110
+__SC_3264(__NR_timer_settime, sys_timer_settime32, sys_timer_settime)
+#endif
+
+#define __NR_timer_delete 111
+__SYSCALL(__NR_timer_delete, sys_timer_delete)
+
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
+#define __NR_clock_settime 112
+__SC_3264(__NR_clock_settime, sys_clock_settime32, sys_clock_settime)
+#define __NR_clock_gettime 113
+__SC_3264(__NR_clock_gettime, sys_clock_gettime32, sys_clock_gettime)
+#define __NR_clock_getres 114
+__SC_3264(__NR_clock_getres, sys_clock_getres_time32, sys_clock_getres)
+#define __NR_clock_nanosleep 115
+__SC_3264(__NR_clock_nanosleep, sys_clock_nanosleep_time32, \
+ sys_clock_nanosleep)
+#endif
+
+#define __NR_syslog 116
+__SYSCALL(__NR_syslog, sys_syslog)
+#define __NR_ptrace 117
+__SC_COMP(__NR_ptrace, sys_ptrace, compat_sys_ptrace)
+#define __NR_sched_setparam 118
+__SYSCALL(__NR_sched_setparam, sys_sched_setparam)
+#define __NR_sched_setscheduler 119
+__SYSCALL(__NR_sched_setscheduler, sys_sched_setscheduler)
+#define __NR_sched_getscheduler 120
+__SYSCALL(__NR_sched_getscheduler, sys_sched_getscheduler)
+#define __NR_sched_getparam 121
+__SYSCALL(__NR_sched_getparam, sys_sched_getparam)
+#define __NR_sched_setaffinity 122
+__SC_COMP(__NR_sched_setaffinity, sys_sched_setaffinity, \
+ compat_sys_sched_setaffinity)
+#define __NR_sched_getaffinity 123
+__SC_COMP(__NR_sched_getaffinity, sys_sched_getaffinity, \
+ compat_sys_sched_getaffinity)
+#define __NR_sched_yield 124
+__SYSCALL(__NR_sched_yield, sys_sched_yield)
+#define __NR_sched_get_priority_max 125
+__SYSCALL(__NR_sched_get_priority_max, sys_sched_get_priority_max)
+#define __NR_sched_get_priority_min 126
+__SYSCALL(__NR_sched_get_priority_min, sys_sched_get_priority_min)
+
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
+#define __NR_sched_rr_get_interval 127
+__SC_3264(__NR_sched_rr_get_interval, sys_sched_rr_get_interval_time32, \
+ sys_sched_rr_get_interval)
+#endif
+
+#define __NR_restart_syscall 128
+__SYSCALL(__NR_restart_syscall, sys_restart_syscall)
+#define __NR_kill 129
+__SYSCALL(__NR_kill, sys_kill)
+#define __NR_tkill 130
+__SYSCALL(__NR_tkill, sys_tkill)
+#define __NR_tgkill 131
+__SYSCALL(__NR_tgkill, sys_tgkill)
+#define __NR_sigaltstack 132
+__SC_COMP(__NR_sigaltstack, sys_sigaltstack, compat_sys_sigaltstack)
+#define __NR_rt_sigsuspend 133
+__SC_COMP(__NR_rt_sigsuspend, sys_rt_sigsuspend, compat_sys_rt_sigsuspend)
+#define __NR_rt_sigaction 134
+__SC_COMP(__NR_rt_sigaction, sys_rt_sigaction, compat_sys_rt_sigaction)
+#define __NR_rt_sigprocmask 135
+__SC_COMP(__NR_rt_sigprocmask, sys_rt_sigprocmask, compat_sys_rt_sigprocmask)
+#define __NR_rt_sigpending 136
+__SC_COMP(__NR_rt_sigpending, sys_rt_sigpending, compat_sys_rt_sigpending)
+
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
+#define __NR_rt_sigtimedwait 137
+__SC_COMP_3264(__NR_rt_sigtimedwait, sys_rt_sigtimedwait_time32, \
+ sys_rt_sigtimedwait, compat_sys_rt_sigtimedwait_time32)
+#endif
+
+#define __NR_rt_sigqueueinfo 138
+__SC_COMP(__NR_rt_sigqueueinfo, sys_rt_sigqueueinfo, \
+ compat_sys_rt_sigqueueinfo)
+#define __NR_rt_sigreturn 139
+__SC_COMP(__NR_rt_sigreturn, sys_rt_sigreturn, compat_sys_rt_sigreturn)
+#define __NR_setpriority 140
+__SYSCALL(__NR_setpriority, sys_setpriority)
+#define __NR_getpriority 141
+__SYSCALL(__NR_getpriority, sys_getpriority)
+#define __NR_reboot 142
+__SYSCALL(__NR_reboot, sys_reboot)
+#define __NR_setregid 143
+__SYSCALL(__NR_setregid, sys_setregid)
+#define __NR_setgid 144
+__SYSCALL(__NR_setgid, sys_setgid)
+#define __NR_setreuid 145
+__SYSCALL(__NR_setreuid, sys_setreuid)
+#define __NR_setuid 146
+__SYSCALL(__NR_setuid, sys_setuid)
+#define __NR_setresuid 147
+__SYSCALL(__NR_setresuid, sys_setresuid)
+#define __NR_getresuid 148
+__SYSCALL(__NR_getresuid, sys_getresuid)
+#define __NR_setresgid 149
+__SYSCALL(__NR_setresgid, sys_setresgid)
+#define __NR_getresgid 150
+__SYSCALL(__NR_getresgid, sys_getresgid)
+#define __NR_setfsuid 151
+__SYSCALL(__NR_setfsuid, sys_setfsuid)
+#define __NR_setfsgid 152
+__SYSCALL(__NR_setfsgid, sys_setfsgid)
+#define __NR_times 153
+__SC_COMP(__NR_times, sys_times, compat_sys_times)
+#define __NR_setpgid 154
+__SYSCALL(__NR_setpgid, sys_setpgid)
+#define __NR_getpgid 155
+__SYSCALL(__NR_getpgid, sys_getpgid)
+#define __NR_getsid 156
+__SYSCALL(__NR_getsid, sys_getsid)
+#define __NR_setsid 157
+__SYSCALL(__NR_setsid, sys_setsid)
+#define __NR_getgroups 158
+__SYSCALL(__NR_getgroups, sys_getgroups)
+#define __NR_setgroups 159
+__SYSCALL(__NR_setgroups, sys_setgroups)
+#define __NR_uname 160
+__SYSCALL(__NR_uname, sys_newuname)
+#define __NR_sethostname 161
+__SYSCALL(__NR_sethostname, sys_sethostname)
+#define __NR_setdomainname 162
+__SYSCALL(__NR_setdomainname, sys_setdomainname)
+
+#ifdef __ARCH_WANT_SET_GET_RLIMIT
+/* getrlimit and setrlimit are superseded with prlimit64 */
+#define __NR_getrlimit 163
+__SC_COMP(__NR_getrlimit, sys_getrlimit, compat_sys_getrlimit)
+#define __NR_setrlimit 164
+__SC_COMP(__NR_setrlimit, sys_setrlimit, compat_sys_setrlimit)
+#endif
+
+#define __NR_getrusage 165
+__SC_COMP(__NR_getrusage, sys_getrusage, compat_sys_getrusage)
+#define __NR_umask 166
+__SYSCALL(__NR_umask, sys_umask)
+#define __NR_prctl 167
+__SYSCALL(__NR_prctl, sys_prctl)
+#define __NR_getcpu 168
+__SYSCALL(__NR_getcpu, sys_getcpu)
+
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
+#define __NR_gettimeofday 169
+__SC_COMP(__NR_gettimeofday, sys_gettimeofday, compat_sys_gettimeofday)
+#define __NR_settimeofday 170
+__SC_COMP(__NR_settimeofday, sys_settimeofday, compat_sys_settimeofday)
+#define __NR_adjtimex 171
+__SC_3264(__NR_adjtimex, sys_adjtimex_time32, sys_adjtimex)
+#endif
+
+#define __NR_getpid 172
+__SYSCALL(__NR_getpid, sys_getpid)
+#define __NR_getppid 173
+__SYSCALL(__NR_getppid, sys_getppid)
+#define __NR_getuid 174
+__SYSCALL(__NR_getuid, sys_getuid)
+#define __NR_geteuid 175
+__SYSCALL(__NR_geteuid, sys_geteuid)
+#define __NR_getgid 176
+__SYSCALL(__NR_getgid, sys_getgid)
+#define __NR_getegid 177
+__SYSCALL(__NR_getegid, sys_getegid)
+#define __NR_gettid 178
+__SYSCALL(__NR_gettid, sys_gettid)
+#define __NR_sysinfo 179
+__SC_COMP(__NR_sysinfo, sys_sysinfo, compat_sys_sysinfo)
+#define __NR_mq_open 180
+__SC_COMP(__NR_mq_open, sys_mq_open, compat_sys_mq_open)
+#define __NR_mq_unlink 181
+__SYSCALL(__NR_mq_unlink, sys_mq_unlink)
+
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
+#define __NR_mq_timedsend 182
+__SC_3264(__NR_mq_timedsend, sys_mq_timedsend_time32, sys_mq_timedsend)
+#define __NR_mq_timedreceive 183
+__SC_3264(__NR_mq_timedreceive, sys_mq_timedreceive_time32, \
+ sys_mq_timedreceive)
+#endif
+
+#define __NR_mq_notify 184
+__SC_COMP(__NR_mq_notify, sys_mq_notify, compat_sys_mq_notify)
+#define __NR_mq_getsetattr 185
+__SC_COMP(__NR_mq_getsetattr, sys_mq_getsetattr, compat_sys_mq_getsetattr)
+#define __NR_msgget 186
+__SYSCALL(__NR_msgget, sys_msgget)
+#define __NR_msgctl 187
+__SC_COMP(__NR_msgctl, sys_msgctl, compat_sys_msgctl)
+#define __NR_msgrcv 188
+__SC_COMP(__NR_msgrcv, sys_msgrcv, compat_sys_msgrcv)
+#define __NR_msgsnd 189
+__SC_COMP(__NR_msgsnd, sys_msgsnd, compat_sys_msgsnd)
+#define __NR_semget 190
+__SYSCALL(__NR_semget, sys_semget)
+#define __NR_semctl 191
+__SC_COMP(__NR_semctl, sys_semctl, compat_sys_semctl)
+
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
+#define __NR_semtimedop 192
+__SC_3264(__NR_semtimedop, sys_semtimedop_time32, sys_semtimedop)
+#endif
+
+#define __NR_semop 193
+__SYSCALL(__NR_semop, sys_semop)
+#define __NR_shmget 194
+__SYSCALL(__NR_shmget, sys_shmget)
+#define __NR_shmctl 195
+__SC_COMP(__NR_shmctl, sys_shmctl, compat_sys_shmctl)
+#define __NR_shmat 196
+__SC_COMP(__NR_shmat, sys_shmat, compat_sys_shmat)
+#define __NR_shmdt 197
+__SYSCALL(__NR_shmdt, sys_shmdt)
+#define __NR_socket 198
+__SYSCALL(__NR_socket, sys_socket)
+#define __NR_socketpair 199
+__SYSCALL(__NR_socketpair, sys_socketpair)
+#define __NR_bind 200
+__SYSCALL(__NR_bind, sys_bind)
+#define __NR_listen 201
+__SYSCALL(__NR_listen, sys_listen)
+#define __NR_accept 202
+__SYSCALL(__NR_accept, sys_accept)
+#define __NR_connect 203
+__SYSCALL(__NR_connect, sys_connect)
+#define __NR_getsockname 204
+__SYSCALL(__NR_getsockname, sys_getsockname)
+#define __NR_getpeername 205
+__SYSCALL(__NR_getpeername, sys_getpeername)
+#define __NR_sendto 206
+__SYSCALL(__NR_sendto, sys_sendto)
+#define __NR_recvfrom 207
+__SC_COMP(__NR_recvfrom, sys_recvfrom, compat_sys_recvfrom)
+#define __NR_setsockopt 208
+__SC_COMP(__NR_setsockopt, sys_setsockopt, sys_setsockopt)
+#define __NR_getsockopt 209
+__SC_COMP(__NR_getsockopt, sys_getsockopt, sys_getsockopt)
+#define __NR_shutdown 210
+__SYSCALL(__NR_shutdown, sys_shutdown)
+#define __NR_sendmsg 211
+__SC_COMP(__NR_sendmsg, sys_sendmsg, compat_sys_sendmsg)
+#define __NR_recvmsg 212
+__SC_COMP(__NR_recvmsg, sys_recvmsg, compat_sys_recvmsg)
+#define __NR_readahead 213
+__SC_COMP(__NR_readahead, sys_readahead, compat_sys_readahead)
+#define __NR_brk 214
+__SYSCALL(__NR_brk, sys_brk)
+#define __NR_munmap 215
+__SYSCALL(__NR_munmap, sys_munmap)
+#define __NR_mremap 216
+__SYSCALL(__NR_mremap, sys_mremap)
+#define __NR_add_key 217
+__SYSCALL(__NR_add_key, sys_add_key)
+#define __NR_request_key 218
+__SYSCALL(__NR_request_key, sys_request_key)
+#define __NR_keyctl 219
+__SC_COMP(__NR_keyctl, sys_keyctl, compat_sys_keyctl)
+#define __NR_clone 220
+__SYSCALL(__NR_clone, sys_clone)
+#define __NR_execve 221
+__SC_COMP(__NR_execve, sys_execve, compat_sys_execve)
+#define __NR3264_mmap 222
+__SC_3264(__NR3264_mmap, sys_mmap2, sys_mmap)
+#define __NR3264_fadvise64 223
+__SC_COMP(__NR3264_fadvise64, sys_fadvise64_64, compat_sys_fadvise64_64)
+
+/* CONFIG_MMU only */
+#ifndef __ARCH_NOMMU
+#define __NR_swapon 224
+__SYSCALL(__NR_swapon, sys_swapon)
+#define __NR_swapoff 225
+__SYSCALL(__NR_swapoff, sys_swapoff)
+#define __NR_mprotect 226
+__SYSCALL(__NR_mprotect, sys_mprotect)
+#define __NR_msync 227
+__SYSCALL(__NR_msync, sys_msync)
+#define __NR_mlock 228
+__SYSCALL(__NR_mlock, sys_mlock)
+#define __NR_munlock 229
+__SYSCALL(__NR_munlock, sys_munlock)
+#define __NR_mlockall 230
+__SYSCALL(__NR_mlockall, sys_mlockall)
+#define __NR_munlockall 231
+__SYSCALL(__NR_munlockall, sys_munlockall)
+#define __NR_mincore 232
+__SYSCALL(__NR_mincore, sys_mincore)
+#define __NR_madvise 233
+__SYSCALL(__NR_madvise, sys_madvise)
+#define __NR_remap_file_pages 234
+__SYSCALL(__NR_remap_file_pages, sys_remap_file_pages)
+#define __NR_mbind 235
+__SYSCALL(__NR_mbind, sys_mbind)
+#define __NR_get_mempolicy 236
+__SYSCALL(__NR_get_mempolicy, sys_get_mempolicy)
+#define __NR_set_mempolicy 237
+__SYSCALL(__NR_set_mempolicy, sys_set_mempolicy)
+#define __NR_migrate_pages 238
+__SYSCALL(__NR_migrate_pages, sys_migrate_pages)
+#define __NR_move_pages 239
+__SYSCALL(__NR_move_pages, sys_move_pages)
+#endif
+
+#define __NR_rt_tgsigqueueinfo 240
+__SC_COMP(__NR_rt_tgsigqueueinfo, sys_rt_tgsigqueueinfo, \
+ compat_sys_rt_tgsigqueueinfo)
+#define __NR_perf_event_open 241
+__SYSCALL(__NR_perf_event_open, sys_perf_event_open)
+#define __NR_accept4 242
+__SYSCALL(__NR_accept4, sys_accept4)
+
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
+#define __NR_recvmmsg 243
+__SC_COMP_3264(__NR_recvmmsg, sys_recvmmsg_time32, sys_recvmmsg, compat_sys_recvmmsg_time32)
+#endif
+
+/*
+ * Architectures may provide up to 16 syscalls of their own
+ * starting with this value.
+ */
+#define __NR_arch_specific_syscall 244
+
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
+#define __NR_wait4 260
+__SC_COMP(__NR_wait4, sys_wait4, compat_sys_wait4)
+#endif
+
+#define __NR_prlimit64 261
+__SYSCALL(__NR_prlimit64, sys_prlimit64)
+#define __NR_fanotify_init 262
+__SYSCALL(__NR_fanotify_init, sys_fanotify_init)
+#define __NR_fanotify_mark 263
+__SYSCALL(__NR_fanotify_mark, sys_fanotify_mark)
+#define __NR_name_to_handle_at 264
+__SYSCALL(__NR_name_to_handle_at, sys_name_to_handle_at)
+#define __NR_open_by_handle_at 265
+__SYSCALL(__NR_open_by_handle_at, sys_open_by_handle_at)
+
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
+#define __NR_clock_adjtime 266
+__SC_3264(__NR_clock_adjtime, sys_clock_adjtime32, sys_clock_adjtime)
+#endif
+
+#define __NR_syncfs 267
+__SYSCALL(__NR_syncfs, sys_syncfs)
+#define __NR_setns 268
+__SYSCALL(__NR_setns, sys_setns)
+#define __NR_sendmmsg 269
+__SC_COMP(__NR_sendmmsg, sys_sendmmsg, compat_sys_sendmmsg)
+#define __NR_process_vm_readv 270
+__SYSCALL(__NR_process_vm_readv, sys_process_vm_readv)
+#define __NR_process_vm_writev 271
+__SYSCALL(__NR_process_vm_writev, sys_process_vm_writev)
+#define __NR_kcmp 272
+__SYSCALL(__NR_kcmp, sys_kcmp)
+#define __NR_finit_module 273
+__SYSCALL(__NR_finit_module, sys_finit_module)
+#define __NR_sched_setattr 274
+__SYSCALL(__NR_sched_setattr, sys_sched_setattr)
+#define __NR_sched_getattr 275
+__SYSCALL(__NR_sched_getattr, sys_sched_getattr)
+#define __NR_renameat2 276
+__SYSCALL(__NR_renameat2, sys_renameat2)
+#define __NR_seccomp 277
+__SYSCALL(__NR_seccomp, sys_seccomp)
+#define __NR_getrandom 278
+__SYSCALL(__NR_getrandom, sys_getrandom)
+#define __NR_memfd_create 279
+__SYSCALL(__NR_memfd_create, sys_memfd_create)
+#define __NR_bpf 280
+__SYSCALL(__NR_bpf, sys_bpf)
+#define __NR_execveat 281
+__SC_COMP(__NR_execveat, sys_execveat, compat_sys_execveat)
+#define __NR_userfaultfd 282
+__SYSCALL(__NR_userfaultfd, sys_userfaultfd)
+#define __NR_membarrier 283
+__SYSCALL(__NR_membarrier, sys_membarrier)
+#define __NR_mlock2 284
+__SYSCALL(__NR_mlock2, sys_mlock2)
+#define __NR_copy_file_range 285
+__SYSCALL(__NR_copy_file_range, sys_copy_file_range)
+#define __NR_preadv2 286
+__SC_COMP(__NR_preadv2, sys_preadv2, compat_sys_preadv2)
+#define __NR_pwritev2 287
+__SC_COMP(__NR_pwritev2, sys_pwritev2, compat_sys_pwritev2)
+#define __NR_pkey_mprotect 288
+__SYSCALL(__NR_pkey_mprotect, sys_pkey_mprotect)
+#define __NR_pkey_alloc 289
+__SYSCALL(__NR_pkey_alloc, sys_pkey_alloc)
+#define __NR_pkey_free 290
+__SYSCALL(__NR_pkey_free, sys_pkey_free)
+#define __NR_statx 291
+__SYSCALL(__NR_statx, sys_statx)
+
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
+#define __NR_io_pgetevents 292
+__SC_COMP_3264(__NR_io_pgetevents, sys_io_pgetevents_time32, sys_io_pgetevents, compat_sys_io_pgetevents)
+#endif
+
+#define __NR_rseq 293
+__SYSCALL(__NR_rseq, sys_rseq)
+#define __NR_kexec_file_load 294
+__SYSCALL(__NR_kexec_file_load, sys_kexec_file_load)
+
+/* 295 through 402 are unassigned to sync up with generic numbers, don't use */
+
+#if defined(__SYSCALL_COMPAT) || __BITS_PER_LONG == 32
+#define __NR_clock_gettime64 403
+__SYSCALL(__NR_clock_gettime64, sys_clock_gettime)
+#define __NR_clock_settime64 404
+__SYSCALL(__NR_clock_settime64, sys_clock_settime)
+#define __NR_clock_adjtime64 405
+__SYSCALL(__NR_clock_adjtime64, sys_clock_adjtime)
+#define __NR_clock_getres_time64 406
+__SYSCALL(__NR_clock_getres_time64, sys_clock_getres)
+#define __NR_clock_nanosleep_time64 407
+__SYSCALL(__NR_clock_nanosleep_time64, sys_clock_nanosleep)
+#define __NR_timer_gettime64 408
+__SYSCALL(__NR_timer_gettime64, sys_timer_gettime)
+#define __NR_timer_settime64 409
+__SYSCALL(__NR_timer_settime64, sys_timer_settime)
+#define __NR_timerfd_gettime64 410
+__SYSCALL(__NR_timerfd_gettime64, sys_timerfd_gettime)
+#define __NR_timerfd_settime64 411
+__SYSCALL(__NR_timerfd_settime64, sys_timerfd_settime)
+#define __NR_utimensat_time64 412
+__SYSCALL(__NR_utimensat_time64, sys_utimensat)
+#define __NR_pselect6_time64 413
+__SC_COMP(__NR_pselect6_time64, sys_pselect6, compat_sys_pselect6_time64)
+#define __NR_ppoll_time64 414
+__SC_COMP(__NR_ppoll_time64, sys_ppoll, compat_sys_ppoll_time64)
+#define __NR_io_pgetevents_time64 416
+__SYSCALL(__NR_io_pgetevents_time64, sys_io_pgetevents)
+#define __NR_recvmmsg_time64 417
+__SC_COMP(__NR_recvmmsg_time64, sys_recvmmsg, compat_sys_recvmmsg_time64)
+#define __NR_mq_timedsend_time64 418
+__SYSCALL(__NR_mq_timedsend_time64, sys_mq_timedsend)
+#define __NR_mq_timedreceive_time64 419
+__SYSCALL(__NR_mq_timedreceive_time64, sys_mq_timedreceive)
+#define __NR_semtimedop_time64 420
+__SYSCALL(__NR_semtimedop_time64, sys_semtimedop)
+#define __NR_rt_sigtimedwait_time64 421
+__SC_COMP(__NR_rt_sigtimedwait_time64, sys_rt_sigtimedwait, compat_sys_rt_sigtimedwait_time64)
+#define __NR_futex_time64 422
+__SYSCALL(__NR_futex_time64, sys_futex)
+#define __NR_sched_rr_get_interval_time64 423
+__SYSCALL(__NR_sched_rr_get_interval_time64, sys_sched_rr_get_interval)
+#endif
+
+#define __NR_pidfd_send_signal 424
+__SYSCALL(__NR_pidfd_send_signal, sys_pidfd_send_signal)
+#define __NR_io_uring_setup 425
+__SYSCALL(__NR_io_uring_setup, sys_io_uring_setup)
+#define __NR_io_uring_enter 426
+__SYSCALL(__NR_io_uring_enter, sys_io_uring_enter)
+#define __NR_io_uring_register 427
+__SYSCALL(__NR_io_uring_register, sys_io_uring_register)
+#define __NR_open_tree 428
+__SYSCALL(__NR_open_tree, sys_open_tree)
+#define __NR_move_mount 429
+__SYSCALL(__NR_move_mount, sys_move_mount)
+#define __NR_fsopen 430
+__SYSCALL(__NR_fsopen, sys_fsopen)
+#define __NR_fsconfig 431
+__SYSCALL(__NR_fsconfig, sys_fsconfig)
+#define __NR_fsmount 432
+__SYSCALL(__NR_fsmount, sys_fsmount)
+#define __NR_fspick 433
+__SYSCALL(__NR_fspick, sys_fspick)
+#define __NR_pidfd_open 434
+__SYSCALL(__NR_pidfd_open, sys_pidfd_open)
+
+#ifdef __ARCH_WANT_SYS_CLONE3
+#define __NR_clone3 435
+__SYSCALL(__NR_clone3, sys_clone3)
+#endif
+
+#define __NR_close_range 436
+__SYSCALL(__NR_close_range, sys_close_range)
+#define __NR_openat2 437
+__SYSCALL(__NR_openat2, sys_openat2)
+#define __NR_pidfd_getfd 438
+__SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd)
+#define __NR_faccessat2 439
+__SYSCALL(__NR_faccessat2, sys_faccessat2)
+#define __NR_process_madvise 440
+__SYSCALL(__NR_process_madvise, sys_process_madvise)
+#define __NR_epoll_pwait2 441
+__SC_COMP(__NR_epoll_pwait2, sys_epoll_pwait2, compat_sys_epoll_pwait2)
+#define __NR_mount_setattr 442
+__SYSCALL(__NR_mount_setattr, sys_mount_setattr)
+#define __NR_quotactl_fd 443
+__SYSCALL(__NR_quotactl_fd, sys_quotactl_fd)
+#define __NR_landlock_create_ruleset 444
+__SYSCALL(__NR_landlock_create_ruleset, sys_landlock_create_ruleset)
+#define __NR_landlock_add_rule 445
+__SYSCALL(__NR_landlock_add_rule, sys_landlock_add_rule)
+#define __NR_landlock_restrict_self 446
+__SYSCALL(__NR_landlock_restrict_self, sys_landlock_restrict_self)
+
+#ifdef __ARCH_WANT_MEMFD_SECRET
+#define __NR_memfd_secret 447
+__SYSCALL(__NR_memfd_secret, sys_memfd_secret)
+#endif
+
+#define __NR_process_mrelease 448
+__SYSCALL(__NR_process_mrelease, sys_process_mrelease)
+#define __NR_futex_waitv 449
+__SYSCALL(__NR_futex_waitv, sys_futex_waitv)
+#define __NR_set_mempolicy_home_node 450
+__SYSCALL(__NR_set_mempolicy_home_node, sys_set_mempolicy_home_node)
+
+#define __NR_cachestat 451
+__SYSCALL(__NR_cachestat, sys_cachestat)
+
+#define __NR_fchmodat2 452
+__SYSCALL(__NR_fchmodat2, sys_fchmodat2)
+
+#undef __NR_syscalls
+#define __NR_syscalls 453
+
+/*
+ * 32 bit systems traditionally used different
+ * syscalls for off_t and loff_t arguments, while
+ * 64 bit systems only need the off_t version.
+ * For new 32 bit platforms, there is no need to
+ * implement the old 32 bit off_t syscalls, so
+ * they take different names.
+ * Here we map the numbers so that both versions
+ * use the same syscall table layout.
+ */
+#if __BITS_PER_LONG == 64 && !defined(__SYSCALL_COMPAT)
+#define __NR_fcntl __NR3264_fcntl
+#define __NR_statfs __NR3264_statfs
+#define __NR_fstatfs __NR3264_fstatfs
+#define __NR_truncate __NR3264_truncate
+#define __NR_ftruncate __NR3264_ftruncate
+#define __NR_lseek __NR3264_lseek
+#define __NR_sendfile __NR3264_sendfile
+#if defined(__ARCH_WANT_NEW_STAT) || defined(__ARCH_WANT_STAT64)
+#define __NR_newfstatat __NR3264_fstatat
+#define __NR_fstat __NR3264_fstat
+#endif
+#define __NR_mmap __NR3264_mmap
+#define __NR_fadvise64 __NR3264_fadvise64
+#ifdef __NR3264_stat
+#define __NR_stat __NR3264_stat
+#define __NR_lstat __NR3264_lstat
+#endif
+#else
+#define __NR_fcntl64 __NR3264_fcntl
+#define __NR_statfs64 __NR3264_statfs
+#define __NR_fstatfs64 __NR3264_fstatfs
+#define __NR_truncate64 __NR3264_truncate
+#define __NR_ftruncate64 __NR3264_ftruncate
+#define __NR_llseek __NR3264_lseek
+#define __NR_sendfile64 __NR3264_sendfile
+#if defined(__ARCH_WANT_NEW_STAT) || defined(__ARCH_WANT_STAT64)
+#define __NR_fstatat64 __NR3264_fstatat
+#define __NR_fstat64 __NR3264_fstat
+#endif
+#define __NR_mmap2 __NR3264_mmap
+#define __NR_fadvise64_64 __NR3264_fadvise64
+#ifdef __NR3264_stat
+#define __NR_stat64 __NR3264_stat
+#define __NR_lstat64 __NR3264_lstat
+#endif
+#endif
diff --git a/tools/include/uapi/asm/bitsperlong.h b/tools/include/uapi/asm/bitsperlong.h
new file mode 100644
index 0000000000..c65267afc3
--- /dev/null
+++ b/tools/include/uapi/asm/bitsperlong.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#if defined(__i386__) || defined(__x86_64__)
+#include "../../../arch/x86/include/uapi/asm/bitsperlong.h"
+#elif defined(__powerpc__)
+#include "../../../arch/powerpc/include/uapi/asm/bitsperlong.h"
+#elif defined(__s390__)
+#include "../../../arch/s390/include/uapi/asm/bitsperlong.h"
+#elif defined(__sparc__)
+#include "../../../arch/sparc/include/uapi/asm/bitsperlong.h"
+#elif defined(__mips__)
+#include "../../../arch/mips/include/uapi/asm/bitsperlong.h"
+#elif defined(__ia64__)
+#include "../../../arch/ia64/include/uapi/asm/bitsperlong.h"
+#elif defined(__alpha__)
+#include "../../../arch/alpha/include/uapi/asm/bitsperlong.h"
+#else
+#include <asm-generic/bitsperlong.h>
+#endif
diff --git a/tools/include/uapi/asm/bpf_perf_event.h b/tools/include/uapi/asm/bpf_perf_event.h
new file mode 100644
index 0000000000..ff52668abf
--- /dev/null
+++ b/tools/include/uapi/asm/bpf_perf_event.h
@@ -0,0 +1,13 @@
+#if defined(__aarch64__)
+#include "../../arch/arm64/include/uapi/asm/bpf_perf_event.h"
+#elif defined(__arc__)
+#include "../../arch/arc/include/uapi/asm/bpf_perf_event.h"
+#elif defined(__s390__)
+#include "../../arch/s390/include/uapi/asm/bpf_perf_event.h"
+#elif defined(__riscv)
+#include "../../arch/riscv/include/uapi/asm/bpf_perf_event.h"
+#elif defined(__loongarch__)
+#include "../../arch/loongarch/include/uapi/asm/bpf_perf_event.h"
+#else
+#include <uapi/asm-generic/bpf_perf_event.h>
+#endif
diff --git a/tools/include/uapi/asm/errno.h b/tools/include/uapi/asm/errno.h
new file mode 100644
index 0000000000..869379f91f
--- /dev/null
+++ b/tools/include/uapi/asm/errno.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#if defined(__i386__) || defined(__x86_64__)
+#include "../../../arch/x86/include/uapi/asm/errno.h"
+#elif defined(__powerpc__)
+#include "../../../arch/powerpc/include/uapi/asm/errno.h"
+#elif defined(__sparc__)
+#include "../../../arch/sparc/include/uapi/asm/errno.h"
+#elif defined(__alpha__)
+#include "../../../arch/alpha/include/uapi/asm/errno.h"
+#elif defined(__mips__)
+#include "../../../arch/mips/include/uapi/asm/errno.h"
+#elif defined(__hppa__)
+#include "../../../arch/parisc/include/uapi/asm/errno.h"
+#else
+#include <asm-generic/errno.h>
+#endif
diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h
new file mode 100644
index 0000000000..794c1d8576
--- /dev/null
+++ b/tools/include/uapi/drm/drm.h
@@ -0,0 +1,1326 @@
+/*
+ * Header for the Direct Rendering Manager
+ *
+ * Author: Rickard E. (Rik) Faith <faith@valinux.com>
+ *
+ * Acknowledgments:
+ * Dec 1999, Richard Henderson <rth@twiddle.net>, move to generic cmpxchg.
+ */
+
+/*
+ * Copyright 1999 Precision Insight, Inc., Cedar Park, Texas.
+ * Copyright 2000 VA Linux Systems, Inc., Sunnyvale, California.
+ * All rights reserved.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * VA LINUX SYSTEMS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+#ifndef _DRM_H_
+#define _DRM_H_
+
+#if defined(__KERNEL__)
+
+#include <linux/types.h>
+#include <asm/ioctl.h>
+typedef unsigned int drm_handle_t;
+
+#elif defined(__linux__)
+
+#include <linux/types.h>
+#include <asm/ioctl.h>
+typedef unsigned int drm_handle_t;
+
+#else /* One of the BSDs */
+
+#include <stdint.h>
+#include <sys/ioccom.h>
+#include <sys/types.h>
+typedef int8_t __s8;
+typedef uint8_t __u8;
+typedef int16_t __s16;
+typedef uint16_t __u16;
+typedef int32_t __s32;
+typedef uint32_t __u32;
+typedef int64_t __s64;
+typedef uint64_t __u64;
+typedef size_t __kernel_size_t;
+typedef unsigned long drm_handle_t;
+
+#endif
+
+#if defined(__cplusplus)
+extern "C" {
+#endif
+
+#define DRM_NAME "drm" /**< Name in kernel, /dev, and /proc */
+#define DRM_MIN_ORDER 5 /**< At least 2^5 bytes = 32 bytes */
+#define DRM_MAX_ORDER 22 /**< Up to 2^22 bytes = 4MB */
+#define DRM_RAM_PERCENT 10 /**< How much system ram can we lock? */
+
+#define _DRM_LOCK_HELD 0x80000000U /**< Hardware lock is held */
+#define _DRM_LOCK_CONT 0x40000000U /**< Hardware lock is contended */
+#define _DRM_LOCK_IS_HELD(lock) ((lock) & _DRM_LOCK_HELD)
+#define _DRM_LOCK_IS_CONT(lock) ((lock) & _DRM_LOCK_CONT)
+#define _DRM_LOCKING_CONTEXT(lock) ((lock) & ~(_DRM_LOCK_HELD|_DRM_LOCK_CONT))
+
+typedef unsigned int drm_context_t;
+typedef unsigned int drm_drawable_t;
+typedef unsigned int drm_magic_t;
+
+/*
+ * Cliprect.
+ *
+ * \warning: If you change this structure, make sure you change
+ * XF86DRIClipRectRec in the server as well
+ *
+ * \note KW: Actually it's illegal to change either for
+ * backwards-compatibility reasons.
+ */
+struct drm_clip_rect {
+ unsigned short x1;
+ unsigned short y1;
+ unsigned short x2;
+ unsigned short y2;
+};
+
+/*
+ * Drawable information.
+ */
+struct drm_drawable_info {
+ unsigned int num_rects;
+ struct drm_clip_rect *rects;
+};
+
+/*
+ * Texture region,
+ */
+struct drm_tex_region {
+ unsigned char next;
+ unsigned char prev;
+ unsigned char in_use;
+ unsigned char padding;
+ unsigned int age;
+};
+
+/*
+ * Hardware lock.
+ *
+ * The lock structure is a simple cache-line aligned integer. To avoid
+ * processor bus contention on a multiprocessor system, there should not be any
+ * other data stored in the same cache line.
+ */
+struct drm_hw_lock {
+ __volatile__ unsigned int lock; /**< lock variable */
+ char padding[60]; /**< Pad to cache line */
+};
+
+/*
+ * DRM_IOCTL_VERSION ioctl argument type.
+ *
+ * \sa drmGetVersion().
+ */
+struct drm_version {
+ int version_major; /**< Major version */
+ int version_minor; /**< Minor version */
+ int version_patchlevel; /**< Patch level */
+ __kernel_size_t name_len; /**< Length of name buffer */
+ char __user *name; /**< Name of driver */
+ __kernel_size_t date_len; /**< Length of date buffer */
+ char __user *date; /**< User-space buffer to hold date */
+ __kernel_size_t desc_len; /**< Length of desc buffer */
+ char __user *desc; /**< User-space buffer to hold desc */
+};
+
+/*
+ * DRM_IOCTL_GET_UNIQUE ioctl argument type.
+ *
+ * \sa drmGetBusid() and drmSetBusId().
+ */
+struct drm_unique {
+ __kernel_size_t unique_len; /**< Length of unique */
+ char __user *unique; /**< Unique name for driver instantiation */
+};
+
+struct drm_list {
+ int count; /**< Length of user-space structures */
+ struct drm_version __user *version;
+};
+
+struct drm_block {
+ int unused;
+};
+
+/*
+ * DRM_IOCTL_CONTROL ioctl argument type.
+ *
+ * \sa drmCtlInstHandler() and drmCtlUninstHandler().
+ */
+struct drm_control {
+ enum {
+ DRM_ADD_COMMAND,
+ DRM_RM_COMMAND,
+ DRM_INST_HANDLER,
+ DRM_UNINST_HANDLER
+ } func;
+ int irq;
+};
+
+/*
+ * Type of memory to map.
+ */
+enum drm_map_type {
+ _DRM_FRAME_BUFFER = 0, /**< WC (no caching), no core dump */
+ _DRM_REGISTERS = 1, /**< no caching, no core dump */
+ _DRM_SHM = 2, /**< shared, cached */
+ _DRM_AGP = 3, /**< AGP/GART */
+ _DRM_SCATTER_GATHER = 4, /**< Scatter/gather memory for PCI DMA */
+ _DRM_CONSISTENT = 5 /**< Consistent memory for PCI DMA */
+};
+
+/*
+ * Memory mapping flags.
+ */
+enum drm_map_flags {
+ _DRM_RESTRICTED = 0x01, /**< Cannot be mapped to user-virtual */
+ _DRM_READ_ONLY = 0x02,
+ _DRM_LOCKED = 0x04, /**< shared, cached, locked */
+ _DRM_KERNEL = 0x08, /**< kernel requires access */
+ _DRM_WRITE_COMBINING = 0x10, /**< use write-combining if available */
+ _DRM_CONTAINS_LOCK = 0x20, /**< SHM page that contains lock */
+ _DRM_REMOVABLE = 0x40, /**< Removable mapping */
+ _DRM_DRIVER = 0x80 /**< Managed by driver */
+};
+
+struct drm_ctx_priv_map {
+ unsigned int ctx_id; /**< Context requesting private mapping */
+ void *handle; /**< Handle of map */
+};
+
+/*
+ * DRM_IOCTL_GET_MAP, DRM_IOCTL_ADD_MAP and DRM_IOCTL_RM_MAP ioctls
+ * argument type.
+ *
+ * \sa drmAddMap().
+ */
+struct drm_map {
+ unsigned long offset; /**< Requested physical address (0 for SAREA)*/
+ unsigned long size; /**< Requested physical size (bytes) */
+ enum drm_map_type type; /**< Type of memory to map */
+ enum drm_map_flags flags; /**< Flags */
+ void *handle; /**< User-space: "Handle" to pass to mmap() */
+ /**< Kernel-space: kernel-virtual address */
+ int mtrr; /**< MTRR slot used */
+ /* Private data */
+};
+
+/*
+ * DRM_IOCTL_GET_CLIENT ioctl argument type.
+ */
+struct drm_client {
+ int idx; /**< Which client desired? */
+ int auth; /**< Is client authenticated? */
+ unsigned long pid; /**< Process ID */
+ unsigned long uid; /**< User ID */
+ unsigned long magic; /**< Magic */
+ unsigned long iocs; /**< Ioctl count */
+};
+
+enum drm_stat_type {
+ _DRM_STAT_LOCK,
+ _DRM_STAT_OPENS,
+ _DRM_STAT_CLOSES,
+ _DRM_STAT_IOCTLS,
+ _DRM_STAT_LOCKS,
+ _DRM_STAT_UNLOCKS,
+ _DRM_STAT_VALUE, /**< Generic value */
+ _DRM_STAT_BYTE, /**< Generic byte counter (1024bytes/K) */
+ _DRM_STAT_COUNT, /**< Generic non-byte counter (1000/k) */
+
+ _DRM_STAT_IRQ, /**< IRQ */
+ _DRM_STAT_PRIMARY, /**< Primary DMA bytes */
+ _DRM_STAT_SECONDARY, /**< Secondary DMA bytes */
+ _DRM_STAT_DMA, /**< DMA */
+ _DRM_STAT_SPECIAL, /**< Special DMA (e.g., priority or polled) */
+ _DRM_STAT_MISSED /**< Missed DMA opportunity */
+ /* Add to the *END* of the list */
+};
+
+/*
+ * DRM_IOCTL_GET_STATS ioctl argument type.
+ */
+struct drm_stats {
+ unsigned long count;
+ struct {
+ unsigned long value;
+ enum drm_stat_type type;
+ } data[15];
+};
+
+/*
+ * Hardware locking flags.
+ */
+enum drm_lock_flags {
+ _DRM_LOCK_READY = 0x01, /**< Wait until hardware is ready for DMA */
+ _DRM_LOCK_QUIESCENT = 0x02, /**< Wait until hardware quiescent */
+ _DRM_LOCK_FLUSH = 0x04, /**< Flush this context's DMA queue first */
+ _DRM_LOCK_FLUSH_ALL = 0x08, /**< Flush all DMA queues first */
+ /* These *HALT* flags aren't supported yet
+ -- they will be used to support the
+ full-screen DGA-like mode. */
+ _DRM_HALT_ALL_QUEUES = 0x10, /**< Halt all current and future queues */
+ _DRM_HALT_CUR_QUEUES = 0x20 /**< Halt all current queues */
+};
+
+/*
+ * DRM_IOCTL_LOCK, DRM_IOCTL_UNLOCK and DRM_IOCTL_FINISH ioctl argument type.
+ *
+ * \sa drmGetLock() and drmUnlock().
+ */
+struct drm_lock {
+ int context;
+ enum drm_lock_flags flags;
+};
+
+/*
+ * DMA flags
+ *
+ * \warning
+ * These values \e must match xf86drm.h.
+ *
+ * \sa drm_dma.
+ */
+enum drm_dma_flags {
+ /* Flags for DMA buffer dispatch */
+ _DRM_DMA_BLOCK = 0x01, /**<
+ * Block until buffer dispatched.
+ *
+ * \note The buffer may not yet have
+ * been processed by the hardware --
+ * getting a hardware lock with the
+ * hardware quiescent will ensure
+ * that the buffer has been
+ * processed.
+ */
+ _DRM_DMA_WHILE_LOCKED = 0x02, /**< Dispatch while lock held */
+ _DRM_DMA_PRIORITY = 0x04, /**< High priority dispatch */
+
+ /* Flags for DMA buffer request */
+ _DRM_DMA_WAIT = 0x10, /**< Wait for free buffers */
+ _DRM_DMA_SMALLER_OK = 0x20, /**< Smaller-than-requested buffers OK */
+ _DRM_DMA_LARGER_OK = 0x40 /**< Larger-than-requested buffers OK */
+};
+
+/*
+ * DRM_IOCTL_ADD_BUFS and DRM_IOCTL_MARK_BUFS ioctl argument type.
+ *
+ * \sa drmAddBufs().
+ */
+struct drm_buf_desc {
+ int count; /**< Number of buffers of this size */
+ int size; /**< Size in bytes */
+ int low_mark; /**< Low water mark */
+ int high_mark; /**< High water mark */
+ enum {
+ _DRM_PAGE_ALIGN = 0x01, /**< Align on page boundaries for DMA */
+ _DRM_AGP_BUFFER = 0x02, /**< Buffer is in AGP space */
+ _DRM_SG_BUFFER = 0x04, /**< Scatter/gather memory buffer */
+ _DRM_FB_BUFFER = 0x08, /**< Buffer is in frame buffer */
+ _DRM_PCI_BUFFER_RO = 0x10 /**< Map PCI DMA buffer read-only */
+ } flags;
+ unsigned long agp_start; /**<
+ * Start address of where the AGP buffers are
+ * in the AGP aperture
+ */
+};
+
+/*
+ * DRM_IOCTL_INFO_BUFS ioctl argument type.
+ */
+struct drm_buf_info {
+ int count; /**< Entries in list */
+ struct drm_buf_desc __user *list;
+};
+
+/*
+ * DRM_IOCTL_FREE_BUFS ioctl argument type.
+ */
+struct drm_buf_free {
+ int count;
+ int __user *list;
+};
+
+/*
+ * Buffer information
+ *
+ * \sa drm_buf_map.
+ */
+struct drm_buf_pub {
+ int idx; /**< Index into the master buffer list */
+ int total; /**< Buffer size */
+ int used; /**< Amount of buffer in use (for DMA) */
+ void __user *address; /**< Address of buffer */
+};
+
+/*
+ * DRM_IOCTL_MAP_BUFS ioctl argument type.
+ */
+struct drm_buf_map {
+ int count; /**< Length of the buffer list */
+#ifdef __cplusplus
+ void __user *virt;
+#else
+ void __user *virtual; /**< Mmap'd area in user-virtual */
+#endif
+ struct drm_buf_pub __user *list; /**< Buffer information */
+};
+
+/*
+ * DRM_IOCTL_DMA ioctl argument type.
+ *
+ * Indices here refer to the offset into the buffer list in drm_buf_get.
+ *
+ * \sa drmDMA().
+ */
+struct drm_dma {
+ int context; /**< Context handle */
+ int send_count; /**< Number of buffers to send */
+ int __user *send_indices; /**< List of handles to buffers */
+ int __user *send_sizes; /**< Lengths of data to send */
+ enum drm_dma_flags flags; /**< Flags */
+ int request_count; /**< Number of buffers requested */
+ int request_size; /**< Desired size for buffers */
+ int __user *request_indices; /**< Buffer information */
+ int __user *request_sizes;
+ int granted_count; /**< Number of buffers granted */
+};
+
+enum drm_ctx_flags {
+ _DRM_CONTEXT_PRESERVED = 0x01,
+ _DRM_CONTEXT_2DONLY = 0x02
+};
+
+/*
+ * DRM_IOCTL_ADD_CTX ioctl argument type.
+ *
+ * \sa drmCreateContext() and drmDestroyContext().
+ */
+struct drm_ctx {
+ drm_context_t handle;
+ enum drm_ctx_flags flags;
+};
+
+/*
+ * DRM_IOCTL_RES_CTX ioctl argument type.
+ */
+struct drm_ctx_res {
+ int count;
+ struct drm_ctx __user *contexts;
+};
+
+/*
+ * DRM_IOCTL_ADD_DRAW and DRM_IOCTL_RM_DRAW ioctl argument type.
+ */
+struct drm_draw {
+ drm_drawable_t handle;
+};
+
+/*
+ * DRM_IOCTL_UPDATE_DRAW ioctl argument type.
+ */
+typedef enum {
+ DRM_DRAWABLE_CLIPRECTS
+} drm_drawable_info_type_t;
+
+struct drm_update_draw {
+ drm_drawable_t handle;
+ unsigned int type;
+ unsigned int num;
+ unsigned long long data;
+};
+
+/*
+ * DRM_IOCTL_GET_MAGIC and DRM_IOCTL_AUTH_MAGIC ioctl argument type.
+ */
+struct drm_auth {
+ drm_magic_t magic;
+};
+
+/*
+ * DRM_IOCTL_IRQ_BUSID ioctl argument type.
+ *
+ * \sa drmGetInterruptFromBusID().
+ */
+struct drm_irq_busid {
+ int irq; /**< IRQ number */
+ int busnum; /**< bus number */
+ int devnum; /**< device number */
+ int funcnum; /**< function number */
+};
+
+enum drm_vblank_seq_type {
+ _DRM_VBLANK_ABSOLUTE = 0x0, /**< Wait for specific vblank sequence number */
+ _DRM_VBLANK_RELATIVE = 0x1, /**< Wait for given number of vblanks */
+ /* bits 1-6 are reserved for high crtcs */
+ _DRM_VBLANK_HIGH_CRTC_MASK = 0x0000003e,
+ _DRM_VBLANK_EVENT = 0x4000000, /**< Send event instead of blocking */
+ _DRM_VBLANK_FLIP = 0x8000000, /**< Scheduled buffer swap should flip */
+ _DRM_VBLANK_NEXTONMISS = 0x10000000, /**< If missed, wait for next vblank */
+ _DRM_VBLANK_SECONDARY = 0x20000000, /**< Secondary display controller */
+ _DRM_VBLANK_SIGNAL = 0x40000000 /**< Send signal instead of blocking, unsupported */
+};
+#define _DRM_VBLANK_HIGH_CRTC_SHIFT 1
+
+#define _DRM_VBLANK_TYPES_MASK (_DRM_VBLANK_ABSOLUTE | _DRM_VBLANK_RELATIVE)
+#define _DRM_VBLANK_FLAGS_MASK (_DRM_VBLANK_EVENT | _DRM_VBLANK_SIGNAL | \
+ _DRM_VBLANK_SECONDARY | _DRM_VBLANK_NEXTONMISS)
+
+struct drm_wait_vblank_request {
+ enum drm_vblank_seq_type type;
+ unsigned int sequence;
+ unsigned long signal;
+};
+
+struct drm_wait_vblank_reply {
+ enum drm_vblank_seq_type type;
+ unsigned int sequence;
+ long tval_sec;
+ long tval_usec;
+};
+
+/*
+ * DRM_IOCTL_WAIT_VBLANK ioctl argument type.
+ *
+ * \sa drmWaitVBlank().
+ */
+union drm_wait_vblank {
+ struct drm_wait_vblank_request request;
+ struct drm_wait_vblank_reply reply;
+};
+
+#define _DRM_PRE_MODESET 1
+#define _DRM_POST_MODESET 2
+
+/*
+ * DRM_IOCTL_MODESET_CTL ioctl argument type
+ *
+ * \sa drmModesetCtl().
+ */
+struct drm_modeset_ctl {
+ __u32 crtc;
+ __u32 cmd;
+};
+
+/*
+ * DRM_IOCTL_AGP_ENABLE ioctl argument type.
+ *
+ * \sa drmAgpEnable().
+ */
+struct drm_agp_mode {
+ unsigned long mode; /**< AGP mode */
+};
+
+/*
+ * DRM_IOCTL_AGP_ALLOC and DRM_IOCTL_AGP_FREE ioctls argument type.
+ *
+ * \sa drmAgpAlloc() and drmAgpFree().
+ */
+struct drm_agp_buffer {
+ unsigned long size; /**< In bytes -- will round to page boundary */
+ unsigned long handle; /**< Used for binding / unbinding */
+ unsigned long type; /**< Type of memory to allocate */
+ unsigned long physical; /**< Physical used by i810 */
+};
+
+/*
+ * DRM_IOCTL_AGP_BIND and DRM_IOCTL_AGP_UNBIND ioctls argument type.
+ *
+ * \sa drmAgpBind() and drmAgpUnbind().
+ */
+struct drm_agp_binding {
+ unsigned long handle; /**< From drm_agp_buffer */
+ unsigned long offset; /**< In bytes -- will round to page boundary */
+};
+
+/*
+ * DRM_IOCTL_AGP_INFO ioctl argument type.
+ *
+ * \sa drmAgpVersionMajor(), drmAgpVersionMinor(), drmAgpGetMode(),
+ * drmAgpBase(), drmAgpSize(), drmAgpMemoryUsed(), drmAgpMemoryAvail(),
+ * drmAgpVendorId() and drmAgpDeviceId().
+ */
+struct drm_agp_info {
+ int agp_version_major;
+ int agp_version_minor;
+ unsigned long mode;
+ unsigned long aperture_base; /* physical address */
+ unsigned long aperture_size; /* bytes */
+ unsigned long memory_allowed; /* bytes */
+ unsigned long memory_used;
+
+ /* PCI information */
+ unsigned short id_vendor;
+ unsigned short id_device;
+};
+
+/*
+ * DRM_IOCTL_SG_ALLOC ioctl argument type.
+ */
+struct drm_scatter_gather {
+ unsigned long size; /**< In bytes -- will round to page boundary */
+ unsigned long handle; /**< Used for mapping / unmapping */
+};
+
+/*
+ * DRM_IOCTL_SET_VERSION ioctl argument type.
+ */
+struct drm_set_version {
+ int drm_di_major;
+ int drm_di_minor;
+ int drm_dd_major;
+ int drm_dd_minor;
+};
+
+/* DRM_IOCTL_GEM_CLOSE ioctl argument type */
+struct drm_gem_close {
+ /** Handle of the object to be closed. */
+ __u32 handle;
+ __u32 pad;
+};
+
+/* DRM_IOCTL_GEM_FLINK ioctl argument type */
+struct drm_gem_flink {
+ /** Handle for the object being named */
+ __u32 handle;
+
+ /** Returned global name */
+ __u32 name;
+};
+
+/* DRM_IOCTL_GEM_OPEN ioctl argument type */
+struct drm_gem_open {
+ /** Name of object being opened */
+ __u32 name;
+
+ /** Returned handle for the object */
+ __u32 handle;
+
+ /** Returned size of the object */
+ __u64 size;
+};
+
+/**
+ * DRM_CAP_DUMB_BUFFER
+ *
+ * If set to 1, the driver supports creating dumb buffers via the
+ * &DRM_IOCTL_MODE_CREATE_DUMB ioctl.
+ */
+#define DRM_CAP_DUMB_BUFFER 0x1
+/**
+ * DRM_CAP_VBLANK_HIGH_CRTC
+ *
+ * If set to 1, the kernel supports specifying a :ref:`CRTC index<crtc_index>`
+ * in the high bits of &drm_wait_vblank_request.type.
+ *
+ * Starting kernel version 2.6.39, this capability is always set to 1.
+ */
+#define DRM_CAP_VBLANK_HIGH_CRTC 0x2
+/**
+ * DRM_CAP_DUMB_PREFERRED_DEPTH
+ *
+ * The preferred bit depth for dumb buffers.
+ *
+ * The bit depth is the number of bits used to indicate the color of a single
+ * pixel excluding any padding. This is different from the number of bits per
+ * pixel. For instance, XRGB8888 has a bit depth of 24 but has 32 bits per
+ * pixel.
+ *
+ * Note that this preference only applies to dumb buffers, it's irrelevant for
+ * other types of buffers.
+ */
+#define DRM_CAP_DUMB_PREFERRED_DEPTH 0x3
+/**
+ * DRM_CAP_DUMB_PREFER_SHADOW
+ *
+ * If set to 1, the driver prefers userspace to render to a shadow buffer
+ * instead of directly rendering to a dumb buffer. For best speed, userspace
+ * should do streaming ordered memory copies into the dumb buffer and never
+ * read from it.
+ *
+ * Note that this preference only applies to dumb buffers, it's irrelevant for
+ * other types of buffers.
+ */
+#define DRM_CAP_DUMB_PREFER_SHADOW 0x4
+/**
+ * DRM_CAP_PRIME
+ *
+ * Bitfield of supported PRIME sharing capabilities. See &DRM_PRIME_CAP_IMPORT
+ * and &DRM_PRIME_CAP_EXPORT.
+ *
+ * Starting from kernel version 6.6, both &DRM_PRIME_CAP_IMPORT and
+ * &DRM_PRIME_CAP_EXPORT are always advertised.
+ *
+ * PRIME buffers are exposed as dma-buf file descriptors.
+ * See :ref:`prime_buffer_sharing`.
+ */
+#define DRM_CAP_PRIME 0x5
+/**
+ * DRM_PRIME_CAP_IMPORT
+ *
+ * If this bit is set in &DRM_CAP_PRIME, the driver supports importing PRIME
+ * buffers via the &DRM_IOCTL_PRIME_FD_TO_HANDLE ioctl.
+ *
+ * Starting from kernel version 6.6, this bit is always set in &DRM_CAP_PRIME.
+ */
+#define DRM_PRIME_CAP_IMPORT 0x1
+/**
+ * DRM_PRIME_CAP_EXPORT
+ *
+ * If this bit is set in &DRM_CAP_PRIME, the driver supports exporting PRIME
+ * buffers via the &DRM_IOCTL_PRIME_HANDLE_TO_FD ioctl.
+ *
+ * Starting from kernel version 6.6, this bit is always set in &DRM_CAP_PRIME.
+ */
+#define DRM_PRIME_CAP_EXPORT 0x2
+/**
+ * DRM_CAP_TIMESTAMP_MONOTONIC
+ *
+ * If set to 0, the kernel will report timestamps with ``CLOCK_REALTIME`` in
+ * struct drm_event_vblank. If set to 1, the kernel will report timestamps with
+ * ``CLOCK_MONOTONIC``. See ``clock_gettime(2)`` for the definition of these
+ * clocks.
+ *
+ * Starting from kernel version 2.6.39, the default value for this capability
+ * is 1. Starting kernel version 4.15, this capability is always set to 1.
+ */
+#define DRM_CAP_TIMESTAMP_MONOTONIC 0x6
+/**
+ * DRM_CAP_ASYNC_PAGE_FLIP
+ *
+ * If set to 1, the driver supports &DRM_MODE_PAGE_FLIP_ASYNC.
+ */
+#define DRM_CAP_ASYNC_PAGE_FLIP 0x7
+/**
+ * DRM_CAP_CURSOR_WIDTH
+ *
+ * The ``CURSOR_WIDTH`` and ``CURSOR_HEIGHT`` capabilities return a valid
+ * width x height combination for the hardware cursor. The intention is that a
+ * hardware agnostic userspace can query a cursor plane size to use.
+ *
+ * Note that the cross-driver contract is to merely return a valid size;
+ * drivers are free to attach another meaning on top, eg. i915 returns the
+ * maximum plane size.
+ */
+#define DRM_CAP_CURSOR_WIDTH 0x8
+/**
+ * DRM_CAP_CURSOR_HEIGHT
+ *
+ * See &DRM_CAP_CURSOR_WIDTH.
+ */
+#define DRM_CAP_CURSOR_HEIGHT 0x9
+/**
+ * DRM_CAP_ADDFB2_MODIFIERS
+ *
+ * If set to 1, the driver supports supplying modifiers in the
+ * &DRM_IOCTL_MODE_ADDFB2 ioctl.
+ */
+#define DRM_CAP_ADDFB2_MODIFIERS 0x10
+/**
+ * DRM_CAP_PAGE_FLIP_TARGET
+ *
+ * If set to 1, the driver supports the &DRM_MODE_PAGE_FLIP_TARGET_ABSOLUTE and
+ * &DRM_MODE_PAGE_FLIP_TARGET_RELATIVE flags in
+ * &drm_mode_crtc_page_flip_target.flags for the &DRM_IOCTL_MODE_PAGE_FLIP
+ * ioctl.
+ */
+#define DRM_CAP_PAGE_FLIP_TARGET 0x11
+/**
+ * DRM_CAP_CRTC_IN_VBLANK_EVENT
+ *
+ * If set to 1, the kernel supports reporting the CRTC ID in
+ * &drm_event_vblank.crtc_id for the &DRM_EVENT_VBLANK and
+ * &DRM_EVENT_FLIP_COMPLETE events.
+ *
+ * Starting kernel version 4.12, this capability is always set to 1.
+ */
+#define DRM_CAP_CRTC_IN_VBLANK_EVENT 0x12
+/**
+ * DRM_CAP_SYNCOBJ
+ *
+ * If set to 1, the driver supports sync objects. See :ref:`drm_sync_objects`.
+ */
+#define DRM_CAP_SYNCOBJ 0x13
+/**
+ * DRM_CAP_SYNCOBJ_TIMELINE
+ *
+ * If set to 1, the driver supports timeline operations on sync objects. See
+ * :ref:`drm_sync_objects`.
+ */
+#define DRM_CAP_SYNCOBJ_TIMELINE 0x14
+
+/* DRM_IOCTL_GET_CAP ioctl argument type */
+struct drm_get_cap {
+ __u64 capability;
+ __u64 value;
+};
+
+/**
+ * DRM_CLIENT_CAP_STEREO_3D
+ *
+ * If set to 1, the DRM core will expose the stereo 3D capabilities of the
+ * monitor by advertising the supported 3D layouts in the flags of struct
+ * drm_mode_modeinfo. See ``DRM_MODE_FLAG_3D_*``.
+ *
+ * This capability is always supported for all drivers starting from kernel
+ * version 3.13.
+ */
+#define DRM_CLIENT_CAP_STEREO_3D 1
+
+/**
+ * DRM_CLIENT_CAP_UNIVERSAL_PLANES
+ *
+ * If set to 1, the DRM core will expose all planes (overlay, primary, and
+ * cursor) to userspace.
+ *
+ * This capability has been introduced in kernel version 3.15. Starting from
+ * kernel version 3.17, this capability is always supported for all drivers.
+ */
+#define DRM_CLIENT_CAP_UNIVERSAL_PLANES 2
+
+/**
+ * DRM_CLIENT_CAP_ATOMIC
+ *
+ * If set to 1, the DRM core will expose atomic properties to userspace. This
+ * implicitly enables &DRM_CLIENT_CAP_UNIVERSAL_PLANES and
+ * &DRM_CLIENT_CAP_ASPECT_RATIO.
+ *
+ * If the driver doesn't support atomic mode-setting, enabling this capability
+ * will fail with -EOPNOTSUPP.
+ *
+ * This capability has been introduced in kernel version 4.0. Starting from
+ * kernel version 4.2, this capability is always supported for atomic-capable
+ * drivers.
+ */
+#define DRM_CLIENT_CAP_ATOMIC 3
+
+/**
+ * DRM_CLIENT_CAP_ASPECT_RATIO
+ *
+ * If set to 1, the DRM core will provide aspect ratio information in modes.
+ * See ``DRM_MODE_FLAG_PIC_AR_*``.
+ *
+ * This capability is always supported for all drivers starting from kernel
+ * version 4.18.
+ */
+#define DRM_CLIENT_CAP_ASPECT_RATIO 4
+
+/**
+ * DRM_CLIENT_CAP_WRITEBACK_CONNECTORS
+ *
+ * If set to 1, the DRM core will expose special connectors to be used for
+ * writing back to memory the scene setup in the commit. The client must enable
+ * &DRM_CLIENT_CAP_ATOMIC first.
+ *
+ * This capability is always supported for atomic-capable drivers starting from
+ * kernel version 4.19.
+ */
+#define DRM_CLIENT_CAP_WRITEBACK_CONNECTORS 5
+
+/* DRM_IOCTL_SET_CLIENT_CAP ioctl argument type */
+struct drm_set_client_cap {
+ __u64 capability;
+ __u64 value;
+};
+
+#define DRM_RDWR O_RDWR
+#define DRM_CLOEXEC O_CLOEXEC
+struct drm_prime_handle {
+ __u32 handle;
+
+ /** Flags.. only applicable for handle->fd */
+ __u32 flags;
+
+ /** Returned dmabuf file descriptor */
+ __s32 fd;
+};
+
+struct drm_syncobj_create {
+ __u32 handle;
+#define DRM_SYNCOBJ_CREATE_SIGNALED (1 << 0)
+ __u32 flags;
+};
+
+struct drm_syncobj_destroy {
+ __u32 handle;
+ __u32 pad;
+};
+
+#define DRM_SYNCOBJ_FD_TO_HANDLE_FLAGS_IMPORT_SYNC_FILE (1 << 0)
+#define DRM_SYNCOBJ_HANDLE_TO_FD_FLAGS_EXPORT_SYNC_FILE (1 << 0)
+struct drm_syncobj_handle {
+ __u32 handle;
+ __u32 flags;
+
+ __s32 fd;
+ __u32 pad;
+};
+
+struct drm_syncobj_transfer {
+ __u32 src_handle;
+ __u32 dst_handle;
+ __u64 src_point;
+ __u64 dst_point;
+ __u32 flags;
+ __u32 pad;
+};
+
+#define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_ALL (1 << 0)
+#define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT (1 << 1)
+#define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE (1 << 2) /* wait for time point to become available */
+struct drm_syncobj_wait {
+ __u64 handles;
+ /* absolute timeout */
+ __s64 timeout_nsec;
+ __u32 count_handles;
+ __u32 flags;
+ __u32 first_signaled; /* only valid when not waiting all */
+ __u32 pad;
+};
+
+struct drm_syncobj_timeline_wait {
+ __u64 handles;
+ /* wait on specific timeline point for every handles*/
+ __u64 points;
+ /* absolute timeout */
+ __s64 timeout_nsec;
+ __u32 count_handles;
+ __u32 flags;
+ __u32 first_signaled; /* only valid when not waiting all */
+ __u32 pad;
+};
+
+/**
+ * struct drm_syncobj_eventfd
+ * @handle: syncobj handle.
+ * @flags: Zero to wait for the point to be signalled, or
+ * &DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE to wait for a fence to be
+ * available for the point.
+ * @point: syncobj timeline point (set to zero for binary syncobjs).
+ * @fd: Existing eventfd to sent events to.
+ * @pad: Must be zero.
+ *
+ * Register an eventfd to be signalled by a syncobj. The eventfd counter will
+ * be incremented by one.
+ */
+struct drm_syncobj_eventfd {
+ __u32 handle;
+ __u32 flags;
+ __u64 point;
+ __s32 fd;
+ __u32 pad;
+};
+
+
+struct drm_syncobj_array {
+ __u64 handles;
+ __u32 count_handles;
+ __u32 pad;
+};
+
+#define DRM_SYNCOBJ_QUERY_FLAGS_LAST_SUBMITTED (1 << 0) /* last available point on timeline syncobj */
+struct drm_syncobj_timeline_array {
+ __u64 handles;
+ __u64 points;
+ __u32 count_handles;
+ __u32 flags;
+};
+
+
+/* Query current scanout sequence number */
+struct drm_crtc_get_sequence {
+ __u32 crtc_id; /* requested crtc_id */
+ __u32 active; /* return: crtc output is active */
+ __u64 sequence; /* return: most recent vblank sequence */
+ __s64 sequence_ns; /* return: most recent time of first pixel out */
+};
+
+/* Queue event to be delivered at specified sequence. Time stamp marks
+ * when the first pixel of the refresh cycle leaves the display engine
+ * for the display
+ */
+#define DRM_CRTC_SEQUENCE_RELATIVE 0x00000001 /* sequence is relative to current */
+#define DRM_CRTC_SEQUENCE_NEXT_ON_MISS 0x00000002 /* Use next sequence if we've missed */
+
+struct drm_crtc_queue_sequence {
+ __u32 crtc_id;
+ __u32 flags;
+ __u64 sequence; /* on input, target sequence. on output, actual sequence */
+ __u64 user_data; /* user data passed to event */
+};
+
+#if defined(__cplusplus)
+}
+#endif
+
+#include "drm_mode.h"
+
+#if defined(__cplusplus)
+extern "C" {
+#endif
+
+#define DRM_IOCTL_BASE 'd'
+#define DRM_IO(nr) _IO(DRM_IOCTL_BASE,nr)
+#define DRM_IOR(nr,type) _IOR(DRM_IOCTL_BASE,nr,type)
+#define DRM_IOW(nr,type) _IOW(DRM_IOCTL_BASE,nr,type)
+#define DRM_IOWR(nr,type) _IOWR(DRM_IOCTL_BASE,nr,type)
+
+#define DRM_IOCTL_VERSION DRM_IOWR(0x00, struct drm_version)
+#define DRM_IOCTL_GET_UNIQUE DRM_IOWR(0x01, struct drm_unique)
+#define DRM_IOCTL_GET_MAGIC DRM_IOR( 0x02, struct drm_auth)
+#define DRM_IOCTL_IRQ_BUSID DRM_IOWR(0x03, struct drm_irq_busid)
+#define DRM_IOCTL_GET_MAP DRM_IOWR(0x04, struct drm_map)
+#define DRM_IOCTL_GET_CLIENT DRM_IOWR(0x05, struct drm_client)
+#define DRM_IOCTL_GET_STATS DRM_IOR( 0x06, struct drm_stats)
+#define DRM_IOCTL_SET_VERSION DRM_IOWR(0x07, struct drm_set_version)
+#define DRM_IOCTL_MODESET_CTL DRM_IOW(0x08, struct drm_modeset_ctl)
+/**
+ * DRM_IOCTL_GEM_CLOSE - Close a GEM handle.
+ *
+ * GEM handles are not reference-counted by the kernel. User-space is
+ * responsible for managing their lifetime. For example, if user-space imports
+ * the same memory object twice on the same DRM file description, the same GEM
+ * handle is returned by both imports, and user-space needs to ensure
+ * &DRM_IOCTL_GEM_CLOSE is performed once only. The same situation can happen
+ * when a memory object is allocated, then exported and imported again on the
+ * same DRM file description. The &DRM_IOCTL_MODE_GETFB2 IOCTL is an exception
+ * and always returns fresh new GEM handles even if an existing GEM handle
+ * already refers to the same memory object before the IOCTL is performed.
+ */
+#define DRM_IOCTL_GEM_CLOSE DRM_IOW (0x09, struct drm_gem_close)
+#define DRM_IOCTL_GEM_FLINK DRM_IOWR(0x0a, struct drm_gem_flink)
+#define DRM_IOCTL_GEM_OPEN DRM_IOWR(0x0b, struct drm_gem_open)
+#define DRM_IOCTL_GET_CAP DRM_IOWR(0x0c, struct drm_get_cap)
+#define DRM_IOCTL_SET_CLIENT_CAP DRM_IOW( 0x0d, struct drm_set_client_cap)
+
+#define DRM_IOCTL_SET_UNIQUE DRM_IOW( 0x10, struct drm_unique)
+#define DRM_IOCTL_AUTH_MAGIC DRM_IOW( 0x11, struct drm_auth)
+#define DRM_IOCTL_BLOCK DRM_IOWR(0x12, struct drm_block)
+#define DRM_IOCTL_UNBLOCK DRM_IOWR(0x13, struct drm_block)
+#define DRM_IOCTL_CONTROL DRM_IOW( 0x14, struct drm_control)
+#define DRM_IOCTL_ADD_MAP DRM_IOWR(0x15, struct drm_map)
+#define DRM_IOCTL_ADD_BUFS DRM_IOWR(0x16, struct drm_buf_desc)
+#define DRM_IOCTL_MARK_BUFS DRM_IOW( 0x17, struct drm_buf_desc)
+#define DRM_IOCTL_INFO_BUFS DRM_IOWR(0x18, struct drm_buf_info)
+#define DRM_IOCTL_MAP_BUFS DRM_IOWR(0x19, struct drm_buf_map)
+#define DRM_IOCTL_FREE_BUFS DRM_IOW( 0x1a, struct drm_buf_free)
+
+#define DRM_IOCTL_RM_MAP DRM_IOW( 0x1b, struct drm_map)
+
+#define DRM_IOCTL_SET_SAREA_CTX DRM_IOW( 0x1c, struct drm_ctx_priv_map)
+#define DRM_IOCTL_GET_SAREA_CTX DRM_IOWR(0x1d, struct drm_ctx_priv_map)
+
+#define DRM_IOCTL_SET_MASTER DRM_IO(0x1e)
+#define DRM_IOCTL_DROP_MASTER DRM_IO(0x1f)
+
+#define DRM_IOCTL_ADD_CTX DRM_IOWR(0x20, struct drm_ctx)
+#define DRM_IOCTL_RM_CTX DRM_IOWR(0x21, struct drm_ctx)
+#define DRM_IOCTL_MOD_CTX DRM_IOW( 0x22, struct drm_ctx)
+#define DRM_IOCTL_GET_CTX DRM_IOWR(0x23, struct drm_ctx)
+#define DRM_IOCTL_SWITCH_CTX DRM_IOW( 0x24, struct drm_ctx)
+#define DRM_IOCTL_NEW_CTX DRM_IOW( 0x25, struct drm_ctx)
+#define DRM_IOCTL_RES_CTX DRM_IOWR(0x26, struct drm_ctx_res)
+#define DRM_IOCTL_ADD_DRAW DRM_IOWR(0x27, struct drm_draw)
+#define DRM_IOCTL_RM_DRAW DRM_IOWR(0x28, struct drm_draw)
+#define DRM_IOCTL_DMA DRM_IOWR(0x29, struct drm_dma)
+#define DRM_IOCTL_LOCK DRM_IOW( 0x2a, struct drm_lock)
+#define DRM_IOCTL_UNLOCK DRM_IOW( 0x2b, struct drm_lock)
+#define DRM_IOCTL_FINISH DRM_IOW( 0x2c, struct drm_lock)
+
+/**
+ * DRM_IOCTL_PRIME_HANDLE_TO_FD - Convert a GEM handle to a DMA-BUF FD.
+ *
+ * User-space sets &drm_prime_handle.handle with the GEM handle to export and
+ * &drm_prime_handle.flags, and gets back a DMA-BUF file descriptor in
+ * &drm_prime_handle.fd.
+ *
+ * The export can fail for any driver-specific reason, e.g. because export is
+ * not supported for this specific GEM handle (but might be for others).
+ *
+ * Support for exporting DMA-BUFs is advertised via &DRM_PRIME_CAP_EXPORT.
+ */
+#define DRM_IOCTL_PRIME_HANDLE_TO_FD DRM_IOWR(0x2d, struct drm_prime_handle)
+/**
+ * DRM_IOCTL_PRIME_FD_TO_HANDLE - Convert a DMA-BUF FD to a GEM handle.
+ *
+ * User-space sets &drm_prime_handle.fd with a DMA-BUF file descriptor to
+ * import, and gets back a GEM handle in &drm_prime_handle.handle.
+ * &drm_prime_handle.flags is unused.
+ *
+ * If an existing GEM handle refers to the memory object backing the DMA-BUF,
+ * that GEM handle is returned. Therefore user-space which needs to handle
+ * arbitrary DMA-BUFs must have a user-space lookup data structure to manually
+ * reference-count duplicated GEM handles. For more information see
+ * &DRM_IOCTL_GEM_CLOSE.
+ *
+ * The import can fail for any driver-specific reason, e.g. because import is
+ * only supported for DMA-BUFs allocated on this DRM device.
+ *
+ * Support for importing DMA-BUFs is advertised via &DRM_PRIME_CAP_IMPORT.
+ */
+#define DRM_IOCTL_PRIME_FD_TO_HANDLE DRM_IOWR(0x2e, struct drm_prime_handle)
+
+#define DRM_IOCTL_AGP_ACQUIRE DRM_IO( 0x30)
+#define DRM_IOCTL_AGP_RELEASE DRM_IO( 0x31)
+#define DRM_IOCTL_AGP_ENABLE DRM_IOW( 0x32, struct drm_agp_mode)
+#define DRM_IOCTL_AGP_INFO DRM_IOR( 0x33, struct drm_agp_info)
+#define DRM_IOCTL_AGP_ALLOC DRM_IOWR(0x34, struct drm_agp_buffer)
+#define DRM_IOCTL_AGP_FREE DRM_IOW( 0x35, struct drm_agp_buffer)
+#define DRM_IOCTL_AGP_BIND DRM_IOW( 0x36, struct drm_agp_binding)
+#define DRM_IOCTL_AGP_UNBIND DRM_IOW( 0x37, struct drm_agp_binding)
+
+#define DRM_IOCTL_SG_ALLOC DRM_IOWR(0x38, struct drm_scatter_gather)
+#define DRM_IOCTL_SG_FREE DRM_IOW( 0x39, struct drm_scatter_gather)
+
+#define DRM_IOCTL_WAIT_VBLANK DRM_IOWR(0x3a, union drm_wait_vblank)
+
+#define DRM_IOCTL_CRTC_GET_SEQUENCE DRM_IOWR(0x3b, struct drm_crtc_get_sequence)
+#define DRM_IOCTL_CRTC_QUEUE_SEQUENCE DRM_IOWR(0x3c, struct drm_crtc_queue_sequence)
+
+#define DRM_IOCTL_UPDATE_DRAW DRM_IOW(0x3f, struct drm_update_draw)
+
+#define DRM_IOCTL_MODE_GETRESOURCES DRM_IOWR(0xA0, struct drm_mode_card_res)
+#define DRM_IOCTL_MODE_GETCRTC DRM_IOWR(0xA1, struct drm_mode_crtc)
+#define DRM_IOCTL_MODE_SETCRTC DRM_IOWR(0xA2, struct drm_mode_crtc)
+#define DRM_IOCTL_MODE_CURSOR DRM_IOWR(0xA3, struct drm_mode_cursor)
+#define DRM_IOCTL_MODE_GETGAMMA DRM_IOWR(0xA4, struct drm_mode_crtc_lut)
+#define DRM_IOCTL_MODE_SETGAMMA DRM_IOWR(0xA5, struct drm_mode_crtc_lut)
+#define DRM_IOCTL_MODE_GETENCODER DRM_IOWR(0xA6, struct drm_mode_get_encoder)
+#define DRM_IOCTL_MODE_GETCONNECTOR DRM_IOWR(0xA7, struct drm_mode_get_connector)
+#define DRM_IOCTL_MODE_ATTACHMODE DRM_IOWR(0xA8, struct drm_mode_mode_cmd) /* deprecated (never worked) */
+#define DRM_IOCTL_MODE_DETACHMODE DRM_IOWR(0xA9, struct drm_mode_mode_cmd) /* deprecated (never worked) */
+
+#define DRM_IOCTL_MODE_GETPROPERTY DRM_IOWR(0xAA, struct drm_mode_get_property)
+#define DRM_IOCTL_MODE_SETPROPERTY DRM_IOWR(0xAB, struct drm_mode_connector_set_property)
+#define DRM_IOCTL_MODE_GETPROPBLOB DRM_IOWR(0xAC, struct drm_mode_get_blob)
+#define DRM_IOCTL_MODE_GETFB DRM_IOWR(0xAD, struct drm_mode_fb_cmd)
+#define DRM_IOCTL_MODE_ADDFB DRM_IOWR(0xAE, struct drm_mode_fb_cmd)
+/**
+ * DRM_IOCTL_MODE_RMFB - Remove a framebuffer.
+ *
+ * This removes a framebuffer previously added via ADDFB/ADDFB2. The IOCTL
+ * argument is a framebuffer object ID.
+ *
+ * Warning: removing a framebuffer currently in-use on an enabled plane will
+ * disable that plane. The CRTC the plane is linked to may also be disabled
+ * (depending on driver capabilities).
+ */
+#define DRM_IOCTL_MODE_RMFB DRM_IOWR(0xAF, unsigned int)
+#define DRM_IOCTL_MODE_PAGE_FLIP DRM_IOWR(0xB0, struct drm_mode_crtc_page_flip)
+#define DRM_IOCTL_MODE_DIRTYFB DRM_IOWR(0xB1, struct drm_mode_fb_dirty_cmd)
+
+#define DRM_IOCTL_MODE_CREATE_DUMB DRM_IOWR(0xB2, struct drm_mode_create_dumb)
+#define DRM_IOCTL_MODE_MAP_DUMB DRM_IOWR(0xB3, struct drm_mode_map_dumb)
+#define DRM_IOCTL_MODE_DESTROY_DUMB DRM_IOWR(0xB4, struct drm_mode_destroy_dumb)
+#define DRM_IOCTL_MODE_GETPLANERESOURCES DRM_IOWR(0xB5, struct drm_mode_get_plane_res)
+#define DRM_IOCTL_MODE_GETPLANE DRM_IOWR(0xB6, struct drm_mode_get_plane)
+#define DRM_IOCTL_MODE_SETPLANE DRM_IOWR(0xB7, struct drm_mode_set_plane)
+#define DRM_IOCTL_MODE_ADDFB2 DRM_IOWR(0xB8, struct drm_mode_fb_cmd2)
+#define DRM_IOCTL_MODE_OBJ_GETPROPERTIES DRM_IOWR(0xB9, struct drm_mode_obj_get_properties)
+#define DRM_IOCTL_MODE_OBJ_SETPROPERTY DRM_IOWR(0xBA, struct drm_mode_obj_set_property)
+#define DRM_IOCTL_MODE_CURSOR2 DRM_IOWR(0xBB, struct drm_mode_cursor2)
+#define DRM_IOCTL_MODE_ATOMIC DRM_IOWR(0xBC, struct drm_mode_atomic)
+#define DRM_IOCTL_MODE_CREATEPROPBLOB DRM_IOWR(0xBD, struct drm_mode_create_blob)
+#define DRM_IOCTL_MODE_DESTROYPROPBLOB DRM_IOWR(0xBE, struct drm_mode_destroy_blob)
+
+#define DRM_IOCTL_SYNCOBJ_CREATE DRM_IOWR(0xBF, struct drm_syncobj_create)
+#define DRM_IOCTL_SYNCOBJ_DESTROY DRM_IOWR(0xC0, struct drm_syncobj_destroy)
+#define DRM_IOCTL_SYNCOBJ_HANDLE_TO_FD DRM_IOWR(0xC1, struct drm_syncobj_handle)
+#define DRM_IOCTL_SYNCOBJ_FD_TO_HANDLE DRM_IOWR(0xC2, struct drm_syncobj_handle)
+#define DRM_IOCTL_SYNCOBJ_WAIT DRM_IOWR(0xC3, struct drm_syncobj_wait)
+#define DRM_IOCTL_SYNCOBJ_RESET DRM_IOWR(0xC4, struct drm_syncobj_array)
+#define DRM_IOCTL_SYNCOBJ_SIGNAL DRM_IOWR(0xC5, struct drm_syncobj_array)
+
+#define DRM_IOCTL_MODE_CREATE_LEASE DRM_IOWR(0xC6, struct drm_mode_create_lease)
+#define DRM_IOCTL_MODE_LIST_LESSEES DRM_IOWR(0xC7, struct drm_mode_list_lessees)
+#define DRM_IOCTL_MODE_GET_LEASE DRM_IOWR(0xC8, struct drm_mode_get_lease)
+#define DRM_IOCTL_MODE_REVOKE_LEASE DRM_IOWR(0xC9, struct drm_mode_revoke_lease)
+
+#define DRM_IOCTL_SYNCOBJ_TIMELINE_WAIT DRM_IOWR(0xCA, struct drm_syncobj_timeline_wait)
+#define DRM_IOCTL_SYNCOBJ_QUERY DRM_IOWR(0xCB, struct drm_syncobj_timeline_array)
+#define DRM_IOCTL_SYNCOBJ_TRANSFER DRM_IOWR(0xCC, struct drm_syncobj_transfer)
+#define DRM_IOCTL_SYNCOBJ_TIMELINE_SIGNAL DRM_IOWR(0xCD, struct drm_syncobj_timeline_array)
+
+/**
+ * DRM_IOCTL_MODE_GETFB2 - Get framebuffer metadata.
+ *
+ * This queries metadata about a framebuffer. User-space fills
+ * &drm_mode_fb_cmd2.fb_id as the input, and the kernels fills the rest of the
+ * struct as the output.
+ *
+ * If the client is DRM master or has &CAP_SYS_ADMIN, &drm_mode_fb_cmd2.handles
+ * will be filled with GEM buffer handles. Fresh new GEM handles are always
+ * returned, even if another GEM handle referring to the same memory object
+ * already exists on the DRM file description. The caller is responsible for
+ * removing the new handles, e.g. via the &DRM_IOCTL_GEM_CLOSE IOCTL. The same
+ * new handle will be returned for multiple planes in case they use the same
+ * memory object. Planes are valid until one has a zero handle -- this can be
+ * used to compute the number of planes.
+ *
+ * Otherwise, &drm_mode_fb_cmd2.handles will be zeroed and planes are valid
+ * until one has a zero &drm_mode_fb_cmd2.pitches.
+ *
+ * If the framebuffer has a format modifier, &DRM_MODE_FB_MODIFIERS will be set
+ * in &drm_mode_fb_cmd2.flags and &drm_mode_fb_cmd2.modifier will contain the
+ * modifier. Otherwise, user-space must ignore &drm_mode_fb_cmd2.modifier.
+ *
+ * To obtain DMA-BUF FDs for each plane without leaking GEM handles, user-space
+ * can export each handle via &DRM_IOCTL_PRIME_HANDLE_TO_FD, then immediately
+ * close each unique handle via &DRM_IOCTL_GEM_CLOSE, making sure to not
+ * double-close handles which are specified multiple times in the array.
+ */
+#define DRM_IOCTL_MODE_GETFB2 DRM_IOWR(0xCE, struct drm_mode_fb_cmd2)
+
+#define DRM_IOCTL_SYNCOBJ_EVENTFD DRM_IOWR(0xCF, struct drm_syncobj_eventfd)
+
+/*
+ * Device specific ioctls should only be in their respective headers
+ * The device specific ioctl range is from 0x40 to 0x9f.
+ * Generic IOCTLS restart at 0xA0.
+ *
+ * \sa drmCommandNone(), drmCommandRead(), drmCommandWrite(), and
+ * drmCommandReadWrite().
+ */
+#define DRM_COMMAND_BASE 0x40
+#define DRM_COMMAND_END 0xA0
+
+/**
+ * struct drm_event - Header for DRM events
+ * @type: event type.
+ * @length: total number of payload bytes (including header).
+ *
+ * This struct is a header for events written back to user-space on the DRM FD.
+ * A read on the DRM FD will always only return complete events: e.g. if the
+ * read buffer is 100 bytes large and there are two 64 byte events pending,
+ * only one will be returned.
+ *
+ * Event types 0 - 0x7fffffff are generic DRM events, 0x80000000 and
+ * up are chipset specific. Generic DRM events include &DRM_EVENT_VBLANK,
+ * &DRM_EVENT_FLIP_COMPLETE and &DRM_EVENT_CRTC_SEQUENCE.
+ */
+struct drm_event {
+ __u32 type;
+ __u32 length;
+};
+
+/**
+ * DRM_EVENT_VBLANK - vertical blanking event
+ *
+ * This event is sent in response to &DRM_IOCTL_WAIT_VBLANK with the
+ * &_DRM_VBLANK_EVENT flag set.
+ *
+ * The event payload is a struct drm_event_vblank.
+ */
+#define DRM_EVENT_VBLANK 0x01
+/**
+ * DRM_EVENT_FLIP_COMPLETE - page-flip completion event
+ *
+ * This event is sent in response to an atomic commit or legacy page-flip with
+ * the &DRM_MODE_PAGE_FLIP_EVENT flag set.
+ *
+ * The event payload is a struct drm_event_vblank.
+ */
+#define DRM_EVENT_FLIP_COMPLETE 0x02
+/**
+ * DRM_EVENT_CRTC_SEQUENCE - CRTC sequence event
+ *
+ * This event is sent in response to &DRM_IOCTL_CRTC_QUEUE_SEQUENCE.
+ *
+ * The event payload is a struct drm_event_crtc_sequence.
+ */
+#define DRM_EVENT_CRTC_SEQUENCE 0x03
+
+struct drm_event_vblank {
+ struct drm_event base;
+ __u64 user_data;
+ __u32 tv_sec;
+ __u32 tv_usec;
+ __u32 sequence;
+ __u32 crtc_id; /* 0 on older kernels that do not support this */
+};
+
+/* Event delivered at sequence. Time stamp marks when the first pixel
+ * of the refresh cycle leaves the display engine for the display
+ */
+struct drm_event_crtc_sequence {
+ struct drm_event base;
+ __u64 user_data;
+ __s64 time_ns;
+ __u64 sequence;
+};
+
+/* typedef area */
+#ifndef __KERNEL__
+typedef struct drm_clip_rect drm_clip_rect_t;
+typedef struct drm_drawable_info drm_drawable_info_t;
+typedef struct drm_tex_region drm_tex_region_t;
+typedef struct drm_hw_lock drm_hw_lock_t;
+typedef struct drm_version drm_version_t;
+typedef struct drm_unique drm_unique_t;
+typedef struct drm_list drm_list_t;
+typedef struct drm_block drm_block_t;
+typedef struct drm_control drm_control_t;
+typedef enum drm_map_type drm_map_type_t;
+typedef enum drm_map_flags drm_map_flags_t;
+typedef struct drm_ctx_priv_map drm_ctx_priv_map_t;
+typedef struct drm_map drm_map_t;
+typedef struct drm_client drm_client_t;
+typedef enum drm_stat_type drm_stat_type_t;
+typedef struct drm_stats drm_stats_t;
+typedef enum drm_lock_flags drm_lock_flags_t;
+typedef struct drm_lock drm_lock_t;
+typedef enum drm_dma_flags drm_dma_flags_t;
+typedef struct drm_buf_desc drm_buf_desc_t;
+typedef struct drm_buf_info drm_buf_info_t;
+typedef struct drm_buf_free drm_buf_free_t;
+typedef struct drm_buf_pub drm_buf_pub_t;
+typedef struct drm_buf_map drm_buf_map_t;
+typedef struct drm_dma drm_dma_t;
+typedef union drm_wait_vblank drm_wait_vblank_t;
+typedef struct drm_agp_mode drm_agp_mode_t;
+typedef enum drm_ctx_flags drm_ctx_flags_t;
+typedef struct drm_ctx drm_ctx_t;
+typedef struct drm_ctx_res drm_ctx_res_t;
+typedef struct drm_draw drm_draw_t;
+typedef struct drm_update_draw drm_update_draw_t;
+typedef struct drm_auth drm_auth_t;
+typedef struct drm_irq_busid drm_irq_busid_t;
+typedef enum drm_vblank_seq_type drm_vblank_seq_type_t;
+
+typedef struct drm_agp_buffer drm_agp_buffer_t;
+typedef struct drm_agp_binding drm_agp_binding_t;
+typedef struct drm_agp_info drm_agp_info_t;
+typedef struct drm_scatter_gather drm_scatter_gather_t;
+typedef struct drm_set_version drm_set_version_t;
+#endif
+
+#if defined(__cplusplus)
+}
+#endif
+
+#endif
diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h
new file mode 100644
index 0000000000..7000e5910a
--- /dev/null
+++ b/tools/include/uapi/drm/i915_drm.h
@@ -0,0 +1,3848 @@
+/*
+ * Copyright 2003 Tungsten Graphics, Inc., Cedar Park, Texas.
+ * All Rights Reserved.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the
+ * "Software"), to deal in the Software without restriction, including
+ * without limitation the rights to use, copy, modify, merge, publish,
+ * distribute, sub license, and/or sell copies of the Software, and to
+ * permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the
+ * next paragraph) shall be included in all copies or substantial portions
+ * of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+ * OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT.
+ * IN NO EVENT SHALL TUNGSTEN GRAPHICS AND/OR ITS SUPPLIERS BE LIABLE FOR
+ * ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
+ * TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
+ * SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+#ifndef _UAPI_I915_DRM_H_
+#define _UAPI_I915_DRM_H_
+
+#include "drm.h"
+
+#if defined(__cplusplus)
+extern "C" {
+#endif
+
+/* Please note that modifications to all structs defined here are
+ * subject to backwards-compatibility constraints.
+ */
+
+/**
+ * DOC: uevents generated by i915 on it's device node
+ *
+ * I915_L3_PARITY_UEVENT - Generated when the driver receives a parity mismatch
+ * event from the gpu l3 cache. Additional information supplied is ROW,
+ * BANK, SUBBANK, SLICE of the affected cacheline. Userspace should keep
+ * track of these events and if a specific cache-line seems to have a
+ * persistent error remap it with the l3 remapping tool supplied in
+ * intel-gpu-tools. The value supplied with the event is always 1.
+ *
+ * I915_ERROR_UEVENT - Generated upon error detection, currently only via
+ * hangcheck. The error detection event is a good indicator of when things
+ * began to go badly. The value supplied with the event is a 1 upon error
+ * detection, and a 0 upon reset completion, signifying no more error
+ * exists. NOTE: Disabling hangcheck or reset via module parameter will
+ * cause the related events to not be seen.
+ *
+ * I915_RESET_UEVENT - Event is generated just before an attempt to reset the
+ * GPU. The value supplied with the event is always 1. NOTE: Disable
+ * reset via module parameter will cause this event to not be seen.
+ */
+#define I915_L3_PARITY_UEVENT "L3_PARITY_ERROR"
+#define I915_ERROR_UEVENT "ERROR"
+#define I915_RESET_UEVENT "RESET"
+
+/**
+ * struct i915_user_extension - Base class for defining a chain of extensions
+ *
+ * Many interfaces need to grow over time. In most cases we can simply
+ * extend the struct and have userspace pass in more data. Another option,
+ * as demonstrated by Vulkan's approach to providing extensions for forward
+ * and backward compatibility, is to use a list of optional structs to
+ * provide those extra details.
+ *
+ * The key advantage to using an extension chain is that it allows us to
+ * redefine the interface more easily than an ever growing struct of
+ * increasing complexity, and for large parts of that interface to be
+ * entirely optional. The downside is more pointer chasing; chasing across
+ * the __user boundary with pointers encapsulated inside u64.
+ *
+ * Example chaining:
+ *
+ * .. code-block:: C
+ *
+ * struct i915_user_extension ext3 {
+ * .next_extension = 0, // end
+ * .name = ...,
+ * };
+ * struct i915_user_extension ext2 {
+ * .next_extension = (uintptr_t)&ext3,
+ * .name = ...,
+ * };
+ * struct i915_user_extension ext1 {
+ * .next_extension = (uintptr_t)&ext2,
+ * .name = ...,
+ * };
+ *
+ * Typically the struct i915_user_extension would be embedded in some uAPI
+ * struct, and in this case we would feed it the head of the chain(i.e ext1),
+ * which would then apply all of the above extensions.
+ *
+ */
+struct i915_user_extension {
+ /**
+ * @next_extension:
+ *
+ * Pointer to the next struct i915_user_extension, or zero if the end.
+ */
+ __u64 next_extension;
+ /**
+ * @name: Name of the extension.
+ *
+ * Note that the name here is just some integer.
+ *
+ * Also note that the name space for this is not global for the whole
+ * driver, but rather its scope/meaning is limited to the specific piece
+ * of uAPI which has embedded the struct i915_user_extension.
+ */
+ __u32 name;
+ /**
+ * @flags: MBZ
+ *
+ * All undefined bits must be zero.
+ */
+ __u32 flags;
+ /**
+ * @rsvd: MBZ
+ *
+ * Reserved for future use; must be zero.
+ */
+ __u32 rsvd[4];
+};
+
+/*
+ * MOCS indexes used for GPU surfaces, defining the cacheability of the
+ * surface data and the coherency for this data wrt. CPU vs. GPU accesses.
+ */
+enum i915_mocs_table_index {
+ /*
+ * Not cached anywhere, coherency between CPU and GPU accesses is
+ * guaranteed.
+ */
+ I915_MOCS_UNCACHED,
+ /*
+ * Cacheability and coherency controlled by the kernel automatically
+ * based on the DRM_I915_GEM_SET_CACHING IOCTL setting and the current
+ * usage of the surface (used for display scanout or not).
+ */
+ I915_MOCS_PTE,
+ /*
+ * Cached in all GPU caches available on the platform.
+ * Coherency between CPU and GPU accesses to the surface is not
+ * guaranteed without extra synchronization.
+ */
+ I915_MOCS_CACHED,
+};
+
+/**
+ * enum drm_i915_gem_engine_class - uapi engine type enumeration
+ *
+ * Different engines serve different roles, and there may be more than one
+ * engine serving each role. This enum provides a classification of the role
+ * of the engine, which may be used when requesting operations to be performed
+ * on a certain subset of engines, or for providing information about that
+ * group.
+ */
+enum drm_i915_gem_engine_class {
+ /**
+ * @I915_ENGINE_CLASS_RENDER:
+ *
+ * Render engines support instructions used for 3D, Compute (GPGPU),
+ * and programmable media workloads. These instructions fetch data and
+ * dispatch individual work items to threads that operate in parallel.
+ * The threads run small programs (called "kernels" or "shaders") on
+ * the GPU's execution units (EUs).
+ */
+ I915_ENGINE_CLASS_RENDER = 0,
+
+ /**
+ * @I915_ENGINE_CLASS_COPY:
+ *
+ * Copy engines (also referred to as "blitters") support instructions
+ * that move blocks of data from one location in memory to another,
+ * or that fill a specified location of memory with fixed data.
+ * Copy engines can perform pre-defined logical or bitwise operations
+ * on the source, destination, or pattern data.
+ */
+ I915_ENGINE_CLASS_COPY = 1,
+
+ /**
+ * @I915_ENGINE_CLASS_VIDEO:
+ *
+ * Video engines (also referred to as "bit stream decode" (BSD) or
+ * "vdbox") support instructions that perform fixed-function media
+ * decode and encode.
+ */
+ I915_ENGINE_CLASS_VIDEO = 2,
+
+ /**
+ * @I915_ENGINE_CLASS_VIDEO_ENHANCE:
+ *
+ * Video enhancement engines (also referred to as "vebox") support
+ * instructions related to image enhancement.
+ */
+ I915_ENGINE_CLASS_VIDEO_ENHANCE = 3,
+
+ /**
+ * @I915_ENGINE_CLASS_COMPUTE:
+ *
+ * Compute engines support a subset of the instructions available
+ * on render engines: compute engines support Compute (GPGPU) and
+ * programmable media workloads, but do not support the 3D pipeline.
+ */
+ I915_ENGINE_CLASS_COMPUTE = 4,
+
+ /* Values in this enum should be kept compact. */
+
+ /**
+ * @I915_ENGINE_CLASS_INVALID:
+ *
+ * Placeholder value to represent an invalid engine class assignment.
+ */
+ I915_ENGINE_CLASS_INVALID = -1
+};
+
+/**
+ * struct i915_engine_class_instance - Engine class/instance identifier
+ *
+ * There may be more than one engine fulfilling any role within the system.
+ * Each engine of a class is given a unique instance number and therefore
+ * any engine can be specified by its class:instance tuplet. APIs that allow
+ * access to any engine in the system will use struct i915_engine_class_instance
+ * for this identification.
+ */
+struct i915_engine_class_instance {
+ /**
+ * @engine_class:
+ *
+ * Engine class from enum drm_i915_gem_engine_class
+ */
+ __u16 engine_class;
+#define I915_ENGINE_CLASS_INVALID_NONE -1
+#define I915_ENGINE_CLASS_INVALID_VIRTUAL -2
+
+ /**
+ * @engine_instance:
+ *
+ * Engine instance.
+ */
+ __u16 engine_instance;
+};
+
+/**
+ * DOC: perf_events exposed by i915 through /sys/bus/event_sources/drivers/i915
+ *
+ */
+
+enum drm_i915_pmu_engine_sample {
+ I915_SAMPLE_BUSY = 0,
+ I915_SAMPLE_WAIT = 1,
+ I915_SAMPLE_SEMA = 2
+};
+
+#define I915_PMU_SAMPLE_BITS (4)
+#define I915_PMU_SAMPLE_MASK (0xf)
+#define I915_PMU_SAMPLE_INSTANCE_BITS (8)
+#define I915_PMU_CLASS_SHIFT \
+ (I915_PMU_SAMPLE_BITS + I915_PMU_SAMPLE_INSTANCE_BITS)
+
+#define __I915_PMU_ENGINE(class, instance, sample) \
+ ((class) << I915_PMU_CLASS_SHIFT | \
+ (instance) << I915_PMU_SAMPLE_BITS | \
+ (sample))
+
+#define I915_PMU_ENGINE_BUSY(class, instance) \
+ __I915_PMU_ENGINE(class, instance, I915_SAMPLE_BUSY)
+
+#define I915_PMU_ENGINE_WAIT(class, instance) \
+ __I915_PMU_ENGINE(class, instance, I915_SAMPLE_WAIT)
+
+#define I915_PMU_ENGINE_SEMA(class, instance) \
+ __I915_PMU_ENGINE(class, instance, I915_SAMPLE_SEMA)
+
+/*
+ * Top 4 bits of every non-engine counter are GT id.
+ */
+#define __I915_PMU_GT_SHIFT (60)
+
+#define ___I915_PMU_OTHER(gt, x) \
+ (((__u64)__I915_PMU_ENGINE(0xff, 0xff, 0xf) + 1 + (x)) | \
+ ((__u64)(gt) << __I915_PMU_GT_SHIFT))
+
+#define __I915_PMU_OTHER(x) ___I915_PMU_OTHER(0, x)
+
+#define I915_PMU_ACTUAL_FREQUENCY __I915_PMU_OTHER(0)
+#define I915_PMU_REQUESTED_FREQUENCY __I915_PMU_OTHER(1)
+#define I915_PMU_INTERRUPTS __I915_PMU_OTHER(2)
+#define I915_PMU_RC6_RESIDENCY __I915_PMU_OTHER(3)
+#define I915_PMU_SOFTWARE_GT_AWAKE_TIME __I915_PMU_OTHER(4)
+
+#define I915_PMU_LAST /* Deprecated - do not use */ I915_PMU_RC6_RESIDENCY
+
+#define __I915_PMU_ACTUAL_FREQUENCY(gt) ___I915_PMU_OTHER(gt, 0)
+#define __I915_PMU_REQUESTED_FREQUENCY(gt) ___I915_PMU_OTHER(gt, 1)
+#define __I915_PMU_INTERRUPTS(gt) ___I915_PMU_OTHER(gt, 2)
+#define __I915_PMU_RC6_RESIDENCY(gt) ___I915_PMU_OTHER(gt, 3)
+#define __I915_PMU_SOFTWARE_GT_AWAKE_TIME(gt) ___I915_PMU_OTHER(gt, 4)
+
+/* Each region is a minimum of 16k, and there are at most 255 of them.
+ */
+#define I915_NR_TEX_REGIONS 255 /* table size 2k - maximum due to use
+ * of chars for next/prev indices */
+#define I915_LOG_MIN_TEX_REGION_SIZE 14
+
+typedef struct _drm_i915_init {
+ enum {
+ I915_INIT_DMA = 0x01,
+ I915_CLEANUP_DMA = 0x02,
+ I915_RESUME_DMA = 0x03
+ } func;
+ unsigned int mmio_offset;
+ int sarea_priv_offset;
+ unsigned int ring_start;
+ unsigned int ring_end;
+ unsigned int ring_size;
+ unsigned int front_offset;
+ unsigned int back_offset;
+ unsigned int depth_offset;
+ unsigned int w;
+ unsigned int h;
+ unsigned int pitch;
+ unsigned int pitch_bits;
+ unsigned int back_pitch;
+ unsigned int depth_pitch;
+ unsigned int cpp;
+ unsigned int chipset;
+} drm_i915_init_t;
+
+typedef struct _drm_i915_sarea {
+ struct drm_tex_region texList[I915_NR_TEX_REGIONS + 1];
+ int last_upload; /* last time texture was uploaded */
+ int last_enqueue; /* last time a buffer was enqueued */
+ int last_dispatch; /* age of the most recently dispatched buffer */
+ int ctxOwner; /* last context to upload state */
+ int texAge;
+ int pf_enabled; /* is pageflipping allowed? */
+ int pf_active;
+ int pf_current_page; /* which buffer is being displayed? */
+ int perf_boxes; /* performance boxes to be displayed */
+ int width, height; /* screen size in pixels */
+
+ drm_handle_t front_handle;
+ int front_offset;
+ int front_size;
+
+ drm_handle_t back_handle;
+ int back_offset;
+ int back_size;
+
+ drm_handle_t depth_handle;
+ int depth_offset;
+ int depth_size;
+
+ drm_handle_t tex_handle;
+ int tex_offset;
+ int tex_size;
+ int log_tex_granularity;
+ int pitch;
+ int rotation; /* 0, 90, 180 or 270 */
+ int rotated_offset;
+ int rotated_size;
+ int rotated_pitch;
+ int virtualX, virtualY;
+
+ unsigned int front_tiled;
+ unsigned int back_tiled;
+ unsigned int depth_tiled;
+ unsigned int rotated_tiled;
+ unsigned int rotated2_tiled;
+
+ int pipeA_x;
+ int pipeA_y;
+ int pipeA_w;
+ int pipeA_h;
+ int pipeB_x;
+ int pipeB_y;
+ int pipeB_w;
+ int pipeB_h;
+
+ /* fill out some space for old userspace triple buffer */
+ drm_handle_t unused_handle;
+ __u32 unused1, unused2, unused3;
+
+ /* buffer object handles for static buffers. May change
+ * over the lifetime of the client.
+ */
+ __u32 front_bo_handle;
+ __u32 back_bo_handle;
+ __u32 unused_bo_handle;
+ __u32 depth_bo_handle;
+
+} drm_i915_sarea_t;
+
+/* due to userspace building against these headers we need some compat here */
+#define planeA_x pipeA_x
+#define planeA_y pipeA_y
+#define planeA_w pipeA_w
+#define planeA_h pipeA_h
+#define planeB_x pipeB_x
+#define planeB_y pipeB_y
+#define planeB_w pipeB_w
+#define planeB_h pipeB_h
+
+/* Flags for perf_boxes
+ */
+#define I915_BOX_RING_EMPTY 0x1
+#define I915_BOX_FLIP 0x2
+#define I915_BOX_WAIT 0x4
+#define I915_BOX_TEXTURE_LOAD 0x8
+#define I915_BOX_LOST_CONTEXT 0x10
+
+/*
+ * i915 specific ioctls.
+ *
+ * The device specific ioctl range is [DRM_COMMAND_BASE, DRM_COMMAND_END) ie
+ * [0x40, 0xa0) (a0 is excluded). The numbers below are defined as offset
+ * against DRM_COMMAND_BASE and should be between [0x0, 0x60).
+ */
+#define DRM_I915_INIT 0x00
+#define DRM_I915_FLUSH 0x01
+#define DRM_I915_FLIP 0x02
+#define DRM_I915_BATCHBUFFER 0x03
+#define DRM_I915_IRQ_EMIT 0x04
+#define DRM_I915_IRQ_WAIT 0x05
+#define DRM_I915_GETPARAM 0x06
+#define DRM_I915_SETPARAM 0x07
+#define DRM_I915_ALLOC 0x08
+#define DRM_I915_FREE 0x09
+#define DRM_I915_INIT_HEAP 0x0a
+#define DRM_I915_CMDBUFFER 0x0b
+#define DRM_I915_DESTROY_HEAP 0x0c
+#define DRM_I915_SET_VBLANK_PIPE 0x0d
+#define DRM_I915_GET_VBLANK_PIPE 0x0e
+#define DRM_I915_VBLANK_SWAP 0x0f
+#define DRM_I915_HWS_ADDR 0x11
+#define DRM_I915_GEM_INIT 0x13
+#define DRM_I915_GEM_EXECBUFFER 0x14
+#define DRM_I915_GEM_PIN 0x15
+#define DRM_I915_GEM_UNPIN 0x16
+#define DRM_I915_GEM_BUSY 0x17
+#define DRM_I915_GEM_THROTTLE 0x18
+#define DRM_I915_GEM_ENTERVT 0x19
+#define DRM_I915_GEM_LEAVEVT 0x1a
+#define DRM_I915_GEM_CREATE 0x1b
+#define DRM_I915_GEM_PREAD 0x1c
+#define DRM_I915_GEM_PWRITE 0x1d
+#define DRM_I915_GEM_MMAP 0x1e
+#define DRM_I915_GEM_SET_DOMAIN 0x1f
+#define DRM_I915_GEM_SW_FINISH 0x20
+#define DRM_I915_GEM_SET_TILING 0x21
+#define DRM_I915_GEM_GET_TILING 0x22
+#define DRM_I915_GEM_GET_APERTURE 0x23
+#define DRM_I915_GEM_MMAP_GTT 0x24
+#define DRM_I915_GET_PIPE_FROM_CRTC_ID 0x25
+#define DRM_I915_GEM_MADVISE 0x26
+#define DRM_I915_OVERLAY_PUT_IMAGE 0x27
+#define DRM_I915_OVERLAY_ATTRS 0x28
+#define DRM_I915_GEM_EXECBUFFER2 0x29
+#define DRM_I915_GEM_EXECBUFFER2_WR DRM_I915_GEM_EXECBUFFER2
+#define DRM_I915_GET_SPRITE_COLORKEY 0x2a
+#define DRM_I915_SET_SPRITE_COLORKEY 0x2b
+#define DRM_I915_GEM_WAIT 0x2c
+#define DRM_I915_GEM_CONTEXT_CREATE 0x2d
+#define DRM_I915_GEM_CONTEXT_DESTROY 0x2e
+#define DRM_I915_GEM_SET_CACHING 0x2f
+#define DRM_I915_GEM_GET_CACHING 0x30
+#define DRM_I915_REG_READ 0x31
+#define DRM_I915_GET_RESET_STATS 0x32
+#define DRM_I915_GEM_USERPTR 0x33
+#define DRM_I915_GEM_CONTEXT_GETPARAM 0x34
+#define DRM_I915_GEM_CONTEXT_SETPARAM 0x35
+#define DRM_I915_PERF_OPEN 0x36
+#define DRM_I915_PERF_ADD_CONFIG 0x37
+#define DRM_I915_PERF_REMOVE_CONFIG 0x38
+#define DRM_I915_QUERY 0x39
+#define DRM_I915_GEM_VM_CREATE 0x3a
+#define DRM_I915_GEM_VM_DESTROY 0x3b
+#define DRM_I915_GEM_CREATE_EXT 0x3c
+/* Must be kept compact -- no holes */
+
+#define DRM_IOCTL_I915_INIT DRM_IOW( DRM_COMMAND_BASE + DRM_I915_INIT, drm_i915_init_t)
+#define DRM_IOCTL_I915_FLUSH DRM_IO ( DRM_COMMAND_BASE + DRM_I915_FLUSH)
+#define DRM_IOCTL_I915_FLIP DRM_IO ( DRM_COMMAND_BASE + DRM_I915_FLIP)
+#define DRM_IOCTL_I915_BATCHBUFFER DRM_IOW( DRM_COMMAND_BASE + DRM_I915_BATCHBUFFER, drm_i915_batchbuffer_t)
+#define DRM_IOCTL_I915_IRQ_EMIT DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_IRQ_EMIT, drm_i915_irq_emit_t)
+#define DRM_IOCTL_I915_IRQ_WAIT DRM_IOW( DRM_COMMAND_BASE + DRM_I915_IRQ_WAIT, drm_i915_irq_wait_t)
+#define DRM_IOCTL_I915_GETPARAM DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GETPARAM, drm_i915_getparam_t)
+#define DRM_IOCTL_I915_SETPARAM DRM_IOW( DRM_COMMAND_BASE + DRM_I915_SETPARAM, drm_i915_setparam_t)
+#define DRM_IOCTL_I915_ALLOC DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_ALLOC, drm_i915_mem_alloc_t)
+#define DRM_IOCTL_I915_FREE DRM_IOW( DRM_COMMAND_BASE + DRM_I915_FREE, drm_i915_mem_free_t)
+#define DRM_IOCTL_I915_INIT_HEAP DRM_IOW( DRM_COMMAND_BASE + DRM_I915_INIT_HEAP, drm_i915_mem_init_heap_t)
+#define DRM_IOCTL_I915_CMDBUFFER DRM_IOW( DRM_COMMAND_BASE + DRM_I915_CMDBUFFER, drm_i915_cmdbuffer_t)
+#define DRM_IOCTL_I915_DESTROY_HEAP DRM_IOW( DRM_COMMAND_BASE + DRM_I915_DESTROY_HEAP, drm_i915_mem_destroy_heap_t)
+#define DRM_IOCTL_I915_SET_VBLANK_PIPE DRM_IOW( DRM_COMMAND_BASE + DRM_I915_SET_VBLANK_PIPE, drm_i915_vblank_pipe_t)
+#define DRM_IOCTL_I915_GET_VBLANK_PIPE DRM_IOR( DRM_COMMAND_BASE + DRM_I915_GET_VBLANK_PIPE, drm_i915_vblank_pipe_t)
+#define DRM_IOCTL_I915_VBLANK_SWAP DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_VBLANK_SWAP, drm_i915_vblank_swap_t)
+#define DRM_IOCTL_I915_HWS_ADDR DRM_IOW(DRM_COMMAND_BASE + DRM_I915_HWS_ADDR, struct drm_i915_gem_init)
+#define DRM_IOCTL_I915_GEM_INIT DRM_IOW(DRM_COMMAND_BASE + DRM_I915_GEM_INIT, struct drm_i915_gem_init)
+#define DRM_IOCTL_I915_GEM_EXECBUFFER DRM_IOW(DRM_COMMAND_BASE + DRM_I915_GEM_EXECBUFFER, struct drm_i915_gem_execbuffer)
+#define DRM_IOCTL_I915_GEM_EXECBUFFER2 DRM_IOW(DRM_COMMAND_BASE + DRM_I915_GEM_EXECBUFFER2, struct drm_i915_gem_execbuffer2)
+#define DRM_IOCTL_I915_GEM_EXECBUFFER2_WR DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_EXECBUFFER2_WR, struct drm_i915_gem_execbuffer2)
+#define DRM_IOCTL_I915_GEM_PIN DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_PIN, struct drm_i915_gem_pin)
+#define DRM_IOCTL_I915_GEM_UNPIN DRM_IOW(DRM_COMMAND_BASE + DRM_I915_GEM_UNPIN, struct drm_i915_gem_unpin)
+#define DRM_IOCTL_I915_GEM_BUSY DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_BUSY, struct drm_i915_gem_busy)
+#define DRM_IOCTL_I915_GEM_SET_CACHING DRM_IOW(DRM_COMMAND_BASE + DRM_I915_GEM_SET_CACHING, struct drm_i915_gem_caching)
+#define DRM_IOCTL_I915_GEM_GET_CACHING DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_GET_CACHING, struct drm_i915_gem_caching)
+#define DRM_IOCTL_I915_GEM_THROTTLE DRM_IO ( DRM_COMMAND_BASE + DRM_I915_GEM_THROTTLE)
+#define DRM_IOCTL_I915_GEM_ENTERVT DRM_IO(DRM_COMMAND_BASE + DRM_I915_GEM_ENTERVT)
+#define DRM_IOCTL_I915_GEM_LEAVEVT DRM_IO(DRM_COMMAND_BASE + DRM_I915_GEM_LEAVEVT)
+#define DRM_IOCTL_I915_GEM_CREATE DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_CREATE, struct drm_i915_gem_create)
+#define DRM_IOCTL_I915_GEM_CREATE_EXT DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_CREATE_EXT, struct drm_i915_gem_create_ext)
+#define DRM_IOCTL_I915_GEM_PREAD DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_PREAD, struct drm_i915_gem_pread)
+#define DRM_IOCTL_I915_GEM_PWRITE DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_PWRITE, struct drm_i915_gem_pwrite)
+#define DRM_IOCTL_I915_GEM_MMAP DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_MMAP, struct drm_i915_gem_mmap)
+#define DRM_IOCTL_I915_GEM_MMAP_GTT DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_MMAP_GTT, struct drm_i915_gem_mmap_gtt)
+#define DRM_IOCTL_I915_GEM_MMAP_OFFSET DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_MMAP_GTT, struct drm_i915_gem_mmap_offset)
+#define DRM_IOCTL_I915_GEM_SET_DOMAIN DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_SET_DOMAIN, struct drm_i915_gem_set_domain)
+#define DRM_IOCTL_I915_GEM_SW_FINISH DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_SW_FINISH, struct drm_i915_gem_sw_finish)
+#define DRM_IOCTL_I915_GEM_SET_TILING DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_SET_TILING, struct drm_i915_gem_set_tiling)
+#define DRM_IOCTL_I915_GEM_GET_TILING DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_GET_TILING, struct drm_i915_gem_get_tiling)
+#define DRM_IOCTL_I915_GEM_GET_APERTURE DRM_IOR (DRM_COMMAND_BASE + DRM_I915_GEM_GET_APERTURE, struct drm_i915_gem_get_aperture)
+#define DRM_IOCTL_I915_GET_PIPE_FROM_CRTC_ID DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GET_PIPE_FROM_CRTC_ID, struct drm_i915_get_pipe_from_crtc_id)
+#define DRM_IOCTL_I915_GEM_MADVISE DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_MADVISE, struct drm_i915_gem_madvise)
+#define DRM_IOCTL_I915_OVERLAY_PUT_IMAGE DRM_IOW(DRM_COMMAND_BASE + DRM_I915_OVERLAY_PUT_IMAGE, struct drm_intel_overlay_put_image)
+#define DRM_IOCTL_I915_OVERLAY_ATTRS DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_OVERLAY_ATTRS, struct drm_intel_overlay_attrs)
+#define DRM_IOCTL_I915_SET_SPRITE_COLORKEY DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_SET_SPRITE_COLORKEY, struct drm_intel_sprite_colorkey)
+#define DRM_IOCTL_I915_GET_SPRITE_COLORKEY DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GET_SPRITE_COLORKEY, struct drm_intel_sprite_colorkey)
+#define DRM_IOCTL_I915_GEM_WAIT DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_WAIT, struct drm_i915_gem_wait)
+#define DRM_IOCTL_I915_GEM_CONTEXT_CREATE DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_CREATE, struct drm_i915_gem_context_create)
+#define DRM_IOCTL_I915_GEM_CONTEXT_CREATE_EXT DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_CREATE, struct drm_i915_gem_context_create_ext)
+#define DRM_IOCTL_I915_GEM_CONTEXT_DESTROY DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_DESTROY, struct drm_i915_gem_context_destroy)
+#define DRM_IOCTL_I915_REG_READ DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_REG_READ, struct drm_i915_reg_read)
+#define DRM_IOCTL_I915_GET_RESET_STATS DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GET_RESET_STATS, struct drm_i915_reset_stats)
+#define DRM_IOCTL_I915_GEM_USERPTR DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_USERPTR, struct drm_i915_gem_userptr)
+#define DRM_IOCTL_I915_GEM_CONTEXT_GETPARAM DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_GETPARAM, struct drm_i915_gem_context_param)
+#define DRM_IOCTL_I915_GEM_CONTEXT_SETPARAM DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_SETPARAM, struct drm_i915_gem_context_param)
+#define DRM_IOCTL_I915_PERF_OPEN DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_OPEN, struct drm_i915_perf_open_param)
+#define DRM_IOCTL_I915_PERF_ADD_CONFIG DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_ADD_CONFIG, struct drm_i915_perf_oa_config)
+#define DRM_IOCTL_I915_PERF_REMOVE_CONFIG DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_REMOVE_CONFIG, __u64)
+#define DRM_IOCTL_I915_QUERY DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_QUERY, struct drm_i915_query)
+#define DRM_IOCTL_I915_GEM_VM_CREATE DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_VM_CREATE, struct drm_i915_gem_vm_control)
+#define DRM_IOCTL_I915_GEM_VM_DESTROY DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_VM_DESTROY, struct drm_i915_gem_vm_control)
+
+/* Allow drivers to submit batchbuffers directly to hardware, relying
+ * on the security mechanisms provided by hardware.
+ */
+typedef struct drm_i915_batchbuffer {
+ int start; /* agp offset */
+ int used; /* nr bytes in use */
+ int DR1; /* hw flags for GFX_OP_DRAWRECT_INFO */
+ int DR4; /* window origin for GFX_OP_DRAWRECT_INFO */
+ int num_cliprects; /* mulitpass with multiple cliprects? */
+ struct drm_clip_rect __user *cliprects; /* pointer to userspace cliprects */
+} drm_i915_batchbuffer_t;
+
+/* As above, but pass a pointer to userspace buffer which can be
+ * validated by the kernel prior to sending to hardware.
+ */
+typedef struct _drm_i915_cmdbuffer {
+ char __user *buf; /* pointer to userspace command buffer */
+ int sz; /* nr bytes in buf */
+ int DR1; /* hw flags for GFX_OP_DRAWRECT_INFO */
+ int DR4; /* window origin for GFX_OP_DRAWRECT_INFO */
+ int num_cliprects; /* mulitpass with multiple cliprects? */
+ struct drm_clip_rect __user *cliprects; /* pointer to userspace cliprects */
+} drm_i915_cmdbuffer_t;
+
+/* Userspace can request & wait on irq's:
+ */
+typedef struct drm_i915_irq_emit {
+ int __user *irq_seq;
+} drm_i915_irq_emit_t;
+
+typedef struct drm_i915_irq_wait {
+ int irq_seq;
+} drm_i915_irq_wait_t;
+
+/*
+ * Different modes of per-process Graphics Translation Table,
+ * see I915_PARAM_HAS_ALIASING_PPGTT
+ */
+#define I915_GEM_PPGTT_NONE 0
+#define I915_GEM_PPGTT_ALIASING 1
+#define I915_GEM_PPGTT_FULL 2
+
+/* Ioctl to query kernel params:
+ */
+#define I915_PARAM_IRQ_ACTIVE 1
+#define I915_PARAM_ALLOW_BATCHBUFFER 2
+#define I915_PARAM_LAST_DISPATCH 3
+#define I915_PARAM_CHIPSET_ID 4
+#define I915_PARAM_HAS_GEM 5
+#define I915_PARAM_NUM_FENCES_AVAIL 6
+#define I915_PARAM_HAS_OVERLAY 7
+#define I915_PARAM_HAS_PAGEFLIPPING 8
+#define I915_PARAM_HAS_EXECBUF2 9
+#define I915_PARAM_HAS_BSD 10
+#define I915_PARAM_HAS_BLT 11
+#define I915_PARAM_HAS_RELAXED_FENCING 12
+#define I915_PARAM_HAS_COHERENT_RINGS 13
+#define I915_PARAM_HAS_EXEC_CONSTANTS 14
+#define I915_PARAM_HAS_RELAXED_DELTA 15
+#define I915_PARAM_HAS_GEN7_SOL_RESET 16
+#define I915_PARAM_HAS_LLC 17
+#define I915_PARAM_HAS_ALIASING_PPGTT 18
+#define I915_PARAM_HAS_WAIT_TIMEOUT 19
+#define I915_PARAM_HAS_SEMAPHORES 20
+#define I915_PARAM_HAS_PRIME_VMAP_FLUSH 21
+#define I915_PARAM_HAS_VEBOX 22
+#define I915_PARAM_HAS_SECURE_BATCHES 23
+#define I915_PARAM_HAS_PINNED_BATCHES 24
+#define I915_PARAM_HAS_EXEC_NO_RELOC 25
+#define I915_PARAM_HAS_EXEC_HANDLE_LUT 26
+#define I915_PARAM_HAS_WT 27
+#define I915_PARAM_CMD_PARSER_VERSION 28
+#define I915_PARAM_HAS_COHERENT_PHYS_GTT 29
+#define I915_PARAM_MMAP_VERSION 30
+#define I915_PARAM_HAS_BSD2 31
+#define I915_PARAM_REVISION 32
+#define I915_PARAM_SUBSLICE_TOTAL 33
+#define I915_PARAM_EU_TOTAL 34
+#define I915_PARAM_HAS_GPU_RESET 35
+#define I915_PARAM_HAS_RESOURCE_STREAMER 36
+#define I915_PARAM_HAS_EXEC_SOFTPIN 37
+#define I915_PARAM_HAS_POOLED_EU 38
+#define I915_PARAM_MIN_EU_IN_POOL 39
+#define I915_PARAM_MMAP_GTT_VERSION 40
+
+/*
+ * Query whether DRM_I915_GEM_EXECBUFFER2 supports user defined execution
+ * priorities and the driver will attempt to execute batches in priority order.
+ * The param returns a capability bitmask, nonzero implies that the scheduler
+ * is enabled, with different features present according to the mask.
+ *
+ * The initial priority for each batch is supplied by the context and is
+ * controlled via I915_CONTEXT_PARAM_PRIORITY.
+ */
+#define I915_PARAM_HAS_SCHEDULER 41
+#define I915_SCHEDULER_CAP_ENABLED (1ul << 0)
+#define I915_SCHEDULER_CAP_PRIORITY (1ul << 1)
+#define I915_SCHEDULER_CAP_PREEMPTION (1ul << 2)
+#define I915_SCHEDULER_CAP_SEMAPHORES (1ul << 3)
+#define I915_SCHEDULER_CAP_ENGINE_BUSY_STATS (1ul << 4)
+/*
+ * Indicates the 2k user priority levels are statically mapped into 3 buckets as
+ * follows:
+ *
+ * -1k to -1 Low priority
+ * 0 Normal priority
+ * 1 to 1k Highest priority
+ */
+#define I915_SCHEDULER_CAP_STATIC_PRIORITY_MAP (1ul << 5)
+
+/*
+ * Query the status of HuC load.
+ *
+ * The query can fail in the following scenarios with the listed error codes:
+ * -ENODEV if HuC is not present on this platform,
+ * -EOPNOTSUPP if HuC firmware usage is disabled,
+ * -ENOPKG if HuC firmware fetch failed,
+ * -ENOEXEC if HuC firmware is invalid or mismatched,
+ * -ENOMEM if i915 failed to prepare the FW objects for transfer to the uC,
+ * -EIO if the FW transfer or the FW authentication failed.
+ *
+ * If the IOCTL is successful, the returned parameter will be set to one of the
+ * following values:
+ * * 0 if HuC firmware load is not complete,
+ * * 1 if HuC firmware is loaded and fully authenticated,
+ * * 2 if HuC firmware is loaded and authenticated for clear media only
+ */
+#define I915_PARAM_HUC_STATUS 42
+
+/* Query whether DRM_I915_GEM_EXECBUFFER2 supports the ability to opt-out of
+ * synchronisation with implicit fencing on individual objects.
+ * See EXEC_OBJECT_ASYNC.
+ */
+#define I915_PARAM_HAS_EXEC_ASYNC 43
+
+/* Query whether DRM_I915_GEM_EXECBUFFER2 supports explicit fence support -
+ * both being able to pass in a sync_file fd to wait upon before executing,
+ * and being able to return a new sync_file fd that is signaled when the
+ * current request is complete. See I915_EXEC_FENCE_IN and I915_EXEC_FENCE_OUT.
+ */
+#define I915_PARAM_HAS_EXEC_FENCE 44
+
+/* Query whether DRM_I915_GEM_EXECBUFFER2 supports the ability to capture
+ * user specified bufffers for post-mortem debugging of GPU hangs. See
+ * EXEC_OBJECT_CAPTURE.
+ */
+#define I915_PARAM_HAS_EXEC_CAPTURE 45
+
+#define I915_PARAM_SLICE_MASK 46
+
+/* Assuming it's uniform for each slice, this queries the mask of subslices
+ * per-slice for this system.
+ */
+#define I915_PARAM_SUBSLICE_MASK 47
+
+/*
+ * Query whether DRM_I915_GEM_EXECBUFFER2 supports supplying the batch buffer
+ * as the first execobject as opposed to the last. See I915_EXEC_BATCH_FIRST.
+ */
+#define I915_PARAM_HAS_EXEC_BATCH_FIRST 48
+
+/* Query whether DRM_I915_GEM_EXECBUFFER2 supports supplying an array of
+ * drm_i915_gem_exec_fence structures. See I915_EXEC_FENCE_ARRAY.
+ */
+#define I915_PARAM_HAS_EXEC_FENCE_ARRAY 49
+
+/*
+ * Query whether every context (both per-file default and user created) is
+ * isolated (insofar as HW supports). If this parameter is not true, then
+ * freshly created contexts may inherit values from an existing context,
+ * rather than default HW values. If true, it also ensures (insofar as HW
+ * supports) that all state set by this context will not leak to any other
+ * context.
+ *
+ * As not every engine across every gen support contexts, the returned
+ * value reports the support of context isolation for individual engines by
+ * returning a bitmask of each engine class set to true if that class supports
+ * isolation.
+ */
+#define I915_PARAM_HAS_CONTEXT_ISOLATION 50
+
+/* Frequency of the command streamer timestamps given by the *_TIMESTAMP
+ * registers. This used to be fixed per platform but from CNL onwards, this
+ * might vary depending on the parts.
+ */
+#define I915_PARAM_CS_TIMESTAMP_FREQUENCY 51
+
+/*
+ * Once upon a time we supposed that writes through the GGTT would be
+ * immediately in physical memory (once flushed out of the CPU path). However,
+ * on a few different processors and chipsets, this is not necessarily the case
+ * as the writes appear to be buffered internally. Thus a read of the backing
+ * storage (physical memory) via a different path (with different physical tags
+ * to the indirect write via the GGTT) will see stale values from before
+ * the GGTT write. Inside the kernel, we can for the most part keep track of
+ * the different read/write domains in use (e.g. set-domain), but the assumption
+ * of coherency is baked into the ABI, hence reporting its true state in this
+ * parameter.
+ *
+ * Reports true when writes via mmap_gtt are immediately visible following an
+ * lfence to flush the WCB.
+ *
+ * Reports false when writes via mmap_gtt are indeterminately delayed in an in
+ * internal buffer and are _not_ immediately visible to third parties accessing
+ * directly via mmap_cpu/mmap_wc. Use of mmap_gtt as part of an IPC
+ * communications channel when reporting false is strongly disadvised.
+ */
+#define I915_PARAM_MMAP_GTT_COHERENT 52
+
+/*
+ * Query whether DRM_I915_GEM_EXECBUFFER2 supports coordination of parallel
+ * execution through use of explicit fence support.
+ * See I915_EXEC_FENCE_OUT and I915_EXEC_FENCE_SUBMIT.
+ */
+#define I915_PARAM_HAS_EXEC_SUBMIT_FENCE 53
+
+/*
+ * Revision of the i915-perf uAPI. The value returned helps determine what
+ * i915-perf features are available. See drm_i915_perf_property_id.
+ */
+#define I915_PARAM_PERF_REVISION 54
+
+/* Query whether DRM_I915_GEM_EXECBUFFER2 supports supplying an array of
+ * timeline syncobj through drm_i915_gem_execbuffer_ext_timeline_fences. See
+ * I915_EXEC_USE_EXTENSIONS.
+ */
+#define I915_PARAM_HAS_EXEC_TIMELINE_FENCES 55
+
+/* Query if the kernel supports the I915_USERPTR_PROBE flag. */
+#define I915_PARAM_HAS_USERPTR_PROBE 56
+
+/*
+ * Frequency of the timestamps in OA reports. This used to be the same as the CS
+ * timestamp frequency, but differs on some platforms.
+ */
+#define I915_PARAM_OA_TIMESTAMP_FREQUENCY 57
+
+/*
+ * Query the status of PXP support in i915.
+ *
+ * The query can fail in the following scenarios with the listed error codes:
+ * -ENODEV = PXP support is not available on the GPU device or in the
+ * kernel due to missing component drivers or kernel configs.
+ *
+ * If the IOCTL is successful, the returned parameter will be set to one of
+ * the following values:
+ * 1 = PXP feature is supported and is ready for use.
+ * 2 = PXP feature is supported but should be ready soon (pending
+ * initialization of non-i915 system dependencies).
+ *
+ * NOTE: When param is supported (positive return values), user space should
+ * still refer to the GEM PXP context-creation UAPI header specs to be
+ * aware of possible failure due to system state machine at the time.
+ */
+#define I915_PARAM_PXP_STATUS 58
+
+/* Must be kept compact -- no holes and well documented */
+
+/**
+ * struct drm_i915_getparam - Driver parameter query structure.
+ */
+struct drm_i915_getparam {
+ /** @param: Driver parameter to query. */
+ __s32 param;
+
+ /**
+ * @value: Address of memory where queried value should be put.
+ *
+ * WARNING: Using pointers instead of fixed-size u64 means we need to write
+ * compat32 code. Don't repeat this mistake.
+ */
+ int __user *value;
+};
+
+/**
+ * typedef drm_i915_getparam_t - Driver parameter query structure.
+ * See struct drm_i915_getparam.
+ */
+typedef struct drm_i915_getparam drm_i915_getparam_t;
+
+/* Ioctl to set kernel params:
+ */
+#define I915_SETPARAM_USE_MI_BATCHBUFFER_START 1
+#define I915_SETPARAM_TEX_LRU_LOG_GRANULARITY 2
+#define I915_SETPARAM_ALLOW_BATCHBUFFER 3
+#define I915_SETPARAM_NUM_USED_FENCES 4
+/* Must be kept compact -- no holes */
+
+typedef struct drm_i915_setparam {
+ int param;
+ int value;
+} drm_i915_setparam_t;
+
+/* A memory manager for regions of shared memory:
+ */
+#define I915_MEM_REGION_AGP 1
+
+typedef struct drm_i915_mem_alloc {
+ int region;
+ int alignment;
+ int size;
+ int __user *region_offset; /* offset from start of fb or agp */
+} drm_i915_mem_alloc_t;
+
+typedef struct drm_i915_mem_free {
+ int region;
+ int region_offset;
+} drm_i915_mem_free_t;
+
+typedef struct drm_i915_mem_init_heap {
+ int region;
+ int size;
+ int start;
+} drm_i915_mem_init_heap_t;
+
+/* Allow memory manager to be torn down and re-initialized (eg on
+ * rotate):
+ */
+typedef struct drm_i915_mem_destroy_heap {
+ int region;
+} drm_i915_mem_destroy_heap_t;
+
+/* Allow X server to configure which pipes to monitor for vblank signals
+ */
+#define DRM_I915_VBLANK_PIPE_A 1
+#define DRM_I915_VBLANK_PIPE_B 2
+
+typedef struct drm_i915_vblank_pipe {
+ int pipe;
+} drm_i915_vblank_pipe_t;
+
+/* Schedule buffer swap at given vertical blank:
+ */
+typedef struct drm_i915_vblank_swap {
+ drm_drawable_t drawable;
+ enum drm_vblank_seq_type seqtype;
+ unsigned int sequence;
+} drm_i915_vblank_swap_t;
+
+typedef struct drm_i915_hws_addr {
+ __u64 addr;
+} drm_i915_hws_addr_t;
+
+struct drm_i915_gem_init {
+ /**
+ * Beginning offset in the GTT to be managed by the DRM memory
+ * manager.
+ */
+ __u64 gtt_start;
+ /**
+ * Ending offset in the GTT to be managed by the DRM memory
+ * manager.
+ */
+ __u64 gtt_end;
+};
+
+struct drm_i915_gem_create {
+ /**
+ * Requested size for the object.
+ *
+ * The (page-aligned) allocated size for the object will be returned.
+ */
+ __u64 size;
+ /**
+ * Returned handle for the object.
+ *
+ * Object handles are nonzero.
+ */
+ __u32 handle;
+ __u32 pad;
+};
+
+struct drm_i915_gem_pread {
+ /** Handle for the object being read. */
+ __u32 handle;
+ __u32 pad;
+ /** Offset into the object to read from */
+ __u64 offset;
+ /** Length of data to read */
+ __u64 size;
+ /**
+ * Pointer to write the data into.
+ *
+ * This is a fixed-size type for 32/64 compatibility.
+ */
+ __u64 data_ptr;
+};
+
+struct drm_i915_gem_pwrite {
+ /** Handle for the object being written to. */
+ __u32 handle;
+ __u32 pad;
+ /** Offset into the object to write to */
+ __u64 offset;
+ /** Length of data to write */
+ __u64 size;
+ /**
+ * Pointer to read the data from.
+ *
+ * This is a fixed-size type for 32/64 compatibility.
+ */
+ __u64 data_ptr;
+};
+
+struct drm_i915_gem_mmap {
+ /** Handle for the object being mapped. */
+ __u32 handle;
+ __u32 pad;
+ /** Offset in the object to map. */
+ __u64 offset;
+ /**
+ * Length of data to map.
+ *
+ * The value will be page-aligned.
+ */
+ __u64 size;
+ /**
+ * Returned pointer the data was mapped at.
+ *
+ * This is a fixed-size type for 32/64 compatibility.
+ */
+ __u64 addr_ptr;
+
+ /**
+ * Flags for extended behaviour.
+ *
+ * Added in version 2.
+ */
+ __u64 flags;
+#define I915_MMAP_WC 0x1
+};
+
+struct drm_i915_gem_mmap_gtt {
+ /** Handle for the object being mapped. */
+ __u32 handle;
+ __u32 pad;
+ /**
+ * Fake offset to use for subsequent mmap call
+ *
+ * This is a fixed-size type for 32/64 compatibility.
+ */
+ __u64 offset;
+};
+
+/**
+ * struct drm_i915_gem_mmap_offset - Retrieve an offset so we can mmap this buffer object.
+ *
+ * This struct is passed as argument to the `DRM_IOCTL_I915_GEM_MMAP_OFFSET` ioctl,
+ * and is used to retrieve the fake offset to mmap an object specified by &handle.
+ *
+ * The legacy way of using `DRM_IOCTL_I915_GEM_MMAP` is removed on gen12+.
+ * `DRM_IOCTL_I915_GEM_MMAP_GTT` is an older supported alias to this struct, but will behave
+ * as setting the &extensions to 0, and &flags to `I915_MMAP_OFFSET_GTT`.
+ */
+struct drm_i915_gem_mmap_offset {
+ /** @handle: Handle for the object being mapped. */
+ __u32 handle;
+ /** @pad: Must be zero */
+ __u32 pad;
+ /**
+ * @offset: The fake offset to use for subsequent mmap call
+ *
+ * This is a fixed-size type for 32/64 compatibility.
+ */
+ __u64 offset;
+
+ /**
+ * @flags: Flags for extended behaviour.
+ *
+ * It is mandatory that one of the `MMAP_OFFSET` types
+ * should be included:
+ *
+ * - `I915_MMAP_OFFSET_GTT`: Use mmap with the object bound to GTT. (Write-Combined)
+ * - `I915_MMAP_OFFSET_WC`: Use Write-Combined caching.
+ * - `I915_MMAP_OFFSET_WB`: Use Write-Back caching.
+ * - `I915_MMAP_OFFSET_FIXED`: Use object placement to determine caching.
+ *
+ * On devices with local memory `I915_MMAP_OFFSET_FIXED` is the only valid
+ * type. On devices without local memory, this caching mode is invalid.
+ *
+ * As caching mode when specifying `I915_MMAP_OFFSET_FIXED`, WC or WB will
+ * be used, depending on the object placement on creation. WB will be used
+ * when the object can only exist in system memory, WC otherwise.
+ */
+ __u64 flags;
+
+#define I915_MMAP_OFFSET_GTT 0
+#define I915_MMAP_OFFSET_WC 1
+#define I915_MMAP_OFFSET_WB 2
+#define I915_MMAP_OFFSET_UC 3
+#define I915_MMAP_OFFSET_FIXED 4
+
+ /**
+ * @extensions: Zero-terminated chain of extensions.
+ *
+ * No current extensions defined; mbz.
+ */
+ __u64 extensions;
+};
+
+/**
+ * struct drm_i915_gem_set_domain - Adjust the objects write or read domain, in
+ * preparation for accessing the pages via some CPU domain.
+ *
+ * Specifying a new write or read domain will flush the object out of the
+ * previous domain(if required), before then updating the objects domain
+ * tracking with the new domain.
+ *
+ * Note this might involve waiting for the object first if it is still active on
+ * the GPU.
+ *
+ * Supported values for @read_domains and @write_domain:
+ *
+ * - I915_GEM_DOMAIN_WC: Uncached write-combined domain
+ * - I915_GEM_DOMAIN_CPU: CPU cache domain
+ * - I915_GEM_DOMAIN_GTT: Mappable aperture domain
+ *
+ * All other domains are rejected.
+ *
+ * Note that for discrete, starting from DG1, this is no longer supported, and
+ * is instead rejected. On such platforms the CPU domain is effectively static,
+ * where we also only support a single &drm_i915_gem_mmap_offset cache mode,
+ * which can't be set explicitly and instead depends on the object placements,
+ * as per the below.
+ *
+ * Implicit caching rules, starting from DG1:
+ *
+ * - If any of the object placements (see &drm_i915_gem_create_ext_memory_regions)
+ * contain I915_MEMORY_CLASS_DEVICE then the object will be allocated and
+ * mapped as write-combined only.
+ *
+ * - Everything else is always allocated and mapped as write-back, with the
+ * guarantee that everything is also coherent with the GPU.
+ *
+ * Note that this is likely to change in the future again, where we might need
+ * more flexibility on future devices, so making this all explicit as part of a
+ * new &drm_i915_gem_create_ext extension is probable.
+ */
+struct drm_i915_gem_set_domain {
+ /** @handle: Handle for the object. */
+ __u32 handle;
+
+ /** @read_domains: New read domains. */
+ __u32 read_domains;
+
+ /**
+ * @write_domain: New write domain.
+ *
+ * Note that having something in the write domain implies it's in the
+ * read domain, and only that read domain.
+ */
+ __u32 write_domain;
+};
+
+struct drm_i915_gem_sw_finish {
+ /** Handle for the object */
+ __u32 handle;
+};
+
+struct drm_i915_gem_relocation_entry {
+ /**
+ * Handle of the buffer being pointed to by this relocation entry.
+ *
+ * It's appealing to make this be an index into the mm_validate_entry
+ * list to refer to the buffer, but this allows the driver to create
+ * a relocation list for state buffers and not re-write it per
+ * exec using the buffer.
+ */
+ __u32 target_handle;
+
+ /**
+ * Value to be added to the offset of the target buffer to make up
+ * the relocation entry.
+ */
+ __u32 delta;
+
+ /** Offset in the buffer the relocation entry will be written into */
+ __u64 offset;
+
+ /**
+ * Offset value of the target buffer that the relocation entry was last
+ * written as.
+ *
+ * If the buffer has the same offset as last time, we can skip syncing
+ * and writing the relocation. This value is written back out by
+ * the execbuffer ioctl when the relocation is written.
+ */
+ __u64 presumed_offset;
+
+ /**
+ * Target memory domains read by this operation.
+ */
+ __u32 read_domains;
+
+ /**
+ * Target memory domains written by this operation.
+ *
+ * Note that only one domain may be written by the whole
+ * execbuffer operation, so that where there are conflicts,
+ * the application will get -EINVAL back.
+ */
+ __u32 write_domain;
+};
+
+/** @{
+ * Intel memory domains
+ *
+ * Most of these just align with the various caches in
+ * the system and are used to flush and invalidate as
+ * objects end up cached in different domains.
+ */
+/** CPU cache */
+#define I915_GEM_DOMAIN_CPU 0x00000001
+/** Render cache, used by 2D and 3D drawing */
+#define I915_GEM_DOMAIN_RENDER 0x00000002
+/** Sampler cache, used by texture engine */
+#define I915_GEM_DOMAIN_SAMPLER 0x00000004
+/** Command queue, used to load batch buffers */
+#define I915_GEM_DOMAIN_COMMAND 0x00000008
+/** Instruction cache, used by shader programs */
+#define I915_GEM_DOMAIN_INSTRUCTION 0x00000010
+/** Vertex address cache */
+#define I915_GEM_DOMAIN_VERTEX 0x00000020
+/** GTT domain - aperture and scanout */
+#define I915_GEM_DOMAIN_GTT 0x00000040
+/** WC domain - uncached access */
+#define I915_GEM_DOMAIN_WC 0x00000080
+/** @} */
+
+struct drm_i915_gem_exec_object {
+ /**
+ * User's handle for a buffer to be bound into the GTT for this
+ * operation.
+ */
+ __u32 handle;
+
+ /** Number of relocations to be performed on this buffer */
+ __u32 relocation_count;
+ /**
+ * Pointer to array of struct drm_i915_gem_relocation_entry containing
+ * the relocations to be performed in this buffer.
+ */
+ __u64 relocs_ptr;
+
+ /** Required alignment in graphics aperture */
+ __u64 alignment;
+
+ /**
+ * Returned value of the updated offset of the object, for future
+ * presumed_offset writes.
+ */
+ __u64 offset;
+};
+
+/* DRM_IOCTL_I915_GEM_EXECBUFFER was removed in Linux 5.13 */
+struct drm_i915_gem_execbuffer {
+ /**
+ * List of buffers to be validated with their relocations to be
+ * performend on them.
+ *
+ * This is a pointer to an array of struct drm_i915_gem_validate_entry.
+ *
+ * These buffers must be listed in an order such that all relocations
+ * a buffer is performing refer to buffers that have already appeared
+ * in the validate list.
+ */
+ __u64 buffers_ptr;
+ __u32 buffer_count;
+
+ /** Offset in the batchbuffer to start execution from. */
+ __u32 batch_start_offset;
+ /** Bytes used in batchbuffer from batch_start_offset */
+ __u32 batch_len;
+ __u32 DR1;
+ __u32 DR4;
+ __u32 num_cliprects;
+ /** This is a struct drm_clip_rect *cliprects */
+ __u64 cliprects_ptr;
+};
+
+struct drm_i915_gem_exec_object2 {
+ /**
+ * User's handle for a buffer to be bound into the GTT for this
+ * operation.
+ */
+ __u32 handle;
+
+ /** Number of relocations to be performed on this buffer */
+ __u32 relocation_count;
+ /**
+ * Pointer to array of struct drm_i915_gem_relocation_entry containing
+ * the relocations to be performed in this buffer.
+ */
+ __u64 relocs_ptr;
+
+ /** Required alignment in graphics aperture */
+ __u64 alignment;
+
+ /**
+ * When the EXEC_OBJECT_PINNED flag is specified this is populated by
+ * the user with the GTT offset at which this object will be pinned.
+ *
+ * When the I915_EXEC_NO_RELOC flag is specified this must contain the
+ * presumed_offset of the object.
+ *
+ * During execbuffer2 the kernel populates it with the value of the
+ * current GTT offset of the object, for future presumed_offset writes.
+ *
+ * See struct drm_i915_gem_create_ext for the rules when dealing with
+ * alignment restrictions with I915_MEMORY_CLASS_DEVICE, on devices with
+ * minimum page sizes, like DG2.
+ */
+ __u64 offset;
+
+#define EXEC_OBJECT_NEEDS_FENCE (1<<0)
+#define EXEC_OBJECT_NEEDS_GTT (1<<1)
+#define EXEC_OBJECT_WRITE (1<<2)
+#define EXEC_OBJECT_SUPPORTS_48B_ADDRESS (1<<3)
+#define EXEC_OBJECT_PINNED (1<<4)
+#define EXEC_OBJECT_PAD_TO_SIZE (1<<5)
+/* The kernel implicitly tracks GPU activity on all GEM objects, and
+ * synchronises operations with outstanding rendering. This includes
+ * rendering on other devices if exported via dma-buf. However, sometimes
+ * this tracking is too coarse and the user knows better. For example,
+ * if the object is split into non-overlapping ranges shared between different
+ * clients or engines (i.e. suballocating objects), the implicit tracking
+ * by kernel assumes that each operation affects the whole object rather
+ * than an individual range, causing needless synchronisation between clients.
+ * The kernel will also forgo any CPU cache flushes prior to rendering from
+ * the object as the client is expected to be also handling such domain
+ * tracking.
+ *
+ * The kernel maintains the implicit tracking in order to manage resources
+ * used by the GPU - this flag only disables the synchronisation prior to
+ * rendering with this object in this execbuf.
+ *
+ * Opting out of implicit synhronisation requires the user to do its own
+ * explicit tracking to avoid rendering corruption. See, for example,
+ * I915_PARAM_HAS_EXEC_FENCE to order execbufs and execute them asynchronously.
+ */
+#define EXEC_OBJECT_ASYNC (1<<6)
+/* Request that the contents of this execobject be copied into the error
+ * state upon a GPU hang involving this batch for post-mortem debugging.
+ * These buffers are recorded in no particular order as "user" in
+ * /sys/class/drm/cardN/error. Query I915_PARAM_HAS_EXEC_CAPTURE to see
+ * if the kernel supports this flag.
+ */
+#define EXEC_OBJECT_CAPTURE (1<<7)
+/* All remaining bits are MBZ and RESERVED FOR FUTURE USE */
+#define __EXEC_OBJECT_UNKNOWN_FLAGS -(EXEC_OBJECT_CAPTURE<<1)
+ __u64 flags;
+
+ union {
+ __u64 rsvd1;
+ __u64 pad_to_size;
+ };
+ __u64 rsvd2;
+};
+
+/**
+ * struct drm_i915_gem_exec_fence - An input or output fence for the execbuf
+ * ioctl.
+ *
+ * The request will wait for input fence to signal before submission.
+ *
+ * The returned output fence will be signaled after the completion of the
+ * request.
+ */
+struct drm_i915_gem_exec_fence {
+ /** @handle: User's handle for a drm_syncobj to wait on or signal. */
+ __u32 handle;
+
+ /**
+ * @flags: Supported flags are:
+ *
+ * I915_EXEC_FENCE_WAIT:
+ * Wait for the input fence before request submission.
+ *
+ * I915_EXEC_FENCE_SIGNAL:
+ * Return request completion fence as output
+ */
+ __u32 flags;
+#define I915_EXEC_FENCE_WAIT (1<<0)
+#define I915_EXEC_FENCE_SIGNAL (1<<1)
+#define __I915_EXEC_FENCE_UNKNOWN_FLAGS (-(I915_EXEC_FENCE_SIGNAL << 1))
+};
+
+/**
+ * struct drm_i915_gem_execbuffer_ext_timeline_fences - Timeline fences
+ * for execbuf ioctl.
+ *
+ * This structure describes an array of drm_syncobj and associated points for
+ * timeline variants of drm_syncobj. It is invalid to append this structure to
+ * the execbuf if I915_EXEC_FENCE_ARRAY is set.
+ */
+struct drm_i915_gem_execbuffer_ext_timeline_fences {
+#define DRM_I915_GEM_EXECBUFFER_EXT_TIMELINE_FENCES 0
+ /** @base: Extension link. See struct i915_user_extension. */
+ struct i915_user_extension base;
+
+ /**
+ * @fence_count: Number of elements in the @handles_ptr & @value_ptr
+ * arrays.
+ */
+ __u64 fence_count;
+
+ /**
+ * @handles_ptr: Pointer to an array of struct drm_i915_gem_exec_fence
+ * of length @fence_count.
+ */
+ __u64 handles_ptr;
+
+ /**
+ * @values_ptr: Pointer to an array of u64 values of length
+ * @fence_count.
+ * Values must be 0 for a binary drm_syncobj. A Value of 0 for a
+ * timeline drm_syncobj is invalid as it turns a drm_syncobj into a
+ * binary one.
+ */
+ __u64 values_ptr;
+};
+
+/**
+ * struct drm_i915_gem_execbuffer2 - Structure for DRM_I915_GEM_EXECBUFFER2
+ * ioctl.
+ */
+struct drm_i915_gem_execbuffer2 {
+ /** @buffers_ptr: Pointer to a list of gem_exec_object2 structs */
+ __u64 buffers_ptr;
+
+ /** @buffer_count: Number of elements in @buffers_ptr array */
+ __u32 buffer_count;
+
+ /**
+ * @batch_start_offset: Offset in the batchbuffer to start execution
+ * from.
+ */
+ __u32 batch_start_offset;
+
+ /**
+ * @batch_len: Length in bytes of the batch buffer, starting from the
+ * @batch_start_offset. If 0, length is assumed to be the batch buffer
+ * object size.
+ */
+ __u32 batch_len;
+
+ /** @DR1: deprecated */
+ __u32 DR1;
+
+ /** @DR4: deprecated */
+ __u32 DR4;
+
+ /** @num_cliprects: See @cliprects_ptr */
+ __u32 num_cliprects;
+
+ /**
+ * @cliprects_ptr: Kernel clipping was a DRI1 misfeature.
+ *
+ * It is invalid to use this field if I915_EXEC_FENCE_ARRAY or
+ * I915_EXEC_USE_EXTENSIONS flags are not set.
+ *
+ * If I915_EXEC_FENCE_ARRAY is set, then this is a pointer to an array
+ * of &drm_i915_gem_exec_fence and @num_cliprects is the length of the
+ * array.
+ *
+ * If I915_EXEC_USE_EXTENSIONS is set, then this is a pointer to a
+ * single &i915_user_extension and num_cliprects is 0.
+ */
+ __u64 cliprects_ptr;
+
+ /** @flags: Execbuf flags */
+ __u64 flags;
+#define I915_EXEC_RING_MASK (0x3f)
+#define I915_EXEC_DEFAULT (0<<0)
+#define I915_EXEC_RENDER (1<<0)
+#define I915_EXEC_BSD (2<<0)
+#define I915_EXEC_BLT (3<<0)
+#define I915_EXEC_VEBOX (4<<0)
+
+/* Used for switching the constants addressing mode on gen4+ RENDER ring.
+ * Gen6+ only supports relative addressing to dynamic state (default) and
+ * absolute addressing.
+ *
+ * These flags are ignored for the BSD and BLT rings.
+ */
+#define I915_EXEC_CONSTANTS_MASK (3<<6)
+#define I915_EXEC_CONSTANTS_REL_GENERAL (0<<6) /* default */
+#define I915_EXEC_CONSTANTS_ABSOLUTE (1<<6)
+#define I915_EXEC_CONSTANTS_REL_SURFACE (2<<6) /* gen4/5 only */
+
+/** Resets the SO write offset registers for transform feedback on gen7. */
+#define I915_EXEC_GEN7_SOL_RESET (1<<8)
+
+/** Request a privileged ("secure") batch buffer. Note only available for
+ * DRM_ROOT_ONLY | DRM_MASTER processes.
+ */
+#define I915_EXEC_SECURE (1<<9)
+
+/** Inform the kernel that the batch is and will always be pinned. This
+ * negates the requirement for a workaround to be performed to avoid
+ * an incoherent CS (such as can be found on 830/845). If this flag is
+ * not passed, the kernel will endeavour to make sure the batch is
+ * coherent with the CS before execution. If this flag is passed,
+ * userspace assumes the responsibility for ensuring the same.
+ */
+#define I915_EXEC_IS_PINNED (1<<10)
+
+/** Provide a hint to the kernel that the command stream and auxiliary
+ * state buffers already holds the correct presumed addresses and so the
+ * relocation process may be skipped if no buffers need to be moved in
+ * preparation for the execbuffer.
+ */
+#define I915_EXEC_NO_RELOC (1<<11)
+
+/** Use the reloc.handle as an index into the exec object array rather
+ * than as the per-file handle.
+ */
+#define I915_EXEC_HANDLE_LUT (1<<12)
+
+/** Used for switching BSD rings on the platforms with two BSD rings */
+#define I915_EXEC_BSD_SHIFT (13)
+#define I915_EXEC_BSD_MASK (3 << I915_EXEC_BSD_SHIFT)
+/* default ping-pong mode */
+#define I915_EXEC_BSD_DEFAULT (0 << I915_EXEC_BSD_SHIFT)
+#define I915_EXEC_BSD_RING1 (1 << I915_EXEC_BSD_SHIFT)
+#define I915_EXEC_BSD_RING2 (2 << I915_EXEC_BSD_SHIFT)
+
+/** Tell the kernel that the batchbuffer is processed by
+ * the resource streamer.
+ */
+#define I915_EXEC_RESOURCE_STREAMER (1<<15)
+
+/* Setting I915_EXEC_FENCE_IN implies that lower_32_bits(rsvd2) represent
+ * a sync_file fd to wait upon (in a nonblocking manner) prior to executing
+ * the batch.
+ *
+ * Returns -EINVAL if the sync_file fd cannot be found.
+ */
+#define I915_EXEC_FENCE_IN (1<<16)
+
+/* Setting I915_EXEC_FENCE_OUT causes the ioctl to return a sync_file fd
+ * in the upper_32_bits(rsvd2) upon success. Ownership of the fd is given
+ * to the caller, and it should be close() after use. (The fd is a regular
+ * file descriptor and will be cleaned up on process termination. It holds
+ * a reference to the request, but nothing else.)
+ *
+ * The sync_file fd can be combined with other sync_file and passed either
+ * to execbuf using I915_EXEC_FENCE_IN, to atomic KMS ioctls (so that a flip
+ * will only occur after this request completes), or to other devices.
+ *
+ * Using I915_EXEC_FENCE_OUT requires use of
+ * DRM_IOCTL_I915_GEM_EXECBUFFER2_WR ioctl so that the result is written
+ * back to userspace. Failure to do so will cause the out-fence to always
+ * be reported as zero, and the real fence fd to be leaked.
+ */
+#define I915_EXEC_FENCE_OUT (1<<17)
+
+/*
+ * Traditionally the execbuf ioctl has only considered the final element in
+ * the execobject[] to be the executable batch. Often though, the client
+ * will known the batch object prior to construction and being able to place
+ * it into the execobject[] array first can simplify the relocation tracking.
+ * Setting I915_EXEC_BATCH_FIRST tells execbuf to use element 0 of the
+ * execobject[] as the * batch instead (the default is to use the last
+ * element).
+ */
+#define I915_EXEC_BATCH_FIRST (1<<18)
+
+/* Setting I915_FENCE_ARRAY implies that num_cliprects and cliprects_ptr
+ * define an array of i915_gem_exec_fence structures which specify a set of
+ * dma fences to wait upon or signal.
+ */
+#define I915_EXEC_FENCE_ARRAY (1<<19)
+
+/*
+ * Setting I915_EXEC_FENCE_SUBMIT implies that lower_32_bits(rsvd2) represent
+ * a sync_file fd to wait upon (in a nonblocking manner) prior to executing
+ * the batch.
+ *
+ * Returns -EINVAL if the sync_file fd cannot be found.
+ */
+#define I915_EXEC_FENCE_SUBMIT (1 << 20)
+
+/*
+ * Setting I915_EXEC_USE_EXTENSIONS implies that
+ * drm_i915_gem_execbuffer2.cliprects_ptr is treated as a pointer to an linked
+ * list of i915_user_extension. Each i915_user_extension node is the base of a
+ * larger structure. The list of supported structures are listed in the
+ * drm_i915_gem_execbuffer_ext enum.
+ */
+#define I915_EXEC_USE_EXTENSIONS (1 << 21)
+#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_USE_EXTENSIONS << 1))
+
+ /** @rsvd1: Context id */
+ __u64 rsvd1;
+
+ /**
+ * @rsvd2: in and out sync_file file descriptors.
+ *
+ * When I915_EXEC_FENCE_IN or I915_EXEC_FENCE_SUBMIT flag is set, the
+ * lower 32 bits of this field will have the in sync_file fd (input).
+ *
+ * When I915_EXEC_FENCE_OUT flag is set, the upper 32 bits of this
+ * field will have the out sync_file fd (output).
+ */
+ __u64 rsvd2;
+};
+
+#define I915_EXEC_CONTEXT_ID_MASK (0xffffffff)
+#define i915_execbuffer2_set_context_id(eb2, context) \
+ (eb2).rsvd1 = context & I915_EXEC_CONTEXT_ID_MASK
+#define i915_execbuffer2_get_context_id(eb2) \
+ ((eb2).rsvd1 & I915_EXEC_CONTEXT_ID_MASK)
+
+struct drm_i915_gem_pin {
+ /** Handle of the buffer to be pinned. */
+ __u32 handle;
+ __u32 pad;
+
+ /** alignment required within the aperture */
+ __u64 alignment;
+
+ /** Returned GTT offset of the buffer. */
+ __u64 offset;
+};
+
+struct drm_i915_gem_unpin {
+ /** Handle of the buffer to be unpinned. */
+ __u32 handle;
+ __u32 pad;
+};
+
+struct drm_i915_gem_busy {
+ /** Handle of the buffer to check for busy */
+ __u32 handle;
+
+ /** Return busy status
+ *
+ * A return of 0 implies that the object is idle (after
+ * having flushed any pending activity), and a non-zero return that
+ * the object is still in-flight on the GPU. (The GPU has not yet
+ * signaled completion for all pending requests that reference the
+ * object.) An object is guaranteed to become idle eventually (so
+ * long as no new GPU commands are executed upon it). Due to the
+ * asynchronous nature of the hardware, an object reported
+ * as busy may become idle before the ioctl is completed.
+ *
+ * Furthermore, if the object is busy, which engine is busy is only
+ * provided as a guide and only indirectly by reporting its class
+ * (there may be more than one engine in each class). There are race
+ * conditions which prevent the report of which engines are busy from
+ * being always accurate. However, the converse is not true. If the
+ * object is idle, the result of the ioctl, that all engines are idle,
+ * is accurate.
+ *
+ * The returned dword is split into two fields to indicate both
+ * the engine classess on which the object is being read, and the
+ * engine class on which it is currently being written (if any).
+ *
+ * The low word (bits 0:15) indicate if the object is being written
+ * to by any engine (there can only be one, as the GEM implicit
+ * synchronisation rules force writes to be serialised). Only the
+ * engine class (offset by 1, I915_ENGINE_CLASS_RENDER is reported as
+ * 1 not 0 etc) for the last write is reported.
+ *
+ * The high word (bits 16:31) are a bitmask of which engines classes
+ * are currently reading from the object. Multiple engines may be
+ * reading from the object simultaneously.
+ *
+ * The value of each engine class is the same as specified in the
+ * I915_CONTEXT_PARAM_ENGINES context parameter and via perf, i.e.
+ * I915_ENGINE_CLASS_RENDER, I915_ENGINE_CLASS_COPY, etc.
+ * Some hardware may have parallel execution engines, e.g. multiple
+ * media engines, which are mapped to the same class identifier and so
+ * are not separately reported for busyness.
+ *
+ * Caveat emptor:
+ * Only the boolean result of this query is reliable; that is whether
+ * the object is idle or busy. The report of which engines are busy
+ * should be only used as a heuristic.
+ */
+ __u32 busy;
+};
+
+/**
+ * struct drm_i915_gem_caching - Set or get the caching for given object
+ * handle.
+ *
+ * Allow userspace to control the GTT caching bits for a given object when the
+ * object is later mapped through the ppGTT(or GGTT on older platforms lacking
+ * ppGTT support, or if the object is used for scanout). Note that this might
+ * require unbinding the object from the GTT first, if its current caching value
+ * doesn't match.
+ *
+ * Note that this all changes on discrete platforms, starting from DG1, the
+ * set/get caching is no longer supported, and is now rejected. Instead the CPU
+ * caching attributes(WB vs WC) will become an immutable creation time property
+ * for the object, along with the GTT caching level. For now we don't expose any
+ * new uAPI for this, instead on DG1 this is all implicit, although this largely
+ * shouldn't matter since DG1 is coherent by default(without any way of
+ * controlling it).
+ *
+ * Implicit caching rules, starting from DG1:
+ *
+ * - If any of the object placements (see &drm_i915_gem_create_ext_memory_regions)
+ * contain I915_MEMORY_CLASS_DEVICE then the object will be allocated and
+ * mapped as write-combined only.
+ *
+ * - Everything else is always allocated and mapped as write-back, with the
+ * guarantee that everything is also coherent with the GPU.
+ *
+ * Note that this is likely to change in the future again, where we might need
+ * more flexibility on future devices, so making this all explicit as part of a
+ * new &drm_i915_gem_create_ext extension is probable.
+ *
+ * Side note: Part of the reason for this is that changing the at-allocation-time CPU
+ * caching attributes for the pages might be required(and is expensive) if we
+ * need to then CPU map the pages later with different caching attributes. This
+ * inconsistent caching behaviour, while supported on x86, is not universally
+ * supported on other architectures. So for simplicity we opt for setting
+ * everything at creation time, whilst also making it immutable, on discrete
+ * platforms.
+ */
+struct drm_i915_gem_caching {
+ /**
+ * @handle: Handle of the buffer to set/get the caching level.
+ */
+ __u32 handle;
+
+ /**
+ * @caching: The GTT caching level to apply or possible return value.
+ *
+ * The supported @caching values:
+ *
+ * I915_CACHING_NONE:
+ *
+ * GPU access is not coherent with CPU caches. Default for machines
+ * without an LLC. This means manual flushing might be needed, if we
+ * want GPU access to be coherent.
+ *
+ * I915_CACHING_CACHED:
+ *
+ * GPU access is coherent with CPU caches and furthermore the data is
+ * cached in last-level caches shared between CPU cores and the GPU GT.
+ *
+ * I915_CACHING_DISPLAY:
+ *
+ * Special GPU caching mode which is coherent with the scanout engines.
+ * Transparently falls back to I915_CACHING_NONE on platforms where no
+ * special cache mode (like write-through or gfdt flushing) is
+ * available. The kernel automatically sets this mode when using a
+ * buffer as a scanout target. Userspace can manually set this mode to
+ * avoid a costly stall and clflush in the hotpath of drawing the first
+ * frame.
+ */
+#define I915_CACHING_NONE 0
+#define I915_CACHING_CACHED 1
+#define I915_CACHING_DISPLAY 2
+ __u32 caching;
+};
+
+#define I915_TILING_NONE 0
+#define I915_TILING_X 1
+#define I915_TILING_Y 2
+/*
+ * Do not add new tiling types here. The I915_TILING_* values are for
+ * de-tiling fence registers that no longer exist on modern platforms. Although
+ * the hardware may support new types of tiling in general (e.g., Tile4), we
+ * do not need to add them to the uapi that is specific to now-defunct ioctls.
+ */
+#define I915_TILING_LAST I915_TILING_Y
+
+#define I915_BIT_6_SWIZZLE_NONE 0
+#define I915_BIT_6_SWIZZLE_9 1
+#define I915_BIT_6_SWIZZLE_9_10 2
+#define I915_BIT_6_SWIZZLE_9_11 3
+#define I915_BIT_6_SWIZZLE_9_10_11 4
+/* Not seen by userland */
+#define I915_BIT_6_SWIZZLE_UNKNOWN 5
+/* Seen by userland. */
+#define I915_BIT_6_SWIZZLE_9_17 6
+#define I915_BIT_6_SWIZZLE_9_10_17 7
+
+struct drm_i915_gem_set_tiling {
+ /** Handle of the buffer to have its tiling state updated */
+ __u32 handle;
+
+ /**
+ * Tiling mode for the object (I915_TILING_NONE, I915_TILING_X,
+ * I915_TILING_Y).
+ *
+ * This value is to be set on request, and will be updated by the
+ * kernel on successful return with the actual chosen tiling layout.
+ *
+ * The tiling mode may be demoted to I915_TILING_NONE when the system
+ * has bit 6 swizzling that can't be managed correctly by GEM.
+ *
+ * Buffer contents become undefined when changing tiling_mode.
+ */
+ __u32 tiling_mode;
+
+ /**
+ * Stride in bytes for the object when in I915_TILING_X or
+ * I915_TILING_Y.
+ */
+ __u32 stride;
+
+ /**
+ * Returned address bit 6 swizzling required for CPU access through
+ * mmap mapping.
+ */
+ __u32 swizzle_mode;
+};
+
+struct drm_i915_gem_get_tiling {
+ /** Handle of the buffer to get tiling state for. */
+ __u32 handle;
+
+ /**
+ * Current tiling mode for the object (I915_TILING_NONE, I915_TILING_X,
+ * I915_TILING_Y).
+ */
+ __u32 tiling_mode;
+
+ /**
+ * Returned address bit 6 swizzling required for CPU access through
+ * mmap mapping.
+ */
+ __u32 swizzle_mode;
+
+ /**
+ * Returned address bit 6 swizzling required for CPU access through
+ * mmap mapping whilst bound.
+ */
+ __u32 phys_swizzle_mode;
+};
+
+struct drm_i915_gem_get_aperture {
+ /** Total size of the aperture used by i915_gem_execbuffer, in bytes */
+ __u64 aper_size;
+
+ /**
+ * Available space in the aperture used by i915_gem_execbuffer, in
+ * bytes
+ */
+ __u64 aper_available_size;
+};
+
+struct drm_i915_get_pipe_from_crtc_id {
+ /** ID of CRTC being requested **/
+ __u32 crtc_id;
+
+ /** pipe of requested CRTC **/
+ __u32 pipe;
+};
+
+#define I915_MADV_WILLNEED 0
+#define I915_MADV_DONTNEED 1
+#define __I915_MADV_PURGED 2 /* internal state */
+
+struct drm_i915_gem_madvise {
+ /** Handle of the buffer to change the backing store advice */
+ __u32 handle;
+
+ /* Advice: either the buffer will be needed again in the near future,
+ * or wont be and could be discarded under memory pressure.
+ */
+ __u32 madv;
+
+ /** Whether the backing store still exists. */
+ __u32 retained;
+};
+
+/* flags */
+#define I915_OVERLAY_TYPE_MASK 0xff
+#define I915_OVERLAY_YUV_PLANAR 0x01
+#define I915_OVERLAY_YUV_PACKED 0x02
+#define I915_OVERLAY_RGB 0x03
+
+#define I915_OVERLAY_DEPTH_MASK 0xff00
+#define I915_OVERLAY_RGB24 0x1000
+#define I915_OVERLAY_RGB16 0x2000
+#define I915_OVERLAY_RGB15 0x3000
+#define I915_OVERLAY_YUV422 0x0100
+#define I915_OVERLAY_YUV411 0x0200
+#define I915_OVERLAY_YUV420 0x0300
+#define I915_OVERLAY_YUV410 0x0400
+
+#define I915_OVERLAY_SWAP_MASK 0xff0000
+#define I915_OVERLAY_NO_SWAP 0x000000
+#define I915_OVERLAY_UV_SWAP 0x010000
+#define I915_OVERLAY_Y_SWAP 0x020000
+#define I915_OVERLAY_Y_AND_UV_SWAP 0x030000
+
+#define I915_OVERLAY_FLAGS_MASK 0xff000000
+#define I915_OVERLAY_ENABLE 0x01000000
+
+struct drm_intel_overlay_put_image {
+ /* various flags and src format description */
+ __u32 flags;
+ /* source picture description */
+ __u32 bo_handle;
+ /* stride values and offsets are in bytes, buffer relative */
+ __u16 stride_Y; /* stride for packed formats */
+ __u16 stride_UV;
+ __u32 offset_Y; /* offset for packet formats */
+ __u32 offset_U;
+ __u32 offset_V;
+ /* in pixels */
+ __u16 src_width;
+ __u16 src_height;
+ /* to compensate the scaling factors for partially covered surfaces */
+ __u16 src_scan_width;
+ __u16 src_scan_height;
+ /* output crtc description */
+ __u32 crtc_id;
+ __u16 dst_x;
+ __u16 dst_y;
+ __u16 dst_width;
+ __u16 dst_height;
+};
+
+/* flags */
+#define I915_OVERLAY_UPDATE_ATTRS (1<<0)
+#define I915_OVERLAY_UPDATE_GAMMA (1<<1)
+#define I915_OVERLAY_DISABLE_DEST_COLORKEY (1<<2)
+struct drm_intel_overlay_attrs {
+ __u32 flags;
+ __u32 color_key;
+ __s32 brightness;
+ __u32 contrast;
+ __u32 saturation;
+ __u32 gamma0;
+ __u32 gamma1;
+ __u32 gamma2;
+ __u32 gamma3;
+ __u32 gamma4;
+ __u32 gamma5;
+};
+
+/*
+ * Intel sprite handling
+ *
+ * Color keying works with a min/mask/max tuple. Both source and destination
+ * color keying is allowed.
+ *
+ * Source keying:
+ * Sprite pixels within the min & max values, masked against the color channels
+ * specified in the mask field, will be transparent. All other pixels will
+ * be displayed on top of the primary plane. For RGB surfaces, only the min
+ * and mask fields will be used; ranged compares are not allowed.
+ *
+ * Destination keying:
+ * Primary plane pixels that match the min value, masked against the color
+ * channels specified in the mask field, will be replaced by corresponding
+ * pixels from the sprite plane.
+ *
+ * Note that source & destination keying are exclusive; only one can be
+ * active on a given plane.
+ */
+
+#define I915_SET_COLORKEY_NONE (1<<0) /* Deprecated. Instead set
+ * flags==0 to disable colorkeying.
+ */
+#define I915_SET_COLORKEY_DESTINATION (1<<1)
+#define I915_SET_COLORKEY_SOURCE (1<<2)
+struct drm_intel_sprite_colorkey {
+ __u32 plane_id;
+ __u32 min_value;
+ __u32 channel_mask;
+ __u32 max_value;
+ __u32 flags;
+};
+
+struct drm_i915_gem_wait {
+ /** Handle of BO we shall wait on */
+ __u32 bo_handle;
+ __u32 flags;
+ /** Number of nanoseconds to wait, Returns time remaining. */
+ __s64 timeout_ns;
+};
+
+struct drm_i915_gem_context_create {
+ __u32 ctx_id; /* output: id of new context*/
+ __u32 pad;
+};
+
+/**
+ * struct drm_i915_gem_context_create_ext - Structure for creating contexts.
+ */
+struct drm_i915_gem_context_create_ext {
+ /** @ctx_id: Id of the created context (output) */
+ __u32 ctx_id;
+
+ /**
+ * @flags: Supported flags are:
+ *
+ * I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS:
+ *
+ * Extensions may be appended to this structure and driver must check
+ * for those. See @extensions.
+ *
+ * I915_CONTEXT_CREATE_FLAGS_SINGLE_TIMELINE
+ *
+ * Created context will have single timeline.
+ */
+ __u32 flags;
+#define I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS (1u << 0)
+#define I915_CONTEXT_CREATE_FLAGS_SINGLE_TIMELINE (1u << 1)
+#define I915_CONTEXT_CREATE_FLAGS_UNKNOWN \
+ (-(I915_CONTEXT_CREATE_FLAGS_SINGLE_TIMELINE << 1))
+
+ /**
+ * @extensions: Zero-terminated chain of extensions.
+ *
+ * I915_CONTEXT_CREATE_EXT_SETPARAM:
+ * Context parameter to set or query during context creation.
+ * See struct drm_i915_gem_context_create_ext_setparam.
+ *
+ * I915_CONTEXT_CREATE_EXT_CLONE:
+ * This extension has been removed. On the off chance someone somewhere
+ * has attempted to use it, never re-use this extension number.
+ */
+ __u64 extensions;
+#define I915_CONTEXT_CREATE_EXT_SETPARAM 0
+#define I915_CONTEXT_CREATE_EXT_CLONE 1
+};
+
+/**
+ * struct drm_i915_gem_context_param - Context parameter to set or query.
+ */
+struct drm_i915_gem_context_param {
+ /** @ctx_id: Context id */
+ __u32 ctx_id;
+
+ /** @size: Size of the parameter @value */
+ __u32 size;
+
+ /** @param: Parameter to set or query */
+ __u64 param;
+#define I915_CONTEXT_PARAM_BAN_PERIOD 0x1
+/* I915_CONTEXT_PARAM_NO_ZEROMAP has been removed. On the off chance
+ * someone somewhere has attempted to use it, never re-use this context
+ * param number.
+ */
+#define I915_CONTEXT_PARAM_NO_ZEROMAP 0x2
+#define I915_CONTEXT_PARAM_GTT_SIZE 0x3
+#define I915_CONTEXT_PARAM_NO_ERROR_CAPTURE 0x4
+#define I915_CONTEXT_PARAM_BANNABLE 0x5
+#define I915_CONTEXT_PARAM_PRIORITY 0x6
+#define I915_CONTEXT_MAX_USER_PRIORITY 1023 /* inclusive */
+#define I915_CONTEXT_DEFAULT_PRIORITY 0
+#define I915_CONTEXT_MIN_USER_PRIORITY -1023 /* inclusive */
+ /*
+ * When using the following param, value should be a pointer to
+ * drm_i915_gem_context_param_sseu.
+ */
+#define I915_CONTEXT_PARAM_SSEU 0x7
+
+/*
+ * Not all clients may want to attempt automatic recover of a context after
+ * a hang (for example, some clients may only submit very small incremental
+ * batches relying on known logical state of previous batches which will never
+ * recover correctly and each attempt will hang), and so would prefer that
+ * the context is forever banned instead.
+ *
+ * If set to false (0), after a reset, subsequent (and in flight) rendering
+ * from this context is discarded, and the client will need to create a new
+ * context to use instead.
+ *
+ * If set to true (1), the kernel will automatically attempt to recover the
+ * context by skipping the hanging batch and executing the next batch starting
+ * from the default context state (discarding the incomplete logical context
+ * state lost due to the reset).
+ *
+ * On creation, all new contexts are marked as recoverable.
+ */
+#define I915_CONTEXT_PARAM_RECOVERABLE 0x8
+
+ /*
+ * The id of the associated virtual memory address space (ppGTT) of
+ * this context. Can be retrieved and passed to another context
+ * (on the same fd) for both to use the same ppGTT and so share
+ * address layouts, and avoid reloading the page tables on context
+ * switches between themselves.
+ *
+ * See DRM_I915_GEM_VM_CREATE and DRM_I915_GEM_VM_DESTROY.
+ */
+#define I915_CONTEXT_PARAM_VM 0x9
+
+/*
+ * I915_CONTEXT_PARAM_ENGINES:
+ *
+ * Bind this context to operate on this subset of available engines. Henceforth,
+ * the I915_EXEC_RING selector for DRM_IOCTL_I915_GEM_EXECBUFFER2 operates as
+ * an index into this array of engines; I915_EXEC_DEFAULT selecting engine[0]
+ * and upwards. Slots 0...N are filled in using the specified (class, instance).
+ * Use
+ * engine_class: I915_ENGINE_CLASS_INVALID,
+ * engine_instance: I915_ENGINE_CLASS_INVALID_NONE
+ * to specify a gap in the array that can be filled in later, e.g. by a
+ * virtual engine used for load balancing.
+ *
+ * Setting the number of engines bound to the context to 0, by passing a zero
+ * sized argument, will revert back to default settings.
+ *
+ * See struct i915_context_param_engines.
+ *
+ * Extensions:
+ * i915_context_engines_load_balance (I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE)
+ * i915_context_engines_bond (I915_CONTEXT_ENGINES_EXT_BOND)
+ * i915_context_engines_parallel_submit (I915_CONTEXT_ENGINES_EXT_PARALLEL_SUBMIT)
+ */
+#define I915_CONTEXT_PARAM_ENGINES 0xa
+
+/*
+ * I915_CONTEXT_PARAM_PERSISTENCE:
+ *
+ * Allow the context and active rendering to survive the process until
+ * completion. Persistence allows fire-and-forget clients to queue up a
+ * bunch of work, hand the output over to a display server and then quit.
+ * If the context is marked as not persistent, upon closing (either via
+ * an explicit DRM_I915_GEM_CONTEXT_DESTROY or implicitly from file closure
+ * or process termination), the context and any outstanding requests will be
+ * cancelled (and exported fences for cancelled requests marked as -EIO).
+ *
+ * By default, new contexts allow persistence.
+ */
+#define I915_CONTEXT_PARAM_PERSISTENCE 0xb
+
+/* This API has been removed. On the off chance someone somewhere has
+ * attempted to use it, never re-use this context param number.
+ */
+#define I915_CONTEXT_PARAM_RINGSIZE 0xc
+
+/*
+ * I915_CONTEXT_PARAM_PROTECTED_CONTENT:
+ *
+ * Mark that the context makes use of protected content, which will result
+ * in the context being invalidated when the protected content session is.
+ * Given that the protected content session is killed on suspend, the device
+ * is kept awake for the lifetime of a protected context, so the user should
+ * make sure to dispose of them once done.
+ * This flag can only be set at context creation time and, when set to true,
+ * must be preceded by an explicit setting of I915_CONTEXT_PARAM_RECOVERABLE
+ * to false. This flag can't be set to true in conjunction with setting the
+ * I915_CONTEXT_PARAM_BANNABLE flag to false. Creation example:
+ *
+ * .. code-block:: C
+ *
+ * struct drm_i915_gem_context_create_ext_setparam p_protected = {
+ * .base = {
+ * .name = I915_CONTEXT_CREATE_EXT_SETPARAM,
+ * },
+ * .param = {
+ * .param = I915_CONTEXT_PARAM_PROTECTED_CONTENT,
+ * .value = 1,
+ * }
+ * };
+ * struct drm_i915_gem_context_create_ext_setparam p_norecover = {
+ * .base = {
+ * .name = I915_CONTEXT_CREATE_EXT_SETPARAM,
+ * .next_extension = to_user_pointer(&p_protected),
+ * },
+ * .param = {
+ * .param = I915_CONTEXT_PARAM_RECOVERABLE,
+ * .value = 0,
+ * }
+ * };
+ * struct drm_i915_gem_context_create_ext create = {
+ * .flags = I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS,
+ * .extensions = to_user_pointer(&p_norecover);
+ * };
+ *
+ * ctx_id = gem_context_create_ext(drm_fd, &create);
+ *
+ * In addition to the normal failure cases, setting this flag during context
+ * creation can result in the following errors:
+ *
+ * -ENODEV: feature not available
+ * -EPERM: trying to mark a recoverable or not bannable context as protected
+ * -ENXIO: A dependency such as a component driver or firmware is not yet
+ * loaded so user space may need to attempt again. Depending on the
+ * device, this error may be reported if protected context creation is
+ * attempted very early after kernel start because the internal timeout
+ * waiting for such dependencies is not guaranteed to be larger than
+ * required (numbers differ depending on system and kernel config):
+ * - ADL/RPL: dependencies may take up to 3 seconds from kernel start
+ * while context creation internal timeout is 250 milisecs
+ * - MTL: dependencies may take up to 8 seconds from kernel start
+ * while context creation internal timeout is 250 milisecs
+ * NOTE: such dependencies happen once, so a subsequent call to create a
+ * protected context after a prior successful call will not experience
+ * such timeouts and will not return -ENXIO (unless the driver is reloaded,
+ * or, depending on the device, resumes from a suspended state).
+ * -EIO: The firmware did not succeed in creating the protected context.
+ */
+#define I915_CONTEXT_PARAM_PROTECTED_CONTENT 0xd
+/* Must be kept compact -- no holes and well documented */
+
+ /** @value: Context parameter value to be set or queried */
+ __u64 value;
+};
+
+/*
+ * Context SSEU programming
+ *
+ * It may be necessary for either functional or performance reason to configure
+ * a context to run with a reduced number of SSEU (where SSEU stands for Slice/
+ * Sub-slice/EU).
+ *
+ * This is done by configuring SSEU configuration using the below
+ * @struct drm_i915_gem_context_param_sseu for every supported engine which
+ * userspace intends to use.
+ *
+ * Not all GPUs or engines support this functionality in which case an error
+ * code -ENODEV will be returned.
+ *
+ * Also, flexibility of possible SSEU configuration permutations varies between
+ * GPU generations and software imposed limitations. Requesting such a
+ * combination will return an error code of -EINVAL.
+ *
+ * NOTE: When perf/OA is active the context's SSEU configuration is ignored in
+ * favour of a single global setting.
+ */
+struct drm_i915_gem_context_param_sseu {
+ /*
+ * Engine class & instance to be configured or queried.
+ */
+ struct i915_engine_class_instance engine;
+
+ /*
+ * Unknown flags must be cleared to zero.
+ */
+ __u32 flags;
+#define I915_CONTEXT_SSEU_FLAG_ENGINE_INDEX (1u << 0)
+
+ /*
+ * Mask of slices to enable for the context. Valid values are a subset
+ * of the bitmask value returned for I915_PARAM_SLICE_MASK.
+ */
+ __u64 slice_mask;
+
+ /*
+ * Mask of subslices to enable for the context. Valid values are a
+ * subset of the bitmask value return by I915_PARAM_SUBSLICE_MASK.
+ */
+ __u64 subslice_mask;
+
+ /*
+ * Minimum/Maximum number of EUs to enable per subslice for the
+ * context. min_eus_per_subslice must be inferior or equal to
+ * max_eus_per_subslice.
+ */
+ __u16 min_eus_per_subslice;
+ __u16 max_eus_per_subslice;
+
+ /*
+ * Unused for now. Must be cleared to zero.
+ */
+ __u32 rsvd;
+};
+
+/**
+ * DOC: Virtual Engine uAPI
+ *
+ * Virtual engine is a concept where userspace is able to configure a set of
+ * physical engines, submit a batch buffer, and let the driver execute it on any
+ * engine from the set as it sees fit.
+ *
+ * This is primarily useful on parts which have multiple instances of a same
+ * class engine, like for example GT3+ Skylake parts with their two VCS engines.
+ *
+ * For instance userspace can enumerate all engines of a certain class using the
+ * previously described `Engine Discovery uAPI`_. After that userspace can
+ * create a GEM context with a placeholder slot for the virtual engine (using
+ * `I915_ENGINE_CLASS_INVALID` and `I915_ENGINE_CLASS_INVALID_NONE` for class
+ * and instance respectively) and finally using the
+ * `I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE` extension place a virtual engine in
+ * the same reserved slot.
+ *
+ * Example of creating a virtual engine and submitting a batch buffer to it:
+ *
+ * .. code-block:: C
+ *
+ * I915_DEFINE_CONTEXT_ENGINES_LOAD_BALANCE(virtual, 2) = {
+ * .base.name = I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE,
+ * .engine_index = 0, // Place this virtual engine into engine map slot 0
+ * .num_siblings = 2,
+ * .engines = { { I915_ENGINE_CLASS_VIDEO, 0 },
+ * { I915_ENGINE_CLASS_VIDEO, 1 }, },
+ * };
+ * I915_DEFINE_CONTEXT_PARAM_ENGINES(engines, 1) = {
+ * .engines = { { I915_ENGINE_CLASS_INVALID,
+ * I915_ENGINE_CLASS_INVALID_NONE } },
+ * .extensions = to_user_pointer(&virtual), // Chains after load_balance extension
+ * };
+ * struct drm_i915_gem_context_create_ext_setparam p_engines = {
+ * .base = {
+ * .name = I915_CONTEXT_CREATE_EXT_SETPARAM,
+ * },
+ * .param = {
+ * .param = I915_CONTEXT_PARAM_ENGINES,
+ * .value = to_user_pointer(&engines),
+ * .size = sizeof(engines),
+ * },
+ * };
+ * struct drm_i915_gem_context_create_ext create = {
+ * .flags = I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS,
+ * .extensions = to_user_pointer(&p_engines);
+ * };
+ *
+ * ctx_id = gem_context_create_ext(drm_fd, &create);
+ *
+ * // Now we have created a GEM context with its engine map containing a
+ * // single virtual engine. Submissions to this slot can go either to
+ * // vcs0 or vcs1, depending on the load balancing algorithm used inside
+ * // the driver. The load balancing is dynamic from one batch buffer to
+ * // another and transparent to userspace.
+ *
+ * ...
+ * execbuf.rsvd1 = ctx_id;
+ * execbuf.flags = 0; // Submits to index 0 which is the virtual engine
+ * gem_execbuf(drm_fd, &execbuf);
+ */
+
+/*
+ * i915_context_engines_load_balance:
+ *
+ * Enable load balancing across this set of engines.
+ *
+ * Into the I915_EXEC_DEFAULT slot [0], a virtual engine is created that when
+ * used will proxy the execbuffer request onto one of the set of engines
+ * in such a way as to distribute the load evenly across the set.
+ *
+ * The set of engines must be compatible (e.g. the same HW class) as they
+ * will share the same logical GPU context and ring.
+ *
+ * To intermix rendering with the virtual engine and direct rendering onto
+ * the backing engines (bypassing the load balancing proxy), the context must
+ * be defined to use a single timeline for all engines.
+ */
+struct i915_context_engines_load_balance {
+ struct i915_user_extension base;
+
+ __u16 engine_index;
+ __u16 num_siblings;
+ __u32 flags; /* all undefined flags must be zero */
+
+ __u64 mbz64; /* reserved for future use; must be zero */
+
+ struct i915_engine_class_instance engines[];
+} __attribute__((packed));
+
+#define I915_DEFINE_CONTEXT_ENGINES_LOAD_BALANCE(name__, N__) struct { \
+ struct i915_user_extension base; \
+ __u16 engine_index; \
+ __u16 num_siblings; \
+ __u32 flags; \
+ __u64 mbz64; \
+ struct i915_engine_class_instance engines[N__]; \
+} __attribute__((packed)) name__
+
+/*
+ * i915_context_engines_bond:
+ *
+ * Constructed bonded pairs for execution within a virtual engine.
+ *
+ * All engines are equal, but some are more equal than others. Given
+ * the distribution of resources in the HW, it may be preferable to run
+ * a request on a given subset of engines in parallel to a request on a
+ * specific engine. We enable this selection of engines within a virtual
+ * engine by specifying bonding pairs, for any given master engine we will
+ * only execute on one of the corresponding siblings within the virtual engine.
+ *
+ * To execute a request in parallel on the master engine and a sibling requires
+ * coordination with a I915_EXEC_FENCE_SUBMIT.
+ */
+struct i915_context_engines_bond {
+ struct i915_user_extension base;
+
+ struct i915_engine_class_instance master;
+
+ __u16 virtual_index; /* index of virtual engine in ctx->engines[] */
+ __u16 num_bonds;
+
+ __u64 flags; /* all undefined flags must be zero */
+ __u64 mbz64[4]; /* reserved for future use; must be zero */
+
+ struct i915_engine_class_instance engines[];
+} __attribute__((packed));
+
+#define I915_DEFINE_CONTEXT_ENGINES_BOND(name__, N__) struct { \
+ struct i915_user_extension base; \
+ struct i915_engine_class_instance master; \
+ __u16 virtual_index; \
+ __u16 num_bonds; \
+ __u64 flags; \
+ __u64 mbz64[4]; \
+ struct i915_engine_class_instance engines[N__]; \
+} __attribute__((packed)) name__
+
+/**
+ * struct i915_context_engines_parallel_submit - Configure engine for
+ * parallel submission.
+ *
+ * Setup a slot in the context engine map to allow multiple BBs to be submitted
+ * in a single execbuf IOCTL. Those BBs will then be scheduled to run on the GPU
+ * in parallel. Multiple hardware contexts are created internally in the i915 to
+ * run these BBs. Once a slot is configured for N BBs only N BBs can be
+ * submitted in each execbuf IOCTL and this is implicit behavior e.g. The user
+ * doesn't tell the execbuf IOCTL there are N BBs, the execbuf IOCTL knows how
+ * many BBs there are based on the slot's configuration. The N BBs are the last
+ * N buffer objects or first N if I915_EXEC_BATCH_FIRST is set.
+ *
+ * The default placement behavior is to create implicit bonds between each
+ * context if each context maps to more than 1 physical engine (e.g. context is
+ * a virtual engine). Also we only allow contexts of same engine class and these
+ * contexts must be in logically contiguous order. Examples of the placement
+ * behavior are described below. Lastly, the default is to not allow BBs to be
+ * preempted mid-batch. Rather insert coordinated preemption points on all
+ * hardware contexts between each set of BBs. Flags could be added in the future
+ * to change both of these default behaviors.
+ *
+ * Returns -EINVAL if hardware context placement configuration is invalid or if
+ * the placement configuration isn't supported on the platform / submission
+ * interface.
+ * Returns -ENODEV if extension isn't supported on the platform / submission
+ * interface.
+ *
+ * .. code-block:: none
+ *
+ * Examples syntax:
+ * CS[X] = generic engine of same class, logical instance X
+ * INVALID = I915_ENGINE_CLASS_INVALID, I915_ENGINE_CLASS_INVALID_NONE
+ *
+ * Example 1 pseudo code:
+ * set_engines(INVALID)
+ * set_parallel(engine_index=0, width=2, num_siblings=1,
+ * engines=CS[0],CS[1])
+ *
+ * Results in the following valid placement:
+ * CS[0], CS[1]
+ *
+ * Example 2 pseudo code:
+ * set_engines(INVALID)
+ * set_parallel(engine_index=0, width=2, num_siblings=2,
+ * engines=CS[0],CS[2],CS[1],CS[3])
+ *
+ * Results in the following valid placements:
+ * CS[0], CS[1]
+ * CS[2], CS[3]
+ *
+ * This can be thought of as two virtual engines, each containing two
+ * engines thereby making a 2D array. However, there are bonds tying the
+ * entries together and placing restrictions on how they can be scheduled.
+ * Specifically, the scheduler can choose only vertical columns from the 2D
+ * array. That is, CS[0] is bonded to CS[1] and CS[2] to CS[3]. So if the
+ * scheduler wants to submit to CS[0], it must also choose CS[1] and vice
+ * versa. Same for CS[2] requires also using CS[3].
+ * VE[0] = CS[0], CS[2]
+ * VE[1] = CS[1], CS[3]
+ *
+ * Example 3 pseudo code:
+ * set_engines(INVALID)
+ * set_parallel(engine_index=0, width=2, num_siblings=2,
+ * engines=CS[0],CS[1],CS[1],CS[3])
+ *
+ * Results in the following valid and invalid placements:
+ * CS[0], CS[1]
+ * CS[1], CS[3] - Not logically contiguous, return -EINVAL
+ */
+struct i915_context_engines_parallel_submit {
+ /**
+ * @base: base user extension.
+ */
+ struct i915_user_extension base;
+
+ /**
+ * @engine_index: slot for parallel engine
+ */
+ __u16 engine_index;
+
+ /**
+ * @width: number of contexts per parallel engine or in other words the
+ * number of batches in each submission
+ */
+ __u16 width;
+
+ /**
+ * @num_siblings: number of siblings per context or in other words the
+ * number of possible placements for each submission
+ */
+ __u16 num_siblings;
+
+ /**
+ * @mbz16: reserved for future use; must be zero
+ */
+ __u16 mbz16;
+
+ /**
+ * @flags: all undefined flags must be zero, currently not defined flags
+ */
+ __u64 flags;
+
+ /**
+ * @mbz64: reserved for future use; must be zero
+ */
+ __u64 mbz64[3];
+
+ /**
+ * @engines: 2-d array of engine instances to configure parallel engine
+ *
+ * length = width (i) * num_siblings (j)
+ * index = j + i * num_siblings
+ */
+ struct i915_engine_class_instance engines[];
+
+} __packed;
+
+#define I915_DEFINE_CONTEXT_ENGINES_PARALLEL_SUBMIT(name__, N__) struct { \
+ struct i915_user_extension base; \
+ __u16 engine_index; \
+ __u16 width; \
+ __u16 num_siblings; \
+ __u16 mbz16; \
+ __u64 flags; \
+ __u64 mbz64[3]; \
+ struct i915_engine_class_instance engines[N__]; \
+} __attribute__((packed)) name__
+
+/**
+ * DOC: Context Engine Map uAPI
+ *
+ * Context engine map is a new way of addressing engines when submitting batch-
+ * buffers, replacing the existing way of using identifiers like `I915_EXEC_BLT`
+ * inside the flags field of `struct drm_i915_gem_execbuffer2`.
+ *
+ * To use it created GEM contexts need to be configured with a list of engines
+ * the user is intending to submit to. This is accomplished using the
+ * `I915_CONTEXT_PARAM_ENGINES` parameter and `struct
+ * i915_context_param_engines`.
+ *
+ * For such contexts the `I915_EXEC_RING_MASK` field becomes an index into the
+ * configured map.
+ *
+ * Example of creating such context and submitting against it:
+ *
+ * .. code-block:: C
+ *
+ * I915_DEFINE_CONTEXT_PARAM_ENGINES(engines, 2) = {
+ * .engines = { { I915_ENGINE_CLASS_RENDER, 0 },
+ * { I915_ENGINE_CLASS_COPY, 0 } }
+ * };
+ * struct drm_i915_gem_context_create_ext_setparam p_engines = {
+ * .base = {
+ * .name = I915_CONTEXT_CREATE_EXT_SETPARAM,
+ * },
+ * .param = {
+ * .param = I915_CONTEXT_PARAM_ENGINES,
+ * .value = to_user_pointer(&engines),
+ * .size = sizeof(engines),
+ * },
+ * };
+ * struct drm_i915_gem_context_create_ext create = {
+ * .flags = I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS,
+ * .extensions = to_user_pointer(&p_engines);
+ * };
+ *
+ * ctx_id = gem_context_create_ext(drm_fd, &create);
+ *
+ * // We have now created a GEM context with two engines in the map:
+ * // Index 0 points to rcs0 while index 1 points to bcs0. Other engines
+ * // will not be accessible from this context.
+ *
+ * ...
+ * execbuf.rsvd1 = ctx_id;
+ * execbuf.flags = 0; // Submits to index 0, which is rcs0 for this context
+ * gem_execbuf(drm_fd, &execbuf);
+ *
+ * ...
+ * execbuf.rsvd1 = ctx_id;
+ * execbuf.flags = 1; // Submits to index 0, which is bcs0 for this context
+ * gem_execbuf(drm_fd, &execbuf);
+ */
+
+struct i915_context_param_engines {
+ __u64 extensions; /* linked chain of extension blocks, 0 terminates */
+#define I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE 0 /* see i915_context_engines_load_balance */
+#define I915_CONTEXT_ENGINES_EXT_BOND 1 /* see i915_context_engines_bond */
+#define I915_CONTEXT_ENGINES_EXT_PARALLEL_SUBMIT 2 /* see i915_context_engines_parallel_submit */
+ struct i915_engine_class_instance engines[];
+} __attribute__((packed));
+
+#define I915_DEFINE_CONTEXT_PARAM_ENGINES(name__, N__) struct { \
+ __u64 extensions; \
+ struct i915_engine_class_instance engines[N__]; \
+} __attribute__((packed)) name__
+
+/**
+ * struct drm_i915_gem_context_create_ext_setparam - Context parameter
+ * to set or query during context creation.
+ */
+struct drm_i915_gem_context_create_ext_setparam {
+ /** @base: Extension link. See struct i915_user_extension. */
+ struct i915_user_extension base;
+
+ /**
+ * @param: Context parameter to set or query.
+ * See struct drm_i915_gem_context_param.
+ */
+ struct drm_i915_gem_context_param param;
+};
+
+struct drm_i915_gem_context_destroy {
+ __u32 ctx_id;
+ __u32 pad;
+};
+
+/**
+ * struct drm_i915_gem_vm_control - Structure to create or destroy VM.
+ *
+ * DRM_I915_GEM_VM_CREATE -
+ *
+ * Create a new virtual memory address space (ppGTT) for use within a context
+ * on the same file. Extensions can be provided to configure exactly how the
+ * address space is setup upon creation.
+ *
+ * The id of new VM (bound to the fd) for use with I915_CONTEXT_PARAM_VM is
+ * returned in the outparam @id.
+ *
+ * An extension chain maybe provided, starting with @extensions, and terminated
+ * by the @next_extension being 0. Currently, no extensions are defined.
+ *
+ * DRM_I915_GEM_VM_DESTROY -
+ *
+ * Destroys a previously created VM id, specified in @vm_id.
+ *
+ * No extensions or flags are allowed currently, and so must be zero.
+ */
+struct drm_i915_gem_vm_control {
+ /** @extensions: Zero-terminated chain of extensions. */
+ __u64 extensions;
+
+ /** @flags: reserved for future usage, currently MBZ */
+ __u32 flags;
+
+ /** @vm_id: Id of the VM created or to be destroyed */
+ __u32 vm_id;
+};
+
+struct drm_i915_reg_read {
+ /*
+ * Register offset.
+ * For 64bit wide registers where the upper 32bits don't immediately
+ * follow the lower 32bits, the offset of the lower 32bits must
+ * be specified
+ */
+ __u64 offset;
+#define I915_REG_READ_8B_WA (1ul << 0)
+
+ __u64 val; /* Return value */
+};
+
+/* Known registers:
+ *
+ * Render engine timestamp - 0x2358 + 64bit - gen7+
+ * - Note this register returns an invalid value if using the default
+ * single instruction 8byte read, in order to workaround that pass
+ * flag I915_REG_READ_8B_WA in offset field.
+ *
+ */
+
+struct drm_i915_reset_stats {
+ __u32 ctx_id;
+ __u32 flags;
+
+ /* All resets since boot/module reload, for all contexts */
+ __u32 reset_count;
+
+ /* Number of batches lost when active in GPU, for this context */
+ __u32 batch_active;
+
+ /* Number of batches lost pending for execution, for this context */
+ __u32 batch_pending;
+
+ __u32 pad;
+};
+
+/**
+ * struct drm_i915_gem_userptr - Create GEM object from user allocated memory.
+ *
+ * Userptr objects have several restrictions on what ioctls can be used with the
+ * object handle.
+ */
+struct drm_i915_gem_userptr {
+ /**
+ * @user_ptr: The pointer to the allocated memory.
+ *
+ * Needs to be aligned to PAGE_SIZE.
+ */
+ __u64 user_ptr;
+
+ /**
+ * @user_size:
+ *
+ * The size in bytes for the allocated memory. This will also become the
+ * object size.
+ *
+ * Needs to be aligned to PAGE_SIZE, and should be at least PAGE_SIZE,
+ * or larger.
+ */
+ __u64 user_size;
+
+ /**
+ * @flags:
+ *
+ * Supported flags:
+ *
+ * I915_USERPTR_READ_ONLY:
+ *
+ * Mark the object as readonly, this also means GPU access can only be
+ * readonly. This is only supported on HW which supports readonly access
+ * through the GTT. If the HW can't support readonly access, an error is
+ * returned.
+ *
+ * I915_USERPTR_PROBE:
+ *
+ * Probe the provided @user_ptr range and validate that the @user_ptr is
+ * indeed pointing to normal memory and that the range is also valid.
+ * For example if some garbage address is given to the kernel, then this
+ * should complain.
+ *
+ * Returns -EFAULT if the probe failed.
+ *
+ * Note that this doesn't populate the backing pages, and also doesn't
+ * guarantee that the object will remain valid when the object is
+ * eventually used.
+ *
+ * The kernel supports this feature if I915_PARAM_HAS_USERPTR_PROBE
+ * returns a non-zero value.
+ *
+ * I915_USERPTR_UNSYNCHRONIZED:
+ *
+ * NOT USED. Setting this flag will result in an error.
+ */
+ __u32 flags;
+#define I915_USERPTR_READ_ONLY 0x1
+#define I915_USERPTR_PROBE 0x2
+#define I915_USERPTR_UNSYNCHRONIZED 0x80000000
+ /**
+ * @handle: Returned handle for the object.
+ *
+ * Object handles are nonzero.
+ */
+ __u32 handle;
+};
+
+enum drm_i915_oa_format {
+ I915_OA_FORMAT_A13 = 1, /* HSW only */
+ I915_OA_FORMAT_A29, /* HSW only */
+ I915_OA_FORMAT_A13_B8_C8, /* HSW only */
+ I915_OA_FORMAT_B4_C8, /* HSW only */
+ I915_OA_FORMAT_A45_B8_C8, /* HSW only */
+ I915_OA_FORMAT_B4_C8_A16, /* HSW only */
+ I915_OA_FORMAT_C4_B8, /* HSW+ */
+
+ /* Gen8+ */
+ I915_OA_FORMAT_A12,
+ I915_OA_FORMAT_A12_B8_C8,
+ I915_OA_FORMAT_A32u40_A4u32_B8_C8,
+
+ /* DG2 */
+ I915_OAR_FORMAT_A32u40_A4u32_B8_C8,
+ I915_OA_FORMAT_A24u40_A14u32_B8_C8,
+
+ /* MTL OAM */
+ I915_OAM_FORMAT_MPEC8u64_B8_C8,
+ I915_OAM_FORMAT_MPEC8u32_B8_C8,
+
+ I915_OA_FORMAT_MAX /* non-ABI */
+};
+
+enum drm_i915_perf_property_id {
+ /**
+ * Open the stream for a specific context handle (as used with
+ * execbuffer2). A stream opened for a specific context this way
+ * won't typically require root privileges.
+ *
+ * This property is available in perf revision 1.
+ */
+ DRM_I915_PERF_PROP_CTX_HANDLE = 1,
+
+ /**
+ * A value of 1 requests the inclusion of raw OA unit reports as
+ * part of stream samples.
+ *
+ * This property is available in perf revision 1.
+ */
+ DRM_I915_PERF_PROP_SAMPLE_OA,
+
+ /**
+ * The value specifies which set of OA unit metrics should be
+ * configured, defining the contents of any OA unit reports.
+ *
+ * This property is available in perf revision 1.
+ */
+ DRM_I915_PERF_PROP_OA_METRICS_SET,
+
+ /**
+ * The value specifies the size and layout of OA unit reports.
+ *
+ * This property is available in perf revision 1.
+ */
+ DRM_I915_PERF_PROP_OA_FORMAT,
+
+ /**
+ * Specifying this property implicitly requests periodic OA unit
+ * sampling and (at least on Haswell) the sampling frequency is derived
+ * from this exponent as follows:
+ *
+ * 80ns * 2^(period_exponent + 1)
+ *
+ * This property is available in perf revision 1.
+ */
+ DRM_I915_PERF_PROP_OA_EXPONENT,
+
+ /**
+ * Specifying this property is only valid when specify a context to
+ * filter with DRM_I915_PERF_PROP_CTX_HANDLE. Specifying this property
+ * will hold preemption of the particular context we want to gather
+ * performance data about. The execbuf2 submissions must include a
+ * drm_i915_gem_execbuffer_ext_perf parameter for this to apply.
+ *
+ * This property is available in perf revision 3.
+ */
+ DRM_I915_PERF_PROP_HOLD_PREEMPTION,
+
+ /**
+ * Specifying this pins all contexts to the specified SSEU power
+ * configuration for the duration of the recording.
+ *
+ * This parameter's value is a pointer to a struct
+ * drm_i915_gem_context_param_sseu.
+ *
+ * This property is available in perf revision 4.
+ */
+ DRM_I915_PERF_PROP_GLOBAL_SSEU,
+
+ /**
+ * This optional parameter specifies the timer interval in nanoseconds
+ * at which the i915 driver will check the OA buffer for available data.
+ * Minimum allowed value is 100 microseconds. A default value is used by
+ * the driver if this parameter is not specified. Note that larger timer
+ * values will reduce cpu consumption during OA perf captures. However,
+ * excessively large values would potentially result in OA buffer
+ * overwrites as captures reach end of the OA buffer.
+ *
+ * This property is available in perf revision 5.
+ */
+ DRM_I915_PERF_PROP_POLL_OA_PERIOD,
+
+ /**
+ * Multiple engines may be mapped to the same OA unit. The OA unit is
+ * identified by class:instance of any engine mapped to it.
+ *
+ * This parameter specifies the engine class and must be passed along
+ * with DRM_I915_PERF_PROP_OA_ENGINE_INSTANCE.
+ *
+ * This property is available in perf revision 6.
+ */
+ DRM_I915_PERF_PROP_OA_ENGINE_CLASS,
+
+ /**
+ * This parameter specifies the engine instance and must be passed along
+ * with DRM_I915_PERF_PROP_OA_ENGINE_CLASS.
+ *
+ * This property is available in perf revision 6.
+ */
+ DRM_I915_PERF_PROP_OA_ENGINE_INSTANCE,
+
+ DRM_I915_PERF_PROP_MAX /* non-ABI */
+};
+
+struct drm_i915_perf_open_param {
+ __u32 flags;
+#define I915_PERF_FLAG_FD_CLOEXEC (1<<0)
+#define I915_PERF_FLAG_FD_NONBLOCK (1<<1)
+#define I915_PERF_FLAG_DISABLED (1<<2)
+
+ /** The number of u64 (id, value) pairs */
+ __u32 num_properties;
+
+ /**
+ * Pointer to array of u64 (id, value) pairs configuring the stream
+ * to open.
+ */
+ __u64 properties_ptr;
+};
+
+/*
+ * Enable data capture for a stream that was either opened in a disabled state
+ * via I915_PERF_FLAG_DISABLED or was later disabled via
+ * I915_PERF_IOCTL_DISABLE.
+ *
+ * It is intended to be cheaper to disable and enable a stream than it may be
+ * to close and re-open a stream with the same configuration.
+ *
+ * It's undefined whether any pending data for the stream will be lost.
+ *
+ * This ioctl is available in perf revision 1.
+ */
+#define I915_PERF_IOCTL_ENABLE _IO('i', 0x0)
+
+/*
+ * Disable data capture for a stream.
+ *
+ * It is an error to try and read a stream that is disabled.
+ *
+ * This ioctl is available in perf revision 1.
+ */
+#define I915_PERF_IOCTL_DISABLE _IO('i', 0x1)
+
+/*
+ * Change metrics_set captured by a stream.
+ *
+ * If the stream is bound to a specific context, the configuration change
+ * will performed inline with that context such that it takes effect before
+ * the next execbuf submission.
+ *
+ * Returns the previously bound metrics set id, or a negative error code.
+ *
+ * This ioctl is available in perf revision 2.
+ */
+#define I915_PERF_IOCTL_CONFIG _IO('i', 0x2)
+
+/*
+ * Common to all i915 perf records
+ */
+struct drm_i915_perf_record_header {
+ __u32 type;
+ __u16 pad;
+ __u16 size;
+};
+
+enum drm_i915_perf_record_type {
+
+ /**
+ * Samples are the work horse record type whose contents are extensible
+ * and defined when opening an i915 perf stream based on the given
+ * properties.
+ *
+ * Boolean properties following the naming convention
+ * DRM_I915_PERF_SAMPLE_xyz_PROP request the inclusion of 'xyz' data in
+ * every sample.
+ *
+ * The order of these sample properties given by userspace has no
+ * affect on the ordering of data within a sample. The order is
+ * documented here.
+ *
+ * struct {
+ * struct drm_i915_perf_record_header header;
+ *
+ * { u32 oa_report[]; } && DRM_I915_PERF_PROP_SAMPLE_OA
+ * };
+ */
+ DRM_I915_PERF_RECORD_SAMPLE = 1,
+
+ /*
+ * Indicates that one or more OA reports were not written by the
+ * hardware. This can happen for example if an MI_REPORT_PERF_COUNT
+ * command collides with periodic sampling - which would be more likely
+ * at higher sampling frequencies.
+ */
+ DRM_I915_PERF_RECORD_OA_REPORT_LOST = 2,
+
+ /**
+ * An error occurred that resulted in all pending OA reports being lost.
+ */
+ DRM_I915_PERF_RECORD_OA_BUFFER_LOST = 3,
+
+ DRM_I915_PERF_RECORD_MAX /* non-ABI */
+};
+
+/**
+ * struct drm_i915_perf_oa_config
+ *
+ * Structure to upload perf dynamic configuration into the kernel.
+ */
+struct drm_i915_perf_oa_config {
+ /**
+ * @uuid:
+ *
+ * String formatted like "%\08x-%\04x-%\04x-%\04x-%\012x"
+ */
+ char uuid[36];
+
+ /**
+ * @n_mux_regs:
+ *
+ * Number of mux regs in &mux_regs_ptr.
+ */
+ __u32 n_mux_regs;
+
+ /**
+ * @n_boolean_regs:
+ *
+ * Number of boolean regs in &boolean_regs_ptr.
+ */
+ __u32 n_boolean_regs;
+
+ /**
+ * @n_flex_regs:
+ *
+ * Number of flex regs in &flex_regs_ptr.
+ */
+ __u32 n_flex_regs;
+
+ /**
+ * @mux_regs_ptr:
+ *
+ * Pointer to tuples of u32 values (register address, value) for mux
+ * registers. Expected length of buffer is (2 * sizeof(u32) *
+ * &n_mux_regs).
+ */
+ __u64 mux_regs_ptr;
+
+ /**
+ * @boolean_regs_ptr:
+ *
+ * Pointer to tuples of u32 values (register address, value) for mux
+ * registers. Expected length of buffer is (2 * sizeof(u32) *
+ * &n_boolean_regs).
+ */
+ __u64 boolean_regs_ptr;
+
+ /**
+ * @flex_regs_ptr:
+ *
+ * Pointer to tuples of u32 values (register address, value) for mux
+ * registers. Expected length of buffer is (2 * sizeof(u32) *
+ * &n_flex_regs).
+ */
+ __u64 flex_regs_ptr;
+};
+
+/**
+ * struct drm_i915_query_item - An individual query for the kernel to process.
+ *
+ * The behaviour is determined by the @query_id. Note that exactly what
+ * @data_ptr is also depends on the specific @query_id.
+ */
+struct drm_i915_query_item {
+ /**
+ * @query_id:
+ *
+ * The id for this query. Currently accepted query IDs are:
+ * - %DRM_I915_QUERY_TOPOLOGY_INFO (see struct drm_i915_query_topology_info)
+ * - %DRM_I915_QUERY_ENGINE_INFO (see struct drm_i915_engine_info)
+ * - %DRM_I915_QUERY_PERF_CONFIG (see struct drm_i915_query_perf_config)
+ * - %DRM_I915_QUERY_MEMORY_REGIONS (see struct drm_i915_query_memory_regions)
+ * - %DRM_I915_QUERY_HWCONFIG_BLOB (see `GuC HWCONFIG blob uAPI`)
+ * - %DRM_I915_QUERY_GEOMETRY_SUBSLICES (see struct drm_i915_query_topology_info)
+ */
+ __u64 query_id;
+#define DRM_I915_QUERY_TOPOLOGY_INFO 1
+#define DRM_I915_QUERY_ENGINE_INFO 2
+#define DRM_I915_QUERY_PERF_CONFIG 3
+#define DRM_I915_QUERY_MEMORY_REGIONS 4
+#define DRM_I915_QUERY_HWCONFIG_BLOB 5
+#define DRM_I915_QUERY_GEOMETRY_SUBSLICES 6
+/* Must be kept compact -- no holes and well documented */
+
+ /**
+ * @length:
+ *
+ * When set to zero by userspace, this is filled with the size of the
+ * data to be written at the @data_ptr pointer. The kernel sets this
+ * value to a negative value to signal an error on a particular query
+ * item.
+ */
+ __s32 length;
+
+ /**
+ * @flags:
+ *
+ * When &query_id == %DRM_I915_QUERY_TOPOLOGY_INFO, must be 0.
+ *
+ * When &query_id == %DRM_I915_QUERY_PERF_CONFIG, must be one of the
+ * following:
+ *
+ * - %DRM_I915_QUERY_PERF_CONFIG_LIST
+ * - %DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_UUID
+ * - %DRM_I915_QUERY_PERF_CONFIG_FOR_UUID
+ *
+ * When &query_id == %DRM_I915_QUERY_GEOMETRY_SUBSLICES must contain
+ * a struct i915_engine_class_instance that references a render engine.
+ */
+ __u32 flags;
+#define DRM_I915_QUERY_PERF_CONFIG_LIST 1
+#define DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_UUID 2
+#define DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_ID 3
+
+ /**
+ * @data_ptr:
+ *
+ * Data will be written at the location pointed by @data_ptr when the
+ * value of @length matches the length of the data to be written by the
+ * kernel.
+ */
+ __u64 data_ptr;
+};
+
+/**
+ * struct drm_i915_query - Supply an array of struct drm_i915_query_item for the
+ * kernel to fill out.
+ *
+ * Note that this is generally a two step process for each struct
+ * drm_i915_query_item in the array:
+ *
+ * 1. Call the DRM_IOCTL_I915_QUERY, giving it our array of struct
+ * drm_i915_query_item, with &drm_i915_query_item.length set to zero. The
+ * kernel will then fill in the size, in bytes, which tells userspace how
+ * memory it needs to allocate for the blob(say for an array of properties).
+ *
+ * 2. Next we call DRM_IOCTL_I915_QUERY again, this time with the
+ * &drm_i915_query_item.data_ptr equal to our newly allocated blob. Note that
+ * the &drm_i915_query_item.length should still be the same as what the
+ * kernel previously set. At this point the kernel can fill in the blob.
+ *
+ * Note that for some query items it can make sense for userspace to just pass
+ * in a buffer/blob equal to or larger than the required size. In this case only
+ * a single ioctl call is needed. For some smaller query items this can work
+ * quite well.
+ *
+ */
+struct drm_i915_query {
+ /** @num_items: The number of elements in the @items_ptr array */
+ __u32 num_items;
+
+ /**
+ * @flags: Unused for now. Must be cleared to zero.
+ */
+ __u32 flags;
+
+ /**
+ * @items_ptr:
+ *
+ * Pointer to an array of struct drm_i915_query_item. The number of
+ * array elements is @num_items.
+ */
+ __u64 items_ptr;
+};
+
+/**
+ * struct drm_i915_query_topology_info
+ *
+ * Describes slice/subslice/EU information queried by
+ * %DRM_I915_QUERY_TOPOLOGY_INFO
+ */
+struct drm_i915_query_topology_info {
+ /**
+ * @flags:
+ *
+ * Unused for now. Must be cleared to zero.
+ */
+ __u16 flags;
+
+ /**
+ * @max_slices:
+ *
+ * The number of bits used to express the slice mask.
+ */
+ __u16 max_slices;
+
+ /**
+ * @max_subslices:
+ *
+ * The number of bits used to express the subslice mask.
+ */
+ __u16 max_subslices;
+
+ /**
+ * @max_eus_per_subslice:
+ *
+ * The number of bits in the EU mask that correspond to a single
+ * subslice's EUs.
+ */
+ __u16 max_eus_per_subslice;
+
+ /**
+ * @subslice_offset:
+ *
+ * Offset in data[] at which the subslice masks are stored.
+ */
+ __u16 subslice_offset;
+
+ /**
+ * @subslice_stride:
+ *
+ * Stride at which each of the subslice masks for each slice are
+ * stored.
+ */
+ __u16 subslice_stride;
+
+ /**
+ * @eu_offset:
+ *
+ * Offset in data[] at which the EU masks are stored.
+ */
+ __u16 eu_offset;
+
+ /**
+ * @eu_stride:
+ *
+ * Stride at which each of the EU masks for each subslice are stored.
+ */
+ __u16 eu_stride;
+
+ /**
+ * @data:
+ *
+ * Contains 3 pieces of information :
+ *
+ * - The slice mask with one bit per slice telling whether a slice is
+ * available. The availability of slice X can be queried with the
+ * following formula :
+ *
+ * .. code:: c
+ *
+ * (data[X / 8] >> (X % 8)) & 1
+ *
+ * Starting with Xe_HP platforms, Intel hardware no longer has
+ * traditional slices so i915 will always report a single slice
+ * (hardcoded slicemask = 0x1) which contains all of the platform's
+ * subslices. I.e., the mask here does not reflect any of the newer
+ * hardware concepts such as "gslices" or "cslices" since userspace
+ * is capable of inferring those from the subslice mask.
+ *
+ * - The subslice mask for each slice with one bit per subslice telling
+ * whether a subslice is available. Starting with Gen12 we use the
+ * term "subslice" to refer to what the hardware documentation
+ * describes as a "dual-subslices." The availability of subslice Y
+ * in slice X can be queried with the following formula :
+ *
+ * .. code:: c
+ *
+ * (data[subslice_offset + X * subslice_stride + Y / 8] >> (Y % 8)) & 1
+ *
+ * - The EU mask for each subslice in each slice, with one bit per EU
+ * telling whether an EU is available. The availability of EU Z in
+ * subslice Y in slice X can be queried with the following formula :
+ *
+ * .. code:: c
+ *
+ * (data[eu_offset +
+ * (X * max_subslices + Y) * eu_stride +
+ * Z / 8
+ * ] >> (Z % 8)) & 1
+ */
+ __u8 data[];
+};
+
+/**
+ * DOC: Engine Discovery uAPI
+ *
+ * Engine discovery uAPI is a way of enumerating physical engines present in a
+ * GPU associated with an open i915 DRM file descriptor. This supersedes the old
+ * way of using `DRM_IOCTL_I915_GETPARAM` and engine identifiers like
+ * `I915_PARAM_HAS_BLT`.
+ *
+ * The need for this interface came starting with Icelake and newer GPUs, which
+ * started to establish a pattern of having multiple engines of a same class,
+ * where not all instances were always completely functionally equivalent.
+ *
+ * Entry point for this uapi is `DRM_IOCTL_I915_QUERY` with the
+ * `DRM_I915_QUERY_ENGINE_INFO` as the queried item id.
+ *
+ * Example for getting the list of engines:
+ *
+ * .. code-block:: C
+ *
+ * struct drm_i915_query_engine_info *info;
+ * struct drm_i915_query_item item = {
+ * .query_id = DRM_I915_QUERY_ENGINE_INFO;
+ * };
+ * struct drm_i915_query query = {
+ * .num_items = 1,
+ * .items_ptr = (uintptr_t)&item,
+ * };
+ * int err, i;
+ *
+ * // First query the size of the blob we need, this needs to be large
+ * // enough to hold our array of engines. The kernel will fill out the
+ * // item.length for us, which is the number of bytes we need.
+ * //
+ * // Alternatively a large buffer can be allocated straight away enabling
+ * // querying in one pass, in which case item.length should contain the
+ * // length of the provided buffer.
+ * err = ioctl(fd, DRM_IOCTL_I915_QUERY, &query);
+ * if (err) ...
+ *
+ * info = calloc(1, item.length);
+ * // Now that we allocated the required number of bytes, we call the ioctl
+ * // again, this time with the data_ptr pointing to our newly allocated
+ * // blob, which the kernel can then populate with info on all engines.
+ * item.data_ptr = (uintptr_t)&info,
+ *
+ * err = ioctl(fd, DRM_IOCTL_I915_QUERY, &query);
+ * if (err) ...
+ *
+ * // We can now access each engine in the array
+ * for (i = 0; i < info->num_engines; i++) {
+ * struct drm_i915_engine_info einfo = info->engines[i];
+ * u16 class = einfo.engine.class;
+ * u16 instance = einfo.engine.instance;
+ * ....
+ * }
+ *
+ * free(info);
+ *
+ * Each of the enumerated engines, apart from being defined by its class and
+ * instance (see `struct i915_engine_class_instance`), also can have flags and
+ * capabilities defined as documented in i915_drm.h.
+ *
+ * For instance video engines which support HEVC encoding will have the
+ * `I915_VIDEO_CLASS_CAPABILITY_HEVC` capability bit set.
+ *
+ * Engine discovery only fully comes to its own when combined with the new way
+ * of addressing engines when submitting batch buffers using contexts with
+ * engine maps configured.
+ */
+
+/**
+ * struct drm_i915_engine_info
+ *
+ * Describes one engine and it's capabilities as known to the driver.
+ */
+struct drm_i915_engine_info {
+ /** @engine: Engine class and instance. */
+ struct i915_engine_class_instance engine;
+
+ /** @rsvd0: Reserved field. */
+ __u32 rsvd0;
+
+ /** @flags: Engine flags. */
+ __u64 flags;
+#define I915_ENGINE_INFO_HAS_LOGICAL_INSTANCE (1 << 0)
+
+ /** @capabilities: Capabilities of this engine. */
+ __u64 capabilities;
+#define I915_VIDEO_CLASS_CAPABILITY_HEVC (1 << 0)
+#define I915_VIDEO_AND_ENHANCE_CLASS_CAPABILITY_SFC (1 << 1)
+
+ /** @logical_instance: Logical instance of engine */
+ __u16 logical_instance;
+
+ /** @rsvd1: Reserved fields. */
+ __u16 rsvd1[3];
+ /** @rsvd2: Reserved fields. */
+ __u64 rsvd2[3];
+};
+
+/**
+ * struct drm_i915_query_engine_info
+ *
+ * Engine info query enumerates all engines known to the driver by filling in
+ * an array of struct drm_i915_engine_info structures.
+ */
+struct drm_i915_query_engine_info {
+ /** @num_engines: Number of struct drm_i915_engine_info structs following. */
+ __u32 num_engines;
+
+ /** @rsvd: MBZ */
+ __u32 rsvd[3];
+
+ /** @engines: Marker for drm_i915_engine_info structures. */
+ struct drm_i915_engine_info engines[];
+};
+
+/**
+ * struct drm_i915_query_perf_config
+ *
+ * Data written by the kernel with query %DRM_I915_QUERY_PERF_CONFIG and
+ * %DRM_I915_QUERY_GEOMETRY_SUBSLICES.
+ */
+struct drm_i915_query_perf_config {
+ union {
+ /**
+ * @n_configs:
+ *
+ * When &drm_i915_query_item.flags ==
+ * %DRM_I915_QUERY_PERF_CONFIG_LIST, i915 sets this fields to
+ * the number of configurations available.
+ */
+ __u64 n_configs;
+
+ /**
+ * @config:
+ *
+ * When &drm_i915_query_item.flags ==
+ * %DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_ID, i915 will use the
+ * value in this field as configuration identifier to decide
+ * what data to write into config_ptr.
+ */
+ __u64 config;
+
+ /**
+ * @uuid:
+ *
+ * When &drm_i915_query_item.flags ==
+ * %DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_UUID, i915 will use the
+ * value in this field as configuration identifier to decide
+ * what data to write into config_ptr.
+ *
+ * String formatted like "%08x-%04x-%04x-%04x-%012x"
+ */
+ char uuid[36];
+ };
+
+ /**
+ * @flags:
+ *
+ * Unused for now. Must be cleared to zero.
+ */
+ __u32 flags;
+
+ /**
+ * @data:
+ *
+ * When &drm_i915_query_item.flags == %DRM_I915_QUERY_PERF_CONFIG_LIST,
+ * i915 will write an array of __u64 of configuration identifiers.
+ *
+ * When &drm_i915_query_item.flags == %DRM_I915_QUERY_PERF_CONFIG_DATA,
+ * i915 will write a struct drm_i915_perf_oa_config. If the following
+ * fields of struct drm_i915_perf_oa_config are not set to 0, i915 will
+ * write into the associated pointers the values of submitted when the
+ * configuration was created :
+ *
+ * - &drm_i915_perf_oa_config.n_mux_regs
+ * - &drm_i915_perf_oa_config.n_boolean_regs
+ * - &drm_i915_perf_oa_config.n_flex_regs
+ */
+ __u8 data[];
+};
+
+/**
+ * enum drm_i915_gem_memory_class - Supported memory classes
+ */
+enum drm_i915_gem_memory_class {
+ /** @I915_MEMORY_CLASS_SYSTEM: System memory */
+ I915_MEMORY_CLASS_SYSTEM = 0,
+ /** @I915_MEMORY_CLASS_DEVICE: Device local-memory */
+ I915_MEMORY_CLASS_DEVICE,
+};
+
+/**
+ * struct drm_i915_gem_memory_class_instance - Identify particular memory region
+ */
+struct drm_i915_gem_memory_class_instance {
+ /** @memory_class: See enum drm_i915_gem_memory_class */
+ __u16 memory_class;
+
+ /** @memory_instance: Which instance */
+ __u16 memory_instance;
+};
+
+/**
+ * struct drm_i915_memory_region_info - Describes one region as known to the
+ * driver.
+ *
+ * Note this is using both struct drm_i915_query_item and struct drm_i915_query.
+ * For this new query we are adding the new query id DRM_I915_QUERY_MEMORY_REGIONS
+ * at &drm_i915_query_item.query_id.
+ */
+struct drm_i915_memory_region_info {
+ /** @region: The class:instance pair encoding */
+ struct drm_i915_gem_memory_class_instance region;
+
+ /** @rsvd0: MBZ */
+ __u32 rsvd0;
+
+ /**
+ * @probed_size: Memory probed by the driver
+ *
+ * Note that it should not be possible to ever encounter a zero value
+ * here, also note that no current region type will ever return -1 here.
+ * Although for future region types, this might be a possibility. The
+ * same applies to the other size fields.
+ */
+ __u64 probed_size;
+
+ /**
+ * @unallocated_size: Estimate of memory remaining
+ *
+ * Requires CAP_PERFMON or CAP_SYS_ADMIN to get reliable accounting.
+ * Without this (or if this is an older kernel) the value here will
+ * always equal the @probed_size. Note this is only currently tracked
+ * for I915_MEMORY_CLASS_DEVICE regions (for other types the value here
+ * will always equal the @probed_size).
+ */
+ __u64 unallocated_size;
+
+ union {
+ /** @rsvd1: MBZ */
+ __u64 rsvd1[8];
+ struct {
+ /**
+ * @probed_cpu_visible_size: Memory probed by the driver
+ * that is CPU accessible.
+ *
+ * This will be always be <= @probed_size, and the
+ * remainder (if there is any) will not be CPU
+ * accessible.
+ *
+ * On systems without small BAR, the @probed_size will
+ * always equal the @probed_cpu_visible_size, since all
+ * of it will be CPU accessible.
+ *
+ * Note this is only tracked for
+ * I915_MEMORY_CLASS_DEVICE regions (for other types the
+ * value here will always equal the @probed_size).
+ *
+ * Note that if the value returned here is zero, then
+ * this must be an old kernel which lacks the relevant
+ * small-bar uAPI support (including
+ * I915_GEM_CREATE_EXT_FLAG_NEEDS_CPU_ACCESS), but on
+ * such systems we should never actually end up with a
+ * small BAR configuration, assuming we are able to load
+ * the kernel module. Hence it should be safe to treat
+ * this the same as when @probed_cpu_visible_size ==
+ * @probed_size.
+ */
+ __u64 probed_cpu_visible_size;
+
+ /**
+ * @unallocated_cpu_visible_size: Estimate of CPU
+ * visible memory remaining.
+ *
+ * Note this is only tracked for
+ * I915_MEMORY_CLASS_DEVICE regions (for other types the
+ * value here will always equal the
+ * @probed_cpu_visible_size).
+ *
+ * Requires CAP_PERFMON or CAP_SYS_ADMIN to get reliable
+ * accounting. Without this the value here will always
+ * equal the @probed_cpu_visible_size. Note this is only
+ * currently tracked for I915_MEMORY_CLASS_DEVICE
+ * regions (for other types the value here will also
+ * always equal the @probed_cpu_visible_size).
+ *
+ * If this is an older kernel the value here will be
+ * zero, see also @probed_cpu_visible_size.
+ */
+ __u64 unallocated_cpu_visible_size;
+ };
+ };
+};
+
+/**
+ * struct drm_i915_query_memory_regions
+ *
+ * The region info query enumerates all regions known to the driver by filling
+ * in an array of struct drm_i915_memory_region_info structures.
+ *
+ * Example for getting the list of supported regions:
+ *
+ * .. code-block:: C
+ *
+ * struct drm_i915_query_memory_regions *info;
+ * struct drm_i915_query_item item = {
+ * .query_id = DRM_I915_QUERY_MEMORY_REGIONS;
+ * };
+ * struct drm_i915_query query = {
+ * .num_items = 1,
+ * .items_ptr = (uintptr_t)&item,
+ * };
+ * int err, i;
+ *
+ * // First query the size of the blob we need, this needs to be large
+ * // enough to hold our array of regions. The kernel will fill out the
+ * // item.length for us, which is the number of bytes we need.
+ * err = ioctl(fd, DRM_IOCTL_I915_QUERY, &query);
+ * if (err) ...
+ *
+ * info = calloc(1, item.length);
+ * // Now that we allocated the required number of bytes, we call the ioctl
+ * // again, this time with the data_ptr pointing to our newly allocated
+ * // blob, which the kernel can then populate with the all the region info.
+ * item.data_ptr = (uintptr_t)&info,
+ *
+ * err = ioctl(fd, DRM_IOCTL_I915_QUERY, &query);
+ * if (err) ...
+ *
+ * // We can now access each region in the array
+ * for (i = 0; i < info->num_regions; i++) {
+ * struct drm_i915_memory_region_info mr = info->regions[i];
+ * u16 class = mr.region.class;
+ * u16 instance = mr.region.instance;
+ *
+ * ....
+ * }
+ *
+ * free(info);
+ */
+struct drm_i915_query_memory_regions {
+ /** @num_regions: Number of supported regions */
+ __u32 num_regions;
+
+ /** @rsvd: MBZ */
+ __u32 rsvd[3];
+
+ /** @regions: Info about each supported region */
+ struct drm_i915_memory_region_info regions[];
+};
+
+/**
+ * DOC: GuC HWCONFIG blob uAPI
+ *
+ * The GuC produces a blob with information about the current device.
+ * i915 reads this blob from GuC and makes it available via this uAPI.
+ *
+ * The format and meaning of the blob content are documented in the
+ * Programmer's Reference Manual.
+ */
+
+/**
+ * struct drm_i915_gem_create_ext - Existing gem_create behaviour, with added
+ * extension support using struct i915_user_extension.
+ *
+ * Note that new buffer flags should be added here, at least for the stuff that
+ * is immutable. Previously we would have two ioctls, one to create the object
+ * with gem_create, and another to apply various parameters, however this
+ * creates some ambiguity for the params which are considered immutable. Also in
+ * general we're phasing out the various SET/GET ioctls.
+ */
+struct drm_i915_gem_create_ext {
+ /**
+ * @size: Requested size for the object.
+ *
+ * The (page-aligned) allocated size for the object will be returned.
+ *
+ * On platforms like DG2/ATS the kernel will always use 64K or larger
+ * pages for I915_MEMORY_CLASS_DEVICE. The kernel also requires a
+ * minimum of 64K GTT alignment for such objects.
+ *
+ * NOTE: Previously the ABI here required a minimum GTT alignment of 2M
+ * on DG2/ATS, due to how the hardware implemented 64K GTT page support,
+ * where we had the following complications:
+ *
+ * 1) The entire PDE (which covers a 2MB virtual address range), must
+ * contain only 64K PTEs, i.e mixing 4K and 64K PTEs in the same
+ * PDE is forbidden by the hardware.
+ *
+ * 2) We still need to support 4K PTEs for I915_MEMORY_CLASS_SYSTEM
+ * objects.
+ *
+ * However on actual production HW this was completely changed to now
+ * allow setting a TLB hint at the PTE level (see PS64), which is a lot
+ * more flexible than the above. With this the 2M restriction was
+ * dropped where we now only require 64K.
+ */
+ __u64 size;
+
+ /**
+ * @handle: Returned handle for the object.
+ *
+ * Object handles are nonzero.
+ */
+ __u32 handle;
+
+ /**
+ * @flags: Optional flags.
+ *
+ * Supported values:
+ *
+ * I915_GEM_CREATE_EXT_FLAG_NEEDS_CPU_ACCESS - Signal to the kernel that
+ * the object will need to be accessed via the CPU.
+ *
+ * Only valid when placing objects in I915_MEMORY_CLASS_DEVICE, and only
+ * strictly required on configurations where some subset of the device
+ * memory is directly visible/mappable through the CPU (which we also
+ * call small BAR), like on some DG2+ systems. Note that this is quite
+ * undesirable, but due to various factors like the client CPU, BIOS etc
+ * it's something we can expect to see in the wild. See
+ * &drm_i915_memory_region_info.probed_cpu_visible_size for how to
+ * determine if this system applies.
+ *
+ * Note that one of the placements MUST be I915_MEMORY_CLASS_SYSTEM, to
+ * ensure the kernel can always spill the allocation to system memory,
+ * if the object can't be allocated in the mappable part of
+ * I915_MEMORY_CLASS_DEVICE.
+ *
+ * Also note that since the kernel only supports flat-CCS on objects
+ * that can *only* be placed in I915_MEMORY_CLASS_DEVICE, we therefore
+ * don't support I915_GEM_CREATE_EXT_FLAG_NEEDS_CPU_ACCESS together with
+ * flat-CCS.
+ *
+ * Without this hint, the kernel will assume that non-mappable
+ * I915_MEMORY_CLASS_DEVICE is preferred for this object. Note that the
+ * kernel can still migrate the object to the mappable part, as a last
+ * resort, if userspace ever CPU faults this object, but this might be
+ * expensive, and so ideally should be avoided.
+ *
+ * On older kernels which lack the relevant small-bar uAPI support (see
+ * also &drm_i915_memory_region_info.probed_cpu_visible_size),
+ * usage of the flag will result in an error, but it should NEVER be
+ * possible to end up with a small BAR configuration, assuming we can
+ * also successfully load the i915 kernel module. In such cases the
+ * entire I915_MEMORY_CLASS_DEVICE region will be CPU accessible, and as
+ * such there are zero restrictions on where the object can be placed.
+ */
+#define I915_GEM_CREATE_EXT_FLAG_NEEDS_CPU_ACCESS (1 << 0)
+ __u32 flags;
+
+ /**
+ * @extensions: The chain of extensions to apply to this object.
+ *
+ * This will be useful in the future when we need to support several
+ * different extensions, and we need to apply more than one when
+ * creating the object. See struct i915_user_extension.
+ *
+ * If we don't supply any extensions then we get the same old gem_create
+ * behaviour.
+ *
+ * For I915_GEM_CREATE_EXT_MEMORY_REGIONS usage see
+ * struct drm_i915_gem_create_ext_memory_regions.
+ *
+ * For I915_GEM_CREATE_EXT_PROTECTED_CONTENT usage see
+ * struct drm_i915_gem_create_ext_protected_content.
+ *
+ * For I915_GEM_CREATE_EXT_SET_PAT usage see
+ * struct drm_i915_gem_create_ext_set_pat.
+ */
+#define I915_GEM_CREATE_EXT_MEMORY_REGIONS 0
+#define I915_GEM_CREATE_EXT_PROTECTED_CONTENT 1
+#define I915_GEM_CREATE_EXT_SET_PAT 2
+ __u64 extensions;
+};
+
+/**
+ * struct drm_i915_gem_create_ext_memory_regions - The
+ * I915_GEM_CREATE_EXT_MEMORY_REGIONS extension.
+ *
+ * Set the object with the desired set of placements/regions in priority
+ * order. Each entry must be unique and supported by the device.
+ *
+ * This is provided as an array of struct drm_i915_gem_memory_class_instance, or
+ * an equivalent layout of class:instance pair encodings. See struct
+ * drm_i915_query_memory_regions and DRM_I915_QUERY_MEMORY_REGIONS for how to
+ * query the supported regions for a device.
+ *
+ * As an example, on discrete devices, if we wish to set the placement as
+ * device local-memory we can do something like:
+ *
+ * .. code-block:: C
+ *
+ * struct drm_i915_gem_memory_class_instance region_lmem = {
+ * .memory_class = I915_MEMORY_CLASS_DEVICE,
+ * .memory_instance = 0,
+ * };
+ * struct drm_i915_gem_create_ext_memory_regions regions = {
+ * .base = { .name = I915_GEM_CREATE_EXT_MEMORY_REGIONS },
+ * .regions = (uintptr_t)&region_lmem,
+ * .num_regions = 1,
+ * };
+ * struct drm_i915_gem_create_ext create_ext = {
+ * .size = 16 * PAGE_SIZE,
+ * .extensions = (uintptr_t)&regions,
+ * };
+ *
+ * int err = ioctl(fd, DRM_IOCTL_I915_GEM_CREATE_EXT, &create_ext);
+ * if (err) ...
+ *
+ * At which point we get the object handle in &drm_i915_gem_create_ext.handle,
+ * along with the final object size in &drm_i915_gem_create_ext.size, which
+ * should account for any rounding up, if required.
+ *
+ * Note that userspace has no means of knowing the current backing region
+ * for objects where @num_regions is larger than one. The kernel will only
+ * ensure that the priority order of the @regions array is honoured, either
+ * when initially placing the object, or when moving memory around due to
+ * memory pressure
+ *
+ * On Flat-CCS capable HW, compression is supported for the objects residing
+ * in I915_MEMORY_CLASS_DEVICE. When such objects (compressed) have other
+ * memory class in @regions and migrated (by i915, due to memory
+ * constraints) to the non I915_MEMORY_CLASS_DEVICE region, then i915 needs to
+ * decompress the content. But i915 doesn't have the required information to
+ * decompress the userspace compressed objects.
+ *
+ * So i915 supports Flat-CCS, on the objects which can reside only on
+ * I915_MEMORY_CLASS_DEVICE regions.
+ */
+struct drm_i915_gem_create_ext_memory_regions {
+ /** @base: Extension link. See struct i915_user_extension. */
+ struct i915_user_extension base;
+
+ /** @pad: MBZ */
+ __u32 pad;
+ /** @num_regions: Number of elements in the @regions array. */
+ __u32 num_regions;
+ /**
+ * @regions: The regions/placements array.
+ *
+ * An array of struct drm_i915_gem_memory_class_instance.
+ */
+ __u64 regions;
+};
+
+/**
+ * struct drm_i915_gem_create_ext_protected_content - The
+ * I915_OBJECT_PARAM_PROTECTED_CONTENT extension.
+ *
+ * If this extension is provided, buffer contents are expected to be protected
+ * by PXP encryption and require decryption for scan out and processing. This
+ * is only possible on platforms that have PXP enabled, on all other scenarios
+ * using this extension will cause the ioctl to fail and return -ENODEV. The
+ * flags parameter is reserved for future expansion and must currently be set
+ * to zero.
+ *
+ * The buffer contents are considered invalid after a PXP session teardown.
+ *
+ * The encryption is guaranteed to be processed correctly only if the object
+ * is submitted with a context created using the
+ * I915_CONTEXT_PARAM_PROTECTED_CONTENT flag. This will also enable extra checks
+ * at submission time on the validity of the objects involved.
+ *
+ * Below is an example on how to create a protected object:
+ *
+ * .. code-block:: C
+ *
+ * struct drm_i915_gem_create_ext_protected_content protected_ext = {
+ * .base = { .name = I915_GEM_CREATE_EXT_PROTECTED_CONTENT },
+ * .flags = 0,
+ * };
+ * struct drm_i915_gem_create_ext create_ext = {
+ * .size = PAGE_SIZE,
+ * .extensions = (uintptr_t)&protected_ext,
+ * };
+ *
+ * int err = ioctl(fd, DRM_IOCTL_I915_GEM_CREATE_EXT, &create_ext);
+ * if (err) ...
+ */
+struct drm_i915_gem_create_ext_protected_content {
+ /** @base: Extension link. See struct i915_user_extension. */
+ struct i915_user_extension base;
+ /** @flags: reserved for future usage, currently MBZ */
+ __u32 flags;
+};
+
+/**
+ * struct drm_i915_gem_create_ext_set_pat - The
+ * I915_GEM_CREATE_EXT_SET_PAT extension.
+ *
+ * If this extension is provided, the specified caching policy (PAT index) is
+ * applied to the buffer object.
+ *
+ * Below is an example on how to create an object with specific caching policy:
+ *
+ * .. code-block:: C
+ *
+ * struct drm_i915_gem_create_ext_set_pat set_pat_ext = {
+ * .base = { .name = I915_GEM_CREATE_EXT_SET_PAT },
+ * .pat_index = 0,
+ * };
+ * struct drm_i915_gem_create_ext create_ext = {
+ * .size = PAGE_SIZE,
+ * .extensions = (uintptr_t)&set_pat_ext,
+ * };
+ *
+ * int err = ioctl(fd, DRM_IOCTL_I915_GEM_CREATE_EXT, &create_ext);
+ * if (err) ...
+ */
+struct drm_i915_gem_create_ext_set_pat {
+ /** @base: Extension link. See struct i915_user_extension. */
+ struct i915_user_extension base;
+ /**
+ * @pat_index: PAT index to be set
+ * PAT index is a bit field in Page Table Entry to control caching
+ * behaviors for GPU accesses. The definition of PAT index is
+ * platform dependent and can be found in hardware specifications,
+ */
+ __u32 pat_index;
+ /** @rsvd: reserved for future use */
+ __u32 rsvd;
+};
+
+/* ID of the protected content session managed by i915 when PXP is active */
+#define I915_PROTECTED_CONTENT_DEFAULT_SESSION 0xf
+
+#if defined(__cplusplus)
+}
+#endif
+
+#endif /* _UAPI_I915_DRM_H_ */
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
new file mode 100644
index 0000000000..ada7acb91a
--- /dev/null
+++ b/tools/include/uapi/linux/bpf.h
@@ -0,0 +1,7319 @@
+/* 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_JMP32 0x06 /* jmp mode in word width */
+#define BPF_ALU64 0x07 /* alu mode in double word width */
+
+/* ld/ldx fields */
+#define BPF_DW 0x18 /* double word (64-bit) */
+#define BPF_MEMSX 0x80 /* load with sign extension */
+#define BPF_ATOMIC 0xc0 /* atomic memory ops - op type in immediate */
+#define BPF_XADD 0xc0 /* exclusive add - legacy name */
+
+/* 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 */
+
+/* atomic op type fields (stored in immediate) */
+#define BPF_FETCH 0x01 /* not an opcode on its own, used to build others */
+#define BPF_XCHG (0xe0 | BPF_FETCH) /* atomic exchange */
+#define BPF_CMPXCHG (0xf0 | BPF_FETCH) /* atomic compare-and-write */
+
+/* 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 (enum bpf_attach_type) */
+};
+
+enum bpf_cgroup_iter_order {
+ BPF_CGROUP_ITER_ORDER_UNSPEC = 0,
+ BPF_CGROUP_ITER_SELF_ONLY, /* process only a single object. */
+ BPF_CGROUP_ITER_DESCENDANTS_PRE, /* walk descendants in pre-order. */
+ BPF_CGROUP_ITER_DESCENDANTS_POST, /* walk descendants in post-order. */
+ BPF_CGROUP_ITER_ANCESTORS_UP, /* walk ancestors upward. */
+};
+
+union bpf_iter_link_info {
+ struct {
+ __u32 map_fd;
+ } map;
+ struct {
+ enum bpf_cgroup_iter_order order;
+
+ /* At most one of cgroup_fd and cgroup_id can be non-zero. If
+ * both are zero, the walk starts from the default cgroup v2
+ * root. For walking v1 hierarchy, one should always explicitly
+ * specify cgroup_fd.
+ */
+ __u32 cgroup_fd;
+ __u64 cgroup_id;
+ } cgroup;
+ /* Parameters of task iterators. */
+ struct {
+ __u32 tid;
+ __u32 pid;
+ __u32 pid_fd;
+ } task;
+};
+
+/* BPF syscall commands, see bpf(2) man-page for more details. */
+/**
+ * DOC: eBPF Syscall Preamble
+ *
+ * The operation to be performed by the **bpf**\ () system call is determined
+ * by the *cmd* argument. Each operation takes an accompanying argument,
+ * provided via *attr*, which is a pointer to a union of type *bpf_attr* (see
+ * below). The size argument is the size of the union pointed to by *attr*.
+ */
+/**
+ * DOC: eBPF Syscall Commands
+ *
+ * BPF_MAP_CREATE
+ * Description
+ * Create a map and return a file descriptor that refers to the
+ * map. The close-on-exec file descriptor flag (see **fcntl**\ (2))
+ * is automatically enabled for the new file descriptor.
+ *
+ * Applying **close**\ (2) to the file descriptor returned by
+ * **BPF_MAP_CREATE** will delete the map (but see NOTES).
+ *
+ * Return
+ * A new file descriptor (a nonnegative integer), or -1 if an
+ * error occurred (in which case, *errno* is set appropriately).
+ *
+ * BPF_MAP_LOOKUP_ELEM
+ * Description
+ * Look up an element with a given *key* in the map referred to
+ * by the file descriptor *map_fd*.
+ *
+ * The *flags* argument may be specified as one of the
+ * following:
+ *
+ * **BPF_F_LOCK**
+ * Look up the value of a spin-locked map without
+ * returning the lock. This must be specified if the
+ * elements contain a spinlock.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * BPF_MAP_UPDATE_ELEM
+ * Description
+ * Create or update an element (key/value pair) in a specified map.
+ *
+ * The *flags* argument should be specified as one of the
+ * following:
+ *
+ * **BPF_ANY**
+ * Create a new element or update an existing element.
+ * **BPF_NOEXIST**
+ * Create a new element only if it did not exist.
+ * **BPF_EXIST**
+ * Update an existing element.
+ * **BPF_F_LOCK**
+ * Update a spin_lock-ed map element.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * May set *errno* to **EINVAL**, **EPERM**, **ENOMEM**,
+ * **E2BIG**, **EEXIST**, or **ENOENT**.
+ *
+ * **E2BIG**
+ * The number of elements in the map reached the
+ * *max_entries* limit specified at map creation time.
+ * **EEXIST**
+ * If *flags* specifies **BPF_NOEXIST** and the element
+ * with *key* already exists in the map.
+ * **ENOENT**
+ * If *flags* specifies **BPF_EXIST** and the element with
+ * *key* does not exist in the map.
+ *
+ * BPF_MAP_DELETE_ELEM
+ * Description
+ * Look up and delete an element by key in a specified map.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * BPF_MAP_GET_NEXT_KEY
+ * Description
+ * Look up an element by key in a specified map and return the key
+ * of the next element. Can be used to iterate over all elements
+ * in the map.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * The following cases can be used to iterate over all elements of
+ * the map:
+ *
+ * * If *key* is not found, the operation returns zero and sets
+ * the *next_key* pointer to the key of the first element.
+ * * If *key* is found, the operation returns zero and sets the
+ * *next_key* pointer to the key of the next element.
+ * * If *key* is the last element, returns -1 and *errno* is set
+ * to **ENOENT**.
+ *
+ * May set *errno* to **ENOMEM**, **EFAULT**, **EPERM**, or
+ * **EINVAL** on error.
+ *
+ * BPF_PROG_LOAD
+ * Description
+ * Verify and load an eBPF program, returning a new file
+ * descriptor associated with the program.
+ *
+ * Applying **close**\ (2) to the file descriptor returned by
+ * **BPF_PROG_LOAD** will unload the eBPF program (but see NOTES).
+ *
+ * The close-on-exec file descriptor flag (see **fcntl**\ (2)) is
+ * automatically enabled for the new file descriptor.
+ *
+ * Return
+ * A new file descriptor (a nonnegative integer), or -1 if an
+ * error occurred (in which case, *errno* is set appropriately).
+ *
+ * BPF_OBJ_PIN
+ * Description
+ * Pin an eBPF program or map referred by the specified *bpf_fd*
+ * to the provided *pathname* on the filesystem.
+ *
+ * The *pathname* argument must not contain a dot (".").
+ *
+ * On success, *pathname* retains a reference to the eBPF object,
+ * preventing deallocation of the object when the original
+ * *bpf_fd* is closed. This allow the eBPF object to live beyond
+ * **close**\ (\ *bpf_fd*\ ), and hence the lifetime of the parent
+ * process.
+ *
+ * Applying **unlink**\ (2) or similar calls to the *pathname*
+ * unpins the object from the filesystem, removing the reference.
+ * If no other file descriptors or filesystem nodes refer to the
+ * same object, it will be deallocated (see NOTES).
+ *
+ * The filesystem type for the parent directory of *pathname* must
+ * be **BPF_FS_MAGIC**.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * BPF_OBJ_GET
+ * Description
+ * Open a file descriptor for the eBPF object pinned to the
+ * specified *pathname*.
+ *
+ * Return
+ * A new file descriptor (a nonnegative integer), or -1 if an
+ * error occurred (in which case, *errno* is set appropriately).
+ *
+ * BPF_PROG_ATTACH
+ * Description
+ * Attach an eBPF program to a *target_fd* at the specified
+ * *attach_type* hook.
+ *
+ * The *attach_type* specifies the eBPF attachment point to
+ * attach the program to, and must be one of *bpf_attach_type*
+ * (see below).
+ *
+ * The *attach_bpf_fd* must be a valid file descriptor for a
+ * loaded eBPF program of a cgroup, flow dissector, LIRC, sockmap
+ * or sock_ops type corresponding to the specified *attach_type*.
+ *
+ * The *target_fd* must be a valid file descriptor for a kernel
+ * object which depends on the attach type of *attach_bpf_fd*:
+ *
+ * **BPF_PROG_TYPE_CGROUP_DEVICE**,
+ * **BPF_PROG_TYPE_CGROUP_SKB**,
+ * **BPF_PROG_TYPE_CGROUP_SOCK**,
+ * **BPF_PROG_TYPE_CGROUP_SOCK_ADDR**,
+ * **BPF_PROG_TYPE_CGROUP_SOCKOPT**,
+ * **BPF_PROG_TYPE_CGROUP_SYSCTL**,
+ * **BPF_PROG_TYPE_SOCK_OPS**
+ *
+ * Control Group v2 hierarchy with the eBPF controller
+ * enabled. Requires the kernel to be compiled with
+ * **CONFIG_CGROUP_BPF**.
+ *
+ * **BPF_PROG_TYPE_FLOW_DISSECTOR**
+ *
+ * Network namespace (eg /proc/self/ns/net).
+ *
+ * **BPF_PROG_TYPE_LIRC_MODE2**
+ *
+ * LIRC device path (eg /dev/lircN). Requires the kernel
+ * to be compiled with **CONFIG_BPF_LIRC_MODE2**.
+ *
+ * **BPF_PROG_TYPE_SK_SKB**,
+ * **BPF_PROG_TYPE_SK_MSG**
+ *
+ * eBPF map of socket type (eg **BPF_MAP_TYPE_SOCKHASH**).
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * BPF_PROG_DETACH
+ * Description
+ * Detach the eBPF program associated with the *target_fd* at the
+ * hook specified by *attach_type*. The program must have been
+ * previously attached using **BPF_PROG_ATTACH**.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * BPF_PROG_TEST_RUN
+ * Description
+ * Run the eBPF program associated with the *prog_fd* a *repeat*
+ * number of times against a provided program context *ctx_in* and
+ * data *data_in*, and return the modified program context
+ * *ctx_out*, *data_out* (for example, packet data), result of the
+ * execution *retval*, and *duration* of the test run.
+ *
+ * The sizes of the buffers provided as input and output
+ * parameters *ctx_in*, *ctx_out*, *data_in*, and *data_out* must
+ * be provided in the corresponding variables *ctx_size_in*,
+ * *ctx_size_out*, *data_size_in*, and/or *data_size_out*. If any
+ * of these parameters are not provided (ie set to NULL), the
+ * corresponding size field must be zero.
+ *
+ * Some program types have particular requirements:
+ *
+ * **BPF_PROG_TYPE_SK_LOOKUP**
+ * *data_in* and *data_out* must be NULL.
+ *
+ * **BPF_PROG_TYPE_RAW_TRACEPOINT**,
+ * **BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE**
+ *
+ * *ctx_out*, *data_in* and *data_out* must be NULL.
+ * *repeat* must be zero.
+ *
+ * BPF_PROG_RUN is an alias for BPF_PROG_TEST_RUN.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * **ENOSPC**
+ * Either *data_size_out* or *ctx_size_out* is too small.
+ * **ENOTSUPP**
+ * This command is not supported by the program type of
+ * the program referred to by *prog_fd*.
+ *
+ * BPF_PROG_GET_NEXT_ID
+ * Description
+ * Fetch the next eBPF program currently loaded into the kernel.
+ *
+ * Looks for the eBPF program with an id greater than *start_id*
+ * and updates *next_id* on success. If no other eBPF programs
+ * remain with ids higher than *start_id*, returns -1 and sets
+ * *errno* to **ENOENT**.
+ *
+ * Return
+ * Returns zero on success. On error, or when no id remains, -1
+ * is returned and *errno* is set appropriately.
+ *
+ * BPF_MAP_GET_NEXT_ID
+ * Description
+ * Fetch the next eBPF map currently loaded into the kernel.
+ *
+ * Looks for the eBPF map with an id greater than *start_id*
+ * and updates *next_id* on success. If no other eBPF maps
+ * remain with ids higher than *start_id*, returns -1 and sets
+ * *errno* to **ENOENT**.
+ *
+ * Return
+ * Returns zero on success. On error, or when no id remains, -1
+ * is returned and *errno* is set appropriately.
+ *
+ * BPF_PROG_GET_FD_BY_ID
+ * Description
+ * Open a file descriptor for the eBPF program corresponding to
+ * *prog_id*.
+ *
+ * Return
+ * A new file descriptor (a nonnegative integer), or -1 if an
+ * error occurred (in which case, *errno* is set appropriately).
+ *
+ * BPF_MAP_GET_FD_BY_ID
+ * Description
+ * Open a file descriptor for the eBPF map corresponding to
+ * *map_id*.
+ *
+ * Return
+ * A new file descriptor (a nonnegative integer), or -1 if an
+ * error occurred (in which case, *errno* is set appropriately).
+ *
+ * BPF_OBJ_GET_INFO_BY_FD
+ * Description
+ * Obtain information about the eBPF object corresponding to
+ * *bpf_fd*.
+ *
+ * Populates up to *info_len* bytes of *info*, which will be in
+ * one of the following formats depending on the eBPF object type
+ * of *bpf_fd*:
+ *
+ * * **struct bpf_prog_info**
+ * * **struct bpf_map_info**
+ * * **struct bpf_btf_info**
+ * * **struct bpf_link_info**
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * BPF_PROG_QUERY
+ * Description
+ * Obtain information about eBPF programs associated with the
+ * specified *attach_type* hook.
+ *
+ * The *target_fd* must be a valid file descriptor for a kernel
+ * object which depends on the attach type of *attach_bpf_fd*:
+ *
+ * **BPF_PROG_TYPE_CGROUP_DEVICE**,
+ * **BPF_PROG_TYPE_CGROUP_SKB**,
+ * **BPF_PROG_TYPE_CGROUP_SOCK**,
+ * **BPF_PROG_TYPE_CGROUP_SOCK_ADDR**,
+ * **BPF_PROG_TYPE_CGROUP_SOCKOPT**,
+ * **BPF_PROG_TYPE_CGROUP_SYSCTL**,
+ * **BPF_PROG_TYPE_SOCK_OPS**
+ *
+ * Control Group v2 hierarchy with the eBPF controller
+ * enabled. Requires the kernel to be compiled with
+ * **CONFIG_CGROUP_BPF**.
+ *
+ * **BPF_PROG_TYPE_FLOW_DISSECTOR**
+ *
+ * Network namespace (eg /proc/self/ns/net).
+ *
+ * **BPF_PROG_TYPE_LIRC_MODE2**
+ *
+ * LIRC device path (eg /dev/lircN). Requires the kernel
+ * to be compiled with **CONFIG_BPF_LIRC_MODE2**.
+ *
+ * **BPF_PROG_QUERY** always fetches the number of programs
+ * attached and the *attach_flags* which were used to attach those
+ * programs. Additionally, if *prog_ids* is nonzero and the number
+ * of attached programs is less than *prog_cnt*, populates
+ * *prog_ids* with the eBPF program ids of the programs attached
+ * at *target_fd*.
+ *
+ * The following flags may alter the result:
+ *
+ * **BPF_F_QUERY_EFFECTIVE**
+ * Only return information regarding programs which are
+ * currently effective at the specified *target_fd*.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * BPF_RAW_TRACEPOINT_OPEN
+ * Description
+ * Attach an eBPF program to a tracepoint *name* to access kernel
+ * internal arguments of the tracepoint in their raw form.
+ *
+ * The *prog_fd* must be a valid file descriptor associated with
+ * a loaded eBPF program of type **BPF_PROG_TYPE_RAW_TRACEPOINT**.
+ *
+ * No ABI guarantees are made about the content of tracepoint
+ * arguments exposed to the corresponding eBPF program.
+ *
+ * Applying **close**\ (2) to the file descriptor returned by
+ * **BPF_RAW_TRACEPOINT_OPEN** will delete the map (but see NOTES).
+ *
+ * Return
+ * A new file descriptor (a nonnegative integer), or -1 if an
+ * error occurred (in which case, *errno* is set appropriately).
+ *
+ * BPF_BTF_LOAD
+ * Description
+ * Verify and load BPF Type Format (BTF) metadata into the kernel,
+ * returning a new file descriptor associated with the metadata.
+ * BTF is described in more detail at
+ * https://www.kernel.org/doc/html/latest/bpf/btf.html.
+ *
+ * The *btf* parameter must point to valid memory providing
+ * *btf_size* bytes of BTF binary metadata.
+ *
+ * The returned file descriptor can be passed to other **bpf**\ ()
+ * subcommands such as **BPF_PROG_LOAD** or **BPF_MAP_CREATE** to
+ * associate the BTF with those objects.
+ *
+ * Similar to **BPF_PROG_LOAD**, **BPF_BTF_LOAD** has optional
+ * parameters to specify a *btf_log_buf*, *btf_log_size* and
+ * *btf_log_level* which allow the kernel to return freeform log
+ * output regarding the BTF verification process.
+ *
+ * Return
+ * A new file descriptor (a nonnegative integer), or -1 if an
+ * error occurred (in which case, *errno* is set appropriately).
+ *
+ * BPF_BTF_GET_FD_BY_ID
+ * Description
+ * Open a file descriptor for the BPF Type Format (BTF)
+ * corresponding to *btf_id*.
+ *
+ * Return
+ * A new file descriptor (a nonnegative integer), or -1 if an
+ * error occurred (in which case, *errno* is set appropriately).
+ *
+ * BPF_TASK_FD_QUERY
+ * Description
+ * Obtain information about eBPF programs associated with the
+ * target process identified by *pid* and *fd*.
+ *
+ * If the *pid* and *fd* are associated with a tracepoint, kprobe
+ * or uprobe perf event, then the *prog_id* and *fd_type* will
+ * be populated with the eBPF program id and file descriptor type
+ * of type **bpf_task_fd_type**. If associated with a kprobe or
+ * uprobe, the *probe_offset* and *probe_addr* will also be
+ * populated. Optionally, if *buf* is provided, then up to
+ * *buf_len* bytes of *buf* will be populated with the name of
+ * the tracepoint, kprobe or uprobe.
+ *
+ * The resulting *prog_id* may be introspected in deeper detail
+ * using **BPF_PROG_GET_FD_BY_ID** and **BPF_OBJ_GET_INFO_BY_FD**.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * BPF_MAP_LOOKUP_AND_DELETE_ELEM
+ * Description
+ * Look up an element with the given *key* in the map referred to
+ * by the file descriptor *fd*, and if found, delete the element.
+ *
+ * For **BPF_MAP_TYPE_QUEUE** and **BPF_MAP_TYPE_STACK** map
+ * types, the *flags* argument needs to be set to 0, but for other
+ * map types, it may be specified as:
+ *
+ * **BPF_F_LOCK**
+ * Look up and delete the value of a spin-locked map
+ * without returning the lock. This must be specified if
+ * the elements contain a spinlock.
+ *
+ * The **BPF_MAP_TYPE_QUEUE** and **BPF_MAP_TYPE_STACK** map types
+ * implement this command as a "pop" operation, deleting the top
+ * element rather than one corresponding to *key*.
+ * The *key* and *key_len* parameters should be zeroed when
+ * issuing this operation for these map types.
+ *
+ * This command is only valid for the following map types:
+ * * **BPF_MAP_TYPE_QUEUE**
+ * * **BPF_MAP_TYPE_STACK**
+ * * **BPF_MAP_TYPE_HASH**
+ * * **BPF_MAP_TYPE_PERCPU_HASH**
+ * * **BPF_MAP_TYPE_LRU_HASH**
+ * * **BPF_MAP_TYPE_LRU_PERCPU_HASH**
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * BPF_MAP_FREEZE
+ * Description
+ * Freeze the permissions of the specified map.
+ *
+ * Write permissions may be frozen by passing zero *flags*.
+ * Upon success, no future syscall invocations may alter the
+ * map state of *map_fd*. Write operations from eBPF programs
+ * are still possible for a frozen map.
+ *
+ * Not supported for maps of type **BPF_MAP_TYPE_STRUCT_OPS**.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * BPF_BTF_GET_NEXT_ID
+ * Description
+ * Fetch the next BPF Type Format (BTF) object currently loaded
+ * into the kernel.
+ *
+ * Looks for the BTF object with an id greater than *start_id*
+ * and updates *next_id* on success. If no other BTF objects
+ * remain with ids higher than *start_id*, returns -1 and sets
+ * *errno* to **ENOENT**.
+ *
+ * Return
+ * Returns zero on success. On error, or when no id remains, -1
+ * is returned and *errno* is set appropriately.
+ *
+ * BPF_MAP_LOOKUP_BATCH
+ * Description
+ * Iterate and fetch multiple elements in a map.
+ *
+ * Two opaque values are used to manage batch operations,
+ * *in_batch* and *out_batch*. Initially, *in_batch* must be set
+ * to NULL to begin the batched operation. After each subsequent
+ * **BPF_MAP_LOOKUP_BATCH**, the caller should pass the resultant
+ * *out_batch* as the *in_batch* for the next operation to
+ * continue iteration from the current point.
+ *
+ * The *keys* and *values* are output parameters which must point
+ * to memory large enough to hold *count* items based on the key
+ * and value size of the map *map_fd*. The *keys* buffer must be
+ * of *key_size* * *count*. The *values* buffer must be of
+ * *value_size* * *count*.
+ *
+ * The *elem_flags* argument may be specified as one of the
+ * following:
+ *
+ * **BPF_F_LOCK**
+ * Look up the value of a spin-locked map without
+ * returning the lock. This must be specified if the
+ * elements contain a spinlock.
+ *
+ * On success, *count* elements from the map are copied into the
+ * user buffer, with the keys copied into *keys* and the values
+ * copied into the corresponding indices in *values*.
+ *
+ * If an error is returned and *errno* is not **EFAULT**, *count*
+ * is set to the number of successfully processed elements.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * May set *errno* to **ENOSPC** to indicate that *keys* or
+ * *values* is too small to dump an entire bucket during
+ * iteration of a hash-based map type.
+ *
+ * BPF_MAP_LOOKUP_AND_DELETE_BATCH
+ * Description
+ * Iterate and delete all elements in a map.
+ *
+ * This operation has the same behavior as
+ * **BPF_MAP_LOOKUP_BATCH** with two exceptions:
+ *
+ * * Every element that is successfully returned is also deleted
+ * from the map. This is at least *count* elements. Note that
+ * *count* is both an input and an output parameter.
+ * * Upon returning with *errno* set to **EFAULT**, up to
+ * *count* elements may be deleted without returning the keys
+ * and values of the deleted elements.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * BPF_MAP_UPDATE_BATCH
+ * Description
+ * Update multiple elements in a map by *key*.
+ *
+ * The *keys* and *values* are input parameters which must point
+ * to memory large enough to hold *count* items based on the key
+ * and value size of the map *map_fd*. The *keys* buffer must be
+ * of *key_size* * *count*. The *values* buffer must be of
+ * *value_size* * *count*.
+ *
+ * Each element specified in *keys* is sequentially updated to the
+ * value in the corresponding index in *values*. The *in_batch*
+ * and *out_batch* parameters are ignored and should be zeroed.
+ *
+ * The *elem_flags* argument should be specified as one of the
+ * following:
+ *
+ * **BPF_ANY**
+ * Create new elements or update a existing elements.
+ * **BPF_NOEXIST**
+ * Create new elements only if they do not exist.
+ * **BPF_EXIST**
+ * Update existing elements.
+ * **BPF_F_LOCK**
+ * Update spin_lock-ed map elements. This must be
+ * specified if the map value contains a spinlock.
+ *
+ * On success, *count* elements from the map are updated.
+ *
+ * If an error is returned and *errno* is not **EFAULT**, *count*
+ * is set to the number of successfully processed elements.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * May set *errno* to **EINVAL**, **EPERM**, **ENOMEM**, or
+ * **E2BIG**. **E2BIG** indicates that the number of elements in
+ * the map reached the *max_entries* limit specified at map
+ * creation time.
+ *
+ * May set *errno* to one of the following error codes under
+ * specific circumstances:
+ *
+ * **EEXIST**
+ * If *flags* specifies **BPF_NOEXIST** and the element
+ * with *key* already exists in the map.
+ * **ENOENT**
+ * If *flags* specifies **BPF_EXIST** and the element with
+ * *key* does not exist in the map.
+ *
+ * BPF_MAP_DELETE_BATCH
+ * Description
+ * Delete multiple elements in a map by *key*.
+ *
+ * The *keys* parameter is an input parameter which must point
+ * to memory large enough to hold *count* items based on the key
+ * size of the map *map_fd*, that is, *key_size* * *count*.
+ *
+ * Each element specified in *keys* is sequentially deleted. The
+ * *in_batch*, *out_batch*, and *values* parameters are ignored
+ * and should be zeroed.
+ *
+ * The *elem_flags* argument may be specified as one of the
+ * following:
+ *
+ * **BPF_F_LOCK**
+ * Look up the value of a spin-locked map without
+ * returning the lock. This must be specified if the
+ * elements contain a spinlock.
+ *
+ * On success, *count* elements from the map are updated.
+ *
+ * If an error is returned and *errno* is not **EFAULT**, *count*
+ * is set to the number of successfully processed elements. If
+ * *errno* is **EFAULT**, up to *count* elements may be been
+ * deleted.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * BPF_LINK_CREATE
+ * Description
+ * Attach an eBPF program to a *target_fd* at the specified
+ * *attach_type* hook and return a file descriptor handle for
+ * managing the link.
+ *
+ * Return
+ * A new file descriptor (a nonnegative integer), or -1 if an
+ * error occurred (in which case, *errno* is set appropriately).
+ *
+ * BPF_LINK_UPDATE
+ * Description
+ * Update the eBPF program in the specified *link_fd* to
+ * *new_prog_fd*.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * BPF_LINK_GET_FD_BY_ID
+ * Description
+ * Open a file descriptor for the eBPF Link corresponding to
+ * *link_id*.
+ *
+ * Return
+ * A new file descriptor (a nonnegative integer), or -1 if an
+ * error occurred (in which case, *errno* is set appropriately).
+ *
+ * BPF_LINK_GET_NEXT_ID
+ * Description
+ * Fetch the next eBPF link currently loaded into the kernel.
+ *
+ * Looks for the eBPF link with an id greater than *start_id*
+ * and updates *next_id* on success. If no other eBPF links
+ * remain with ids higher than *start_id*, returns -1 and sets
+ * *errno* to **ENOENT**.
+ *
+ * Return
+ * Returns zero on success. On error, or when no id remains, -1
+ * is returned and *errno* is set appropriately.
+ *
+ * BPF_ENABLE_STATS
+ * Description
+ * Enable eBPF runtime statistics gathering.
+ *
+ * Runtime statistics gathering for the eBPF runtime is disabled
+ * by default to minimize the corresponding performance overhead.
+ * This command enables statistics globally.
+ *
+ * Multiple programs may independently enable statistics.
+ * After gathering the desired statistics, eBPF runtime statistics
+ * may be disabled again by calling **close**\ (2) for the file
+ * descriptor returned by this function. Statistics will only be
+ * disabled system-wide when all outstanding file descriptors
+ * returned by prior calls for this subcommand are closed.
+ *
+ * Return
+ * A new file descriptor (a nonnegative integer), or -1 if an
+ * error occurred (in which case, *errno* is set appropriately).
+ *
+ * BPF_ITER_CREATE
+ * Description
+ * Create an iterator on top of the specified *link_fd* (as
+ * previously created using **BPF_LINK_CREATE**) and return a
+ * file descriptor that can be used to trigger the iteration.
+ *
+ * If the resulting file descriptor is pinned to the filesystem
+ * using **BPF_OBJ_PIN**, then subsequent **read**\ (2) syscalls
+ * for that path will trigger the iterator to read kernel state
+ * using the eBPF program attached to *link_fd*.
+ *
+ * Return
+ * A new file descriptor (a nonnegative integer), or -1 if an
+ * error occurred (in which case, *errno* is set appropriately).
+ *
+ * BPF_LINK_DETACH
+ * Description
+ * Forcefully detach the specified *link_fd* from its
+ * corresponding attachment point.
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * BPF_PROG_BIND_MAP
+ * Description
+ * Bind a map to the lifetime of an eBPF program.
+ *
+ * The map identified by *map_fd* is bound to the program
+ * identified by *prog_fd* and only released when *prog_fd* is
+ * released. This may be used in cases where metadata should be
+ * associated with a program which otherwise does not contain any
+ * references to the map (for example, embedded in the eBPF
+ * program instructions).
+ *
+ * Return
+ * Returns zero on success. On error, -1 is returned and *errno*
+ * is set appropriately.
+ *
+ * NOTES
+ * eBPF objects (maps and programs) can be shared between processes.
+ *
+ * * After **fork**\ (2), the child inherits file descriptors
+ * referring to the same eBPF objects.
+ * * File descriptors referring to eBPF objects can be transferred over
+ * **unix**\ (7) domain sockets.
+ * * File descriptors referring to eBPF objects can be duplicated in the
+ * usual way, using **dup**\ (2) and similar calls.
+ * * File descriptors referring to eBPF objects can be pinned to the
+ * filesystem using the **BPF_OBJ_PIN** command of **bpf**\ (2).
+ *
+ * An eBPF object is deallocated only after all file descriptors referring
+ * to the object have been closed and no references remain pinned to the
+ * filesystem or attached (for example, bound to a program or device).
+ */
+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_RUN = 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,
+ BPF_MAP_LOOKUP_AND_DELETE_ELEM,
+ BPF_MAP_FREEZE,
+ BPF_BTF_GET_NEXT_ID,
+ BPF_MAP_LOOKUP_BATCH,
+ BPF_MAP_LOOKUP_AND_DELETE_BATCH,
+ BPF_MAP_UPDATE_BATCH,
+ BPF_MAP_DELETE_BATCH,
+ BPF_LINK_CREATE,
+ BPF_LINK_UPDATE,
+ BPF_LINK_GET_FD_BY_ID,
+ BPF_LINK_GET_NEXT_ID,
+ BPF_ENABLE_STATS,
+ BPF_ITER_CREATE,
+ BPF_LINK_DETACH,
+ BPF_PROG_BIND_MAP,
+};
+
+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_DEPRECATED,
+ /* BPF_MAP_TYPE_CGROUP_STORAGE is available to bpf programs attaching
+ * to a cgroup. The newer BPF_MAP_TYPE_CGRP_STORAGE is available to
+ * both cgroup-attached and other progs and supports all functionality
+ * provided by BPF_MAP_TYPE_CGROUP_STORAGE. So mark
+ * BPF_MAP_TYPE_CGROUP_STORAGE deprecated.
+ */
+ BPF_MAP_TYPE_CGROUP_STORAGE = BPF_MAP_TYPE_CGROUP_STORAGE_DEPRECATED,
+ BPF_MAP_TYPE_REUSEPORT_SOCKARRAY,
+ BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE,
+ BPF_MAP_TYPE_QUEUE,
+ BPF_MAP_TYPE_STACK,
+ BPF_MAP_TYPE_SK_STORAGE,
+ BPF_MAP_TYPE_DEVMAP_HASH,
+ BPF_MAP_TYPE_STRUCT_OPS,
+ BPF_MAP_TYPE_RINGBUF,
+ BPF_MAP_TYPE_INODE_STORAGE,
+ BPF_MAP_TYPE_TASK_STORAGE,
+ BPF_MAP_TYPE_BLOOM_FILTER,
+ BPF_MAP_TYPE_USER_RINGBUF,
+ BPF_MAP_TYPE_CGRP_STORAGE,
+};
+
+/* Note that tracing related programs such as
+ * BPF_PROG_TYPE_{KPROBE,TRACEPOINT,PERF_EVENT,RAW_TRACEPOINT}
+ * are not subject to a stable API since kernel internal data
+ * structures can change from release to release and may
+ * therefore break existing tracing BPF programs. Tracing BPF
+ * programs correspond to /a/ specific kernel which is to be
+ * analyzed, and not /a/ specific kernel /and/ all future ones.
+ */
+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,
+ BPF_PROG_TYPE_FLOW_DISSECTOR,
+ BPF_PROG_TYPE_CGROUP_SYSCTL,
+ BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE,
+ BPF_PROG_TYPE_CGROUP_SOCKOPT,
+ BPF_PROG_TYPE_TRACING,
+ BPF_PROG_TYPE_STRUCT_OPS,
+ BPF_PROG_TYPE_EXT,
+ BPF_PROG_TYPE_LSM,
+ BPF_PROG_TYPE_SK_LOOKUP,
+ BPF_PROG_TYPE_SYSCALL, /* a program that can execute syscalls */
+ BPF_PROG_TYPE_NETFILTER,
+};
+
+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,
+ BPF_FLOW_DISSECTOR,
+ BPF_CGROUP_SYSCTL,
+ BPF_CGROUP_UDP4_RECVMSG,
+ BPF_CGROUP_UDP6_RECVMSG,
+ BPF_CGROUP_GETSOCKOPT,
+ BPF_CGROUP_SETSOCKOPT,
+ BPF_TRACE_RAW_TP,
+ BPF_TRACE_FENTRY,
+ BPF_TRACE_FEXIT,
+ BPF_MODIFY_RETURN,
+ BPF_LSM_MAC,
+ BPF_TRACE_ITER,
+ BPF_CGROUP_INET4_GETPEERNAME,
+ BPF_CGROUP_INET6_GETPEERNAME,
+ BPF_CGROUP_INET4_GETSOCKNAME,
+ BPF_CGROUP_INET6_GETSOCKNAME,
+ BPF_XDP_DEVMAP,
+ BPF_CGROUP_INET_SOCK_RELEASE,
+ BPF_XDP_CPUMAP,
+ BPF_SK_LOOKUP,
+ BPF_XDP,
+ BPF_SK_SKB_VERDICT,
+ BPF_SK_REUSEPORT_SELECT,
+ BPF_SK_REUSEPORT_SELECT_OR_MIGRATE,
+ BPF_PERF_EVENT,
+ BPF_TRACE_KPROBE_MULTI,
+ BPF_LSM_CGROUP,
+ BPF_STRUCT_OPS,
+ BPF_NETFILTER,
+ BPF_TCX_INGRESS,
+ BPF_TCX_EGRESS,
+ BPF_TRACE_UPROBE_MULTI,
+ __MAX_BPF_ATTACH_TYPE
+};
+
+#define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE
+
+enum bpf_link_type {
+ BPF_LINK_TYPE_UNSPEC = 0,
+ BPF_LINK_TYPE_RAW_TRACEPOINT = 1,
+ BPF_LINK_TYPE_TRACING = 2,
+ BPF_LINK_TYPE_CGROUP = 3,
+ BPF_LINK_TYPE_ITER = 4,
+ BPF_LINK_TYPE_NETNS = 5,
+ BPF_LINK_TYPE_XDP = 6,
+ BPF_LINK_TYPE_PERF_EVENT = 7,
+ BPF_LINK_TYPE_KPROBE_MULTI = 8,
+ BPF_LINK_TYPE_STRUCT_OPS = 9,
+ BPF_LINK_TYPE_NETFILTER = 10,
+ BPF_LINK_TYPE_TCX = 11,
+ BPF_LINK_TYPE_UPROBE_MULTI = 12,
+ MAX_BPF_LINK_TYPE,
+};
+
+enum bpf_perf_event_type {
+ BPF_PERF_EVENT_UNSPEC = 0,
+ BPF_PERF_EVENT_UPROBE = 1,
+ BPF_PERF_EVENT_URETPROBE = 2,
+ BPF_PERF_EVENT_KPROBE = 3,
+ BPF_PERF_EVENT_KRETPROBE = 4,
+ BPF_PERF_EVENT_TRACEPOINT = 5,
+ BPF_PERF_EVENT_EVENT = 6,
+};
+
+/* 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.
+ *
+ * With BPF_F_ALLOW_MULTI a new program is added to the end of the list of
+ * programs for a cgroup. Though it's possible to replace an old program at
+ * any position by also specifying BPF_F_REPLACE flag and position itself in
+ * replace_bpf_fd attribute. Old program at this position will be released.
+ *
+ * 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)
+/* Generic attachment flags. */
+#define BPF_F_REPLACE (1U << 2)
+#define BPF_F_BEFORE (1U << 3)
+#define BPF_F_AFTER (1U << 4)
+#define BPF_F_ID (1U << 5)
+#define BPF_F_LINK BPF_F_LINK /* 1 << 13 */
+
+/* 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)
+
+/* If BPF_F_ANY_ALIGNMENT is used in BPF_PROG_LOAD command, the
+ * verifier will allow any alignment whatsoever. On platforms
+ * with strict alignment requirements for loads ands stores (such
+ * as sparc and mips) the verifier validates that all loads and
+ * stores provably follow this requirement. This flag turns that
+ * checking and enforcement off.
+ *
+ * It is mostly used for testing when we want to validate the
+ * context and memory access aspects of the verifier, but because
+ * of an unaligned access the alignment check would trigger before
+ * the one we are interested in.
+ */
+#define BPF_F_ANY_ALIGNMENT (1U << 1)
+
+/* BPF_F_TEST_RND_HI32 is used in BPF_PROG_LOAD command for testing purpose.
+ * Verifier does sub-register def/use analysis and identifies instructions whose
+ * def only matters for low 32-bit, high 32-bit is never referenced later
+ * through implicit zero extension. Therefore verifier notifies JIT back-ends
+ * that it is safe to ignore clearing high 32-bit for these instructions. This
+ * saves some back-ends a lot of code-gen. However such optimization is not
+ * necessary on some arches, for example x86_64, arm64 etc, whose JIT back-ends
+ * hence hasn't used verifier's analysis result. But, we really want to have a
+ * way to be able to verify the correctness of the described optimization on
+ * x86_64 on which testsuites are frequently exercised.
+ *
+ * So, this flag is introduced. Once it is set, verifier will randomize high
+ * 32-bit for those instructions who has been identified as safe to ignore them.
+ * Then, if verifier is not doing correct analysis, such randomization will
+ * regress tests to expose bugs.
+ */
+#define BPF_F_TEST_RND_HI32 (1U << 2)
+
+/* The verifier internal test flag. Behavior is undefined */
+#define BPF_F_TEST_STATE_FREQ (1U << 3)
+
+/* If BPF_F_SLEEPABLE is used in BPF_PROG_LOAD command, the verifier will
+ * restrict map and helper usage for such programs. Sleepable BPF programs can
+ * only be attached to hooks where kernel execution context allows sleeping.
+ * Such programs are allowed to use helpers that may sleep like
+ * bpf_copy_from_user().
+ */
+#define BPF_F_SLEEPABLE (1U << 4)
+
+/* If BPF_F_XDP_HAS_FRAGS is used in BPF_PROG_LOAD command, the loaded program
+ * fully support xdp frags.
+ */
+#define BPF_F_XDP_HAS_FRAGS (1U << 5)
+
+/* If BPF_F_XDP_DEV_BOUND_ONLY is used in BPF_PROG_LOAD command, the loaded
+ * program becomes device-bound but can access XDP metadata.
+ */
+#define BPF_F_XDP_DEV_BOUND_ONLY (1U << 6)
+
+/* link_create.kprobe_multi.flags used in LINK_CREATE command for
+ * BPF_TRACE_KPROBE_MULTI attach type to create return probe.
+ */
+enum {
+ BPF_F_KPROBE_MULTI_RETURN = (1U << 0)
+};
+
+/* link_create.uprobe_multi.flags used in LINK_CREATE command for
+ * BPF_TRACE_UPROBE_MULTI attach type to create return probe.
+ */
+enum {
+ BPF_F_UPROBE_MULTI_RETURN = (1U << 0)
+};
+
+/* link_create.netfilter.flags used in LINK_CREATE command for
+ * BPF_PROG_TYPE_NETFILTER to enable IP packet defragmentation.
+ */
+#define BPF_F_NETFILTER_IP_DEFRAG (1U << 0)
+
+/* When BPF ldimm64's insn[0].src_reg != 0 then this can have
+ * the following extensions:
+ *
+ * insn[0].src_reg: BPF_PSEUDO_MAP_[FD|IDX]
+ * insn[0].imm: map fd or fd_idx
+ * insn[1].imm: 0
+ * insn[0].off: 0
+ * insn[1].off: 0
+ * ldimm64 rewrite: address of map
+ * verifier type: CONST_PTR_TO_MAP
+ */
+#define BPF_PSEUDO_MAP_FD 1
+#define BPF_PSEUDO_MAP_IDX 5
+
+/* insn[0].src_reg: BPF_PSEUDO_MAP_[IDX_]VALUE
+ * insn[0].imm: map fd or fd_idx
+ * insn[1].imm: offset into value
+ * insn[0].off: 0
+ * insn[1].off: 0
+ * ldimm64 rewrite: address of map[0]+offset
+ * verifier type: PTR_TO_MAP_VALUE
+ */
+#define BPF_PSEUDO_MAP_VALUE 2
+#define BPF_PSEUDO_MAP_IDX_VALUE 6
+
+/* insn[0].src_reg: BPF_PSEUDO_BTF_ID
+ * insn[0].imm: kernel btd id of VAR
+ * insn[1].imm: 0
+ * insn[0].off: 0
+ * insn[1].off: 0
+ * ldimm64 rewrite: address of the kernel variable
+ * verifier type: PTR_TO_BTF_ID or PTR_TO_MEM, depending on whether the var
+ * is struct/union.
+ */
+#define BPF_PSEUDO_BTF_ID 3
+/* insn[0].src_reg: BPF_PSEUDO_FUNC
+ * insn[0].imm: insn offset to the func
+ * insn[1].imm: 0
+ * insn[0].off: 0
+ * insn[1].off: 0
+ * ldimm64 rewrite: address of the function
+ * verifier type: PTR_TO_FUNC.
+ */
+#define BPF_PSEUDO_FUNC 4
+
+/* when bpf_call->src_reg == BPF_PSEUDO_CALL, bpf_call->imm == pc-relative
+ * offset to another bpf function
+ */
+#define BPF_PSEUDO_CALL 1
+/* when bpf_call->src_reg == BPF_PSEUDO_KFUNC_CALL,
+ * bpf_call->imm == btf_id of a BTF_KIND_FUNC in the running kernel
+ */
+#define BPF_PSEUDO_KFUNC_CALL 2
+
+/* flags for BPF_MAP_UPDATE_ELEM command */
+enum {
+ BPF_ANY = 0, /* create new element or update existing */
+ BPF_NOEXIST = 1, /* create new element if it didn't exist */
+ BPF_EXIST = 2, /* update existing element */
+ BPF_F_LOCK = 4, /* spin_lock-ed map_lookup/map_update */
+};
+
+/* flags for BPF_MAP_CREATE command */
+enum {
+ 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.
+ */
+ BPF_F_NO_COMMON_LRU = (1U << 1),
+/* Specify numa node during map creation */
+ BPF_F_NUMA_NODE = (1U << 2),
+
+/* Flags for accessing BPF object from syscall side. */
+ BPF_F_RDONLY = (1U << 3),
+ BPF_F_WRONLY = (1U << 4),
+
+/* Flag for stack_map, store build_id+offset instead of pointer */
+ BPF_F_STACK_BUILD_ID = (1U << 5),
+
+/* Zero-initialize hash function seed. This should only be used for testing. */
+ BPF_F_ZERO_SEED = (1U << 6),
+
+/* Flags for accessing BPF object from program side. */
+ BPF_F_RDONLY_PROG = (1U << 7),
+ BPF_F_WRONLY_PROG = (1U << 8),
+
+/* Clone map from listener for newly accepted socket */
+ BPF_F_CLONE = (1U << 9),
+
+/* Enable memory-mapping BPF map */
+ BPF_F_MMAPABLE = (1U << 10),
+
+/* Share perf_event among processes */
+ BPF_F_PRESERVE_ELEMS = (1U << 11),
+
+/* Create a map that is suitable to be an inner map with dynamic max entries */
+ BPF_F_INNER_MAP = (1U << 12),
+
+/* Create a map that will be registered/unregesitered by the backed bpf_link */
+ BPF_F_LINK = (1U << 13),
+
+/* Get path from provided FD in BPF_OBJ_PIN/BPF_OBJ_GET commands */
+ BPF_F_PATH_FD = (1U << 14),
+};
+
+/* Flags for BPF_PROG_QUERY. */
+
+/* Query effective (directly attached + inherited from ancestor cgroups)
+ * programs that will be executed for events within a cgroup.
+ * attach_flags with this flag are always returned 0.
+ */
+#define BPF_F_QUERY_EFFECTIVE (1U << 0)
+
+/* Flags for BPF_PROG_TEST_RUN */
+
+/* If set, run the test on the cpu specified by bpf_attr.test.cpu */
+#define BPF_F_TEST_RUN_ON_CPU (1U << 0)
+/* If set, XDP frames will be transmitted after processing */
+#define BPF_F_TEST_XDP_LIVE_FRAMES (1U << 1)
+
+/* type for BPF_ENABLE_STATS */
+enum bpf_stats_type {
+ /* enabled run_time_ns and run_cnt */
+ BPF_STATS_RUN_TIME = 0,
+};
+
+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;
+ };
+};
+
+#define BPF_OBJ_NAME_LEN 16U
+
+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 */
+ __u32 btf_vmlinux_value_type_id;/* BTF type_id of a kernel-
+ * struct stored as the
+ * map value
+ */
+ /* Any per-map-type extra fields
+ *
+ * BPF_MAP_TYPE_BLOOM_FILTER - the lowest 4 bits indicate the
+ * number of hash functions (if 0, the bloom filter will default
+ * to using 5 hash functions).
+ */
+ __u64 map_extra;
+ };
+
+ 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 { /* struct used by BPF_MAP_*_BATCH commands */
+ __aligned_u64 in_batch; /* start batch,
+ * NULL to start from beginning
+ */
+ __aligned_u64 out_batch; /* output: next start batch */
+ __aligned_u64 keys;
+ __aligned_u64 values;
+ __u32 count; /* input/output:
+ * input: # of key/value
+ * elements
+ * output: # of filled elements
+ */
+ __u32 map_fd;
+ __u64 elem_flags;
+ __u64 flags;
+ } batch;
+
+ 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; /* not used */
+ __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;
+ __u32 prog_btf_fd; /* fd pointing to BTF type data */
+ __u32 func_info_rec_size; /* userspace bpf_func_info size */
+ __aligned_u64 func_info; /* func info */
+ __u32 func_info_cnt; /* number of bpf_func_info records */
+ __u32 line_info_rec_size; /* userspace bpf_line_info size */
+ __aligned_u64 line_info; /* line info */
+ __u32 line_info_cnt; /* number of bpf_line_info records */
+ __u32 attach_btf_id; /* in-kernel BTF type id to attach to */
+ union {
+ /* valid prog_fd to attach to bpf prog */
+ __u32 attach_prog_fd;
+ /* or valid module BTF object fd or 0 to attach to vmlinux */
+ __u32 attach_btf_obj_fd;
+ };
+ __u32 core_relo_cnt; /* number of bpf_core_relo */
+ __aligned_u64 fd_array; /* array of FDs */
+ __aligned_u64 core_relos;
+ __u32 core_relo_rec_size; /* sizeof(struct bpf_core_relo) */
+ /* output: actual total log contents size (including termintaing zero).
+ * It could be both larger than original log_size (if log was
+ * truncated), or smaller (if log buffer wasn't filled completely).
+ */
+ __u32 log_true_size;
+ };
+
+ struct { /* anonymous struct used by BPF_OBJ_* commands */
+ __aligned_u64 pathname;
+ __u32 bpf_fd;
+ __u32 file_flags;
+ /* Same as dirfd in openat() syscall; see openat(2)
+ * manpage for details of path FD and pathname semantics;
+ * path_fd should accompanied by BPF_F_PATH_FD flag set in
+ * file_flags field, otherwise it should be set to zero;
+ * if BPF_F_PATH_FD flag is not set, AT_FDCWD is assumed.
+ */
+ __s32 path_fd;
+ };
+
+ struct { /* anonymous struct used by BPF_PROG_ATTACH/DETACH commands */
+ union {
+ __u32 target_fd; /* target object to attach to or ... */
+ __u32 target_ifindex; /* target ifindex */
+ };
+ __u32 attach_bpf_fd;
+ __u32 attach_type;
+ __u32 attach_flags;
+ __u32 replace_bpf_fd;
+ union {
+ __u32 relative_fd;
+ __u32 relative_id;
+ };
+ __u64 expected_revision;
+ };
+
+ struct { /* anonymous struct used by BPF_PROG_TEST_RUN command */
+ __u32 prog_fd;
+ __u32 retval;
+ __u32 data_size_in; /* input: len of data_in */
+ __u32 data_size_out; /* input/output: len of data_out
+ * returns ENOSPC if data_out
+ * is too small.
+ */
+ __aligned_u64 data_in;
+ __aligned_u64 data_out;
+ __u32 repeat;
+ __u32 duration;
+ __u32 ctx_size_in; /* input: len of ctx_in */
+ __u32 ctx_size_out; /* input/output: len of ctx_out
+ * returns ENOSPC if ctx_out
+ * is too small.
+ */
+ __aligned_u64 ctx_in;
+ __aligned_u64 ctx_out;
+ __u32 flags;
+ __u32 cpu;
+ __u32 batch_size;
+ } test;
+
+ struct { /* anonymous struct used by BPF_*_GET_*_ID */
+ union {
+ __u32 start_id;
+ __u32 prog_id;
+ __u32 map_id;
+ __u32 btf_id;
+ __u32 link_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 */
+ union {
+ __u32 target_fd; /* target object to query or ... */
+ __u32 target_ifindex; /* target ifindex */
+ };
+ __u32 attach_type;
+ __u32 query_flags;
+ __u32 attach_flags;
+ __aligned_u64 prog_ids;
+ union {
+ __u32 prog_cnt;
+ __u32 count;
+ };
+ __u32 :32;
+ /* output: per-program attach_flags.
+ * not allowed to be set during effective query.
+ */
+ __aligned_u64 prog_attach_flags;
+ __aligned_u64 link_ids;
+ __aligned_u64 link_attach_flags;
+ __u64 revision;
+ } query;
+
+ struct { /* anonymous struct used by BPF_RAW_TRACEPOINT_OPEN command */
+ __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;
+ /* output: actual total log contents size (including termintaing zero).
+ * It could be both larger than original log_size (if log was
+ * truncated), or smaller (if log buffer wasn't filled completely).
+ */
+ __u32 btf_log_true_size;
+ };
+
+ 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;
+
+ struct { /* struct used by BPF_LINK_CREATE command */
+ union {
+ __u32 prog_fd; /* eBPF program to attach */
+ __u32 map_fd; /* struct_ops to attach */
+ };
+ union {
+ __u32 target_fd; /* target object to attach to or ... */
+ __u32 target_ifindex; /* target ifindex */
+ };
+ __u32 attach_type; /* attach type */
+ __u32 flags; /* extra flags */
+ union {
+ __u32 target_btf_id; /* btf_id of target to attach to */
+ struct {
+ __aligned_u64 iter_info; /* extra bpf_iter_link_info */
+ __u32 iter_info_len; /* iter_info length */
+ };
+ struct {
+ /* black box user-provided value passed through
+ * to BPF program at the execution time and
+ * accessible through bpf_get_attach_cookie() BPF helper
+ */
+ __u64 bpf_cookie;
+ } perf_event;
+ struct {
+ __u32 flags;
+ __u32 cnt;
+ __aligned_u64 syms;
+ __aligned_u64 addrs;
+ __aligned_u64 cookies;
+ } kprobe_multi;
+ struct {
+ /* this is overlaid with the target_btf_id above. */
+ __u32 target_btf_id;
+ /* black box user-provided value passed through
+ * to BPF program at the execution time and
+ * accessible through bpf_get_attach_cookie() BPF helper
+ */
+ __u64 cookie;
+ } tracing;
+ struct {
+ __u32 pf;
+ __u32 hooknum;
+ __s32 priority;
+ __u32 flags;
+ } netfilter;
+ struct {
+ union {
+ __u32 relative_fd;
+ __u32 relative_id;
+ };
+ __u64 expected_revision;
+ } tcx;
+ struct {
+ __aligned_u64 path;
+ __aligned_u64 offsets;
+ __aligned_u64 ref_ctr_offsets;
+ __aligned_u64 cookies;
+ __u32 cnt;
+ __u32 flags;
+ __u32 pid;
+ } uprobe_multi;
+ };
+ } link_create;
+
+ struct { /* struct used by BPF_LINK_UPDATE command */
+ __u32 link_fd; /* link fd */
+ union {
+ /* new program fd to update link with */
+ __u32 new_prog_fd;
+ /* new struct_ops map fd to update link with */
+ __u32 new_map_fd;
+ };
+ __u32 flags; /* extra flags */
+ union {
+ /* expected link's program fd; is specified only if
+ * BPF_F_REPLACE flag is set in flags.
+ */
+ __u32 old_prog_fd;
+ /* expected link's map fd; is specified only
+ * if BPF_F_REPLACE flag is set.
+ */
+ __u32 old_map_fd;
+ };
+ } link_update;
+
+ struct {
+ __u32 link_fd;
+ } link_detach;
+
+ struct { /* struct used by BPF_ENABLE_STATS command */
+ __u32 type;
+ } enable_stats;
+
+ struct { /* struct used by BPF_ITER_CREATE command */
+ __u32 link_fd;
+ __u32 flags;
+ } iter_create;
+
+ struct { /* struct used by BPF_PROG_BIND_MAP command */
+ __u32 prog_fd;
+ __u32 map_fd;
+ __u32 flags; /* extra flags */
+ } prog_bind_map;
+
+} __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_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.
+ *
+ * long 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.
+ *
+ * long 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.
+ *
+ * long bpf_probe_read(void *dst, u32 size, const void *unsafe_ptr)
+ * Description
+ * For tracing programs, safely attempt to read *size* bytes from
+ * kernel space address *unsafe_ptr* and store the data in *dst*.
+ *
+ * Generally, use **bpf_probe_read_user**\ () or
+ * **bpf_probe_read_kernel**\ () instead.
+ * 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.
+ * Does not include time the system was suspended.
+ * See: **clock_gettime**\ (**CLOCK_MONOTONIC**)
+ * Return
+ * Current *ktime*.
+ *
+ * long 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/tracing/trace* from TraceFS, 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.
+ * Lines are discarded while *\/sys/kernel/tracing/trace* is
+ * open, use *\/sys/kernel/tracing/trace_pipe* to avoid this.
+ * The format of the trace is customizable, and the exact output
+ * one will get depends on the options set in
+ * *\/sys/kernel/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
+ * block (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 migration 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.
+ *
+ * long 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 underlying
+ * 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.
+ *
+ * long 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 underlying
+ * 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.
+ *
+ * long 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 underlying
+ * 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.
+ *
+ * long 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 33.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long 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 underlying
+ * 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. Positive
+ * error indicates a potential drop or congestion in the target
+ * device. The particular positive error codes are not defined.
+ *
+ * u64 bpf_get_current_pid_tgid(void)
+ * Description
+ * Get the current pid and tgid.
+ * 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)
+ * Description
+ * Get the current uid and gid.
+ * Return
+ * A 64-bit integer containing the current GID and UID, and
+ * created as such: *current_gid* **<< 32 \|** *current_uid*.
+ *
+ * long bpf_get_current_comm(void *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/admin-guide/cgroup-v1/net_cls.rst*.
+ *
+ * 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.
+ *
+ * long 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 underlying
+ * 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.
+ *
+ * long 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 underlying
+ * 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.
+ *
+ * long 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.
+ *
+ * long 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.
+ * **BPF_F_NO_TUNNEL_KEY**
+ * Add a flag to tunnel metadata indicating that no tunnel
+ * key should be set in the resulting tunnel header.
+ *
+ * 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.
+ *
+ * long 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 also be attained with the more generic
+ * **bpf_redirect_map**\ (), which uses a BPF map to store the
+ * redirect target instead of providing it directly to the helper.
+ * 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
+ * identifier 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.
+ *
+ * long bpf_perf_event_output(void *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.
+ *
+ * long bpf_skb_load_bytes(const void *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.
+ *
+ * long bpf_get_stackid(void *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.
+ *
+ * long bpf_skb_get_tunnel_opt(struct sk_buff *skb, void *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.
+ *
+ * long bpf_skb_set_tunnel_opt(struct sk_buff *skb, void *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.
+ *
+ * long 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 underlying
+ * 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.
+ *
+ * long 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.
+ *
+ * long 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)
+ * Description
+ * Get the current task.
+ * Return
+ * A pointer to the current task struct.
+ *
+ * long 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.
+ *
+ * long 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:
+ *
+ * * 1, if current task belongs to the cgroup2.
+ * * 0, if current task does not belong to the cgroup2.
+ * * A negative error code, if an error occurred.
+ *
+ * long 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 underlying
+ * 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.
+ *
+ * long 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 all bytes in the linear part of *skb* will be made
+ * readable and writable.
+ *
+ * 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 underlying
+ * 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.
+ * Return
+ * void.
+ *
+ * long 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.
+ *
+ * long 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 underlying
+ * 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.
+ *
+ * long 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 underlying
+ * 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.
+ *
+ * long bpf_probe_read_str(void *dst, u32 size, const void *unsafe_ptr)
+ * Description
+ * Copy a NUL terminated string from an unsafe kernel address
+ * *unsafe_ptr* to *dst*. See **bpf_probe_read_kernel_str**\ () for
+ * more details.
+ *
+ * Generally, use **bpf_probe_read_user_str**\ () or
+ * **bpf_probe_read_kernel_str**\ () instead.
+ * 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 global socket
+ * identifier that can be assumed unique.
+ * Return
+ * A 8-byte long unique 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** context.
+ * Return
+ * A 8-byte long unique 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** context.
+ * Return
+ * A 8-byte long unique number.
+ *
+ * u64 bpf_get_socket_cookie(struct sock *sk)
+ * Description
+ * Equivalent to **bpf_get_socket_cookie**\ () helper that accepts
+ * *sk*, but gets socket from a BTF **struct sock**. This helper
+ * also works for sleepable programs.
+ * Return
+ * A 8-byte long unique number or 0 if *sk* is NULL.
+ *
+ * u32 bpf_get_socket_uid(struct sk_buff *skb)
+ * Description
+ * Get the owner UID of the socked associated to *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).
+ *
+ * long 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
+ *
+ * long bpf_setsockopt(void *bpf_socket, int level, int optname, void *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*.
+ *
+ * *bpf_socket* should be one of the following:
+ *
+ * * **struct bpf_sock_ops** for **BPF_PROG_TYPE_SOCK_OPS**.
+ * * **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT**
+ * and **BPF_CGROUP_INET6_CONNECT**.
+ *
+ * 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**,
+ * **SO_BINDTODEVICE**, **SO_KEEPALIVE**, **SO_REUSEADDR**,
+ * **SO_REUSEPORT**, **SO_BINDTOIFINDEX**, **SO_TXREHASH**.
+ * * **IPPROTO_TCP**, which supports the following *optname*\ s:
+ * **TCP_CONGESTION**, **TCP_BPF_IW**,
+ * **TCP_BPF_SNDCWND_CLAMP**, **TCP_SAVE_SYN**,
+ * **TCP_KEEPIDLE**, **TCP_KEEPINTVL**, **TCP_KEEPCNT**,
+ * **TCP_SYNCNT**, **TCP_USER_TIMEOUT**, **TCP_NOTSENT_LOWAT**,
+ * **TCP_NODELAY**, **TCP_MAXSEG**, **TCP_WINDOW_CLAMP**,
+ * **TCP_THIN_LINEAR_TIMEOUTS**, **TCP_BPF_DELACK_MAX**,
+ * **TCP_BPF_RTO_MIN**.
+ * * **IPPROTO_IP**, which supports *optname* **IP_TOS**.
+ * * **IPPROTO_IPV6**, which supports the following *optname*\ s:
+ * **IPV6_TCLASS**, **IPV6_AUTOFLOWLABEL**.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_skb_adjust_room(struct sk_buff *skb, s32 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*.
+ *
+ * By default, the helper will reset any offloaded checksum
+ * indicator of the skb to CHECKSUM_NONE. This can be avoided
+ * by the following flag:
+ *
+ * * **BPF_F_ADJ_ROOM_NO_CSUM_RESET**: Do not reset offloaded
+ * checksum data of the skb to CHECKSUM_NONE.
+ *
+ * There are two supported modes at this time:
+ *
+ * * **BPF_ADJ_ROOM_MAC**: Adjust room at the mac layer
+ * (room space is added or removed between the layer 2 and
+ * layer 3 headers).
+ *
+ * * **BPF_ADJ_ROOM_NET**: Adjust room at the network layer
+ * (room space is added or removed between the layer 3 and
+ * layer 4 headers).
+ *
+ * The following flags are supported at this time:
+ *
+ * * **BPF_F_ADJ_ROOM_FIXED_GSO**: Do not adjust gso_size.
+ * Adjusting mss in this way is not allowed for datagrams.
+ *
+ * * **BPF_F_ADJ_ROOM_ENCAP_L3_IPV4**,
+ * **BPF_F_ADJ_ROOM_ENCAP_L3_IPV6**:
+ * Any new space is reserved to hold a tunnel header.
+ * Configure skb offsets and other fields accordingly.
+ *
+ * * **BPF_F_ADJ_ROOM_ENCAP_L4_GRE**,
+ * **BPF_F_ADJ_ROOM_ENCAP_L4_UDP**:
+ * Use with ENCAP_L3 flags to further specify the tunnel type.
+ *
+ * * **BPF_F_ADJ_ROOM_ENCAP_L2**\ (*len*):
+ * Use with ENCAP_L3/L4 flags to further specify the tunnel
+ * type; *len* is the length of the inner MAC header.
+ *
+ * * **BPF_F_ADJ_ROOM_ENCAP_L2_ETH**:
+ * Use with BPF_F_ADJ_ROOM_ENCAP_L2 flag to further specify the
+ * L2 type as Ethernet.
+ *
+ * * **BPF_F_ADJ_ROOM_DECAP_L3_IPV4**,
+ * **BPF_F_ADJ_ROOM_DECAP_L3_IPV6**:
+ * Indicate the new IP header version after decapsulating the outer
+ * IP header. Used when the inner and outer IP versions are different.
+ *
+ * A call to this helper is susceptible to change the underlying
+ * 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.
+ *
+ * long bpf_redirect_map(struct bpf_map *map, u64 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).
+ *
+ * The lower two bits of *flags* are used as the return code if
+ * the map lookup fails. This is so that the return value can be
+ * one of the XDP program return codes up to **XDP_TX**, as chosen
+ * by the caller. The higher bits of *flags* can be set to
+ * BPF_F_BROADCAST or BPF_F_EXCLUDE_INGRESS as defined below.
+ *
+ * With BPF_F_BROADCAST the packet will be broadcasted to all the
+ * interfaces in the map, with BPF_F_EXCLUDE_INGRESS the ingress
+ * interface will be excluded when do broadcasting.
+ *
+ * See also **bpf_redirect**\ (), which only supports redirecting
+ * to an ifindex, but doesn't require a map to do so.
+ * Return
+ * **XDP_REDIRECT** on success, or the value of the two lower bits
+ * of the *flags* argument on error.
+ *
+ * long bpf_sk_redirect_map(struct sk_buff *skb, 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.
+ *
+ * long 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.
+ *
+ * long 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 underlying
+ * 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.
+ *
+ * long 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 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.
+ *
+ * long bpf_perf_prog_read_value(struct bpf_perf_event_data *ctx, struct bpf_perf_event_value *buf, u32 buf_size)
+ * Description
+ * For an 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.
+ *
+ * long bpf_getsockopt(void *bpf_socket, int level, int optname, void *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*.
+ *
+ * *bpf_socket* should be one of the following:
+ *
+ * * **struct bpf_sock_ops** for **BPF_PROG_TYPE_SOCK_OPS**.
+ * * **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT**
+ * and **BPF_CGROUP_INET6_CONNECT**.
+ *
+ * This helper actually implements a subset of **getsockopt()**.
+ * It supports the same set of *optname*\ s that is supported by
+ * the **bpf_setsockopt**\ () helper. The exceptions are
+ * **TCP_BPF_*** is **bpf_setsockopt**\ () only and
+ * **TCP_SAVED_SYN** is **bpf_getsockopt**\ () only.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_override_return(struct pt_regs *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 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
+ *
+ * long 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.
+ *
+ * *argval* is a flag array which can combine these flags:
+ *
+ * * **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)
+ * * **BPF_SOCK_OPS_RTT_CB_FLAG** (every RTT)
+ *
+ * Therefore, this function can be used to clear a callback flag by
+ * setting the appropriate bit to zero. e.g. to disable the RTO
+ * callback:
+ *
+ * **bpf_sock_ops_cb_flags_set(bpf_sock,**
+ * **bpf_sock->bpf_sock_ops_cb_flags & ~BPF_SOCK_OPS_RTO_CB_FLAG)**
+ *
+ * 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).
+ *
+ * long 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.
+ *
+ * long 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
+ *
+ * long 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
+ *
+ * long 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 underlying
+ * 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.
+ *
+ * long 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**). It's advised to pass zero port (**sin_port**
+ * or **sin6_port**) which triggers IP_BIND_ADDRESS_NO_PORT-like
+ * behavior and lets the kernel efficiently pick up an unused
+ * port as long as 4-tuple is unique. Passing non-zero port might
+ * lead to degraded performance.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_xdp_adjust_tail(struct xdp_buff *xdp_md, int delta)
+ * Description
+ * Adjust (move) *xdp_md*\ **->data_end** by *delta* bytes. It is
+ * possible to both shrink and grow the packet tail.
+ * Shrink done via *delta* being a negative integer.
+ *
+ * A call to this helper is susceptible to change the underlying
+ * 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.
+ *
+ * long 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.
+ *
+ * long bpf_get_stack(void *ctx, 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 (build_id, file_offset) instead of ips for user
+ * stack, only valid if **BPF_F_USER_STACK** is also
+ * specified.
+ *
+ * *file_offset* is an offset relative to the beginning
+ * of the executable or shared object file backing the vma
+ * which the *ip* falls in. It is *not* an offset relative
+ * to that object's base address. Accordingly, it must be
+ * adjusted by adding (sh_addr - sh_offset), where
+ * sh_{addr,offset} correspond to the executable section
+ * containing *file_offset* in the object, for comparisons
+ * to symbols' st_value to be valid.
+ *
+ * **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
+ * The non-negative copied *buf* length equal to or less than
+ * *size* on success, or a negative error in case of failure.
+ *
+ * long bpf_skb_load_bytes_relative(const void *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.
+ *
+ * long 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_TBID**
+ * Used with BPF_FIB_LOOKUP_DIRECT.
+ * Use the routing table ID present in *params*->tbid
+ * for the fib lookup.
+ * **BPF_FIB_LOOKUP_OUTPUT**
+ * Perform lookup from an egress perspective (default is
+ * ingress).
+ * **BPF_FIB_LOOKUP_SKIP_NEIGH**
+ * Skip the neighbour table lookup. *params*->dmac
+ * and *params*->smac will not be set as output. A common
+ * use case is to call **bpf_redirect_neigh**\ () after
+ * doing **bpf_fib_lookup**\ ().
+ *
+ * *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
+ *
+ * If lookup fails with BPF_FIB_LKUP_RET_FRAG_NEEDED, then the MTU
+ * was exceeded and output params->mtu_result contains the MTU.
+ *
+ * long bpf_sock_hash_update(struct bpf_sock_ops *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.
+ *
+ * long 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.
+ *
+ * long 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 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 otherwise). This is the only flag supported for now.
+ * Return
+ * **SK_PASS** on success, or **SK_DROP** on error.
+ *
+ * long 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.
+ * **BPF_LWT_ENCAP_IP**
+ * IP encapsulation (GRE/GUE/IPIP/etc). The outer header
+ * must be IPv4 or IPv6, followed by zero or more
+ * additional headers, up to **LWT_BPF_MAX_HEADROOM**
+ * total bytes in all prepended headers. Please note that
+ * if **skb_is_gso**\ (*skb*) is true, no more than two
+ * headers can be prepended, and the inner header, if
+ * present, should be either GRE or UDP/GUE.
+ *
+ * **BPF_LWT_ENCAP_SEG6**\ \* types can be called by BPF programs
+ * of type **BPF_PROG_TYPE_LWT_IN**; **BPF_LWT_ENCAP_IP** type can
+ * be called by bpf programs of types **BPF_PROG_TYPE_LWT_IN** and
+ * **BPF_PROG_TYPE_LWT_XMIT**.
+ *
+ * A call to this helper is susceptible to change the underlying
+ * 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.
+ *
+ * long 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 underlying
+ * 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.
+ *
+ * long 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 underlying
+ * 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.
+ *
+ * long 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 underlying
+ * 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.
+ *
+ * long 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
+ *
+ * long 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
+ *
+ * u64 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_get_current_cgroup_id(void)
+ * Description
+ * Get the current cgroup id based on the cgroup within which
+ * the current task is running.
+ * Return
+ * A 64-bit integer containing the current cgroup id based
+ * on the cgroup within which the current task is running.
+ *
+ * void *bpf_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_ATOMIC** instructions to alter
+ * the shared data.
+ * Return
+ * A pointer to the local storage area.
+ *
+ * long bpf_sk_select_reuseport(struct sk_reuseport_md *reuse, struct bpf_map *map, void *key, u64 flags)
+ * Description
+ * Select a **SO_REUSEPORT** socket from a
+ * **BPF_MAP_TYPE_REUSEPORT_SOCKARRAY** *map*.
+ * It checks the selected socket is matching the incoming
+ * request in the socket buffer.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * 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.
+ *
+ * struct bpf_sock *bpf_sk_lookup_tcp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags)
+ * Description
+ * Look for TCP socket matching *tuple*, optionally in a child
+ * network namespace *netns*. The return value must be checked,
+ * and if non-**NULL**, released via **bpf_sk_release**\ ().
+ *
+ * The *ctx* should point to the context of the program, such as
+ * the skb or socket (depending on the hook in use). This is used
+ * to determine the base network namespace for the lookup.
+ *
+ * *tuple_size* must be one of:
+ *
+ * **sizeof**\ (*tuple*\ **->ipv4**)
+ * Look for an IPv4 socket.
+ * **sizeof**\ (*tuple*\ **->ipv6**)
+ * Look for an IPv6 socket.
+ *
+ * If the *netns* is a negative signed 32-bit integer, then the
+ * socket lookup table in the netns associated with the *ctx*
+ * will be used. For the TC hooks, this is the netns of the device
+ * in the skb. For socket hooks, this is the netns of the socket.
+ * If *netns* is any other signed 32-bit value greater than or
+ * equal to zero then it specifies the ID of the netns relative to
+ * the netns associated with the *ctx*. *netns* values beyond the
+ * range of 32-bit integers are reserved for future use.
+ *
+ * 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_NET** configuration option.
+ * Return
+ * Pointer to **struct bpf_sock**, or **NULL** in case of failure.
+ * For sockets with reuseport option, the **struct bpf_sock**
+ * result is from *reuse*\ **->socks**\ [] using the hash of the
+ * tuple.
+ *
+ * struct bpf_sock *bpf_sk_lookup_udp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags)
+ * Description
+ * Look for UDP socket matching *tuple*, optionally in a child
+ * network namespace *netns*. The return value must be checked,
+ * and if non-**NULL**, released via **bpf_sk_release**\ ().
+ *
+ * The *ctx* should point to the context of the program, such as
+ * the skb or socket (depending on the hook in use). This is used
+ * to determine the base network namespace for the lookup.
+ *
+ * *tuple_size* must be one of:
+ *
+ * **sizeof**\ (*tuple*\ **->ipv4**)
+ * Look for an IPv4 socket.
+ * **sizeof**\ (*tuple*\ **->ipv6**)
+ * Look for an IPv6 socket.
+ *
+ * If the *netns* is a negative signed 32-bit integer, then the
+ * socket lookup table in the netns associated with the *ctx*
+ * will be used. For the TC hooks, this is the netns of the device
+ * in the skb. For socket hooks, this is the netns of the socket.
+ * If *netns* is any other signed 32-bit value greater than or
+ * equal to zero then it specifies the ID of the netns relative to
+ * the netns associated with the *ctx*. *netns* values beyond the
+ * range of 32-bit integers are reserved for future use.
+ *
+ * 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_NET** configuration option.
+ * Return
+ * Pointer to **struct bpf_sock**, or **NULL** in case of failure.
+ * For sockets with reuseport option, the **struct bpf_sock**
+ * result is from *reuse*\ **->socks**\ [] using the hash of the
+ * tuple.
+ *
+ * long bpf_sk_release(void *sock)
+ * Description
+ * Release the reference held by *sock*. *sock* must be a
+ * non-**NULL** pointer that was returned from
+ * **bpf_sk_lookup_xxx**\ ().
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_map_push_elem(struct bpf_map *map, const void *value, u64 flags)
+ * Description
+ * Push an element *value* in *map*. *flags* is one of:
+ *
+ * **BPF_EXIST**
+ * If the queue/stack is full, the oldest element is
+ * removed to make room for this.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_map_pop_elem(struct bpf_map *map, void *value)
+ * Description
+ * Pop an element from *map*.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_map_peek_elem(struct bpf_map *map, void *value)
+ * Description
+ * Get an element from *map* without removing it.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_msg_push_data(struct sk_msg_buff *msg, u32 start, u32 len, u64 flags)
+ * Description
+ * For socket policies, insert *len* bytes into *msg* at offset
+ * *start*.
+ *
+ * If a program of type **BPF_PROG_TYPE_SK_MSG** is run on a
+ * *msg* it may want to insert metadata or options into the *msg*.
+ * This can later be read and used by any of the lower layer BPF
+ * hooks.
+ *
+ * This helper may fail if under memory pressure (a malloc
+ * fails) in these cases BPF programs will get an appropriate
+ * error and BPF programs will need to handle them.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_msg_pop_data(struct sk_msg_buff *msg, u32 start, u32 len, u64 flags)
+ * Description
+ * Will remove *len* bytes from a *msg* starting at byte *start*.
+ * This may result in **ENOMEM** errors under certain situations if
+ * an allocation and copy are required due to a full ring buffer.
+ * However, the helper will try to avoid doing the allocation
+ * if possible. Other errors can occur if input parameters are
+ * invalid either due to *start* byte not being valid part of *msg*
+ * payload and/or *pop* value being to large.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_rc_pointer_rel(void *ctx, s32 rel_x, s32 rel_y)
+ * Description
+ * This helper is used in programs implementing IR decoding, to
+ * report a successfully decoded pointer movement.
+ *
+ * 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
+ *
+ * long bpf_spin_lock(struct bpf_spin_lock *lock)
+ * Description
+ * Acquire a spinlock represented by the pointer *lock*, which is
+ * stored as part of a value of a map. Taking the lock allows to
+ * safely update the rest of the fields in that value. The
+ * spinlock can (and must) later be released with a call to
+ * **bpf_spin_unlock**\ (\ *lock*\ ).
+ *
+ * Spinlocks in BPF programs come with a number of restrictions
+ * and constraints:
+ *
+ * * **bpf_spin_lock** objects are only allowed inside maps of
+ * types **BPF_MAP_TYPE_HASH** and **BPF_MAP_TYPE_ARRAY** (this
+ * list could be extended in the future).
+ * * BTF description of the map is mandatory.
+ * * The BPF program can take ONE lock at a time, since taking two
+ * or more could cause dead locks.
+ * * Only one **struct bpf_spin_lock** is allowed per map element.
+ * * When the lock is taken, calls (either BPF to BPF or helpers)
+ * are not allowed.
+ * * The **BPF_LD_ABS** and **BPF_LD_IND** instructions are not
+ * allowed inside a spinlock-ed region.
+ * * The BPF program MUST call **bpf_spin_unlock**\ () to release
+ * the lock, on all execution paths, before it returns.
+ * * The BPF program can access **struct bpf_spin_lock** only via
+ * the **bpf_spin_lock**\ () and **bpf_spin_unlock**\ ()
+ * helpers. Loading or storing data into the **struct
+ * bpf_spin_lock** *lock*\ **;** field of a map is not allowed.
+ * * To use the **bpf_spin_lock**\ () helper, the BTF description
+ * of the map value must be a struct and have **struct
+ * bpf_spin_lock** *anyname*\ **;** field at the top level.
+ * Nested lock inside another struct is not allowed.
+ * * The **struct bpf_spin_lock** *lock* field in a map value must
+ * be aligned on a multiple of 4 bytes in that value.
+ * * Syscall with command **BPF_MAP_LOOKUP_ELEM** does not copy
+ * the **bpf_spin_lock** field to user space.
+ * * Syscall with command **BPF_MAP_UPDATE_ELEM**, or update from
+ * a BPF program, do not update the **bpf_spin_lock** field.
+ * * **bpf_spin_lock** cannot be on the stack or inside a
+ * networking packet (it can only be inside of a map values).
+ * * **bpf_spin_lock** is available to root only.
+ * * Tracing programs and socket filter programs cannot use
+ * **bpf_spin_lock**\ () due to insufficient preemption checks
+ * (but this may change in the future).
+ * * **bpf_spin_lock** is not allowed in inner maps of map-in-map.
+ * Return
+ * 0
+ *
+ * long bpf_spin_unlock(struct bpf_spin_lock *lock)
+ * Description
+ * Release the *lock* previously locked by a call to
+ * **bpf_spin_lock**\ (\ *lock*\ ).
+ * Return
+ * 0
+ *
+ * struct bpf_sock *bpf_sk_fullsock(struct bpf_sock *sk)
+ * Description
+ * This helper gets a **struct bpf_sock** pointer such
+ * that all the fields in this **bpf_sock** can be accessed.
+ * Return
+ * A **struct bpf_sock** pointer on success, or **NULL** in
+ * case of failure.
+ *
+ * struct bpf_tcp_sock *bpf_tcp_sock(struct bpf_sock *sk)
+ * Description
+ * This helper gets a **struct bpf_tcp_sock** pointer from a
+ * **struct bpf_sock** pointer.
+ * Return
+ * A **struct bpf_tcp_sock** pointer on success, or **NULL** in
+ * case of failure.
+ *
+ * long bpf_skb_ecn_set_ce(struct sk_buff *skb)
+ * Description
+ * Set ECN (Explicit Congestion Notification) field of IP header
+ * to **CE** (Congestion Encountered) if current value is **ECT**
+ * (ECN Capable Transport). Otherwise, do nothing. Works with IPv6
+ * and IPv4.
+ * Return
+ * 1 if the **CE** flag is set (either by the current helper call
+ * or because it was already present), 0 if it is not set.
+ *
+ * struct bpf_sock *bpf_get_listener_sock(struct bpf_sock *sk)
+ * Description
+ * Return a **struct bpf_sock** pointer in **TCP_LISTEN** state.
+ * **bpf_sk_release**\ () is unnecessary and not allowed.
+ * Return
+ * A **struct bpf_sock** pointer on success, or **NULL** in
+ * case of failure.
+ *
+ * struct bpf_sock *bpf_skc_lookup_tcp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags)
+ * Description
+ * Look for TCP socket matching *tuple*, optionally in a child
+ * network namespace *netns*. The return value must be checked,
+ * and if non-**NULL**, released via **bpf_sk_release**\ ().
+ *
+ * This function is identical to **bpf_sk_lookup_tcp**\ (), except
+ * that it also returns timewait or request sockets. Use
+ * **bpf_sk_fullsock**\ () or **bpf_tcp_sock**\ () to access the
+ * full structure.
+ *
+ * This helper is available only if the kernel was compiled with
+ * **CONFIG_NET** configuration option.
+ * Return
+ * Pointer to **struct bpf_sock**, or **NULL** in case of failure.
+ * For sockets with reuseport option, the **struct bpf_sock**
+ * result is from *reuse*\ **->socks**\ [] using the hash of the
+ * tuple.
+ *
+ * long bpf_tcp_check_syncookie(void *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len)
+ * Description
+ * Check whether *iph* and *th* contain a valid SYN cookie ACK for
+ * the listening socket in *sk*.
+ *
+ * *iph* points to the start of the IPv4 or IPv6 header, while
+ * *iph_len* contains **sizeof**\ (**struct iphdr**) or
+ * **sizeof**\ (**struct ipv6hdr**).
+ *
+ * *th* points to the start of the TCP header, while *th_len*
+ * contains the length of the TCP header (at least
+ * **sizeof**\ (**struct tcphdr**)).
+ * Return
+ * 0 if *iph* and *th* are a valid SYN cookie ACK, or a negative
+ * error otherwise.
+ *
+ * long bpf_sysctl_get_name(struct bpf_sysctl *ctx, char *buf, size_t buf_len, u64 flags)
+ * Description
+ * Get name of sysctl in /proc/sys/ and copy it into provided by
+ * program buffer *buf* of size *buf_len*.
+ *
+ * The buffer is always NUL terminated, unless it's zero-sized.
+ *
+ * If *flags* is zero, full name (e.g. "net/ipv4/tcp_mem") is
+ * copied. Use **BPF_F_SYSCTL_BASE_NAME** flag to copy base name
+ * only (e.g. "tcp_mem").
+ * Return
+ * Number of character copied (not including the trailing NUL).
+ *
+ * **-E2BIG** if the buffer wasn't big enough (*buf* will contain
+ * truncated name in this case).
+ *
+ * long bpf_sysctl_get_current_value(struct bpf_sysctl *ctx, char *buf, size_t buf_len)
+ * Description
+ * Get current value of sysctl as it is presented in /proc/sys
+ * (incl. newline, etc), and copy it as a string into provided
+ * by program buffer *buf* of size *buf_len*.
+ *
+ * The whole value is copied, no matter what file position user
+ * space issued e.g. sys_read at.
+ *
+ * The buffer is always NUL terminated, unless it's zero-sized.
+ * Return
+ * Number of character copied (not including the trailing NUL).
+ *
+ * **-E2BIG** if the buffer wasn't big enough (*buf* will contain
+ * truncated name in this case).
+ *
+ * **-EINVAL** if current value was unavailable, e.g. because
+ * sysctl is uninitialized and read returns -EIO for it.
+ *
+ * long bpf_sysctl_get_new_value(struct bpf_sysctl *ctx, char *buf, size_t buf_len)
+ * Description
+ * Get new value being written by user space to sysctl (before
+ * the actual write happens) and copy it as a string into
+ * provided by program buffer *buf* of size *buf_len*.
+ *
+ * User space may write new value at file position > 0.
+ *
+ * The buffer is always NUL terminated, unless it's zero-sized.
+ * Return
+ * Number of character copied (not including the trailing NUL).
+ *
+ * **-E2BIG** if the buffer wasn't big enough (*buf* will contain
+ * truncated name in this case).
+ *
+ * **-EINVAL** if sysctl is being read.
+ *
+ * long bpf_sysctl_set_new_value(struct bpf_sysctl *ctx, const char *buf, size_t buf_len)
+ * Description
+ * Override new value being written by user space to sysctl with
+ * value provided by program in buffer *buf* of size *buf_len*.
+ *
+ * *buf* should contain a string in same form as provided by user
+ * space on sysctl write.
+ *
+ * User space may write new value at file position > 0. To override
+ * the whole sysctl value file position should be set to zero.
+ * Return
+ * 0 on success.
+ *
+ * **-E2BIG** if the *buf_len* is too big.
+ *
+ * **-EINVAL** if sysctl is being read.
+ *
+ * long bpf_strtol(const char *buf, size_t buf_len, u64 flags, long *res)
+ * Description
+ * Convert the initial part of the string from buffer *buf* of
+ * size *buf_len* to a long integer according to the given base
+ * and save the result in *res*.
+ *
+ * The string may begin with an arbitrary amount of white space
+ * (as determined by **isspace**\ (3)) followed by a single
+ * optional '**-**' sign.
+ *
+ * Five least significant bits of *flags* encode base, other bits
+ * are currently unused.
+ *
+ * Base must be either 8, 10, 16 or 0 to detect it automatically
+ * similar to user space **strtol**\ (3).
+ * Return
+ * Number of characters consumed on success. Must be positive but
+ * no more than *buf_len*.
+ *
+ * **-EINVAL** if no valid digits were found or unsupported base
+ * was provided.
+ *
+ * **-ERANGE** if resulting value was out of range.
+ *
+ * long bpf_strtoul(const char *buf, size_t buf_len, u64 flags, unsigned long *res)
+ * Description
+ * Convert the initial part of the string from buffer *buf* of
+ * size *buf_len* to an unsigned long integer according to the
+ * given base and save the result in *res*.
+ *
+ * The string may begin with an arbitrary amount of white space
+ * (as determined by **isspace**\ (3)).
+ *
+ * Five least significant bits of *flags* encode base, other bits
+ * are currently unused.
+ *
+ * Base must be either 8, 10, 16 or 0 to detect it automatically
+ * similar to user space **strtoul**\ (3).
+ * Return
+ * Number of characters consumed on success. Must be positive but
+ * no more than *buf_len*.
+ *
+ * **-EINVAL** if no valid digits were found or unsupported base
+ * was provided.
+ *
+ * **-ERANGE** if resulting value was out of range.
+ *
+ * void *bpf_sk_storage_get(struct bpf_map *map, void *sk, void *value, u64 flags)
+ * Description
+ * Get a bpf-local-storage from a *sk*.
+ *
+ * Logically, it could be thought of getting the value from
+ * a *map* with *sk* as the **key**. From this
+ * perspective, the usage is not much different from
+ * **bpf_map_lookup_elem**\ (*map*, **&**\ *sk*) except this
+ * helper enforces the key must be a full socket and the map must
+ * be a **BPF_MAP_TYPE_SK_STORAGE** also.
+ *
+ * Underneath, the value is stored locally at *sk* instead of
+ * the *map*. The *map* is used as the bpf-local-storage
+ * "type". The bpf-local-storage "type" (i.e. the *map*) is
+ * searched against all bpf-local-storages residing at *sk*.
+ *
+ * *sk* is a kernel **struct sock** pointer for LSM program.
+ * *sk* is a **struct bpf_sock** pointer for other program types.
+ *
+ * An optional *flags* (**BPF_SK_STORAGE_GET_F_CREATE**) can be
+ * used such that a new bpf-local-storage will be
+ * created if one does not exist. *value* can be used
+ * together with **BPF_SK_STORAGE_GET_F_CREATE** to specify
+ * the initial value of a bpf-local-storage. If *value* is
+ * **NULL**, the new bpf-local-storage will be zero initialized.
+ * Return
+ * A bpf-local-storage pointer is returned on success.
+ *
+ * **NULL** if not found or there was an error in adding
+ * a new bpf-local-storage.
+ *
+ * long bpf_sk_storage_delete(struct bpf_map *map, void *sk)
+ * Description
+ * Delete a bpf-local-storage from a *sk*.
+ * Return
+ * 0 on success.
+ *
+ * **-ENOENT** if the bpf-local-storage cannot be found.
+ * **-EINVAL** if sk is not a fullsock (e.g. a request_sock).
+ *
+ * long bpf_send_signal(u32 sig)
+ * Description
+ * Send signal *sig* to the process of the current task.
+ * The signal may be delivered to any of this process's threads.
+ * Return
+ * 0 on success or successfully queued.
+ *
+ * **-EBUSY** if work queue under nmi is full.
+ *
+ * **-EINVAL** if *sig* is invalid.
+ *
+ * **-EPERM** if no permission to send the *sig*.
+ *
+ * **-EAGAIN** if bpf program can try again.
+ *
+ * s64 bpf_tcp_gen_syncookie(void *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len)
+ * Description
+ * Try to issue a SYN cookie for the packet with corresponding
+ * IP/TCP headers, *iph* and *th*, on the listening socket in *sk*.
+ *
+ * *iph* points to the start of the IPv4 or IPv6 header, while
+ * *iph_len* contains **sizeof**\ (**struct iphdr**) or
+ * **sizeof**\ (**struct ipv6hdr**).
+ *
+ * *th* points to the start of the TCP header, while *th_len*
+ * contains the length of the TCP header with options (at least
+ * **sizeof**\ (**struct tcphdr**)).
+ * Return
+ * On success, lower 32 bits hold the generated SYN cookie in
+ * followed by 16 bits which hold the MSS value for that cookie,
+ * and the top 16 bits are unused.
+ *
+ * On failure, the returned value is one of the following:
+ *
+ * **-EINVAL** SYN cookie cannot be issued due to error
+ *
+ * **-ENOENT** SYN cookie should not be issued (no SYN flood)
+ *
+ * **-EOPNOTSUPP** kernel configuration does not enable SYN cookies
+ *
+ * **-EPROTONOSUPPORT** IP packet version is not 4 or 6
+ *
+ * long bpf_skb_output(void *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*.
+ *
+ * *ctx* is a pointer to in-kernel struct sk_buff.
+ *
+ * This helper is similar to **bpf_perf_event_output**\ () but
+ * restricted to raw_tracepoint bpf programs.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_probe_read_user(void *dst, u32 size, const void *unsafe_ptr)
+ * Description
+ * Safely attempt to read *size* bytes from user space address
+ * *unsafe_ptr* and store the data in *dst*.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_probe_read_kernel(void *dst, u32 size, const void *unsafe_ptr)
+ * Description
+ * Safely attempt to read *size* bytes from kernel space address
+ * *unsafe_ptr* and store the data in *dst*.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_probe_read_user_str(void *dst, u32 size, const void *unsafe_ptr)
+ * Description
+ * Copy a NUL terminated string from an unsafe user 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, returns the number of bytes that were written,
+ * including the terminal NUL. 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_user_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_user**\ () 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 output string,
+ * including the trailing NUL character. On error, a negative
+ * value.
+ *
+ * long bpf_probe_read_kernel_str(void *dst, u32 size, const void *unsafe_ptr)
+ * Description
+ * Copy a NUL terminated string from an unsafe kernel address *unsafe_ptr*
+ * to *dst*. Same semantics as with **bpf_probe_read_user_str**\ () apply.
+ * Return
+ * On success, the strictly positive length of the string, including
+ * the trailing NUL character. On error, a negative value.
+ *
+ * long bpf_tcp_send_ack(void *tp, u32 rcv_nxt)
+ * Description
+ * Send out a tcp-ack. *tp* is the in-kernel struct **tcp_sock**.
+ * *rcv_nxt* is the ack_seq to be sent out.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_send_signal_thread(u32 sig)
+ * Description
+ * Send signal *sig* to the thread corresponding to the current task.
+ * Return
+ * 0 on success or successfully queued.
+ *
+ * **-EBUSY** if work queue under nmi is full.
+ *
+ * **-EINVAL** if *sig* is invalid.
+ *
+ * **-EPERM** if no permission to send the *sig*.
+ *
+ * **-EAGAIN** if bpf program can try again.
+ *
+ * u64 bpf_jiffies64(void)
+ * Description
+ * Obtain the 64bit jiffies
+ * Return
+ * The 64 bit jiffies
+ *
+ * long bpf_read_branch_records(struct bpf_perf_event_data *ctx, void *buf, u32 size, u64 flags)
+ * Description
+ * For an eBPF program attached to a perf event, retrieve the
+ * branch records (**struct perf_branch_entry**) associated to *ctx*
+ * and store it in the buffer pointed by *buf* up to size
+ * *size* bytes.
+ * Return
+ * On success, number of bytes written to *buf*. On error, a
+ * negative value.
+ *
+ * The *flags* can be set to **BPF_F_GET_BRANCH_RECORDS_SIZE** to
+ * instead return the number of bytes required to store all the
+ * branch entries. If this flag is set, *buf* may be NULL.
+ *
+ * **-EINVAL** if arguments invalid or **size** not a multiple
+ * of **sizeof**\ (**struct perf_branch_entry**\ ).
+ *
+ * **-ENOENT** if architecture does not support branch records.
+ *
+ * long bpf_get_ns_current_pid_tgid(u64 dev, u64 ino, struct bpf_pidns_info *nsdata, u32 size)
+ * Description
+ * Returns 0 on success, values for *pid* and *tgid* as seen from the current
+ * *namespace* will be returned in *nsdata*.
+ * Return
+ * 0 on success, or one of the following in case of failure:
+ *
+ * **-EINVAL** if dev and inum supplied don't match dev_t and inode number
+ * with nsfs of current task, or if dev conversion to dev_t lost high bits.
+ *
+ * **-ENOENT** if pidns does not exists for the current task.
+ *
+ * long bpf_xdp_output(void *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*.
+ *
+ * *ctx* is a pointer to in-kernel struct xdp_buff.
+ *
+ * This helper is similar to **bpf_perf_eventoutput**\ () but
+ * restricted to raw_tracepoint bpf programs.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * u64 bpf_get_netns_cookie(void *ctx)
+ * Description
+ * Retrieve the cookie (generated by the kernel) of the network
+ * namespace the input *ctx* is associated with. The network
+ * namespace cookie remains stable for its lifetime and provides
+ * a global identifier that can be assumed unique. If *ctx* is
+ * NULL, then the helper returns the cookie for the initial
+ * network namespace. The cookie itself is very similar to that
+ * of **bpf_get_socket_cookie**\ () helper, but for network
+ * namespaces instead of sockets.
+ * Return
+ * A 8-byte long opaque number.
+ *
+ * u64 bpf_get_current_ancestor_cgroup_id(int ancestor_level)
+ * Description
+ * Return id of cgroup v2 that is ancestor of the cgroup associated
+ * with the current task 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 the current task, then return value will be the
+ * same as that of **bpf_get_current_cgroup_id**\ ().
+ *
+ * The helper is useful to implement policies based on cgroups
+ * that are upper in hierarchy than immediate cgroup associated
+ * with the current task.
+ *
+ * The format of returned id and helper limitations are same as in
+ * **bpf_get_current_cgroup_id**\ ().
+ * Return
+ * The id is returned or 0 in case the id could not be retrieved.
+ *
+ * long bpf_sk_assign(struct sk_buff *skb, void *sk, u64 flags)
+ * Description
+ * Helper is overloaded depending on BPF program type. This
+ * description applies to **BPF_PROG_TYPE_SCHED_CLS** and
+ * **BPF_PROG_TYPE_SCHED_ACT** programs.
+ *
+ * Assign the *sk* to the *skb*. When combined with appropriate
+ * routing configuration to receive the packet towards the socket,
+ * will cause *skb* to be delivered to the specified socket.
+ * Subsequent redirection of *skb* via **bpf_redirect**\ (),
+ * **bpf_clone_redirect**\ () or other methods outside of BPF may
+ * interfere with successful delivery to the socket.
+ *
+ * This operation is only valid from TC ingress path.
+ *
+ * The *flags* argument must be zero.
+ * Return
+ * 0 on success, or a negative error in case of failure:
+ *
+ * **-EINVAL** if specified *flags* are not supported.
+ *
+ * **-ENOENT** if the socket is unavailable for assignment.
+ *
+ * **-ENETUNREACH** if the socket is unreachable (wrong netns).
+ *
+ * **-EOPNOTSUPP** if the operation is not supported, for example
+ * a call from outside of TC ingress.
+ *
+ * long bpf_sk_assign(struct bpf_sk_lookup *ctx, struct bpf_sock *sk, u64 flags)
+ * Description
+ * Helper is overloaded depending on BPF program type. This
+ * description applies to **BPF_PROG_TYPE_SK_LOOKUP** programs.
+ *
+ * Select the *sk* as a result of a socket lookup.
+ *
+ * For the operation to succeed passed socket must be compatible
+ * with the packet description provided by the *ctx* object.
+ *
+ * L4 protocol (**IPPROTO_TCP** or **IPPROTO_UDP**) must
+ * be an exact match. While IP family (**AF_INET** or
+ * **AF_INET6**) must be compatible, that is IPv6 sockets
+ * that are not v6-only can be selected for IPv4 packets.
+ *
+ * Only TCP listeners and UDP unconnected sockets can be
+ * selected. *sk* can also be NULL to reset any previous
+ * selection.
+ *
+ * *flags* argument can combination of following values:
+ *
+ * * **BPF_SK_LOOKUP_F_REPLACE** to override the previous
+ * socket selection, potentially done by a BPF program
+ * that ran before us.
+ *
+ * * **BPF_SK_LOOKUP_F_NO_REUSEPORT** to skip
+ * load-balancing within reuseport group for the socket
+ * being selected.
+ *
+ * On success *ctx->sk* will point to the selected socket.
+ *
+ * Return
+ * 0 on success, or a negative errno in case of failure.
+ *
+ * * **-EAFNOSUPPORT** if socket family (*sk->family*) is
+ * not compatible with packet family (*ctx->family*).
+ *
+ * * **-EEXIST** if socket has been already selected,
+ * potentially by another program, and
+ * **BPF_SK_LOOKUP_F_REPLACE** flag was not specified.
+ *
+ * * **-EINVAL** if unsupported flags were specified.
+ *
+ * * **-EPROTOTYPE** if socket L4 protocol
+ * (*sk->protocol*) doesn't match packet protocol
+ * (*ctx->protocol*).
+ *
+ * * **-ESOCKTNOSUPPORT** if socket is not in allowed
+ * state (TCP listening or UDP unconnected).
+ *
+ * u64 bpf_ktime_get_boot_ns(void)
+ * Description
+ * Return the time elapsed since system boot, in nanoseconds.
+ * Does include the time the system was suspended.
+ * See: **clock_gettime**\ (**CLOCK_BOOTTIME**)
+ * Return
+ * Current *ktime*.
+ *
+ * long bpf_seq_printf(struct seq_file *m, const char *fmt, u32 fmt_size, const void *data, u32 data_len)
+ * Description
+ * **bpf_seq_printf**\ () uses seq_file **seq_printf**\ () to print
+ * out the format string.
+ * The *m* represents the seq_file. The *fmt* and *fmt_size* are for
+ * the format string itself. The *data* and *data_len* are format string
+ * arguments. The *data* are a **u64** array and corresponding format string
+ * values are stored in the array. For strings and pointers where pointees
+ * are accessed, only the pointer values are stored in the *data* array.
+ * The *data_len* is the size of *data* in bytes - must be a multiple of 8.
+ *
+ * Formats **%s**, **%p{i,I}{4,6}** requires to read kernel memory.
+ * Reading kernel memory may fail due to either invalid address or
+ * valid address but requiring a major memory fault. If reading kernel memory
+ * fails, the string for **%s** will be an empty string, and the ip
+ * address for **%p{i,I}{4,6}** will be 0. Not returning error to
+ * bpf program is consistent with what **bpf_trace_printk**\ () does for now.
+ * Return
+ * 0 on success, or a negative error in case of failure:
+ *
+ * **-EBUSY** if per-CPU memory copy buffer is busy, can try again
+ * by returning 1 from bpf program.
+ *
+ * **-EINVAL** if arguments are invalid, or if *fmt* is invalid/unsupported.
+ *
+ * **-E2BIG** if *fmt* contains too many format specifiers.
+ *
+ * **-EOVERFLOW** if an overflow happened: The same object will be tried again.
+ *
+ * long bpf_seq_write(struct seq_file *m, const void *data, u32 len)
+ * Description
+ * **bpf_seq_write**\ () uses seq_file **seq_write**\ () to write the data.
+ * The *m* represents the seq_file. The *data* and *len* represent the
+ * data to write in bytes.
+ * Return
+ * 0 on success, or a negative error in case of failure:
+ *
+ * **-EOVERFLOW** if an overflow happened: The same object will be tried again.
+ *
+ * u64 bpf_sk_cgroup_id(void *sk)
+ * Description
+ * Return the cgroup v2 id of the socket *sk*.
+ *
+ * *sk* must be a non-**NULL** pointer to a socket, e.g. one
+ * returned from **bpf_sk_lookup_xxx**\ (),
+ * **bpf_sk_fullsock**\ (), etc. The format of returned id is
+ * same as in **bpf_skb_cgroup_id**\ ().
+ *
+ * This helper 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_sk_ancestor_cgroup_id(void *sk, int ancestor_level)
+ * Description
+ * Return id of cgroup v2 that is ancestor of cgroup associated
+ * with the *sk* 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 *sk*, then return value will be same as that
+ * of **bpf_sk_cgroup_id**\ ().
+ *
+ * The helper is useful to implement policies based on cgroups
+ * that are upper in hierarchy than immediate cgroup associated
+ * with *sk*.
+ *
+ * The format of returned id and helper limitations are same as in
+ * **bpf_sk_cgroup_id**\ ().
+ * Return
+ * The id is returned or 0 in case the id could not be retrieved.
+ *
+ * long bpf_ringbuf_output(void *ringbuf, void *data, u64 size, u64 flags)
+ * Description
+ * Copy *size* bytes from *data* into a ring buffer *ringbuf*.
+ * If **BPF_RB_NO_WAKEUP** is specified in *flags*, no notification
+ * of new data availability is sent.
+ * If **BPF_RB_FORCE_WAKEUP** is specified in *flags*, notification
+ * of new data availability is sent unconditionally.
+ * If **0** is specified in *flags*, an adaptive notification
+ * of new data availability is sent.
+ *
+ * An adaptive notification is a notification sent whenever the user-space
+ * process has caught up and consumed all available payloads. In case the user-space
+ * process is still processing a previous payload, then no notification is needed
+ * as it will process the newly added payload automatically.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * void *bpf_ringbuf_reserve(void *ringbuf, u64 size, u64 flags)
+ * Description
+ * Reserve *size* bytes of payload in a ring buffer *ringbuf*.
+ * *flags* must be 0.
+ * Return
+ * Valid pointer with *size* bytes of memory available; NULL,
+ * otherwise.
+ *
+ * void bpf_ringbuf_submit(void *data, u64 flags)
+ * Description
+ * Submit reserved ring buffer sample, pointed to by *data*.
+ * If **BPF_RB_NO_WAKEUP** is specified in *flags*, no notification
+ * of new data availability is sent.
+ * If **BPF_RB_FORCE_WAKEUP** is specified in *flags*, notification
+ * of new data availability is sent unconditionally.
+ * If **0** is specified in *flags*, an adaptive notification
+ * of new data availability is sent.
+ *
+ * See 'bpf_ringbuf_output()' for the definition of adaptive notification.
+ * Return
+ * Nothing. Always succeeds.
+ *
+ * void bpf_ringbuf_discard(void *data, u64 flags)
+ * Description
+ * Discard reserved ring buffer sample, pointed to by *data*.
+ * If **BPF_RB_NO_WAKEUP** is specified in *flags*, no notification
+ * of new data availability is sent.
+ * If **BPF_RB_FORCE_WAKEUP** is specified in *flags*, notification
+ * of new data availability is sent unconditionally.
+ * If **0** is specified in *flags*, an adaptive notification
+ * of new data availability is sent.
+ *
+ * See 'bpf_ringbuf_output()' for the definition of adaptive notification.
+ * Return
+ * Nothing. Always succeeds.
+ *
+ * u64 bpf_ringbuf_query(void *ringbuf, u64 flags)
+ * Description
+ * Query various characteristics of provided ring buffer. What
+ * exactly is queries is determined by *flags*:
+ *
+ * * **BPF_RB_AVAIL_DATA**: Amount of data not yet consumed.
+ * * **BPF_RB_RING_SIZE**: The size of ring buffer.
+ * * **BPF_RB_CONS_POS**: Consumer position (can wrap around).
+ * * **BPF_RB_PROD_POS**: Producer(s) position (can wrap around).
+ *
+ * Data returned is just a momentary snapshot of actual values
+ * and could be inaccurate, so this facility should be used to
+ * power heuristics and for reporting, not to make 100% correct
+ * calculation.
+ * Return
+ * Requested value, or 0, if *flags* are not recognized.
+ *
+ * long bpf_csum_level(struct sk_buff *skb, u64 level)
+ * Description
+ * Change the skbs checksum level by one layer up or down, or
+ * reset it entirely to none in order to have the stack perform
+ * checksum validation. The level is applicable to the following
+ * protocols: TCP, UDP, GRE, SCTP, FCOE. For example, a decap of
+ * | ETH | IP | UDP | GUE | IP | TCP | into | ETH | IP | TCP |
+ * through **bpf_skb_adjust_room**\ () helper with passing in
+ * **BPF_F_ADJ_ROOM_NO_CSUM_RESET** flag would require one call
+ * to **bpf_csum_level**\ () with **BPF_CSUM_LEVEL_DEC** since
+ * the UDP header is removed. Similarly, an encap of the latter
+ * into the former could be accompanied by a helper call to
+ * **bpf_csum_level**\ () with **BPF_CSUM_LEVEL_INC** if the
+ * skb is still intended to be processed in higher layers of the
+ * stack instead of just egressing at tc.
+ *
+ * There are three supported level settings at this time:
+ *
+ * * **BPF_CSUM_LEVEL_INC**: Increases skb->csum_level for skbs
+ * with CHECKSUM_UNNECESSARY.
+ * * **BPF_CSUM_LEVEL_DEC**: Decreases skb->csum_level for skbs
+ * with CHECKSUM_UNNECESSARY.
+ * * **BPF_CSUM_LEVEL_RESET**: Resets skb->csum_level to 0 and
+ * sets CHECKSUM_NONE to force checksum validation by the stack.
+ * * **BPF_CSUM_LEVEL_QUERY**: No-op, returns the current
+ * skb->csum_level.
+ * Return
+ * 0 on success, or a negative error in case of failure. In the
+ * case of **BPF_CSUM_LEVEL_QUERY**, the current skb->csum_level
+ * is returned or the error code -EACCES in case the skb is not
+ * subject to CHECKSUM_UNNECESSARY.
+ *
+ * struct tcp6_sock *bpf_skc_to_tcp6_sock(void *sk)
+ * Description
+ * Dynamically cast a *sk* pointer to a *tcp6_sock* pointer.
+ * Return
+ * *sk* if casting is valid, or **NULL** otherwise.
+ *
+ * struct tcp_sock *bpf_skc_to_tcp_sock(void *sk)
+ * Description
+ * Dynamically cast a *sk* pointer to a *tcp_sock* pointer.
+ * Return
+ * *sk* if casting is valid, or **NULL** otherwise.
+ *
+ * struct tcp_timewait_sock *bpf_skc_to_tcp_timewait_sock(void *sk)
+ * Description
+ * Dynamically cast a *sk* pointer to a *tcp_timewait_sock* pointer.
+ * Return
+ * *sk* if casting is valid, or **NULL** otherwise.
+ *
+ * struct tcp_request_sock *bpf_skc_to_tcp_request_sock(void *sk)
+ * Description
+ * Dynamically cast a *sk* pointer to a *tcp_request_sock* pointer.
+ * Return
+ * *sk* if casting is valid, or **NULL** otherwise.
+ *
+ * struct udp6_sock *bpf_skc_to_udp6_sock(void *sk)
+ * Description
+ * Dynamically cast a *sk* pointer to a *udp6_sock* pointer.
+ * Return
+ * *sk* if casting is valid, or **NULL** otherwise.
+ *
+ * long bpf_get_task_stack(struct task_struct *task, void *buf, u32 size, u64 flags)
+ * Description
+ * Return a user or a kernel stack in bpf program provided buffer.
+ * Note: the user stack will only be populated if the *task* is
+ * the current task; all other tasks will return -EOPNOTSUPP.
+ * To achieve this, the helper needs *task*, which is a valid
+ * pointer to **struct task_struct**. 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.
+ * The *task* must be the current task.
+ * **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_task_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
+ * The non-negative copied *buf* length equal to or less than
+ * *size* on success, or a negative error in case of failure.
+ *
+ * long bpf_load_hdr_opt(struct bpf_sock_ops *skops, void *searchby_res, u32 len, u64 flags)
+ * Description
+ * Load header option. Support reading a particular TCP header
+ * option for bpf program (**BPF_PROG_TYPE_SOCK_OPS**).
+ *
+ * If *flags* is 0, it will search the option from the
+ * *skops*\ **->skb_data**. The comment in **struct bpf_sock_ops**
+ * has details on what skb_data contains under different
+ * *skops*\ **->op**.
+ *
+ * The first byte of the *searchby_res* specifies the
+ * kind that it wants to search.
+ *
+ * If the searching kind is an experimental kind
+ * (i.e. 253 or 254 according to RFC6994). It also
+ * needs to specify the "magic" which is either
+ * 2 bytes or 4 bytes. It then also needs to
+ * specify the size of the magic by using
+ * the 2nd byte which is "kind-length" of a TCP
+ * header option and the "kind-length" also
+ * includes the first 2 bytes "kind" and "kind-length"
+ * itself as a normal TCP header option also does.
+ *
+ * For example, to search experimental kind 254 with
+ * 2 byte magic 0xeB9F, the searchby_res should be
+ * [ 254, 4, 0xeB, 0x9F, 0, 0, .... 0 ].
+ *
+ * To search for the standard window scale option (3),
+ * the *searchby_res* should be [ 3, 0, 0, .... 0 ].
+ * Note, kind-length must be 0 for regular option.
+ *
+ * Searching for No-Op (0) and End-of-Option-List (1) are
+ * not supported.
+ *
+ * *len* must be at least 2 bytes which is the minimal size
+ * of a header option.
+ *
+ * Supported flags:
+ *
+ * * **BPF_LOAD_HDR_OPT_TCP_SYN** to search from the
+ * saved_syn packet or the just-received syn packet.
+ *
+ * Return
+ * > 0 when found, the header option is copied to *searchby_res*.
+ * The return value is the total length copied. On failure, a
+ * negative error code is returned:
+ *
+ * **-EINVAL** if a parameter is invalid.
+ *
+ * **-ENOMSG** if the option is not found.
+ *
+ * **-ENOENT** if no syn packet is available when
+ * **BPF_LOAD_HDR_OPT_TCP_SYN** is used.
+ *
+ * **-ENOSPC** if there is not enough space. Only *len* number of
+ * bytes are copied.
+ *
+ * **-EFAULT** on failure to parse the header options in the
+ * packet.
+ *
+ * **-EPERM** if the helper cannot be used under the current
+ * *skops*\ **->op**.
+ *
+ * long bpf_store_hdr_opt(struct bpf_sock_ops *skops, const void *from, u32 len, u64 flags)
+ * Description
+ * Store header option. The data will be copied
+ * from buffer *from* with length *len* to the TCP header.
+ *
+ * The buffer *from* should have the whole option that
+ * includes the kind, kind-length, and the actual
+ * option data. The *len* must be at least kind-length
+ * long. The kind-length does not have to be 4 byte
+ * aligned. The kernel will take care of the padding
+ * and setting the 4 bytes aligned value to th->doff.
+ *
+ * This helper will check for duplicated option
+ * by searching the same option in the outgoing skb.
+ *
+ * This helper can only be called during
+ * **BPF_SOCK_OPS_WRITE_HDR_OPT_CB**.
+ *
+ * Return
+ * 0 on success, or negative error in case of failure:
+ *
+ * **-EINVAL** If param is invalid.
+ *
+ * **-ENOSPC** if there is not enough space in the header.
+ * Nothing has been written
+ *
+ * **-EEXIST** if the option already exists.
+ *
+ * **-EFAULT** on failure to parse the existing header options.
+ *
+ * **-EPERM** if the helper cannot be used under the current
+ * *skops*\ **->op**.
+ *
+ * long bpf_reserve_hdr_opt(struct bpf_sock_ops *skops, u32 len, u64 flags)
+ * Description
+ * Reserve *len* bytes for the bpf header option. The
+ * space will be used by **bpf_store_hdr_opt**\ () later in
+ * **BPF_SOCK_OPS_WRITE_HDR_OPT_CB**.
+ *
+ * If **bpf_reserve_hdr_opt**\ () is called multiple times,
+ * the total number of bytes will be reserved.
+ *
+ * This helper can only be called during
+ * **BPF_SOCK_OPS_HDR_OPT_LEN_CB**.
+ *
+ * Return
+ * 0 on success, or negative error in case of failure:
+ *
+ * **-EINVAL** if a parameter is invalid.
+ *
+ * **-ENOSPC** if there is not enough space in the header.
+ *
+ * **-EPERM** if the helper cannot be used under the current
+ * *skops*\ **->op**.
+ *
+ * void *bpf_inode_storage_get(struct bpf_map *map, void *inode, void *value, u64 flags)
+ * Description
+ * Get a bpf_local_storage from an *inode*.
+ *
+ * Logically, it could be thought of as getting the value from
+ * a *map* with *inode* as the **key**. From this
+ * perspective, the usage is not much different from
+ * **bpf_map_lookup_elem**\ (*map*, **&**\ *inode*) except this
+ * helper enforces the key must be an inode and the map must also
+ * be a **BPF_MAP_TYPE_INODE_STORAGE**.
+ *
+ * Underneath, the value is stored locally at *inode* instead of
+ * the *map*. The *map* is used as the bpf-local-storage
+ * "type". The bpf-local-storage "type" (i.e. the *map*) is
+ * searched against all bpf_local_storage residing at *inode*.
+ *
+ * An optional *flags* (**BPF_LOCAL_STORAGE_GET_F_CREATE**) can be
+ * used such that a new bpf_local_storage will be
+ * created if one does not exist. *value* can be used
+ * together with **BPF_LOCAL_STORAGE_GET_F_CREATE** to specify
+ * the initial value of a bpf_local_storage. If *value* is
+ * **NULL**, the new bpf_local_storage will be zero initialized.
+ * Return
+ * A bpf_local_storage pointer is returned on success.
+ *
+ * **NULL** if not found or there was an error in adding
+ * a new bpf_local_storage.
+ *
+ * int bpf_inode_storage_delete(struct bpf_map *map, void *inode)
+ * Description
+ * Delete a bpf_local_storage from an *inode*.
+ * Return
+ * 0 on success.
+ *
+ * **-ENOENT** if the bpf_local_storage cannot be found.
+ *
+ * long bpf_d_path(struct path *path, char *buf, u32 sz)
+ * Description
+ * Return full path for given **struct path** object, which
+ * needs to be the kernel BTF *path* object. The path is
+ * returned in the provided buffer *buf* of size *sz* and
+ * is zero terminated.
+ *
+ * Return
+ * On success, the strictly positive length of the string,
+ * including the trailing NUL character. On error, a negative
+ * value.
+ *
+ * long bpf_copy_from_user(void *dst, u32 size, const void *user_ptr)
+ * Description
+ * Read *size* bytes from user space address *user_ptr* and store
+ * the data in *dst*. This is a wrapper of **copy_from_user**\ ().
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_snprintf_btf(char *str, u32 str_size, struct btf_ptr *ptr, u32 btf_ptr_size, u64 flags)
+ * Description
+ * Use BTF to store a string representation of *ptr*->ptr in *str*,
+ * using *ptr*->type_id. This value should specify the type
+ * that *ptr*->ptr points to. LLVM __builtin_btf_type_id(type, 1)
+ * can be used to look up vmlinux BTF type ids. Traversing the
+ * data structure using BTF, the type information and values are
+ * stored in the first *str_size* - 1 bytes of *str*. Safe copy of
+ * the pointer data is carried out to avoid kernel crashes during
+ * operation. Smaller types can use string space on the stack;
+ * larger programs can use map data to store the string
+ * representation.
+ *
+ * The string can be subsequently shared with userspace via
+ * bpf_perf_event_output() or ring buffer interfaces.
+ * bpf_trace_printk() is to be avoided as it places too small
+ * a limit on string size to be useful.
+ *
+ * *flags* is a combination of
+ *
+ * **BTF_F_COMPACT**
+ * no formatting around type information
+ * **BTF_F_NONAME**
+ * no struct/union member names/types
+ * **BTF_F_PTR_RAW**
+ * show raw (unobfuscated) pointer values;
+ * equivalent to printk specifier %px.
+ * **BTF_F_ZERO**
+ * show zero-valued struct/union members; they
+ * are not displayed by default
+ *
+ * Return
+ * The number of bytes that were written (or would have been
+ * written if output had to be truncated due to string size),
+ * or a negative error in cases of failure.
+ *
+ * long bpf_seq_printf_btf(struct seq_file *m, struct btf_ptr *ptr, u32 ptr_size, u64 flags)
+ * Description
+ * Use BTF to write to seq_write a string representation of
+ * *ptr*->ptr, using *ptr*->type_id as per bpf_snprintf_btf().
+ * *flags* are identical to those used for bpf_snprintf_btf.
+ * Return
+ * 0 on success or a negative error in case of failure.
+ *
+ * u64 bpf_skb_cgroup_classid(struct sk_buff *skb)
+ * Description
+ * See **bpf_get_cgroup_classid**\ () for the main description.
+ * This helper differs from **bpf_get_cgroup_classid**\ () in that
+ * the cgroup v1 net_cls class is retrieved only from the *skb*'s
+ * associated socket instead of the current process.
+ * Return
+ * The id is returned or 0 in case the id could not be retrieved.
+ *
+ * long bpf_redirect_neigh(u32 ifindex, struct bpf_redir_neigh *params, int plen, u64 flags)
+ * Description
+ * Redirect the packet to another net device of index *ifindex*
+ * and fill in L2 addresses from neighboring subsystem. This helper
+ * is somewhat similar to **bpf_redirect**\ (), except that it
+ * populates L2 addresses as well, meaning, internally, the helper
+ * relies on the neighbor lookup for the L2 address of the nexthop.
+ *
+ * The helper will perform a FIB lookup based on the skb's
+ * networking header to get the address of the next hop, unless
+ * this is supplied by the caller in the *params* argument. The
+ * *plen* argument indicates the len of *params* and should be set
+ * to 0 if *params* is NULL.
+ *
+ * The *flags* argument is reserved and must be 0. The helper is
+ * currently only supported for tc BPF program types, and enabled
+ * for IPv4 and IPv6 protocols.
+ * Return
+ * The helper returns **TC_ACT_REDIRECT** on success or
+ * **TC_ACT_SHOT** on error.
+ *
+ * void *bpf_per_cpu_ptr(const void *percpu_ptr, u32 cpu)
+ * Description
+ * Take a pointer to a percpu ksym, *percpu_ptr*, and return a
+ * pointer to the percpu kernel variable on *cpu*. A ksym is an
+ * extern variable decorated with '__ksym'. For ksym, there is a
+ * global var (either static or global) defined of the same name
+ * in the kernel. The ksym is percpu if the global var is percpu.
+ * The returned pointer points to the global percpu var on *cpu*.
+ *
+ * bpf_per_cpu_ptr() has the same semantic as per_cpu_ptr() in the
+ * kernel, except that bpf_per_cpu_ptr() may return NULL. This
+ * happens if *cpu* is larger than nr_cpu_ids. The caller of
+ * bpf_per_cpu_ptr() must check the returned value.
+ * Return
+ * A pointer pointing to the kernel percpu variable on *cpu*, or
+ * NULL, if *cpu* is invalid.
+ *
+ * void *bpf_this_cpu_ptr(const void *percpu_ptr)
+ * Description
+ * Take a pointer to a percpu ksym, *percpu_ptr*, and return a
+ * pointer to the percpu kernel variable on this cpu. See the
+ * description of 'ksym' in **bpf_per_cpu_ptr**\ ().
+ *
+ * bpf_this_cpu_ptr() has the same semantic as this_cpu_ptr() in
+ * the kernel. Different from **bpf_per_cpu_ptr**\ (), it would
+ * never return NULL.
+ * Return
+ * A pointer pointing to the kernel percpu variable on this cpu.
+ *
+ * long bpf_redirect_peer(u32 ifindex, u64 flags)
+ * Description
+ * Redirect the packet to another net device of index *ifindex*.
+ * This helper is somewhat similar to **bpf_redirect**\ (), except
+ * that the redirection happens to the *ifindex*' peer device and
+ * the netns switch takes place from ingress to ingress without
+ * going through the CPU's backlog queue.
+ *
+ * The *flags* argument is reserved and must be 0. The helper is
+ * currently only supported for tc BPF program types at the ingress
+ * hook and for veth device types. The peer device must reside in a
+ * different network namespace.
+ * Return
+ * The helper returns **TC_ACT_REDIRECT** on success or
+ * **TC_ACT_SHOT** on error.
+ *
+ * void *bpf_task_storage_get(struct bpf_map *map, struct task_struct *task, void *value, u64 flags)
+ * Description
+ * Get a bpf_local_storage from the *task*.
+ *
+ * Logically, it could be thought of as getting the value from
+ * a *map* with *task* as the **key**. From this
+ * perspective, the usage is not much different from
+ * **bpf_map_lookup_elem**\ (*map*, **&**\ *task*) except this
+ * helper enforces the key must be a task_struct and the map must also
+ * be a **BPF_MAP_TYPE_TASK_STORAGE**.
+ *
+ * Underneath, the value is stored locally at *task* instead of
+ * the *map*. The *map* is used as the bpf-local-storage
+ * "type". The bpf-local-storage "type" (i.e. the *map*) is
+ * searched against all bpf_local_storage residing at *task*.
+ *
+ * An optional *flags* (**BPF_LOCAL_STORAGE_GET_F_CREATE**) can be
+ * used such that a new bpf_local_storage will be
+ * created if one does not exist. *value* can be used
+ * together with **BPF_LOCAL_STORAGE_GET_F_CREATE** to specify
+ * the initial value of a bpf_local_storage. If *value* is
+ * **NULL**, the new bpf_local_storage will be zero initialized.
+ * Return
+ * A bpf_local_storage pointer is returned on success.
+ *
+ * **NULL** if not found or there was an error in adding
+ * a new bpf_local_storage.
+ *
+ * long bpf_task_storage_delete(struct bpf_map *map, struct task_struct *task)
+ * Description
+ * Delete a bpf_local_storage from a *task*.
+ * Return
+ * 0 on success.
+ *
+ * **-ENOENT** if the bpf_local_storage cannot be found.
+ *
+ * struct task_struct *bpf_get_current_task_btf(void)
+ * Description
+ * Return a BTF pointer to the "current" task.
+ * This pointer can also be used in helpers that accept an
+ * *ARG_PTR_TO_BTF_ID* of type *task_struct*.
+ * Return
+ * Pointer to the current task.
+ *
+ * long bpf_bprm_opts_set(struct linux_binprm *bprm, u64 flags)
+ * Description
+ * Set or clear certain options on *bprm*:
+ *
+ * **BPF_F_BPRM_SECUREEXEC** Set the secureexec bit
+ * which sets the **AT_SECURE** auxv for glibc. The bit
+ * is cleared if the flag is not specified.
+ * Return
+ * **-EINVAL** if invalid *flags* are passed, zero otherwise.
+ *
+ * u64 bpf_ktime_get_coarse_ns(void)
+ * Description
+ * Return a coarse-grained version of the time elapsed since
+ * system boot, in nanoseconds. Does not include time the system
+ * was suspended.
+ *
+ * See: **clock_gettime**\ (**CLOCK_MONOTONIC_COARSE**)
+ * Return
+ * Current *ktime*.
+ *
+ * long bpf_ima_inode_hash(struct inode *inode, void *dst, u32 size)
+ * Description
+ * Returns the stored IMA hash of the *inode* (if it's available).
+ * If the hash is larger than *size*, then only *size*
+ * bytes will be copied to *dst*
+ * Return
+ * The **hash_algo** is returned on success,
+ * **-EOPNOTSUP** if IMA is disabled or **-EINVAL** if
+ * invalid arguments are passed.
+ *
+ * struct socket *bpf_sock_from_file(struct file *file)
+ * Description
+ * If the given file represents a socket, returns the associated
+ * socket.
+ * Return
+ * A pointer to a struct socket on success or NULL if the file is
+ * not a socket.
+ *
+ * long bpf_check_mtu(void *ctx, u32 ifindex, u32 *mtu_len, s32 len_diff, u64 flags)
+ * Description
+ * Check packet size against exceeding MTU of net device (based
+ * on *ifindex*). This helper will likely be used in combination
+ * with helpers that adjust/change the packet size.
+ *
+ * The argument *len_diff* can be used for querying with a planned
+ * size change. This allows to check MTU prior to changing packet
+ * ctx. Providing a *len_diff* adjustment that is larger than the
+ * actual packet size (resulting in negative packet size) will in
+ * principle not exceed the MTU, which is why it is not considered
+ * a failure. Other BPF helpers are needed for performing the
+ * planned size change; therefore the responsibility for catching
+ * a negative packet size belongs in those helpers.
+ *
+ * Specifying *ifindex* zero means the MTU check is performed
+ * against the current net device. This is practical if this isn't
+ * used prior to redirect.
+ *
+ * On input *mtu_len* must be a valid pointer, else verifier will
+ * reject BPF program. If the value *mtu_len* is initialized to
+ * zero then the ctx packet size is use. When value *mtu_len* is
+ * provided as input this specify the L3 length that the MTU check
+ * is done against. Remember XDP and TC length operate at L2, but
+ * this value is L3 as this correlate to MTU and IP-header tot_len
+ * values which are L3 (similar behavior as bpf_fib_lookup).
+ *
+ * The Linux kernel route table can configure MTUs on a more
+ * specific per route level, which is not provided by this helper.
+ * For route level MTU checks use the **bpf_fib_lookup**\ ()
+ * helper.
+ *
+ * *ctx* is either **struct xdp_md** for XDP programs or
+ * **struct sk_buff** for tc cls_act programs.
+ *
+ * The *flags* argument can be a combination of one or more of the
+ * following values:
+ *
+ * **BPF_MTU_CHK_SEGS**
+ * This flag will only works for *ctx* **struct sk_buff**.
+ * If packet context contains extra packet segment buffers
+ * (often knows as GSO skb), then MTU check is harder to
+ * check at this point, because in transmit path it is
+ * possible for the skb packet to get re-segmented
+ * (depending on net device features). This could still be
+ * a MTU violation, so this flag enables performing MTU
+ * check against segments, with a different violation
+ * return code to tell it apart. Check cannot use len_diff.
+ *
+ * On return *mtu_len* pointer contains the MTU value of the net
+ * device. Remember the net device configured MTU is the L3 size,
+ * which is returned here and XDP and TC length operate at L2.
+ * Helper take this into account for you, but remember when using
+ * MTU value in your BPF-code.
+ *
+ * Return
+ * * 0 on success, and populate MTU value in *mtu_len* pointer.
+ *
+ * * < 0 if any input argument is invalid (*mtu_len* not updated)
+ *
+ * MTU violations return positive values, but also populate MTU
+ * value in *mtu_len* pointer, as this can be needed for
+ * implementing PMTU handing:
+ *
+ * * **BPF_MTU_CHK_RET_FRAG_NEEDED**
+ * * **BPF_MTU_CHK_RET_SEGS_TOOBIG**
+ *
+ * long bpf_for_each_map_elem(struct bpf_map *map, void *callback_fn, void *callback_ctx, u64 flags)
+ * Description
+ * For each element in **map**, call **callback_fn** function with
+ * **map**, **callback_ctx** and other map-specific parameters.
+ * The **callback_fn** should be a static function and
+ * the **callback_ctx** should be a pointer to the stack.
+ * The **flags** is used to control certain aspects of the helper.
+ * Currently, the **flags** must be 0.
+ *
+ * The following are a list of supported map types and their
+ * respective expected callback signatures:
+ *
+ * BPF_MAP_TYPE_HASH, BPF_MAP_TYPE_PERCPU_HASH,
+ * BPF_MAP_TYPE_LRU_HASH, BPF_MAP_TYPE_LRU_PERCPU_HASH,
+ * BPF_MAP_TYPE_ARRAY, BPF_MAP_TYPE_PERCPU_ARRAY
+ *
+ * long (\*callback_fn)(struct bpf_map \*map, const void \*key, void \*value, void \*ctx);
+ *
+ * For per_cpu maps, the map_value is the value on the cpu where the
+ * bpf_prog is running.
+ *
+ * If **callback_fn** return 0, the helper will continue to the next
+ * element. If return value is 1, the helper will skip the rest of
+ * elements and return. Other return values are not used now.
+ *
+ * Return
+ * The number of traversed map elements for success, **-EINVAL** for
+ * invalid **flags**.
+ *
+ * long bpf_snprintf(char *str, u32 str_size, const char *fmt, u64 *data, u32 data_len)
+ * Description
+ * Outputs a string into the **str** buffer of size **str_size**
+ * based on a format string stored in a read-only map pointed by
+ * **fmt**.
+ *
+ * Each format specifier in **fmt** corresponds to one u64 element
+ * in the **data** array. For strings and pointers where pointees
+ * are accessed, only the pointer values are stored in the *data*
+ * array. The *data_len* is the size of *data* in bytes - must be
+ * a multiple of 8.
+ *
+ * Formats **%s** and **%p{i,I}{4,6}** require to read kernel
+ * memory. Reading kernel memory may fail due to either invalid
+ * address or valid address but requiring a major memory fault. If
+ * reading kernel memory fails, the string for **%s** will be an
+ * empty string, and the ip address for **%p{i,I}{4,6}** will be 0.
+ * Not returning error to bpf program is consistent with what
+ * **bpf_trace_printk**\ () does for now.
+ *
+ * Return
+ * The strictly positive length of the formatted string, including
+ * the trailing zero character. If the return value is greater than
+ * **str_size**, **str** contains a truncated string, guaranteed to
+ * be zero-terminated except when **str_size** is 0.
+ *
+ * Or **-EBUSY** if the per-CPU memory copy buffer is busy.
+ *
+ * long bpf_sys_bpf(u32 cmd, void *attr, u32 attr_size)
+ * Description
+ * Execute bpf syscall with given arguments.
+ * Return
+ * A syscall result.
+ *
+ * long bpf_btf_find_by_name_kind(char *name, int name_sz, u32 kind, int flags)
+ * Description
+ * Find BTF type with given name and kind in vmlinux BTF or in module's BTFs.
+ * Return
+ * Returns btf_id and btf_obj_fd in lower and upper 32 bits.
+ *
+ * long bpf_sys_close(u32 fd)
+ * Description
+ * Execute close syscall for given FD.
+ * Return
+ * A syscall result.
+ *
+ * long bpf_timer_init(struct bpf_timer *timer, struct bpf_map *map, u64 flags)
+ * Description
+ * Initialize the timer.
+ * First 4 bits of *flags* specify clockid.
+ * Only CLOCK_MONOTONIC, CLOCK_REALTIME, CLOCK_BOOTTIME are allowed.
+ * All other bits of *flags* are reserved.
+ * The verifier will reject the program if *timer* is not from
+ * the same *map*.
+ * Return
+ * 0 on success.
+ * **-EBUSY** if *timer* is already initialized.
+ * **-EINVAL** if invalid *flags* are passed.
+ * **-EPERM** if *timer* is in a map that doesn't have any user references.
+ * The user space should either hold a file descriptor to a map with timers
+ * or pin such map in bpffs. When map is unpinned or file descriptor is
+ * closed all timers in the map will be cancelled and freed.
+ *
+ * long bpf_timer_set_callback(struct bpf_timer *timer, void *callback_fn)
+ * Description
+ * Configure the timer to call *callback_fn* static function.
+ * Return
+ * 0 on success.
+ * **-EINVAL** if *timer* was not initialized with bpf_timer_init() earlier.
+ * **-EPERM** if *timer* is in a map that doesn't have any user references.
+ * The user space should either hold a file descriptor to a map with timers
+ * or pin such map in bpffs. When map is unpinned or file descriptor is
+ * closed all timers in the map will be cancelled and freed.
+ *
+ * long bpf_timer_start(struct bpf_timer *timer, u64 nsecs, u64 flags)
+ * Description
+ * Set timer expiration N nanoseconds from the current time. The
+ * configured callback will be invoked in soft irq context on some cpu
+ * and will not repeat unless another bpf_timer_start() is made.
+ * In such case the next invocation can migrate to a different cpu.
+ * Since struct bpf_timer is a field inside map element the map
+ * owns the timer. The bpf_timer_set_callback() will increment refcnt
+ * of BPF program to make sure that callback_fn code stays valid.
+ * When user space reference to a map reaches zero all timers
+ * in a map are cancelled and corresponding program's refcnts are
+ * decremented. This is done to make sure that Ctrl-C of a user
+ * process doesn't leave any timers running. If map is pinned in
+ * bpffs the callback_fn can re-arm itself indefinitely.
+ * bpf_map_update/delete_elem() helpers and user space sys_bpf commands
+ * cancel and free the timer in the given map element.
+ * The map can contain timers that invoke callback_fn-s from different
+ * programs. The same callback_fn can serve different timers from
+ * different maps if key/value layout matches across maps.
+ * Every bpf_timer_set_callback() can have different callback_fn.
+ *
+ * *flags* can be one of:
+ *
+ * **BPF_F_TIMER_ABS**
+ * Start the timer in absolute expire value instead of the
+ * default relative one.
+ *
+ * Return
+ * 0 on success.
+ * **-EINVAL** if *timer* was not initialized with bpf_timer_init() earlier
+ * or invalid *flags* are passed.
+ *
+ * long bpf_timer_cancel(struct bpf_timer *timer)
+ * Description
+ * Cancel the timer and wait for callback_fn to finish if it was running.
+ * Return
+ * 0 if the timer was not active.
+ * 1 if the timer was active.
+ * **-EINVAL** if *timer* was not initialized with bpf_timer_init() earlier.
+ * **-EDEADLK** if callback_fn tried to call bpf_timer_cancel() on its
+ * own timer which would have led to a deadlock otherwise.
+ *
+ * u64 bpf_get_func_ip(void *ctx)
+ * Description
+ * Get address of the traced function (for tracing and kprobe programs).
+ *
+ * When called for kprobe program attached as uprobe it returns
+ * probe address for both entry and return uprobe.
+ *
+ * Return
+ * Address of the traced function for kprobe.
+ * 0 for kprobes placed within the function (not at the entry).
+ * Address of the probe for uprobe and return uprobe.
+ *
+ * u64 bpf_get_attach_cookie(void *ctx)
+ * Description
+ * Get bpf_cookie value provided (optionally) during the program
+ * attachment. It might be different for each individual
+ * attachment, even if BPF program itself is the same.
+ * Expects BPF program context *ctx* as a first argument.
+ *
+ * Supported for the following program types:
+ * - kprobe/uprobe;
+ * - tracepoint;
+ * - perf_event.
+ * Return
+ * Value specified by user at BPF link creation/attachment time
+ * or 0, if it was not specified.
+ *
+ * long bpf_task_pt_regs(struct task_struct *task)
+ * Description
+ * Get the struct pt_regs associated with **task**.
+ * Return
+ * A pointer to struct pt_regs.
+ *
+ * long bpf_get_branch_snapshot(void *entries, u32 size, u64 flags)
+ * Description
+ * Get branch trace from hardware engines like Intel LBR. The
+ * hardware engine is stopped shortly after the helper is
+ * called. Therefore, the user need to filter branch entries
+ * based on the actual use case. To capture branch trace
+ * before the trigger point of the BPF program, the helper
+ * should be called at the beginning of the BPF program.
+ *
+ * The data is stored as struct perf_branch_entry into output
+ * buffer *entries*. *size* is the size of *entries* in bytes.
+ * *flags* is reserved for now and must be zero.
+ *
+ * Return
+ * On success, number of bytes written to *buf*. On error, a
+ * negative value.
+ *
+ * **-EINVAL** if *flags* is not zero.
+ *
+ * **-ENOENT** if architecture does not support branch records.
+ *
+ * long bpf_trace_vprintk(const char *fmt, u32 fmt_size, const void *data, u32 data_len)
+ * Description
+ * Behaves like **bpf_trace_printk**\ () helper, but takes an array of u64
+ * to format and can handle more format args as a result.
+ *
+ * Arguments are to be used as in **bpf_seq_printf**\ () helper.
+ * Return
+ * The number of bytes written to the buffer, or a negative error
+ * in case of failure.
+ *
+ * struct unix_sock *bpf_skc_to_unix_sock(void *sk)
+ * Description
+ * Dynamically cast a *sk* pointer to a *unix_sock* pointer.
+ * Return
+ * *sk* if casting is valid, or **NULL** otherwise.
+ *
+ * long bpf_kallsyms_lookup_name(const char *name, int name_sz, int flags, u64 *res)
+ * Description
+ * Get the address of a kernel symbol, returned in *res*. *res* is
+ * set to 0 if the symbol is not found.
+ * Return
+ * On success, zero. On error, a negative value.
+ *
+ * **-EINVAL** if *flags* is not zero.
+ *
+ * **-EINVAL** if string *name* is not the same size as *name_sz*.
+ *
+ * **-ENOENT** if symbol is not found.
+ *
+ * **-EPERM** if caller does not have permission to obtain kernel address.
+ *
+ * long bpf_find_vma(struct task_struct *task, u64 addr, void *callback_fn, void *callback_ctx, u64 flags)
+ * Description
+ * Find vma of *task* that contains *addr*, call *callback_fn*
+ * function with *task*, *vma*, and *callback_ctx*.
+ * The *callback_fn* should be a static function and
+ * the *callback_ctx* should be a pointer to the stack.
+ * The *flags* is used to control certain aspects of the helper.
+ * Currently, the *flags* must be 0.
+ *
+ * The expected callback signature is
+ *
+ * long (\*callback_fn)(struct task_struct \*task, struct vm_area_struct \*vma, void \*callback_ctx);
+ *
+ * Return
+ * 0 on success.
+ * **-ENOENT** if *task->mm* is NULL, or no vma contains *addr*.
+ * **-EBUSY** if failed to try lock mmap_lock.
+ * **-EINVAL** for invalid **flags**.
+ *
+ * long bpf_loop(u32 nr_loops, void *callback_fn, void *callback_ctx, u64 flags)
+ * Description
+ * For **nr_loops**, call **callback_fn** function
+ * with **callback_ctx** as the context parameter.
+ * The **callback_fn** should be a static function and
+ * the **callback_ctx** should be a pointer to the stack.
+ * The **flags** is used to control certain aspects of the helper.
+ * Currently, the **flags** must be 0. Currently, nr_loops is
+ * limited to 1 << 23 (~8 million) loops.
+ *
+ * long (\*callback_fn)(u32 index, void \*ctx);
+ *
+ * where **index** is the current index in the loop. The index
+ * is zero-indexed.
+ *
+ * If **callback_fn** returns 0, the helper will continue to the next
+ * loop. If return value is 1, the helper will skip the rest of
+ * the loops and return. Other return values are not used now,
+ * and will be rejected by the verifier.
+ *
+ * Return
+ * The number of loops performed, **-EINVAL** for invalid **flags**,
+ * **-E2BIG** if **nr_loops** exceeds the maximum number of loops.
+ *
+ * long bpf_strncmp(const char *s1, u32 s1_sz, const char *s2)
+ * Description
+ * Do strncmp() between **s1** and **s2**. **s1** doesn't need
+ * to be null-terminated and **s1_sz** is the maximum storage
+ * size of **s1**. **s2** must be a read-only string.
+ * Return
+ * An integer less than, equal to, or greater than zero
+ * if the first **s1_sz** bytes of **s1** is found to be
+ * less than, to match, or be greater than **s2**.
+ *
+ * long bpf_get_func_arg(void *ctx, u32 n, u64 *value)
+ * Description
+ * Get **n**-th argument register (zero based) of the traced function (for tracing programs)
+ * returned in **value**.
+ *
+ * Return
+ * 0 on success.
+ * **-EINVAL** if n >= argument register count of traced function.
+ *
+ * long bpf_get_func_ret(void *ctx, u64 *value)
+ * Description
+ * Get return value of the traced function (for tracing programs)
+ * in **value**.
+ *
+ * Return
+ * 0 on success.
+ * **-EOPNOTSUPP** for tracing programs other than BPF_TRACE_FEXIT or BPF_MODIFY_RETURN.
+ *
+ * long bpf_get_func_arg_cnt(void *ctx)
+ * Description
+ * Get number of registers of the traced function (for tracing programs) where
+ * function arguments are stored in these registers.
+ *
+ * Return
+ * The number of argument registers of the traced function.
+ *
+ * int bpf_get_retval(void)
+ * Description
+ * Get the BPF program's return value that will be returned to the upper layers.
+ *
+ * This helper is currently supported by cgroup programs and only by the hooks
+ * where BPF program's return value is returned to the userspace via errno.
+ * Return
+ * The BPF program's return value.
+ *
+ * int bpf_set_retval(int retval)
+ * Description
+ * Set the BPF program's return value that will be returned to the upper layers.
+ *
+ * This helper is currently supported by cgroup programs and only by the hooks
+ * where BPF program's return value is returned to the userspace via errno.
+ *
+ * Note that there is the following corner case where the program exports an error
+ * via bpf_set_retval but signals success via 'return 1':
+ *
+ * bpf_set_retval(-EPERM);
+ * return 1;
+ *
+ * In this case, the BPF program's return value will use helper's -EPERM. This
+ * still holds true for cgroup/bind{4,6} which supports extra 'return 3' success case.
+ *
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * u64 bpf_xdp_get_buff_len(struct xdp_buff *xdp_md)
+ * Description
+ * Get the total size of a given xdp buff (linear and paged area)
+ * Return
+ * The total size of a given xdp buffer.
+ *
+ * long bpf_xdp_load_bytes(struct xdp_buff *xdp_md, u32 offset, void *buf, u32 len)
+ * Description
+ * This helper is provided as an easy way to load data from a
+ * xdp buffer. It can be used to load *len* bytes from *offset* from
+ * the frame associated to *xdp_md*, into the buffer pointed by
+ * *buf*.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_xdp_store_bytes(struct xdp_buff *xdp_md, u32 offset, void *buf, u32 len)
+ * Description
+ * Store *len* bytes from buffer *buf* into the frame
+ * associated to *xdp_md*, at *offset*.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_copy_from_user_task(void *dst, u32 size, const void *user_ptr, struct task_struct *tsk, u64 flags)
+ * Description
+ * Read *size* bytes from user space address *user_ptr* in *tsk*'s
+ * address space, and stores the data in *dst*. *flags* is not
+ * used yet and is provided for future extensibility. This helper
+ * can only be used by sleepable programs.
+ * Return
+ * 0 on success, or a negative error in case of failure. On error
+ * *dst* buffer is zeroed out.
+ *
+ * long bpf_skb_set_tstamp(struct sk_buff *skb, u64 tstamp, u32 tstamp_type)
+ * Description
+ * Change the __sk_buff->tstamp_type to *tstamp_type*
+ * and set *tstamp* to the __sk_buff->tstamp together.
+ *
+ * If there is no need to change the __sk_buff->tstamp_type,
+ * the tstamp value can be directly written to __sk_buff->tstamp
+ * instead.
+ *
+ * BPF_SKB_TSTAMP_DELIVERY_MONO is the only tstamp that
+ * will be kept during bpf_redirect_*(). A non zero
+ * *tstamp* must be used with the BPF_SKB_TSTAMP_DELIVERY_MONO
+ * *tstamp_type*.
+ *
+ * A BPF_SKB_TSTAMP_UNSPEC *tstamp_type* can only be used
+ * with a zero *tstamp*.
+ *
+ * Only IPv4 and IPv6 skb->protocol are supported.
+ *
+ * This function is most useful when it needs to set a
+ * mono delivery time to __sk_buff->tstamp and then
+ * bpf_redirect_*() to the egress of an iface. For example,
+ * changing the (rcv) timestamp in __sk_buff->tstamp at
+ * ingress to a mono delivery time and then bpf_redirect_*()
+ * to sch_fq@phy-dev.
+ * Return
+ * 0 on success.
+ * **-EINVAL** for invalid input
+ * **-EOPNOTSUPP** for unsupported protocol
+ *
+ * long bpf_ima_file_hash(struct file *file, void *dst, u32 size)
+ * Description
+ * Returns a calculated IMA hash of the *file*.
+ * If the hash is larger than *size*, then only *size*
+ * bytes will be copied to *dst*
+ * Return
+ * The **hash_algo** is returned on success,
+ * **-EOPNOTSUP** if the hash calculation failed or **-EINVAL** if
+ * invalid arguments are passed.
+ *
+ * void *bpf_kptr_xchg(void *map_value, void *ptr)
+ * Description
+ * Exchange kptr at pointer *map_value* with *ptr*, and return the
+ * old value. *ptr* can be NULL, otherwise it must be a referenced
+ * pointer which will be released when this helper is called.
+ * Return
+ * The old value of kptr (which can be NULL). The returned pointer
+ * if not NULL, is a reference which must be released using its
+ * corresponding release function, or moved into a BPF map before
+ * program exit.
+ *
+ * void *bpf_map_lookup_percpu_elem(struct bpf_map *map, const void *key, u32 cpu)
+ * Description
+ * Perform a lookup in *percpu map* for an entry associated to
+ * *key* on *cpu*.
+ * Return
+ * Map value associated to *key* on *cpu*, or **NULL** if no entry
+ * was found or *cpu* is invalid.
+ *
+ * struct mptcp_sock *bpf_skc_to_mptcp_sock(void *sk)
+ * Description
+ * Dynamically cast a *sk* pointer to a *mptcp_sock* pointer.
+ * Return
+ * *sk* if casting is valid, or **NULL** otherwise.
+ *
+ * long bpf_dynptr_from_mem(void *data, u32 size, u64 flags, struct bpf_dynptr *ptr)
+ * Description
+ * Get a dynptr to local memory *data*.
+ *
+ * *data* must be a ptr to a map value.
+ * The maximum *size* supported is DYNPTR_MAX_SIZE.
+ * *flags* is currently unused.
+ * Return
+ * 0 on success, -E2BIG if the size exceeds DYNPTR_MAX_SIZE,
+ * -EINVAL if flags is not 0.
+ *
+ * long bpf_ringbuf_reserve_dynptr(void *ringbuf, u32 size, u64 flags, struct bpf_dynptr *ptr)
+ * Description
+ * Reserve *size* bytes of payload in a ring buffer *ringbuf*
+ * through the dynptr interface. *flags* must be 0.
+ *
+ * Please note that a corresponding bpf_ringbuf_submit_dynptr or
+ * bpf_ringbuf_discard_dynptr must be called on *ptr*, even if the
+ * reservation fails. This is enforced by the verifier.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * void bpf_ringbuf_submit_dynptr(struct bpf_dynptr *ptr, u64 flags)
+ * Description
+ * Submit reserved ring buffer sample, pointed to by *data*,
+ * through the dynptr interface. This is a no-op if the dynptr is
+ * invalid/null.
+ *
+ * For more information on *flags*, please see
+ * 'bpf_ringbuf_submit'.
+ * Return
+ * Nothing. Always succeeds.
+ *
+ * void bpf_ringbuf_discard_dynptr(struct bpf_dynptr *ptr, u64 flags)
+ * Description
+ * Discard reserved ring buffer sample through the dynptr
+ * interface. This is a no-op if the dynptr is invalid/null.
+ *
+ * For more information on *flags*, please see
+ * 'bpf_ringbuf_discard'.
+ * Return
+ * Nothing. Always succeeds.
+ *
+ * long bpf_dynptr_read(void *dst, u32 len, const struct bpf_dynptr *src, u32 offset, u64 flags)
+ * Description
+ * Read *len* bytes from *src* into *dst*, starting from *offset*
+ * into *src*.
+ * *flags* is currently unused.
+ * Return
+ * 0 on success, -E2BIG if *offset* + *len* exceeds the length
+ * of *src*'s data, -EINVAL if *src* is an invalid dynptr or if
+ * *flags* is not 0.
+ *
+ * long bpf_dynptr_write(const struct bpf_dynptr *dst, u32 offset, void *src, u32 len, u64 flags)
+ * Description
+ * Write *len* bytes from *src* into *dst*, starting from *offset*
+ * into *dst*.
+ *
+ * *flags* must be 0 except for skb-type dynptrs.
+ *
+ * For skb-type dynptrs:
+ * * All data slices of the dynptr are automatically
+ * invalidated after **bpf_dynptr_write**\ (). This is
+ * because writing may pull the skb and change the
+ * underlying packet buffer.
+ *
+ * * For *flags*, please see the flags accepted by
+ * **bpf_skb_store_bytes**\ ().
+ * Return
+ * 0 on success, -E2BIG if *offset* + *len* exceeds the length
+ * of *dst*'s data, -EINVAL if *dst* is an invalid dynptr or if *dst*
+ * is a read-only dynptr or if *flags* is not correct. For skb-type dynptrs,
+ * other errors correspond to errors returned by **bpf_skb_store_bytes**\ ().
+ *
+ * void *bpf_dynptr_data(const struct bpf_dynptr *ptr, u32 offset, u32 len)
+ * Description
+ * Get a pointer to the underlying dynptr data.
+ *
+ * *len* must be a statically known value. The returned data slice
+ * is invalidated whenever the dynptr is invalidated.
+ *
+ * skb and xdp type dynptrs may not use bpf_dynptr_data. They should
+ * instead use bpf_dynptr_slice and bpf_dynptr_slice_rdwr.
+ * Return
+ * Pointer to the underlying dynptr data, NULL if the dynptr is
+ * read-only, if the dynptr is invalid, or if the offset and length
+ * is out of bounds.
+ *
+ * s64 bpf_tcp_raw_gen_syncookie_ipv4(struct iphdr *iph, struct tcphdr *th, u32 th_len)
+ * Description
+ * Try to issue a SYN cookie for the packet with corresponding
+ * IPv4/TCP headers, *iph* and *th*, without depending on a
+ * listening socket.
+ *
+ * *iph* points to the IPv4 header.
+ *
+ * *th* points to the start of the TCP header, while *th_len*
+ * contains the length of the TCP header (at least
+ * **sizeof**\ (**struct tcphdr**)).
+ * Return
+ * On success, lower 32 bits hold the generated SYN cookie in
+ * followed by 16 bits which hold the MSS value for that cookie,
+ * and the top 16 bits are unused.
+ *
+ * On failure, the returned value is one of the following:
+ *
+ * **-EINVAL** if *th_len* is invalid.
+ *
+ * s64 bpf_tcp_raw_gen_syncookie_ipv6(struct ipv6hdr *iph, struct tcphdr *th, u32 th_len)
+ * Description
+ * Try to issue a SYN cookie for the packet with corresponding
+ * IPv6/TCP headers, *iph* and *th*, without depending on a
+ * listening socket.
+ *
+ * *iph* points to the IPv6 header.
+ *
+ * *th* points to the start of the TCP header, while *th_len*
+ * contains the length of the TCP header (at least
+ * **sizeof**\ (**struct tcphdr**)).
+ * Return
+ * On success, lower 32 bits hold the generated SYN cookie in
+ * followed by 16 bits which hold the MSS value for that cookie,
+ * and the top 16 bits are unused.
+ *
+ * On failure, the returned value is one of the following:
+ *
+ * **-EINVAL** if *th_len* is invalid.
+ *
+ * **-EPROTONOSUPPORT** if CONFIG_IPV6 is not builtin.
+ *
+ * long bpf_tcp_raw_check_syncookie_ipv4(struct iphdr *iph, struct tcphdr *th)
+ * Description
+ * Check whether *iph* and *th* contain a valid SYN cookie ACK
+ * without depending on a listening socket.
+ *
+ * *iph* points to the IPv4 header.
+ *
+ * *th* points to the TCP header.
+ * Return
+ * 0 if *iph* and *th* are a valid SYN cookie ACK.
+ *
+ * On failure, the returned value is one of the following:
+ *
+ * **-EACCES** if the SYN cookie is not valid.
+ *
+ * long bpf_tcp_raw_check_syncookie_ipv6(struct ipv6hdr *iph, struct tcphdr *th)
+ * Description
+ * Check whether *iph* and *th* contain a valid SYN cookie ACK
+ * without depending on a listening socket.
+ *
+ * *iph* points to the IPv6 header.
+ *
+ * *th* points to the TCP header.
+ * Return
+ * 0 if *iph* and *th* are a valid SYN cookie ACK.
+ *
+ * On failure, the returned value is one of the following:
+ *
+ * **-EACCES** if the SYN cookie is not valid.
+ *
+ * **-EPROTONOSUPPORT** if CONFIG_IPV6 is not builtin.
+ *
+ * u64 bpf_ktime_get_tai_ns(void)
+ * Description
+ * A nonsettable system-wide clock derived from wall-clock time but
+ * ignoring leap seconds. This clock does not experience
+ * discontinuities and backwards jumps caused by NTP inserting leap
+ * seconds as CLOCK_REALTIME does.
+ *
+ * See: **clock_gettime**\ (**CLOCK_TAI**)
+ * Return
+ * Current *ktime*.
+ *
+ * long bpf_user_ringbuf_drain(struct bpf_map *map, void *callback_fn, void *ctx, u64 flags)
+ * Description
+ * Drain samples from the specified user ring buffer, and invoke
+ * the provided callback for each such sample:
+ *
+ * long (\*callback_fn)(const struct bpf_dynptr \*dynptr, void \*ctx);
+ *
+ * If **callback_fn** returns 0, the helper will continue to try
+ * and drain the next sample, up to a maximum of
+ * BPF_MAX_USER_RINGBUF_SAMPLES samples. If the return value is 1,
+ * the helper will skip the rest of the samples and return. Other
+ * return values are not used now, and will be rejected by the
+ * verifier.
+ * Return
+ * The number of drained samples if no error was encountered while
+ * draining samples, or 0 if no samples were present in the ring
+ * buffer. If a user-space producer was epoll-waiting on this map,
+ * and at least one sample was drained, they will receive an event
+ * notification notifying them of available space in the ring
+ * buffer. If the BPF_RB_NO_WAKEUP flag is passed to this
+ * function, no wakeup notification will be sent. If the
+ * BPF_RB_FORCE_WAKEUP flag is passed, a wakeup notification will
+ * be sent even if no sample was drained.
+ *
+ * On failure, the returned value is one of the following:
+ *
+ * **-EBUSY** if the ring buffer is contended, and another calling
+ * context was concurrently draining the ring buffer.
+ *
+ * **-EINVAL** if user-space is not properly tracking the ring
+ * buffer due to the producer position not being aligned to 8
+ * bytes, a sample not being aligned to 8 bytes, or the producer
+ * position not matching the advertised length of a sample.
+ *
+ * **-E2BIG** if user-space has tried to publish a sample which is
+ * larger than the size of the ring buffer, or which cannot fit
+ * within a struct bpf_dynptr.
+ *
+ * void *bpf_cgrp_storage_get(struct bpf_map *map, struct cgroup *cgroup, void *value, u64 flags)
+ * Description
+ * Get a bpf_local_storage from the *cgroup*.
+ *
+ * Logically, it could be thought of as getting the value from
+ * a *map* with *cgroup* as the **key**. From this
+ * perspective, the usage is not much different from
+ * **bpf_map_lookup_elem**\ (*map*, **&**\ *cgroup*) except this
+ * helper enforces the key must be a cgroup struct and the map must also
+ * be a **BPF_MAP_TYPE_CGRP_STORAGE**.
+ *
+ * In reality, the local-storage value is embedded directly inside of the
+ * *cgroup* object itself, rather than being located in the
+ * **BPF_MAP_TYPE_CGRP_STORAGE** map. When the local-storage value is
+ * queried for some *map* on a *cgroup* object, the kernel will perform an
+ * O(n) iteration over all of the live local-storage values for that
+ * *cgroup* object until the local-storage value for the *map* is found.
+ *
+ * An optional *flags* (**BPF_LOCAL_STORAGE_GET_F_CREATE**) can be
+ * used such that a new bpf_local_storage will be
+ * created if one does not exist. *value* can be used
+ * together with **BPF_LOCAL_STORAGE_GET_F_CREATE** to specify
+ * the initial value of a bpf_local_storage. If *value* is
+ * **NULL**, the new bpf_local_storage will be zero initialized.
+ * Return
+ * A bpf_local_storage pointer is returned on success.
+ *
+ * **NULL** if not found or there was an error in adding
+ * a new bpf_local_storage.
+ *
+ * long bpf_cgrp_storage_delete(struct bpf_map *map, struct cgroup *cgroup)
+ * Description
+ * Delete a bpf_local_storage from a *cgroup*.
+ * Return
+ * 0 on success.
+ *
+ * **-ENOENT** if the bpf_local_storage cannot be found.
+ */
+#define ___BPF_FUNC_MAPPER(FN, ctx...) \
+ FN(unspec, 0, ##ctx) \
+ FN(map_lookup_elem, 1, ##ctx) \
+ FN(map_update_elem, 2, ##ctx) \
+ FN(map_delete_elem, 3, ##ctx) \
+ FN(probe_read, 4, ##ctx) \
+ FN(ktime_get_ns, 5, ##ctx) \
+ FN(trace_printk, 6, ##ctx) \
+ FN(get_prandom_u32, 7, ##ctx) \
+ FN(get_smp_processor_id, 8, ##ctx) \
+ FN(skb_store_bytes, 9, ##ctx) \
+ FN(l3_csum_replace, 10, ##ctx) \
+ FN(l4_csum_replace, 11, ##ctx) \
+ FN(tail_call, 12, ##ctx) \
+ FN(clone_redirect, 13, ##ctx) \
+ FN(get_current_pid_tgid, 14, ##ctx) \
+ FN(get_current_uid_gid, 15, ##ctx) \
+ FN(get_current_comm, 16, ##ctx) \
+ FN(get_cgroup_classid, 17, ##ctx) \
+ FN(skb_vlan_push, 18, ##ctx) \
+ FN(skb_vlan_pop, 19, ##ctx) \
+ FN(skb_get_tunnel_key, 20, ##ctx) \
+ FN(skb_set_tunnel_key, 21, ##ctx) \
+ FN(perf_event_read, 22, ##ctx) \
+ FN(redirect, 23, ##ctx) \
+ FN(get_route_realm, 24, ##ctx) \
+ FN(perf_event_output, 25, ##ctx) \
+ FN(skb_load_bytes, 26, ##ctx) \
+ FN(get_stackid, 27, ##ctx) \
+ FN(csum_diff, 28, ##ctx) \
+ FN(skb_get_tunnel_opt, 29, ##ctx) \
+ FN(skb_set_tunnel_opt, 30, ##ctx) \
+ FN(skb_change_proto, 31, ##ctx) \
+ FN(skb_change_type, 32, ##ctx) \
+ FN(skb_under_cgroup, 33, ##ctx) \
+ FN(get_hash_recalc, 34, ##ctx) \
+ FN(get_current_task, 35, ##ctx) \
+ FN(probe_write_user, 36, ##ctx) \
+ FN(current_task_under_cgroup, 37, ##ctx) \
+ FN(skb_change_tail, 38, ##ctx) \
+ FN(skb_pull_data, 39, ##ctx) \
+ FN(csum_update, 40, ##ctx) \
+ FN(set_hash_invalid, 41, ##ctx) \
+ FN(get_numa_node_id, 42, ##ctx) \
+ FN(skb_change_head, 43, ##ctx) \
+ FN(xdp_adjust_head, 44, ##ctx) \
+ FN(probe_read_str, 45, ##ctx) \
+ FN(get_socket_cookie, 46, ##ctx) \
+ FN(get_socket_uid, 47, ##ctx) \
+ FN(set_hash, 48, ##ctx) \
+ FN(setsockopt, 49, ##ctx) \
+ FN(skb_adjust_room, 50, ##ctx) \
+ FN(redirect_map, 51, ##ctx) \
+ FN(sk_redirect_map, 52, ##ctx) \
+ FN(sock_map_update, 53, ##ctx) \
+ FN(xdp_adjust_meta, 54, ##ctx) \
+ FN(perf_event_read_value, 55, ##ctx) \
+ FN(perf_prog_read_value, 56, ##ctx) \
+ FN(getsockopt, 57, ##ctx) \
+ FN(override_return, 58, ##ctx) \
+ FN(sock_ops_cb_flags_set, 59, ##ctx) \
+ FN(msg_redirect_map, 60, ##ctx) \
+ FN(msg_apply_bytes, 61, ##ctx) \
+ FN(msg_cork_bytes, 62, ##ctx) \
+ FN(msg_pull_data, 63, ##ctx) \
+ FN(bind, 64, ##ctx) \
+ FN(xdp_adjust_tail, 65, ##ctx) \
+ FN(skb_get_xfrm_state, 66, ##ctx) \
+ FN(get_stack, 67, ##ctx) \
+ FN(skb_load_bytes_relative, 68, ##ctx) \
+ FN(fib_lookup, 69, ##ctx) \
+ FN(sock_hash_update, 70, ##ctx) \
+ FN(msg_redirect_hash, 71, ##ctx) \
+ FN(sk_redirect_hash, 72, ##ctx) \
+ FN(lwt_push_encap, 73, ##ctx) \
+ FN(lwt_seg6_store_bytes, 74, ##ctx) \
+ FN(lwt_seg6_adjust_srh, 75, ##ctx) \
+ FN(lwt_seg6_action, 76, ##ctx) \
+ FN(rc_repeat, 77, ##ctx) \
+ FN(rc_keydown, 78, ##ctx) \
+ FN(skb_cgroup_id, 79, ##ctx) \
+ FN(get_current_cgroup_id, 80, ##ctx) \
+ FN(get_local_storage, 81, ##ctx) \
+ FN(sk_select_reuseport, 82, ##ctx) \
+ FN(skb_ancestor_cgroup_id, 83, ##ctx) \
+ FN(sk_lookup_tcp, 84, ##ctx) \
+ FN(sk_lookup_udp, 85, ##ctx) \
+ FN(sk_release, 86, ##ctx) \
+ FN(map_push_elem, 87, ##ctx) \
+ FN(map_pop_elem, 88, ##ctx) \
+ FN(map_peek_elem, 89, ##ctx) \
+ FN(msg_push_data, 90, ##ctx) \
+ FN(msg_pop_data, 91, ##ctx) \
+ FN(rc_pointer_rel, 92, ##ctx) \
+ FN(spin_lock, 93, ##ctx) \
+ FN(spin_unlock, 94, ##ctx) \
+ FN(sk_fullsock, 95, ##ctx) \
+ FN(tcp_sock, 96, ##ctx) \
+ FN(skb_ecn_set_ce, 97, ##ctx) \
+ FN(get_listener_sock, 98, ##ctx) \
+ FN(skc_lookup_tcp, 99, ##ctx) \
+ FN(tcp_check_syncookie, 100, ##ctx) \
+ FN(sysctl_get_name, 101, ##ctx) \
+ FN(sysctl_get_current_value, 102, ##ctx) \
+ FN(sysctl_get_new_value, 103, ##ctx) \
+ FN(sysctl_set_new_value, 104, ##ctx) \
+ FN(strtol, 105, ##ctx) \
+ FN(strtoul, 106, ##ctx) \
+ FN(sk_storage_get, 107, ##ctx) \
+ FN(sk_storage_delete, 108, ##ctx) \
+ FN(send_signal, 109, ##ctx) \
+ FN(tcp_gen_syncookie, 110, ##ctx) \
+ FN(skb_output, 111, ##ctx) \
+ FN(probe_read_user, 112, ##ctx) \
+ FN(probe_read_kernel, 113, ##ctx) \
+ FN(probe_read_user_str, 114, ##ctx) \
+ FN(probe_read_kernel_str, 115, ##ctx) \
+ FN(tcp_send_ack, 116, ##ctx) \
+ FN(send_signal_thread, 117, ##ctx) \
+ FN(jiffies64, 118, ##ctx) \
+ FN(read_branch_records, 119, ##ctx) \
+ FN(get_ns_current_pid_tgid, 120, ##ctx) \
+ FN(xdp_output, 121, ##ctx) \
+ FN(get_netns_cookie, 122, ##ctx) \
+ FN(get_current_ancestor_cgroup_id, 123, ##ctx) \
+ FN(sk_assign, 124, ##ctx) \
+ FN(ktime_get_boot_ns, 125, ##ctx) \
+ FN(seq_printf, 126, ##ctx) \
+ FN(seq_write, 127, ##ctx) \
+ FN(sk_cgroup_id, 128, ##ctx) \
+ FN(sk_ancestor_cgroup_id, 129, ##ctx) \
+ FN(ringbuf_output, 130, ##ctx) \
+ FN(ringbuf_reserve, 131, ##ctx) \
+ FN(ringbuf_submit, 132, ##ctx) \
+ FN(ringbuf_discard, 133, ##ctx) \
+ FN(ringbuf_query, 134, ##ctx) \
+ FN(csum_level, 135, ##ctx) \
+ FN(skc_to_tcp6_sock, 136, ##ctx) \
+ FN(skc_to_tcp_sock, 137, ##ctx) \
+ FN(skc_to_tcp_timewait_sock, 138, ##ctx) \
+ FN(skc_to_tcp_request_sock, 139, ##ctx) \
+ FN(skc_to_udp6_sock, 140, ##ctx) \
+ FN(get_task_stack, 141, ##ctx) \
+ FN(load_hdr_opt, 142, ##ctx) \
+ FN(store_hdr_opt, 143, ##ctx) \
+ FN(reserve_hdr_opt, 144, ##ctx) \
+ FN(inode_storage_get, 145, ##ctx) \
+ FN(inode_storage_delete, 146, ##ctx) \
+ FN(d_path, 147, ##ctx) \
+ FN(copy_from_user, 148, ##ctx) \
+ FN(snprintf_btf, 149, ##ctx) \
+ FN(seq_printf_btf, 150, ##ctx) \
+ FN(skb_cgroup_classid, 151, ##ctx) \
+ FN(redirect_neigh, 152, ##ctx) \
+ FN(per_cpu_ptr, 153, ##ctx) \
+ FN(this_cpu_ptr, 154, ##ctx) \
+ FN(redirect_peer, 155, ##ctx) \
+ FN(task_storage_get, 156, ##ctx) \
+ FN(task_storage_delete, 157, ##ctx) \
+ FN(get_current_task_btf, 158, ##ctx) \
+ FN(bprm_opts_set, 159, ##ctx) \
+ FN(ktime_get_coarse_ns, 160, ##ctx) \
+ FN(ima_inode_hash, 161, ##ctx) \
+ FN(sock_from_file, 162, ##ctx) \
+ FN(check_mtu, 163, ##ctx) \
+ FN(for_each_map_elem, 164, ##ctx) \
+ FN(snprintf, 165, ##ctx) \
+ FN(sys_bpf, 166, ##ctx) \
+ FN(btf_find_by_name_kind, 167, ##ctx) \
+ FN(sys_close, 168, ##ctx) \
+ FN(timer_init, 169, ##ctx) \
+ FN(timer_set_callback, 170, ##ctx) \
+ FN(timer_start, 171, ##ctx) \
+ FN(timer_cancel, 172, ##ctx) \
+ FN(get_func_ip, 173, ##ctx) \
+ FN(get_attach_cookie, 174, ##ctx) \
+ FN(task_pt_regs, 175, ##ctx) \
+ FN(get_branch_snapshot, 176, ##ctx) \
+ FN(trace_vprintk, 177, ##ctx) \
+ FN(skc_to_unix_sock, 178, ##ctx) \
+ FN(kallsyms_lookup_name, 179, ##ctx) \
+ FN(find_vma, 180, ##ctx) \
+ FN(loop, 181, ##ctx) \
+ FN(strncmp, 182, ##ctx) \
+ FN(get_func_arg, 183, ##ctx) \
+ FN(get_func_ret, 184, ##ctx) \
+ FN(get_func_arg_cnt, 185, ##ctx) \
+ FN(get_retval, 186, ##ctx) \
+ FN(set_retval, 187, ##ctx) \
+ FN(xdp_get_buff_len, 188, ##ctx) \
+ FN(xdp_load_bytes, 189, ##ctx) \
+ FN(xdp_store_bytes, 190, ##ctx) \
+ FN(copy_from_user_task, 191, ##ctx) \
+ FN(skb_set_tstamp, 192, ##ctx) \
+ FN(ima_file_hash, 193, ##ctx) \
+ FN(kptr_xchg, 194, ##ctx) \
+ FN(map_lookup_percpu_elem, 195, ##ctx) \
+ FN(skc_to_mptcp_sock, 196, ##ctx) \
+ FN(dynptr_from_mem, 197, ##ctx) \
+ FN(ringbuf_reserve_dynptr, 198, ##ctx) \
+ FN(ringbuf_submit_dynptr, 199, ##ctx) \
+ FN(ringbuf_discard_dynptr, 200, ##ctx) \
+ FN(dynptr_read, 201, ##ctx) \
+ FN(dynptr_write, 202, ##ctx) \
+ FN(dynptr_data, 203, ##ctx) \
+ FN(tcp_raw_gen_syncookie_ipv4, 204, ##ctx) \
+ FN(tcp_raw_gen_syncookie_ipv6, 205, ##ctx) \
+ FN(tcp_raw_check_syncookie_ipv4, 206, ##ctx) \
+ FN(tcp_raw_check_syncookie_ipv6, 207, ##ctx) \
+ FN(ktime_get_tai_ns, 208, ##ctx) \
+ FN(user_ringbuf_drain, 209, ##ctx) \
+ FN(cgrp_storage_get, 210, ##ctx) \
+ FN(cgrp_storage_delete, 211, ##ctx) \
+ /* */
+
+/* backwards-compatibility macros for users of __BPF_FUNC_MAPPER that don't
+ * know or care about integer value that is now passed as second argument
+ */
+#define __BPF_FUNC_MAPPER_APPLY(name, value, FN) FN(name),
+#define __BPF_FUNC_MAPPER(FN) ___BPF_FUNC_MAPPER(__BPF_FUNC_MAPPER_APPLY, FN)
+
+/* integer value in 'imm' field of BPF_CALL instruction selects which helper
+ * function eBPF program intends to call
+ */
+#define __BPF_ENUM_FN(x, y) BPF_FUNC_ ## x = y,
+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. */
+enum {
+ BPF_F_RECOMPUTE_CSUM = (1ULL << 0),
+ 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.
+ */
+enum {
+ BPF_F_HDR_FIELD_MASK = 0xfULL,
+};
+
+/* BPF_FUNC_l4_csum_replace flags. */
+enum {
+ BPF_F_PSEUDO_HDR = (1ULL << 4),
+ BPF_F_MARK_MANGLED_0 = (1ULL << 5),
+ BPF_F_MARK_ENFORCE = (1ULL << 6),
+};
+
+/* BPF_FUNC_clone_redirect and BPF_FUNC_redirect flags. */
+enum {
+ BPF_F_INGRESS = (1ULL << 0),
+};
+
+/* BPF_FUNC_skb_set_tunnel_key and BPF_FUNC_skb_get_tunnel_key flags. */
+enum {
+ BPF_F_TUNINFO_IPV6 = (1ULL << 0),
+};
+
+/* flags for both BPF_FUNC_get_stackid and BPF_FUNC_get_stack. */
+enum {
+ BPF_F_SKIP_FIELD_MASK = 0xffULL,
+ BPF_F_USER_STACK = (1ULL << 8),
+/* flags used by BPF_FUNC_get_stackid only. */
+ BPF_F_FAST_STACK_CMP = (1ULL << 9),
+ BPF_F_REUSE_STACKID = (1ULL << 10),
+/* flags used by BPF_FUNC_get_stack only. */
+ BPF_F_USER_BUILD_ID = (1ULL << 11),
+};
+
+/* BPF_FUNC_skb_set_tunnel_key flags. */
+enum {
+ BPF_F_ZERO_CSUM_TX = (1ULL << 1),
+ BPF_F_DONT_FRAGMENT = (1ULL << 2),
+ BPF_F_SEQ_NUMBER = (1ULL << 3),
+ BPF_F_NO_TUNNEL_KEY = (1ULL << 4),
+};
+
+/* BPF_FUNC_skb_get_tunnel_key flags. */
+enum {
+ BPF_F_TUNINFO_FLAGS = (1ULL << 4),
+};
+
+/* BPF_FUNC_perf_event_output, BPF_FUNC_perf_event_read and
+ * BPF_FUNC_perf_event_read_value flags.
+ */
+enum {
+ BPF_F_INDEX_MASK = 0xffffffffULL,
+ BPF_F_CURRENT_CPU = BPF_F_INDEX_MASK,
+/* BPF_FUNC_perf_event_output for sk_buff input context. */
+ BPF_F_CTXLEN_MASK = (0xfffffULL << 32),
+};
+
+/* Current network namespace */
+enum {
+ BPF_F_CURRENT_NETNS = (-1L),
+};
+
+/* BPF_FUNC_csum_level level values. */
+enum {
+ BPF_CSUM_LEVEL_QUERY,
+ BPF_CSUM_LEVEL_INC,
+ BPF_CSUM_LEVEL_DEC,
+ BPF_CSUM_LEVEL_RESET,
+};
+
+/* BPF_FUNC_skb_adjust_room flags. */
+enum {
+ BPF_F_ADJ_ROOM_FIXED_GSO = (1ULL << 0),
+ BPF_F_ADJ_ROOM_ENCAP_L3_IPV4 = (1ULL << 1),
+ BPF_F_ADJ_ROOM_ENCAP_L3_IPV6 = (1ULL << 2),
+ BPF_F_ADJ_ROOM_ENCAP_L4_GRE = (1ULL << 3),
+ BPF_F_ADJ_ROOM_ENCAP_L4_UDP = (1ULL << 4),
+ BPF_F_ADJ_ROOM_NO_CSUM_RESET = (1ULL << 5),
+ BPF_F_ADJ_ROOM_ENCAP_L2_ETH = (1ULL << 6),
+ BPF_F_ADJ_ROOM_DECAP_L3_IPV4 = (1ULL << 7),
+ BPF_F_ADJ_ROOM_DECAP_L3_IPV6 = (1ULL << 8),
+};
+
+enum {
+ BPF_ADJ_ROOM_ENCAP_L2_MASK = 0xff,
+ BPF_ADJ_ROOM_ENCAP_L2_SHIFT = 56,
+};
+
+#define BPF_F_ADJ_ROOM_ENCAP_L2(len) (((__u64)len & \
+ BPF_ADJ_ROOM_ENCAP_L2_MASK) \
+ << BPF_ADJ_ROOM_ENCAP_L2_SHIFT)
+
+/* BPF_FUNC_sysctl_get_name flags. */
+enum {
+ BPF_F_SYSCTL_BASE_NAME = (1ULL << 0),
+};
+
+/* BPF_FUNC_<kernel_obj>_storage_get flags */
+enum {
+ BPF_LOCAL_STORAGE_GET_F_CREATE = (1ULL << 0),
+ /* BPF_SK_STORAGE_GET_F_CREATE is only kept for backward compatibility
+ * and BPF_LOCAL_STORAGE_GET_F_CREATE must be used instead.
+ */
+ BPF_SK_STORAGE_GET_F_CREATE = BPF_LOCAL_STORAGE_GET_F_CREATE,
+};
+
+/* BPF_FUNC_read_branch_records flags. */
+enum {
+ BPF_F_GET_BRANCH_RECORDS_SIZE = (1ULL << 0),
+};
+
+/* BPF_FUNC_bpf_ringbuf_commit, BPF_FUNC_bpf_ringbuf_discard, and
+ * BPF_FUNC_bpf_ringbuf_output flags.
+ */
+enum {
+ BPF_RB_NO_WAKEUP = (1ULL << 0),
+ BPF_RB_FORCE_WAKEUP = (1ULL << 1),
+};
+
+/* BPF_FUNC_bpf_ringbuf_query flags */
+enum {
+ BPF_RB_AVAIL_DATA = 0,
+ BPF_RB_RING_SIZE = 1,
+ BPF_RB_CONS_POS = 2,
+ BPF_RB_PROD_POS = 3,
+};
+
+/* BPF ring buffer constants */
+enum {
+ BPF_RINGBUF_BUSY_BIT = (1U << 31),
+ BPF_RINGBUF_DISCARD_BIT = (1U << 30),
+ BPF_RINGBUF_HDR_SZ = 8,
+};
+
+/* BPF_FUNC_sk_assign flags in bpf_sk_lookup context. */
+enum {
+ BPF_SK_LOOKUP_F_REPLACE = (1ULL << 0),
+ BPF_SK_LOOKUP_F_NO_REUSEPORT = (1ULL << 1),
+};
+
+/* Mode for BPF_FUNC_skb_adjust_room helper. */
+enum bpf_adj_room_mode {
+ BPF_ADJ_ROOM_NET,
+ BPF_ADJ_ROOM_MAC,
+};
+
+/* 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,
+ BPF_LWT_ENCAP_IP,
+};
+
+/* Flags for bpf_bprm_opts_set helper */
+enum {
+ BPF_F_BPRM_SECUREEXEC = (1ULL << 0),
+};
+
+/* Flags for bpf_redirect_map helper */
+enum {
+ BPF_F_BROADCAST = (1ULL << 3),
+ BPF_F_EXCLUDE_INGRESS = (1ULL << 4),
+};
+
+#define __bpf_md_ptr(type, name) \
+union { \
+ type name; \
+ __u64 :64; \
+} __attribute__((aligned(8)))
+
+enum {
+ BPF_SKB_TSTAMP_UNSPEC,
+ BPF_SKB_TSTAMP_DELIVERY_MONO, /* tstamp has mono delivery time */
+ /* For any BPF_SKB_TSTAMP_* that the bpf prog cannot handle,
+ * the bpf prog should handle it like BPF_SKB_TSTAMP_UNSPEC
+ * and try to deduce it by ingress, egress or skb->sk->sk_clockid.
+ */
+};
+
+/* 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;
+ __bpf_md_ptr(struct bpf_flow_keys *, flow_keys);
+ __u64 tstamp;
+ __u32 wire_len;
+ __u32 gso_segs;
+ __bpf_md_ptr(struct bpf_sock *, sk);
+ __u32 gso_size;
+ __u8 tstamp_type;
+ __u32 :24; /* Padding, future use. */
+ __u64 hwtstamp;
+};
+
+struct bpf_tunnel_key {
+ __u32 tunnel_id;
+ union {
+ __u32 remote_ipv4;
+ __u32 remote_ipv6[4];
+ };
+ __u8 tunnel_tos;
+ __u8 tunnel_ttl;
+ union {
+ __u16 tunnel_ext; /* compat */
+ __be16 tunnel_flags;
+ };
+ __u32 tunnel_label;
+ union {
+ __u32 local_ipv4;
+ __u32 local_ipv6[4];
+ };
+};
+
+/* 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.
+ *
+ * BPF_LWT_REROUTE: used by BPF_PROG_TYPE_LWT_IN and
+ * BPF_PROG_TYPE_LWT_XMIT to indicate that skb had been
+ * changed and should be routed based on its new L3 header.
+ * (This is an L3 redirect, as opposed to L2 redirect
+ * represented by BPF_REDIRECT above).
+ */
+ BPF_LWT_REROUTE = 128,
+ /* BPF_FLOW_DISSECTOR_CONTINUE: used by BPF_PROG_TYPE_FLOW_DISSECTOR
+ * to indicate that no custom dissection was performed, and
+ * fallback to standard dissector is requested.
+ */
+ BPF_FLOW_DISSECTOR_CONTINUE = 129,
+};
+
+struct bpf_sock {
+ __u32 bound_dev_if;
+ __u32 family;
+ __u32 type;
+ __u32 protocol;
+ __u32 mark;
+ __u32 priority;
+ /* IP address also allows 1 and 2 bytes access */
+ __u32 src_ip4;
+ __u32 src_ip6[4];
+ __u32 src_port; /* host byte order */
+ __be16 dst_port; /* network byte order */
+ __u16 :16; /* zero padding */
+ __u32 dst_ip4;
+ __u32 dst_ip6[4];
+ __u32 state;
+ __s32 rx_queue_mapping;
+};
+
+struct bpf_tcp_sock {
+ __u32 snd_cwnd; /* Sending congestion window */
+ __u32 srtt_us; /* smoothed round trip time << 3 in usecs */
+ __u32 rtt_min;
+ __u32 snd_ssthresh; /* Slow start size threshold */
+ __u32 rcv_nxt; /* What we want to receive next */
+ __u32 snd_nxt; /* Next sequence we send */
+ __u32 snd_una; /* First byte we want an ack for */
+ __u32 mss_cache; /* Cached effective mss, not including SACKS */
+ __u32 ecn_flags; /* ECN status bits. */
+ __u32 rate_delivered; /* saved rate sample: packets delivered */
+ __u32 rate_interval_us; /* saved rate sample: time elapsed */
+ __u32 packets_out; /* Packets which are "in flight" */
+ __u32 retrans_out; /* Retransmitted packets out */
+ __u32 total_retrans; /* Total retransmits for entire connection */
+ __u32 segs_in; /* RFC4898 tcpEStatsPerfSegsIn
+ * total number of segments in.
+ */
+ __u32 data_segs_in; /* RFC4898 tcpEStatsPerfDataSegsIn
+ * total number of data segments in.
+ */
+ __u32 segs_out; /* RFC4898 tcpEStatsPerfSegsOut
+ * The total number of segments sent.
+ */
+ __u32 data_segs_out; /* RFC4898 tcpEStatsPerfDataSegsOut
+ * total number of data segments sent.
+ */
+ __u32 lost_out; /* Lost packets */
+ __u32 sacked_out; /* SACK'd packets */
+ __u64 bytes_received; /* RFC4898 tcpEStatsAppHCThruOctetsReceived
+ * sum(delta(rcv_nxt)), or how many bytes
+ * were acked.
+ */
+ __u64 bytes_acked; /* RFC4898 tcpEStatsAppHCThruOctetsAcked
+ * sum(delta(snd_una)), or how many bytes
+ * were acked.
+ */
+ __u32 dsack_dups; /* RFC4898 tcpEStatsStackDSACKDups
+ * total number of DSACK blocks received
+ */
+ __u32 delivered; /* Total data packets delivered incl. rexmits */
+ __u32 delivered_ce; /* Like the above but only ECE marked packets */
+ __u32 icsk_retransmits; /* Number of unrecovered [RTO] timeouts */
+};
+
+struct bpf_sock_tuple {
+ union {
+ struct {
+ __be32 saddr;
+ __be32 daddr;
+ __be16 sport;
+ __be16 dport;
+ } ipv4;
+ struct {
+ __be32 saddr[4];
+ __be32 daddr[4];
+ __be16 sport;
+ __be16 dport;
+ } ipv6;
+ };
+};
+
+/* (Simplified) user return codes for tcx prog type.
+ * A valid tcx program must return one of these defined values. All other
+ * return codes are reserved for future use. Must remain compatible with
+ * their TC_ACT_* counter-parts. For compatibility in behavior, unknown
+ * return codes are mapped to TCX_NEXT.
+ */
+enum tcx_action_base {
+ TCX_NEXT = -1,
+ TCX_PASS = 0,
+ TCX_DROP = 2,
+ TCX_REDIRECT = 7,
+};
+
+struct bpf_xdp_sock {
+ __u32 queue_id;
+};
+
+#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 */
+
+ __u32 egress_ifindex; /* txq->dev->ifindex */
+};
+
+/* DEVMAP map-value layout
+ *
+ * The struct data-layout of map-value is a configuration interface.
+ * New members can only be added to the end of this structure.
+ */
+struct bpf_devmap_val {
+ __u32 ifindex; /* device index */
+ union {
+ int fd; /* prog fd on map write */
+ __u32 id; /* prog id on map read */
+ } bpf_prog;
+};
+
+/* CPUMAP map-value layout
+ *
+ * The struct data-layout of map-value is a configuration interface.
+ * New members can only be added to the end of this structure.
+ */
+struct bpf_cpumap_val {
+ __u32 qsize; /* queue size to remote target CPU */
+ union {
+ int fd; /* prog fd on map write */
+ __u32 id; /* prog id on map read */
+ } bpf_prog;
+};
+
+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 {
+ __bpf_md_ptr(void *, data);
+ __bpf_md_ptr(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 */
+ __u32 size; /* Total size of sk_msg */
+
+ __bpf_md_ptr(struct bpf_sock *, sk); /* current socket */
+};
+
+struct sk_reuseport_md {
+ /*
+ * Start of directly accessible data. It begins from
+ * the tcp/udp header.
+ */
+ __bpf_md_ptr(void *, data);
+ /* End of directly accessible data */
+ __bpf_md_ptr(void *, data_end);
+ /*
+ * 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 */
+ /* When reuse->migrating_sk is NULL, it is selecting a sk for the
+ * new incoming connection request (e.g. selecting a listen sk for
+ * the received SYN in the TCP case). reuse->sk is one of the sk
+ * in the reuseport group. The bpf prog can use reuse->sk to learn
+ * the local listening ip/port without looking into the skb.
+ *
+ * When reuse->migrating_sk is not NULL, reuse->sk is closed and
+ * reuse->migrating_sk is the socket that needs to be migrated
+ * to another listening socket. migrating_sk could be a fullsock
+ * sk that is fully established or a reqsk that is in-the-middle
+ * of 3-way handshake.
+ */
+ __bpf_md_ptr(struct bpf_sock *, sk);
+ __bpf_md_ptr(struct bpf_sock *, migrating_sk);
+};
+
+#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;
+ __u32 :31; /* alignment pad */
+ __u64 netns_dev;
+ __u64 netns_ino;
+ __u32 nr_jited_ksyms;
+ __u32 nr_jited_func_lens;
+ __aligned_u64 jited_ksyms;
+ __aligned_u64 jited_func_lens;
+ __u32 btf_id;
+ __u32 func_info_rec_size;
+ __aligned_u64 func_info;
+ __u32 nr_func_info;
+ __u32 nr_line_info;
+ __aligned_u64 line_info;
+ __aligned_u64 jited_line_info;
+ __u32 nr_jited_line_info;
+ __u32 line_info_rec_size;
+ __u32 jited_line_info_rec_size;
+ __u32 nr_prog_tags;
+ __aligned_u64 prog_tags;
+ __u64 run_time_ns;
+ __u64 run_cnt;
+ __u64 recursion_misses;
+ __u32 verified_insns;
+ __u32 attach_btf_obj_id;
+ __u32 attach_btf_id;
+} __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 btf_vmlinux_value_type_id;
+ __u64 netns_dev;
+ __u64 netns_ino;
+ __u32 btf_id;
+ __u32 btf_key_type_id;
+ __u32 btf_value_type_id;
+ __u32 :32; /* alignment pad */
+ __u64 map_extra;
+} __attribute__((aligned(8)));
+
+struct bpf_btf_info {
+ __aligned_u64 btf;
+ __u32 btf_size;
+ __u32 id;
+ __aligned_u64 name;
+ __u32 name_len;
+ __u32 kernel_btf;
+} __attribute__((aligned(8)));
+
+struct bpf_link_info {
+ __u32 type;
+ __u32 id;
+ __u32 prog_id;
+ union {
+ struct {
+ __aligned_u64 tp_name; /* in/out: tp_name buffer ptr */
+ __u32 tp_name_len; /* in/out: tp_name buffer len */
+ } raw_tracepoint;
+ struct {
+ __u32 attach_type;
+ __u32 target_obj_id; /* prog_id for PROG_EXT, otherwise btf object id */
+ __u32 target_btf_id; /* BTF type id inside the object */
+ } tracing;
+ struct {
+ __u64 cgroup_id;
+ __u32 attach_type;
+ } cgroup;
+ struct {
+ __aligned_u64 target_name; /* in/out: target_name buffer ptr */
+ __u32 target_name_len; /* in/out: target_name buffer len */
+
+ /* If the iter specific field is 32 bits, it can be put
+ * in the first or second union. Otherwise it should be
+ * put in the second union.
+ */
+ union {
+ struct {
+ __u32 map_id;
+ } map;
+ };
+ union {
+ struct {
+ __u64 cgroup_id;
+ __u32 order;
+ } cgroup;
+ struct {
+ __u32 tid;
+ __u32 pid;
+ } task;
+ };
+ } iter;
+ struct {
+ __u32 netns_ino;
+ __u32 attach_type;
+ } netns;
+ struct {
+ __u32 ifindex;
+ } xdp;
+ struct {
+ __u32 map_id;
+ } struct_ops;
+ struct {
+ __u32 pf;
+ __u32 hooknum;
+ __s32 priority;
+ __u32 flags;
+ } netfilter;
+ struct {
+ __aligned_u64 addrs;
+ __u32 count; /* in/out: kprobe_multi function count */
+ __u32 flags;
+ } kprobe_multi;
+ struct {
+ __u32 type; /* enum bpf_perf_event_type */
+ __u32 :32;
+ union {
+ struct {
+ __aligned_u64 file_name; /* in/out */
+ __u32 name_len;
+ __u32 offset; /* offset from file_name */
+ } uprobe; /* BPF_PERF_EVENT_UPROBE, BPF_PERF_EVENT_URETPROBE */
+ struct {
+ __aligned_u64 func_name; /* in/out */
+ __u32 name_len;
+ __u32 offset; /* offset from func_name */
+ __u64 addr;
+ } kprobe; /* BPF_PERF_EVENT_KPROBE, BPF_PERF_EVENT_KRETPROBE */
+ struct {
+ __aligned_u64 tp_name; /* in/out */
+ __u32 name_len;
+ } tracepoint; /* BPF_PERF_EVENT_TRACEPOINT */
+ struct {
+ __u64 config;
+ __u32 type;
+ } event; /* BPF_PERF_EVENT_EVENT */
+ };
+ } perf_event;
+ struct {
+ __u32 ifindex;
+ __u32 attach_type;
+ } tcx;
+ };
+} __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 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 1,2,4,8-byte read and 4,8-byte write.
+ * Stored in network byte order.
+ */
+ __u32 user_port; /* Allows 1,2,4-byte read and 4-byte 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 and 4-byte write.
+ * Stored in network byte order.
+ */
+ __u32 msg_src_ip6[4]; /* Allows 1,2,4,8-byte read and 4,8-byte write.
+ * Stored in network byte order.
+ */
+ __bpf_md_ptr(struct bpf_sock *, sk);
+};
+
+/* 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;
+ __bpf_md_ptr(struct bpf_sock *, sk);
+ /* [skb_data, skb_data_end) covers the whole TCP header.
+ *
+ * BPF_SOCK_OPS_PARSE_HDR_OPT_CB: The packet received
+ * BPF_SOCK_OPS_HDR_OPT_LEN_CB: Not useful because the
+ * header has not been written.
+ * BPF_SOCK_OPS_WRITE_HDR_OPT_CB: The header and options have
+ * been written so far.
+ * BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB: The SYNACK that concludes
+ * the 3WHS.
+ * BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB: The ACK that concludes
+ * the 3WHS.
+ *
+ * bpf_load_hdr_opt() can also be used to read a particular option.
+ */
+ __bpf_md_ptr(void *, skb_data);
+ __bpf_md_ptr(void *, skb_data_end);
+ __u32 skb_len; /* The total length of a packet.
+ * It includes the header, options,
+ * and payload.
+ */
+ __u32 skb_tcp_flags; /* tcp_flags of the header. It provides
+ * an easy way to check for tcp_flags
+ * without parsing skb_data.
+ *
+ * In particular, the skb_tcp_flags
+ * will still be available in
+ * BPF_SOCK_OPS_HDR_OPT_LEN even though
+ * the outgoing header has not
+ * been written yet.
+ */
+ __u64 skb_hwtstamp;
+};
+
+/* Definitions for bpf_sock_ops_cb_flags */
+enum {
+ BPF_SOCK_OPS_RTO_CB_FLAG = (1<<0),
+ BPF_SOCK_OPS_RETRANS_CB_FLAG = (1<<1),
+ BPF_SOCK_OPS_STATE_CB_FLAG = (1<<2),
+ BPF_SOCK_OPS_RTT_CB_FLAG = (1<<3),
+ /* Call bpf for all received TCP headers. The bpf prog will be
+ * called under sock_ops->op == BPF_SOCK_OPS_PARSE_HDR_OPT_CB
+ *
+ * Please refer to the comment in BPF_SOCK_OPS_PARSE_HDR_OPT_CB
+ * for the header option related helpers that will be useful
+ * to the bpf programs.
+ *
+ * It could be used at the client/active side (i.e. connect() side)
+ * when the server told it that the server was in syncookie
+ * mode and required the active side to resend the bpf-written
+ * options. The active side can keep writing the bpf-options until
+ * it received a valid packet from the server side to confirm
+ * the earlier packet (and options) has been received. The later
+ * example patch is using it like this at the active side when the
+ * server is in syncookie mode.
+ *
+ * The bpf prog will usually turn this off in the common cases.
+ */
+ BPF_SOCK_OPS_PARSE_ALL_HDR_OPT_CB_FLAG = (1<<4),
+ /* Call bpf when kernel has received a header option that
+ * the kernel cannot handle. The bpf prog will be called under
+ * sock_ops->op == BPF_SOCK_OPS_PARSE_HDR_OPT_CB.
+ *
+ * Please refer to the comment in BPF_SOCK_OPS_PARSE_HDR_OPT_CB
+ * for the header option related helpers that will be useful
+ * to the bpf programs.
+ */
+ BPF_SOCK_OPS_PARSE_UNKNOWN_HDR_OPT_CB_FLAG = (1<<5),
+ /* Call bpf when the kernel is writing header options for the
+ * outgoing packet. The bpf prog will first be called
+ * to reserve space in a skb under
+ * sock_ops->op == BPF_SOCK_OPS_HDR_OPT_LEN_CB. Then
+ * the bpf prog will be called to write the header option(s)
+ * under sock_ops->op == BPF_SOCK_OPS_WRITE_HDR_OPT_CB.
+ *
+ * Please refer to the comment in BPF_SOCK_OPS_HDR_OPT_LEN_CB
+ * and BPF_SOCK_OPS_WRITE_HDR_OPT_CB for the header option
+ * related helpers that will be useful to the bpf programs.
+ *
+ * The kernel gets its chance to reserve space and write
+ * options first before the BPF program does.
+ */
+ BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG = (1<<6),
+/* Mask of all currently supported cb flags */
+ BPF_SOCK_OPS_ALL_CB_FLAGS = 0x7F,
+};
+
+/* 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.
+ */
+ BPF_SOCK_OPS_RTT_CB, /* Called on every RTT.
+ */
+ BPF_SOCK_OPS_PARSE_HDR_OPT_CB, /* Parse the header option.
+ * It will be called to handle
+ * the packets received at
+ * an already established
+ * connection.
+ *
+ * sock_ops->skb_data:
+ * Referring to the received skb.
+ * It covers the TCP header only.
+ *
+ * bpf_load_hdr_opt() can also
+ * be used to search for a
+ * particular option.
+ */
+ BPF_SOCK_OPS_HDR_OPT_LEN_CB, /* Reserve space for writing the
+ * header option later in
+ * BPF_SOCK_OPS_WRITE_HDR_OPT_CB.
+ * Arg1: bool want_cookie. (in
+ * writing SYNACK only)
+ *
+ * sock_ops->skb_data:
+ * Not available because no header has
+ * been written yet.
+ *
+ * sock_ops->skb_tcp_flags:
+ * The tcp_flags of the
+ * outgoing skb. (e.g. SYN, ACK, FIN).
+ *
+ * bpf_reserve_hdr_opt() should
+ * be used to reserve space.
+ */
+ BPF_SOCK_OPS_WRITE_HDR_OPT_CB, /* Write the header options
+ * Arg1: bool want_cookie. (in
+ * writing SYNACK only)
+ *
+ * sock_ops->skb_data:
+ * Referring to the outgoing skb.
+ * It covers the TCP header
+ * that has already been written
+ * by the kernel and the
+ * earlier bpf-progs.
+ *
+ * sock_ops->skb_tcp_flags:
+ * The tcp_flags of the outgoing
+ * skb. (e.g. SYN, ACK, FIN).
+ *
+ * bpf_store_hdr_opt() should
+ * be used to write the
+ * option.
+ *
+ * bpf_load_hdr_opt() can also
+ * be used to search for a
+ * particular option that
+ * has already been written
+ * by the kernel or the
+ * earlier bpf-progs.
+ */
+};
+
+/* 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! */
+};
+
+enum {
+ TCP_BPF_IW = 1001, /* Set TCP initial congestion window */
+ TCP_BPF_SNDCWND_CLAMP = 1002, /* Set sndcwnd_clamp */
+ TCP_BPF_DELACK_MAX = 1003, /* Max delay ack in usecs */
+ TCP_BPF_RTO_MIN = 1004, /* Min delay ack in usecs */
+ /* Copy the SYN pkt to optval
+ *
+ * BPF_PROG_TYPE_SOCK_OPS only. It is similar to the
+ * bpf_getsockopt(TCP_SAVED_SYN) but it does not limit
+ * to only getting from the saved_syn. It can either get the
+ * syn packet from:
+ *
+ * 1. the just-received SYN packet (only available when writing the
+ * SYNACK). It will be useful when it is not necessary to
+ * save the SYN packet for latter use. It is also the only way
+ * to get the SYN during syncookie mode because the syn
+ * packet cannot be saved during syncookie.
+ *
+ * OR
+ *
+ * 2. the earlier saved syn which was done by
+ * bpf_setsockopt(TCP_SAVE_SYN).
+ *
+ * The bpf_getsockopt(TCP_BPF_SYN*) option will hide where the
+ * SYN packet is obtained.
+ *
+ * If the bpf-prog does not need the IP[46] header, the
+ * bpf-prog can avoid parsing the IP header by using
+ * TCP_BPF_SYN. Otherwise, the bpf-prog can get both
+ * IP[46] and TCP header by using TCP_BPF_SYN_IP.
+ *
+ * >0: Total number of bytes copied
+ * -ENOSPC: Not enough space in optval. Only optlen number of
+ * bytes is copied.
+ * -ENOENT: The SYN skb is not available now and the earlier SYN pkt
+ * is not saved by setsockopt(TCP_SAVE_SYN).
+ */
+ TCP_BPF_SYN = 1005, /* Copy the TCP header */
+ TCP_BPF_SYN_IP = 1006, /* Copy the IP[46] and TCP header */
+ TCP_BPF_SYN_MAC = 1007, /* Copy the MAC, IP[46], and TCP header */
+};
+
+enum {
+ BPF_LOAD_HDR_OPT_TCP_SYN = (1ULL << 0),
+};
+
+/* args[0] value during BPF_SOCK_OPS_HDR_OPT_LEN_CB and
+ * BPF_SOCK_OPS_WRITE_HDR_OPT_CB.
+ */
+enum {
+ BPF_WRITE_HDR_TCP_CURRENT_MSS = 1, /* Kernel is finding the
+ * total option spaces
+ * required for an established
+ * sk in order to calculate the
+ * MSS. No skb is actually
+ * sent.
+ */
+ BPF_WRITE_HDR_TCP_SYNACK_COOKIE = 2, /* Kernel is in syncookie mode
+ * when sending a SYN.
+ */
+};
+
+struct bpf_perf_event_value {
+ __u64 counter;
+ __u64 enabled;
+ __u64 running;
+};
+
+enum {
+ BPF_DEVCG_ACC_MKNOD = (1ULL << 0),
+ BPF_DEVCG_ACC_READ = (1ULL << 1),
+ BPF_DEVCG_ACC_WRITE = (1ULL << 2),
+};
+
+enum {
+ BPF_DEVCG_DEV_BLOCK = (1ULL << 0),
+ 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
+ */
+enum {
+ BPF_FIB_LOOKUP_DIRECT = (1U << 0),
+ BPF_FIB_LOOKUP_OUTPUT = (1U << 1),
+ BPF_FIB_LOOKUP_SKIP_NEIGH = (1U << 2),
+ BPF_FIB_LOOKUP_TBID = (1U << 3),
+};
+
+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;
+
+ union { /* used for MTU check */
+ /* input to lookup */
+ __u16 tot_len; /* L3 length from network hdr (iph->tot_len) */
+
+ /* output: MTU value */
+ __u16 mtu_result;
+ };
+ /* 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 */
+ };
+
+ union {
+ struct {
+ /* output */
+ __be16 h_vlan_proto;
+ __be16 h_vlan_TCI;
+ };
+ /* input: when accompanied with the
+ * 'BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_TBID` flags, a
+ * specific routing table to use for the fib lookup.
+ */
+ __u32 tbid;
+ };
+
+ __u8 smac[6]; /* ETH_ALEN */
+ __u8 dmac[6]; /* ETH_ALEN */
+};
+
+struct bpf_redir_neigh {
+ /* network family for lookup (AF_INET, AF_INET6) */
+ __u32 nh_family;
+ /* network address of nexthop; skips fib lookup to find gateway */
+ union {
+ __be32 ipv4_nh;
+ __u32 ipv6_nh[4]; /* in6_addr; network order */
+ };
+};
+
+/* bpf_check_mtu flags*/
+enum bpf_check_mtu_flags {
+ BPF_MTU_CHK_SEGS = (1U << 0),
+};
+
+enum bpf_check_mtu_ret {
+ BPF_MTU_CHK_RET_SUCCESS, /* check and lookup successful */
+ BPF_MTU_CHK_RET_FRAG_NEEDED, /* fragmentation required to fwd */
+ BPF_MTU_CHK_RET_SEGS_TOOBIG, /* GSO re-segmentation needed to fwd */
+};
+
+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 */
+};
+
+enum {
+ BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG = (1U << 0),
+ BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL = (1U << 1),
+ BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP = (1U << 2),
+};
+
+struct bpf_flow_keys {
+ __u16 nhoff;
+ __u16 thoff;
+ __u16 addr_proto; /* ETH_P_* of valid addrs */
+ __u8 is_frag;
+ __u8 is_first_frag;
+ __u8 is_encap;
+ __u8 ip_proto;
+ __be16 n_proto;
+ __be16 sport;
+ __be16 dport;
+ union {
+ struct {
+ __be32 ipv4_src;
+ __be32 ipv4_dst;
+ };
+ struct {
+ __u32 ipv6_src[4]; /* in6_addr; network order */
+ __u32 ipv6_dst[4]; /* in6_addr; network order */
+ };
+ };
+ __u32 flags;
+ __be32 flow_label;
+};
+
+struct bpf_func_info {
+ __u32 insn_off;
+ __u32 type_id;
+};
+
+#define BPF_LINE_INFO_LINE_NUM(line_col) ((line_col) >> 10)
+#define BPF_LINE_INFO_LINE_COL(line_col) ((line_col) & 0x3ff)
+
+struct bpf_line_info {
+ __u32 insn_off;
+ __u32 file_name_off;
+ __u32 line_off;
+ __u32 line_col;
+};
+
+struct bpf_spin_lock {
+ __u32 val;
+};
+
+struct bpf_timer {
+ __u64 :64;
+ __u64 :64;
+} __attribute__((aligned(8)));
+
+struct bpf_dynptr {
+ __u64 :64;
+ __u64 :64;
+} __attribute__((aligned(8)));
+
+struct bpf_list_head {
+ __u64 :64;
+ __u64 :64;
+} __attribute__((aligned(8)));
+
+struct bpf_list_node {
+ __u64 :64;
+ __u64 :64;
+ __u64 :64;
+} __attribute__((aligned(8)));
+
+struct bpf_rb_root {
+ __u64 :64;
+ __u64 :64;
+} __attribute__((aligned(8)));
+
+struct bpf_rb_node {
+ __u64 :64;
+ __u64 :64;
+ __u64 :64;
+ __u64 :64;
+} __attribute__((aligned(8)));
+
+struct bpf_refcount {
+ __u32 :32;
+} __attribute__((aligned(4)));
+
+struct bpf_sysctl {
+ __u32 write; /* Sysctl is being read (= 0) or written (= 1).
+ * Allows 1,2,4-byte read, but no write.
+ */
+ __u32 file_pos; /* Sysctl file position to read from, write to.
+ * Allows 1,2,4-byte read an 4-byte write.
+ */
+};
+
+struct bpf_sockopt {
+ __bpf_md_ptr(struct bpf_sock *, sk);
+ __bpf_md_ptr(void *, optval);
+ __bpf_md_ptr(void *, optval_end);
+
+ __s32 level;
+ __s32 optname;
+ __s32 optlen;
+ __s32 retval;
+};
+
+struct bpf_pidns_info {
+ __u32 pid;
+ __u32 tgid;
+};
+
+/* User accessible data for SK_LOOKUP programs. Add new fields at the end. */
+struct bpf_sk_lookup {
+ union {
+ __bpf_md_ptr(struct bpf_sock *, sk); /* Selected socket */
+ __u64 cookie; /* Non-zero if socket was selected in PROG_TEST_RUN */
+ };
+
+ __u32 family; /* Protocol family (AF_INET, AF_INET6) */
+ __u32 protocol; /* IP protocol (IPPROTO_TCP, IPPROTO_UDP) */
+ __u32 remote_ip4; /* Network byte order */
+ __u32 remote_ip6[4]; /* Network byte order */
+ __be16 remote_port; /* Network byte order */
+ __u16 :16; /* Zero padding */
+ __u32 local_ip4; /* Network byte order */
+ __u32 local_ip6[4]; /* Network byte order */
+ __u32 local_port; /* Host byte order */
+ __u32 ingress_ifindex; /* The arriving interface. Determined by inet_iif. */
+};
+
+/*
+ * struct btf_ptr is used for typed pointer representation; the
+ * type id is used to render the pointer data as the appropriate type
+ * via the bpf_snprintf_btf() helper described above. A flags field -
+ * potentially to specify additional details about the BTF pointer
+ * (rather than its mode of display) - is included for future use.
+ * Display flags - BTF_F_* - are passed to bpf_snprintf_btf separately.
+ */
+struct btf_ptr {
+ void *ptr;
+ __u32 type_id;
+ __u32 flags; /* BTF ptr flags; unused at present. */
+};
+
+/*
+ * Flags to control bpf_snprintf_btf() behaviour.
+ * - BTF_F_COMPACT: no formatting around type information
+ * - BTF_F_NONAME: no struct/union member names/types
+ * - BTF_F_PTR_RAW: show raw (unobfuscated) pointer values;
+ * equivalent to %px.
+ * - BTF_F_ZERO: show zero-valued struct/union members; they
+ * are not displayed by default
+ */
+enum {
+ BTF_F_COMPACT = (1ULL << 0),
+ BTF_F_NONAME = (1ULL << 1),
+ BTF_F_PTR_RAW = (1ULL << 2),
+ BTF_F_ZERO = (1ULL << 3),
+};
+
+/* bpf_core_relo_kind encodes which aspect of captured field/type/enum value
+ * has to be adjusted by relocations. It is emitted by llvm and passed to
+ * libbpf and later to the kernel.
+ */
+enum bpf_core_relo_kind {
+ BPF_CORE_FIELD_BYTE_OFFSET = 0, /* field byte offset */
+ BPF_CORE_FIELD_BYTE_SIZE = 1, /* field size in bytes */
+ BPF_CORE_FIELD_EXISTS = 2, /* field existence in target kernel */
+ BPF_CORE_FIELD_SIGNED = 3, /* field signedness (0 - unsigned, 1 - signed) */
+ BPF_CORE_FIELD_LSHIFT_U64 = 4, /* bitfield-specific left bitshift */
+ BPF_CORE_FIELD_RSHIFT_U64 = 5, /* bitfield-specific right bitshift */
+ BPF_CORE_TYPE_ID_LOCAL = 6, /* type ID in local BPF object */
+ BPF_CORE_TYPE_ID_TARGET = 7, /* type ID in target kernel */
+ BPF_CORE_TYPE_EXISTS = 8, /* type existence in target kernel */
+ BPF_CORE_TYPE_SIZE = 9, /* type size in bytes */
+ BPF_CORE_ENUMVAL_EXISTS = 10, /* enum value existence in target kernel */
+ BPF_CORE_ENUMVAL_VALUE = 11, /* enum value integer value */
+ BPF_CORE_TYPE_MATCHES = 12, /* type match in target kernel */
+};
+
+/*
+ * "struct bpf_core_relo" is used to pass relocation data form LLVM to libbpf
+ * and from libbpf to the kernel.
+ *
+ * CO-RE relocation captures the following data:
+ * - insn_off - instruction offset (in bytes) within a BPF program that needs
+ * its insn->imm field to be relocated with actual field info;
+ * - type_id - BTF type ID of the "root" (containing) entity of a relocatable
+ * type or field;
+ * - access_str_off - offset into corresponding .BTF string section. String
+ * interpretation depends on specific relocation kind:
+ * - for field-based relocations, string encodes an accessed field using
+ * a sequence of field and array indices, separated by colon (:). It's
+ * conceptually very close to LLVM's getelementptr ([0]) instruction's
+ * arguments for identifying offset to a field.
+ * - for type-based relocations, strings is expected to be just "0";
+ * - for enum value-based relocations, string contains an index of enum
+ * value within its enum type;
+ * - kind - one of enum bpf_core_relo_kind;
+ *
+ * Example:
+ * struct sample {
+ * int a;
+ * struct {
+ * int b[10];
+ * };
+ * };
+ *
+ * struct sample *s = ...;
+ * int *x = &s->a; // encoded as "0:0" (a is field #0)
+ * int *y = &s->b[5]; // encoded as "0:1:0:5" (anon struct is field #1,
+ * // b is field #0 inside anon struct, accessing elem #5)
+ * int *z = &s[10]->b; // encoded as "10:1" (ptr is used as an array)
+ *
+ * type_id for all relocs in this example will capture BTF type id of
+ * `struct sample`.
+ *
+ * Such relocation is emitted when using __builtin_preserve_access_index()
+ * Clang built-in, passing expression that captures field address, e.g.:
+ *
+ * bpf_probe_read(&dst, sizeof(dst),
+ * __builtin_preserve_access_index(&src->a.b.c));
+ *
+ * In this case Clang will emit field relocation recording necessary data to
+ * be able to find offset of embedded `a.b.c` field within `src` struct.
+ *
+ * [0] https://llvm.org/docs/LangRef.html#getelementptr-instruction
+ */
+struct bpf_core_relo {
+ __u32 insn_off;
+ __u32 type_id;
+ __u32 access_str_off;
+ enum bpf_core_relo_kind kind;
+};
+
+/*
+ * Flags to control bpf_timer_start() behaviour.
+ * - BPF_F_TIMER_ABS: Timeout passed is absolute time, by default it is
+ * relative to current time.
+ */
+enum {
+ BPF_F_TIMER_ABS = (1ULL << 0),
+};
+
+/* BPF numbers iterator state */
+struct bpf_iter_num {
+ /* opaque iterator state; having __u64 here allows to preserve correct
+ * alignment requirements in vmlinux.h, generated from BTF
+ */
+ __u64 __opaque[1];
+} __attribute__((aligned(8)));
+
+#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 0000000000..ee97668bda
--- /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 0000000000..eb1b9d2125
--- /dev/null
+++ b/tools/include/uapi/linux/bpf_perf_event.h
@@ -0,0 +1,19 @@
+/* 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;
+ __u64 addr;
+};
+
+#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 0000000000..ec1798b6d3
--- /dev/null
+++ b/tools/include/uapi/linux/btf.h
@@ -0,0 +1,200 @@
+/* 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 0x000fffff
+/* Max offset into the string section */
+#define BTF_MAX_NAME_OFFSET 0x00ffffff
+/* 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 24-28: kind (e.g. int, ptr, array...etc)
+ * bits 29-30: unused
+ * bit 31: kind_flag, currently used by
+ * struct, union, enum, fwd and enum64
+ */
+ __u32 info;
+ /* "size" is used by INT, ENUM, STRUCT, UNION, DATASEC and ENUM64.
+ * "size" tells the size of the type it is describing.
+ *
+ * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT,
+ * FUNC, FUNC_PROTO, VAR, DECL_TAG and TYPE_TAG.
+ * "type" is a type_id referring to another type.
+ */
+ union {
+ __u32 size;
+ __u32 type;
+ };
+};
+
+#define BTF_INFO_KIND(info) (((info) >> 24) & 0x1f)
+#define BTF_INFO_VLEN(info) ((info) & 0xffff)
+#define BTF_INFO_KFLAG(info) ((info) >> 31)
+
+enum {
+ BTF_KIND_UNKN = 0, /* Unknown */
+ BTF_KIND_INT = 1, /* Integer */
+ BTF_KIND_PTR = 2, /* Pointer */
+ BTF_KIND_ARRAY = 3, /* Array */
+ BTF_KIND_STRUCT = 4, /* Struct */
+ BTF_KIND_UNION = 5, /* Union */
+ BTF_KIND_ENUM = 6, /* Enumeration up to 32-bit values */
+ BTF_KIND_FWD = 7, /* Forward */
+ BTF_KIND_TYPEDEF = 8, /* Typedef */
+ BTF_KIND_VOLATILE = 9, /* Volatile */
+ BTF_KIND_CONST = 10, /* Const */
+ BTF_KIND_RESTRICT = 11, /* Restrict */
+ BTF_KIND_FUNC = 12, /* Function */
+ BTF_KIND_FUNC_PROTO = 13, /* Function Proto */
+ BTF_KIND_VAR = 14, /* Variable */
+ BTF_KIND_DATASEC = 15, /* Section */
+ BTF_KIND_FLOAT = 16, /* Floating point */
+ BTF_KIND_DECL_TAG = 17, /* Decl Tag */
+ BTF_KIND_TYPE_TAG = 18, /* Type Tag */
+ BTF_KIND_ENUM64 = 19, /* Enumeration up to 64-bit values */
+
+ NR_BTF_KINDS,
+ BTF_KIND_MAX = NR_BTF_KINDS - 1,
+};
+
+/* 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;
+ /* If the type info kind_flag is set, the btf_member offset
+ * contains both member bitfield size and bit offset. The
+ * bitfield size is set for bitfield members. If the type
+ * info kind_flag is not set, the offset contains only bit
+ * offset.
+ */
+ __u32 offset;
+};
+
+/* If the struct/union type info kind_flag is set, the
+ * following two macros are used to access bitfield_size
+ * and bit_offset from btf_member.offset.
+ */
+#define BTF_MEMBER_BITFIELD_SIZE(val) ((val) >> 24)
+#define BTF_MEMBER_BIT_OFFSET(val) ((val) & 0xffffff)
+
+/* BTF_KIND_FUNC_PROTO is followed by multiple "struct btf_param".
+ * The exact number of btf_param is stored in the vlen (of the
+ * info in "struct btf_type").
+ */
+struct btf_param {
+ __u32 name_off;
+ __u32 type;
+};
+
+enum {
+ BTF_VAR_STATIC = 0,
+ BTF_VAR_GLOBAL_ALLOCATED = 1,
+ BTF_VAR_GLOBAL_EXTERN = 2,
+};
+
+enum btf_func_linkage {
+ BTF_FUNC_STATIC = 0,
+ BTF_FUNC_GLOBAL = 1,
+ BTF_FUNC_EXTERN = 2,
+};
+
+/* BTF_KIND_VAR is followed by a single "struct btf_var" to describe
+ * additional information related to the variable such as its linkage.
+ */
+struct btf_var {
+ __u32 linkage;
+};
+
+/* BTF_KIND_DATASEC is followed by multiple "struct btf_var_secinfo"
+ * to describe all BTF_KIND_VAR types it contains along with it's
+ * in-section offset as well as size.
+ */
+struct btf_var_secinfo {
+ __u32 type;
+ __u32 offset;
+ __u32 size;
+};
+
+/* BTF_KIND_DECL_TAG is followed by a single "struct btf_decl_tag" to describe
+ * additional information related to the tag applied location.
+ * If component_idx == -1, the tag is applied to a struct, union,
+ * variable or function. Otherwise, it is applied to a struct/union
+ * member or a func argument, and component_idx indicates which member
+ * or argument (0 ... vlen-1).
+ */
+struct btf_decl_tag {
+ __s32 component_idx;
+};
+
+/* BTF_KIND_ENUM64 is followed by multiple "struct btf_enum64".
+ * The exact number of btf_enum64 is stored in the vlen (of the
+ * info in "struct btf_type").
+ */
+struct btf_enum64 {
+ __u32 name_off;
+ __u32 val_lo32;
+ __u32 val_hi32;
+};
+
+#endif /* _UAPI__LINUX_BTF_H__ */
diff --git a/tools/include/uapi/linux/const.h b/tools/include/uapi/linux/const.h
new file mode 100644
index 0000000000..a429381e7c
--- /dev/null
+++ b/tools/include/uapi/linux/const.h
@@ -0,0 +1,36 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* const.h: Macros for dealing with constants. */
+
+#ifndef _UAPI_LINUX_CONST_H
+#define _UAPI_LINUX_CONST_H
+
+/* Some constant macros are used in both assembler and
+ * C code. Therefore we cannot annotate them always with
+ * 'UL' and other type specifiers unilaterally. We
+ * use the following macros to deal with this.
+ *
+ * Similarly, _AT() will cast an expression with a type in C, but
+ * leave it unchanged in asm.
+ */
+
+#ifdef __ASSEMBLY__
+#define _AC(X,Y) X
+#define _AT(T,X) X
+#else
+#define __AC(X,Y) (X##Y)
+#define _AC(X,Y) __AC(X,Y)
+#define _AT(T,X) ((T)(X))
+#endif
+
+#define _UL(x) (_AC(x, UL))
+#define _ULL(x) (_AC(x, ULL))
+
+#define _BITUL(x) (_UL(1) << (x))
+#define _BITULL(x) (_ULL(1) << (x))
+
+#define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (__typeof__(x))(a) - 1)
+#define __ALIGN_KERNEL_MASK(x, mask) (((x) + (mask)) & ~(mask))
+
+#define __KERNEL_DIV_ROUND_UP(n, d) (((n) + (d) - 1) / (d))
+
+#endif /* _UAPI_LINUX_CONST_H */
diff --git a/tools/include/uapi/linux/erspan.h b/tools/include/uapi/linux/erspan.h
new file mode 100644
index 0000000000..841573019a
--- /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/ethtool.h b/tools/include/uapi/linux/ethtool.h
new file mode 100644
index 0000000000..47afae3895
--- /dev/null
+++ b/tools/include/uapi/linux/ethtool.h
@@ -0,0 +1,104 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * ethtool.h: Defines for Linux ethtool.
+ *
+ * Copyright (C) 1998 David S. Miller (davem@redhat.com)
+ * Copyright 2001 Jeff Garzik <jgarzik@pobox.com>
+ * Portions Copyright 2001 Sun Microsystems (thockin@sun.com)
+ * Portions Copyright 2002 Intel (eli.kupermann@intel.com,
+ * christopher.leech@intel.com,
+ * scott.feldman@intel.com)
+ * Portions Copyright (C) Sun Microsystems 2008
+ */
+
+#ifndef _UAPI_LINUX_ETHTOOL_H
+#define _UAPI_LINUX_ETHTOOL_H
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/if_ether.h>
+
+#define ETHTOOL_GCHANNELS 0x0000003c /* Get no of channels */
+
+/**
+ * struct ethtool_channels - configuring number of network channel
+ * @cmd: ETHTOOL_{G,S}CHANNELS
+ * @max_rx: Read only. Maximum number of receive channel the driver support.
+ * @max_tx: Read only. Maximum number of transmit channel the driver support.
+ * @max_other: Read only. Maximum number of other channel the driver support.
+ * @max_combined: Read only. Maximum number of combined channel the driver
+ * support. Set of queues RX, TX or other.
+ * @rx_count: Valid values are in the range 1 to the max_rx.
+ * @tx_count: Valid values are in the range 1 to the max_tx.
+ * @other_count: Valid values are in the range 1 to the max_other.
+ * @combined_count: Valid values are in the range 1 to the max_combined.
+ *
+ * This can be used to configure RX, TX and other channels.
+ */
+
+struct ethtool_channels {
+ __u32 cmd;
+ __u32 max_rx;
+ __u32 max_tx;
+ __u32 max_other;
+ __u32 max_combined;
+ __u32 rx_count;
+ __u32 tx_count;
+ __u32 other_count;
+ __u32 combined_count;
+};
+
+#define ETHTOOL_FWVERS_LEN 32
+#define ETHTOOL_BUSINFO_LEN 32
+#define ETHTOOL_EROMVERS_LEN 32
+
+/**
+ * struct ethtool_drvinfo - general driver and device information
+ * @cmd: Command number = %ETHTOOL_GDRVINFO
+ * @driver: Driver short name. This should normally match the name
+ * in its bus driver structure (e.g. pci_driver::name). Must
+ * not be an empty string.
+ * @version: Driver version string; may be an empty string
+ * @fw_version: Firmware version string; may be an empty string
+ * @erom_version: Expansion ROM version string; may be an empty string
+ * @bus_info: Device bus address. This should match the dev_name()
+ * string for the underlying bus device, if there is one. May be
+ * an empty string.
+ * @reserved2: Reserved for future use; see the note on reserved space.
+ * @n_priv_flags: Number of flags valid for %ETHTOOL_GPFLAGS and
+ * %ETHTOOL_SPFLAGS commands; also the number of strings in the
+ * %ETH_SS_PRIV_FLAGS set
+ * @n_stats: Number of u64 statistics returned by the %ETHTOOL_GSTATS
+ * command; also the number of strings in the %ETH_SS_STATS set
+ * @testinfo_len: Number of results returned by the %ETHTOOL_TEST
+ * command; also the number of strings in the %ETH_SS_TEST set
+ * @eedump_len: Size of EEPROM accessible through the %ETHTOOL_GEEPROM
+ * and %ETHTOOL_SEEPROM commands, in bytes
+ * @regdump_len: Size of register dump returned by the %ETHTOOL_GREGS
+ * command, in bytes
+ *
+ * Users can use the %ETHTOOL_GSSET_INFO command to get the number of
+ * strings in any string set (from Linux 2.6.34).
+ *
+ * Drivers should set at most @driver, @version, @fw_version and
+ * @bus_info in their get_drvinfo() implementation. The ethtool
+ * core fills in the other fields using other driver operations.
+ */
+struct ethtool_drvinfo {
+ __u32 cmd;
+ char driver[32];
+ char version[32];
+ char fw_version[ETHTOOL_FWVERS_LEN];
+ char bus_info[ETHTOOL_BUSINFO_LEN];
+ char erom_version[ETHTOOL_EROMVERS_LEN];
+ char reserved2[12];
+ __u32 n_priv_flags;
+ __u32 n_stats;
+ __u32 testinfo_len;
+ __u32 eedump_len;
+ __u32 regdump_len;
+};
+
+#define ETHTOOL_GDRVINFO 0x00000003
+
+#endif /* _UAPI_LINUX_ETHTOOL_H */
diff --git a/tools/include/uapi/linux/fadvise.h b/tools/include/uapi/linux/fadvise.h
new file mode 100644
index 0000000000..0862b87434
--- /dev/null
+++ b/tools/include/uapi/linux/fadvise.h
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef FADVISE_H_INCLUDED
+#define FADVISE_H_INCLUDED
+
+#define POSIX_FADV_NORMAL 0 /* No further special treatment. */
+#define POSIX_FADV_RANDOM 1 /* Expect random page references. */
+#define POSIX_FADV_SEQUENTIAL 2 /* Expect sequential page references. */
+#define POSIX_FADV_WILLNEED 3 /* Will need these pages. */
+
+/*
+ * The advise values for POSIX_FADV_DONTNEED and POSIX_ADV_NOREUSE
+ * for s390-64 differ from the values for the rest of the world.
+ */
+#if defined(__s390x__)
+#define POSIX_FADV_DONTNEED 6 /* Don't need these pages. */
+#define POSIX_FADV_NOREUSE 7 /* Data will be accessed once. */
+#else
+#define POSIX_FADV_DONTNEED 4 /* Don't need these pages. */
+#define POSIX_FADV_NOREUSE 5 /* Data will be accessed once. */
+#endif
+
+#endif /* FADVISE_H_INCLUDED */
diff --git a/tools/include/uapi/linux/fcntl.h b/tools/include/uapi/linux/fcntl.h
new file mode 100644
index 0000000000..6c80f96049
--- /dev/null
+++ b/tools/include/uapi/linux/fcntl.h
@@ -0,0 +1,120 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_LINUX_FCNTL_H
+#define _UAPI_LINUX_FCNTL_H
+
+#include <asm/fcntl.h>
+#include <linux/openat2.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 */
+#define F_SEAL_FUTURE_WRITE 0x0010 /* prevent future writes while mapped */
+#define F_SEAL_EXEC 0x0020 /* prevent chmod modifying exec bits */
+/* (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 RWH_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
+
+/*
+ * The originally introduced spelling is remained from the first
+ * versions of the patch set that introduced the feature, see commit
+ * v4.13-rc1~212^2~51.
+ */
+#define RWF_WRITE_LIFE_NOT_SET RWH_WRITE_LIFE_NOT_SET
+
+/*
+ * 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 */
+
+/*
+ * The constants AT_REMOVEDIR and AT_EACCESS have the same value. AT_EACCESS is
+ * meaningful only to faccessat, while AT_REMOVEDIR is meaningful only to
+ * unlinkat. The two functions do completely different things and therefore,
+ * the flags can be allowed to overlap. For example, passing AT_REMOVEDIR to
+ * faccessat would be undefined behavior and thus treating it equivalent to
+ * AT_EACCESS is valid undefined behavior.
+ */
+#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_EACCESS 0x200 /* Test access permitted for
+ effective IDs, not real IDs. */
+#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 */
+
+#define AT_RECURSIVE 0x8000 /* Apply to the entire subtree */
+
+/* Flags for name_to_handle_at(2). We reuse AT_ flag space to save bits... */
+#define AT_HANDLE_FID AT_REMOVEDIR /* file handle is needed to
+ compare object identity and may not
+ be usable to open_by_handle_at(2) */
+
+#endif /* _UAPI_LINUX_FCNTL_H */
diff --git a/tools/include/uapi/linux/filter.h b/tools/include/uapi/linux/filter.h
new file mode 100644
index 0000000000..eaef459e7b
--- /dev/null
+++ b/tools/include/uapi/linux/filter.h
@@ -0,0 +1,90 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Linux Socket Filter Data Structures
+ */
+
+#ifndef __LINUX_FILTER_H__
+#define __LINUX_FILTER_H__
+
+
+#include <linux/types.h>
+#include <linux/bpf_common.h>
+
+/*
+ * Current version of the filter code architecture.
+ */
+#define BPF_MAJOR_VERSION 1
+#define BPF_MINOR_VERSION 1
+
+/*
+ * Try and keep these values and structures similar to BSD, especially
+ * the BPF code definitions which need to match so you can share filters
+ */
+
+struct sock_filter { /* Filter block */
+ __u16 code; /* Actual filter code */
+ __u8 jt; /* Jump true */
+ __u8 jf; /* Jump false */
+ __u32 k; /* Generic multiuse field */
+};
+
+struct sock_fprog { /* Required for SO_ATTACH_FILTER. */
+ unsigned short len; /* Number of filter blocks */
+ struct sock_filter *filter;
+};
+
+/* ret - BPF_K and BPF_X also apply */
+#define BPF_RVAL(code) ((code) & 0x18)
+#define BPF_A 0x10
+
+/* misc */
+#define BPF_MISCOP(code) ((code) & 0xf8)
+#define BPF_TAX 0x00
+#define BPF_TXA 0x80
+
+/*
+ * Macros for filter block array initializers.
+ */
+#ifndef BPF_STMT
+#define BPF_STMT(code, k) { (unsigned short)(code), 0, 0, k }
+#endif
+#ifndef BPF_JUMP
+#define BPF_JUMP(code, k, jt, jf) { (unsigned short)(code), jt, jf, k }
+#endif
+
+/*
+ * Number of scratch memory words for: BPF_ST and BPF_STX
+ */
+#define BPF_MEMWORDS 16
+
+/* RATIONALE. Negative offsets are invalid in BPF.
+ We use them to reference ancillary data.
+ Unlike introduction new instructions, it does not break
+ existing compilers/optimizers.
+ */
+#define SKF_AD_OFF (-0x1000)
+#define SKF_AD_PROTOCOL 0
+#define SKF_AD_PKTTYPE 4
+#define SKF_AD_IFINDEX 8
+#define SKF_AD_NLATTR 12
+#define SKF_AD_NLATTR_NEST 16
+#define SKF_AD_MARK 20
+#define SKF_AD_QUEUE 24
+#define SKF_AD_HATYPE 28
+#define SKF_AD_RXHASH 32
+#define SKF_AD_CPU 36
+#define SKF_AD_ALU_XOR_X 40
+#define SKF_AD_VLAN_TAG 44
+#define SKF_AD_VLAN_TAG_PRESENT 48
+#define SKF_AD_PAY_OFFSET 52
+#define SKF_AD_RANDOM 56
+#define SKF_AD_VLAN_TPID 60
+#define SKF_AD_MAX 64
+
+#define SKF_NET_OFF (-0x100000)
+#define SKF_LL_OFF (-0x200000)
+
+#define BPF_NET_OFF SKF_NET_OFF
+#define BPF_LL_OFF SKF_LL_OFF
+
+#endif /* __LINUX_FILTER_H__ */
diff --git a/tools/include/uapi/linux/fs.h b/tools/include/uapi/linux/fs.h
new file mode 100644
index 0000000000..b7b5687102
--- /dev/null
+++ b/tools/include/uapi/linux/fs.h
@@ -0,0 +1,308 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_LINUX_FS_H
+#define _UAPI_LINUX_FS_H
+
+/*
+ * This file has definitions for some important file table structures
+ * and constants and structures used by various generic file system
+ * ioctl's. Please do not make any changes in this file before
+ * sending patches for review to linux-fsdevel@vger.kernel.org and
+ * linux-api@vger.kernel.org.
+ */
+
+#include <linux/limits.h>
+#include <linux/ioctl.h>
+#include <linux/types.h>
+#ifndef __KERNEL__
+#include <linux/fscrypt.h>
+#endif
+
+/* Use of MS_* flags within the kernel is restricted to core mount(2) code. */
+#if !defined(__KERNEL__)
+#include <linux/mount.h>
+#endif
+
+/*
+ * It's silly to have NR_OPEN bigger than NR_FILE, but you can change
+ * the file limit at runtime and only root can increase the per-process
+ * nr_file rlimit, so it's safe to set up a ridiculously high absolute
+ * upper limit on files-per-process.
+ *
+ * Some programs (notably those using select()) may have to be
+ * recompiled to take full advantage of the new limits..
+ */
+
+/* Fixed constants first: */
+#undef NR_OPEN
+#define INR_OPEN_CUR 1024 /* Initial setting for nfile rlimits */
+#define INR_OPEN_MAX 4096 /* Hard limit for nfile rlimits */
+
+#define BLOCK_SIZE_BITS 10
+#define BLOCK_SIZE (1<<BLOCK_SIZE_BITS)
+
+#define SEEK_SET 0 /* seek relative to beginning of file */
+#define SEEK_CUR 1 /* seek relative to current file position */
+#define SEEK_END 2 /* seek relative to end of file */
+#define SEEK_DATA 3 /* seek to the next data */
+#define SEEK_HOLE 4 /* seek to the next hole */
+#define SEEK_MAX SEEK_HOLE
+
+#define RENAME_NOREPLACE (1 << 0) /* Don't overwrite target */
+#define RENAME_EXCHANGE (1 << 1) /* Exchange source and dest */
+#define RENAME_WHITEOUT (1 << 2) /* Whiteout source */
+
+struct file_clone_range {
+ __s64 src_fd;
+ __u64 src_offset;
+ __u64 src_length;
+ __u64 dest_offset;
+};
+
+struct fstrim_range {
+ __u64 start;
+ __u64 len;
+ __u64 minlen;
+};
+
+/* extent-same (dedupe) ioctls; these MUST match the btrfs ioctl definitions */
+#define FILE_DEDUPE_RANGE_SAME 0
+#define FILE_DEDUPE_RANGE_DIFFERS 1
+
+/* from struct btrfs_ioctl_file_extent_same_info */
+struct file_dedupe_range_info {
+ __s64 dest_fd; /* in - destination file */
+ __u64 dest_offset; /* in - start of extent in destination */
+ __u64 bytes_deduped; /* out - total # of bytes we were able
+ * to dedupe from this file. */
+ /* status of this dedupe operation:
+ * < 0 for error
+ * == FILE_DEDUPE_RANGE_SAME if dedupe succeeds
+ * == FILE_DEDUPE_RANGE_DIFFERS if data differs
+ */
+ __s32 status; /* out - see above description */
+ __u32 reserved; /* must be zero */
+};
+
+/* from struct btrfs_ioctl_file_extent_same_args */
+struct file_dedupe_range {
+ __u64 src_offset; /* in - start of extent in source */
+ __u64 src_length; /* in - length of extent */
+ __u16 dest_count; /* in - total elements in info array */
+ __u16 reserved1; /* must be zero */
+ __u32 reserved2; /* must be zero */
+ struct file_dedupe_range_info info[];
+};
+
+/* And dynamically-tunable limits and defaults: */
+struct files_stat_struct {
+ unsigned long nr_files; /* read only */
+ unsigned long nr_free_files; /* read only */
+ unsigned long max_files; /* tunable */
+};
+
+struct inodes_stat_t {
+ long nr_inodes;
+ long nr_unused;
+ long dummy[5]; /* padding for sysctl ABI compatibility */
+};
+
+
+#define NR_FILE 8192 /* this can well be larger on a larger system */
+
+/*
+ * Structure for FS_IOC_FSGETXATTR[A] and FS_IOC_FSSETXATTR.
+ */
+struct fsxattr {
+ __u32 fsx_xflags; /* xflags field value (get/set) */
+ __u32 fsx_extsize; /* extsize field value (get/set)*/
+ __u32 fsx_nextents; /* nextents field value (get) */
+ __u32 fsx_projid; /* project identifier (get/set) */
+ __u32 fsx_cowextsize; /* CoW extsize field value (get/set)*/
+ unsigned char fsx_pad[8];
+};
+
+/*
+ * Flags for the fsx_xflags field
+ */
+#define FS_XFLAG_REALTIME 0x00000001 /* data in realtime volume */
+#define FS_XFLAG_PREALLOC 0x00000002 /* preallocated file extents */
+#define FS_XFLAG_IMMUTABLE 0x00000008 /* file cannot be modified */
+#define FS_XFLAG_APPEND 0x00000010 /* all writes append */
+#define FS_XFLAG_SYNC 0x00000020 /* all writes synchronous */
+#define FS_XFLAG_NOATIME 0x00000040 /* do not update access time */
+#define FS_XFLAG_NODUMP 0x00000080 /* do not include in backups */
+#define FS_XFLAG_RTINHERIT 0x00000100 /* create with rt bit set */
+#define FS_XFLAG_PROJINHERIT 0x00000200 /* create with parents projid */
+#define FS_XFLAG_NOSYMLINKS 0x00000400 /* disallow symlink creation */
+#define FS_XFLAG_EXTSIZE 0x00000800 /* extent size allocator hint */
+#define FS_XFLAG_EXTSZINHERIT 0x00001000 /* inherit inode extent size */
+#define FS_XFLAG_NODEFRAG 0x00002000 /* do not defragment */
+#define FS_XFLAG_FILESTREAM 0x00004000 /* use filestream allocator */
+#define FS_XFLAG_DAX 0x00008000 /* use DAX for IO */
+#define FS_XFLAG_COWEXTSIZE 0x00010000 /* CoW extent size allocator hint */
+#define FS_XFLAG_HASATTR 0x80000000 /* no DIFLAG for this */
+
+/* the read-only stuff doesn't really belong here, but any other place is
+ probably as bad and I don't want to create yet another include file. */
+
+#define BLKROSET _IO(0x12,93) /* set device read-only (0 = read-write) */
+#define BLKROGET _IO(0x12,94) /* get read-only status (0 = read_write) */
+#define BLKRRPART _IO(0x12,95) /* re-read partition table */
+#define BLKGETSIZE _IO(0x12,96) /* return device size /512 (long *arg) */
+#define BLKFLSBUF _IO(0x12,97) /* flush buffer cache */
+#define BLKRASET _IO(0x12,98) /* set read ahead for block device */
+#define BLKRAGET _IO(0x12,99) /* get current read ahead setting */
+#define BLKFRASET _IO(0x12,100)/* set filesystem (mm/filemap.c) read-ahead */
+#define BLKFRAGET _IO(0x12,101)/* get filesystem (mm/filemap.c) read-ahead */
+#define BLKSECTSET _IO(0x12,102)/* set max sectors per request (ll_rw_blk.c) */
+#define BLKSECTGET _IO(0x12,103)/* get max sectors per request (ll_rw_blk.c) */
+#define BLKSSZGET _IO(0x12,104)/* get block device sector size */
+#if 0
+#define BLKPG _IO(0x12,105)/* See blkpg.h */
+
+/* Some people are morons. Do not use sizeof! */
+
+#define BLKELVGET _IOR(0x12,106,size_t)/* elevator get */
+#define BLKELVSET _IOW(0x12,107,size_t)/* elevator set */
+/* This was here just to show that the number is taken -
+ probably all these _IO(0x12,*) ioctls should be moved to blkpg.h. */
+#endif
+/* A jump here: 108-111 have been used for various private purposes. */
+#define BLKBSZGET _IOR(0x12,112,size_t)
+#define BLKBSZSET _IOW(0x12,113,size_t)
+#define BLKGETSIZE64 _IOR(0x12,114,size_t) /* return device size in bytes (u64 *arg) */
+#define BLKTRACESETUP _IOWR(0x12,115,struct blk_user_trace_setup)
+#define BLKTRACESTART _IO(0x12,116)
+#define BLKTRACESTOP _IO(0x12,117)
+#define BLKTRACETEARDOWN _IO(0x12,118)
+#define BLKDISCARD _IO(0x12,119)
+#define BLKIOMIN _IO(0x12,120)
+#define BLKIOOPT _IO(0x12,121)
+#define BLKALIGNOFF _IO(0x12,122)
+#define BLKPBSZGET _IO(0x12,123)
+#define BLKDISCARDZEROES _IO(0x12,124)
+#define BLKSECDISCARD _IO(0x12,125)
+#define BLKROTATIONAL _IO(0x12,126)
+#define BLKZEROOUT _IO(0x12,127)
+#define BLKGETDISKSEQ _IOR(0x12,128,__u64)
+/*
+ * A jump here: 130-136 are reserved for zoned block devices
+ * (see uapi/linux/blkzoned.h)
+ */
+
+#define BMAP_IOCTL 1 /* obsolete - kept for compatibility */
+#define FIBMAP _IO(0x00,1) /* bmap access */
+#define FIGETBSZ _IO(0x00,2) /* get the block size used for bmap */
+#define FIFREEZE _IOWR('X', 119, int) /* Freeze */
+#define FITHAW _IOWR('X', 120, int) /* Thaw */
+#define FITRIM _IOWR('X', 121, struct fstrim_range) /* Trim */
+#define FICLONE _IOW(0x94, 9, int)
+#define FICLONERANGE _IOW(0x94, 13, struct file_clone_range)
+#define FIDEDUPERANGE _IOWR(0x94, 54, struct file_dedupe_range)
+
+#define FSLABEL_MAX 256 /* Max chars for the interface; each fs may differ */
+
+#define FS_IOC_GETFLAGS _IOR('f', 1, long)
+#define FS_IOC_SETFLAGS _IOW('f', 2, long)
+#define FS_IOC_GETVERSION _IOR('v', 1, long)
+#define FS_IOC_SETVERSION _IOW('v', 2, long)
+#define FS_IOC_FIEMAP _IOWR('f', 11, struct fiemap)
+#define FS_IOC32_GETFLAGS _IOR('f', 1, int)
+#define FS_IOC32_SETFLAGS _IOW('f', 2, int)
+#define FS_IOC32_GETVERSION _IOR('v', 1, int)
+#define FS_IOC32_SETVERSION _IOW('v', 2, int)
+#define FS_IOC_FSGETXATTR _IOR('X', 31, struct fsxattr)
+#define FS_IOC_FSSETXATTR _IOW('X', 32, struct fsxattr)
+#define FS_IOC_GETFSLABEL _IOR(0x94, 49, char[FSLABEL_MAX])
+#define FS_IOC_SETFSLABEL _IOW(0x94, 50, char[FSLABEL_MAX])
+
+/*
+ * Inode flags (FS_IOC_GETFLAGS / FS_IOC_SETFLAGS)
+ *
+ * Note: for historical reasons, these flags were originally used and
+ * defined for use by ext2/ext3, and then other file systems started
+ * using these flags so they wouldn't need to write their own version
+ * of chattr/lsattr (which was shipped as part of e2fsprogs). You
+ * should think twice before trying to use these flags in new
+ * contexts, or trying to assign these flags, since they are used both
+ * as the UAPI and the on-disk encoding for ext2/3/4. Also, we are
+ * almost out of 32-bit flags. :-)
+ *
+ * We have recently hoisted FS_IOC_FSGETXATTR / FS_IOC_FSSETXATTR from
+ * XFS to the generic FS level interface. This uses a structure that
+ * has padding and hence has more room to grow, so it may be more
+ * appropriate for many new use cases.
+ *
+ * Please do not change these flags or interfaces before checking with
+ * linux-fsdevel@vger.kernel.org and linux-api@vger.kernel.org.
+ */
+#define FS_SECRM_FL 0x00000001 /* Secure deletion */
+#define FS_UNRM_FL 0x00000002 /* Undelete */
+#define FS_COMPR_FL 0x00000004 /* Compress file */
+#define FS_SYNC_FL 0x00000008 /* Synchronous updates */
+#define FS_IMMUTABLE_FL 0x00000010 /* Immutable file */
+#define FS_APPEND_FL 0x00000020 /* writes to file may only append */
+#define FS_NODUMP_FL 0x00000040 /* do not dump file */
+#define FS_NOATIME_FL 0x00000080 /* do not update atime */
+/* Reserved for compression usage... */
+#define FS_DIRTY_FL 0x00000100
+#define FS_COMPRBLK_FL 0x00000200 /* One or more compressed clusters */
+#define FS_NOCOMP_FL 0x00000400 /* Don't compress */
+/* End compression flags --- maybe not all used */
+#define FS_ENCRYPT_FL 0x00000800 /* Encrypted file */
+#define FS_BTREE_FL 0x00001000 /* btree format dir */
+#define FS_INDEX_FL 0x00001000 /* hash-indexed directory */
+#define FS_IMAGIC_FL 0x00002000 /* AFS directory */
+#define FS_JOURNAL_DATA_FL 0x00004000 /* Reserved for ext3 */
+#define FS_NOTAIL_FL 0x00008000 /* file tail should not be merged */
+#define FS_DIRSYNC_FL 0x00010000 /* dirsync behaviour (directories only) */
+#define FS_TOPDIR_FL 0x00020000 /* Top of directory hierarchies*/
+#define FS_HUGE_FILE_FL 0x00040000 /* Reserved for ext4 */
+#define FS_EXTENT_FL 0x00080000 /* Extents */
+#define FS_VERITY_FL 0x00100000 /* Verity protected inode */
+#define FS_EA_INODE_FL 0x00200000 /* Inode used for large EA */
+#define FS_EOFBLOCKS_FL 0x00400000 /* Reserved for ext4 */
+#define FS_NOCOW_FL 0x00800000 /* Do not cow file */
+#define FS_DAX_FL 0x02000000 /* Inode is DAX */
+#define FS_INLINE_DATA_FL 0x10000000 /* Reserved for ext4 */
+#define FS_PROJINHERIT_FL 0x20000000 /* Create with parents projid */
+#define FS_CASEFOLD_FL 0x40000000 /* Folder is case insensitive */
+#define FS_RESERVED_FL 0x80000000 /* reserved for ext2 lib */
+
+#define FS_FL_USER_VISIBLE 0x0003DFFF /* User visible flags */
+#define FS_FL_USER_MODIFIABLE 0x000380FF /* User modifiable flags */
+
+
+#define SYNC_FILE_RANGE_WAIT_BEFORE 1
+#define SYNC_FILE_RANGE_WRITE 2
+#define SYNC_FILE_RANGE_WAIT_AFTER 4
+#define SYNC_FILE_RANGE_WRITE_AND_WAIT (SYNC_FILE_RANGE_WRITE | \
+ SYNC_FILE_RANGE_WAIT_BEFORE | \
+ SYNC_FILE_RANGE_WAIT_AFTER)
+
+/*
+ * Flags for preadv2/pwritev2:
+ */
+
+typedef int __bitwise __kernel_rwf_t;
+
+/* high priority request, poll if possible */
+#define RWF_HIPRI ((__force __kernel_rwf_t)0x00000001)
+
+/* per-IO O_DSYNC */
+#define RWF_DSYNC ((__force __kernel_rwf_t)0x00000002)
+
+/* per-IO O_SYNC */
+#define RWF_SYNC ((__force __kernel_rwf_t)0x00000004)
+
+/* per-IO, return -EAGAIN if operation would block */
+#define RWF_NOWAIT ((__force __kernel_rwf_t)0x00000008)
+
+/* per-IO O_APPEND */
+#define RWF_APPEND ((__force __kernel_rwf_t)0x00000010)
+
+/* mask of flags supported by the kernel */
+#define RWF_SUPPORTED (RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\
+ RWF_APPEND)
+
+#endif /* _UAPI_LINUX_FS_H */
diff --git a/tools/include/uapi/linux/fscrypt.h b/tools/include/uapi/linux/fscrypt.h
new file mode 100644
index 0000000000..fd1fb0d538
--- /dev/null
+++ b/tools/include/uapi/linux/fscrypt.h
@@ -0,0 +1,196 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * fscrypt user API
+ *
+ * These ioctls can be used on filesystems that support fscrypt. See the
+ * "User API" section of Documentation/filesystems/fscrypt.rst.
+ */
+#ifndef _UAPI_LINUX_FSCRYPT_H
+#define _UAPI_LINUX_FSCRYPT_H
+
+#include <linux/ioctl.h>
+#include <linux/types.h>
+
+/* Encryption policy flags */
+#define FSCRYPT_POLICY_FLAGS_PAD_4 0x00
+#define FSCRYPT_POLICY_FLAGS_PAD_8 0x01
+#define FSCRYPT_POLICY_FLAGS_PAD_16 0x02
+#define FSCRYPT_POLICY_FLAGS_PAD_32 0x03
+#define FSCRYPT_POLICY_FLAGS_PAD_MASK 0x03
+#define FSCRYPT_POLICY_FLAG_DIRECT_KEY 0x04
+#define FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64 0x08
+#define FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32 0x10
+
+/* Encryption algorithms */
+#define FSCRYPT_MODE_AES_256_XTS 1
+#define FSCRYPT_MODE_AES_256_CTS 4
+#define FSCRYPT_MODE_AES_128_CBC 5
+#define FSCRYPT_MODE_AES_128_CTS 6
+#define FSCRYPT_MODE_SM4_XTS 7
+#define FSCRYPT_MODE_SM4_CTS 8
+#define FSCRYPT_MODE_ADIANTUM 9
+#define FSCRYPT_MODE_AES_256_HCTR2 10
+/* If adding a mode number > 10, update FSCRYPT_MODE_MAX in fscrypt_private.h */
+
+/*
+ * Legacy policy version; ad-hoc KDF and no key verification.
+ * For new encrypted directories, use fscrypt_policy_v2 instead.
+ *
+ * Careful: the .version field for this is actually 0, not 1.
+ */
+#define FSCRYPT_POLICY_V1 0
+#define FSCRYPT_KEY_DESCRIPTOR_SIZE 8
+struct fscrypt_policy_v1 {
+ __u8 version;
+ __u8 contents_encryption_mode;
+ __u8 filenames_encryption_mode;
+ __u8 flags;
+ __u8 master_key_descriptor[FSCRYPT_KEY_DESCRIPTOR_SIZE];
+};
+
+/*
+ * Process-subscribed "logon" key description prefix and payload format.
+ * Deprecated; prefer FS_IOC_ADD_ENCRYPTION_KEY instead.
+ */
+#define FSCRYPT_KEY_DESC_PREFIX "fscrypt:"
+#define FSCRYPT_KEY_DESC_PREFIX_SIZE 8
+#define FSCRYPT_MAX_KEY_SIZE 64
+struct fscrypt_key {
+ __u32 mode;
+ __u8 raw[FSCRYPT_MAX_KEY_SIZE];
+ __u32 size;
+};
+
+/*
+ * New policy version with HKDF and key verification (recommended).
+ */
+#define FSCRYPT_POLICY_V2 2
+#define FSCRYPT_KEY_IDENTIFIER_SIZE 16
+struct fscrypt_policy_v2 {
+ __u8 version;
+ __u8 contents_encryption_mode;
+ __u8 filenames_encryption_mode;
+ __u8 flags;
+ __u8 __reserved[4];
+ __u8 master_key_identifier[FSCRYPT_KEY_IDENTIFIER_SIZE];
+};
+
+/* Struct passed to FS_IOC_GET_ENCRYPTION_POLICY_EX */
+struct fscrypt_get_policy_ex_arg {
+ __u64 policy_size; /* input/output */
+ union {
+ __u8 version;
+ struct fscrypt_policy_v1 v1;
+ struct fscrypt_policy_v2 v2;
+ } policy; /* output */
+};
+
+/*
+ * v1 policy keys are specified by an arbitrary 8-byte key "descriptor",
+ * matching fscrypt_policy_v1::master_key_descriptor.
+ */
+#define FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR 1
+
+/*
+ * v2 policy keys are specified by a 16-byte key "identifier" which the kernel
+ * calculates as a cryptographic hash of the key itself,
+ * matching fscrypt_policy_v2::master_key_identifier.
+ */
+#define FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER 2
+
+/*
+ * Specifies a key, either for v1 or v2 policies. This doesn't contain the
+ * actual key itself; this is just the "name" of the key.
+ */
+struct fscrypt_key_specifier {
+ __u32 type; /* one of FSCRYPT_KEY_SPEC_TYPE_* */
+ __u32 __reserved;
+ union {
+ __u8 __reserved[32]; /* reserve some extra space */
+ __u8 descriptor[FSCRYPT_KEY_DESCRIPTOR_SIZE];
+ __u8 identifier[FSCRYPT_KEY_IDENTIFIER_SIZE];
+ } u;
+};
+
+/*
+ * Payload of Linux keyring key of type "fscrypt-provisioning", referenced by
+ * fscrypt_add_key_arg::key_id as an alternative to fscrypt_add_key_arg::raw.
+ */
+struct fscrypt_provisioning_key_payload {
+ __u32 type;
+ __u32 __reserved;
+ __u8 raw[];
+};
+
+/* Struct passed to FS_IOC_ADD_ENCRYPTION_KEY */
+struct fscrypt_add_key_arg {
+ struct fscrypt_key_specifier key_spec;
+ __u32 raw_size;
+ __u32 key_id;
+ __u32 __reserved[8];
+ __u8 raw[];
+};
+
+/* Struct passed to FS_IOC_REMOVE_ENCRYPTION_KEY */
+struct fscrypt_remove_key_arg {
+ struct fscrypt_key_specifier key_spec;
+#define FSCRYPT_KEY_REMOVAL_STATUS_FLAG_FILES_BUSY 0x00000001
+#define FSCRYPT_KEY_REMOVAL_STATUS_FLAG_OTHER_USERS 0x00000002
+ __u32 removal_status_flags; /* output */
+ __u32 __reserved[5];
+};
+
+/* Struct passed to FS_IOC_GET_ENCRYPTION_KEY_STATUS */
+struct fscrypt_get_key_status_arg {
+ /* input */
+ struct fscrypt_key_specifier key_spec;
+ __u32 __reserved[6];
+
+ /* output */
+#define FSCRYPT_KEY_STATUS_ABSENT 1
+#define FSCRYPT_KEY_STATUS_PRESENT 2
+#define FSCRYPT_KEY_STATUS_INCOMPLETELY_REMOVED 3
+ __u32 status;
+#define FSCRYPT_KEY_STATUS_FLAG_ADDED_BY_SELF 0x00000001
+ __u32 status_flags;
+ __u32 user_count;
+ __u32 __out_reserved[13];
+};
+
+#define FS_IOC_SET_ENCRYPTION_POLICY _IOR('f', 19, struct fscrypt_policy_v1)
+#define FS_IOC_GET_ENCRYPTION_PWSALT _IOW('f', 20, __u8[16])
+#define FS_IOC_GET_ENCRYPTION_POLICY _IOW('f', 21, struct fscrypt_policy_v1)
+#define FS_IOC_GET_ENCRYPTION_POLICY_EX _IOWR('f', 22, __u8[9]) /* size + version */
+#define FS_IOC_ADD_ENCRYPTION_KEY _IOWR('f', 23, struct fscrypt_add_key_arg)
+#define FS_IOC_REMOVE_ENCRYPTION_KEY _IOWR('f', 24, struct fscrypt_remove_key_arg)
+#define FS_IOC_REMOVE_ENCRYPTION_KEY_ALL_USERS _IOWR('f', 25, struct fscrypt_remove_key_arg)
+#define FS_IOC_GET_ENCRYPTION_KEY_STATUS _IOWR('f', 26, struct fscrypt_get_key_status_arg)
+#define FS_IOC_GET_ENCRYPTION_NONCE _IOR('f', 27, __u8[16])
+
+/**********************************************************************/
+
+/* old names; don't add anything new here! */
+#ifndef __KERNEL__
+#define fscrypt_policy fscrypt_policy_v1
+#define FS_KEY_DESCRIPTOR_SIZE FSCRYPT_KEY_DESCRIPTOR_SIZE
+#define FS_POLICY_FLAGS_PAD_4 FSCRYPT_POLICY_FLAGS_PAD_4
+#define FS_POLICY_FLAGS_PAD_8 FSCRYPT_POLICY_FLAGS_PAD_8
+#define FS_POLICY_FLAGS_PAD_16 FSCRYPT_POLICY_FLAGS_PAD_16
+#define FS_POLICY_FLAGS_PAD_32 FSCRYPT_POLICY_FLAGS_PAD_32
+#define FS_POLICY_FLAGS_PAD_MASK FSCRYPT_POLICY_FLAGS_PAD_MASK
+#define FS_POLICY_FLAG_DIRECT_KEY FSCRYPT_POLICY_FLAG_DIRECT_KEY
+#define FS_POLICY_FLAGS_VALID 0x07 /* contains old flags only */
+#define FS_ENCRYPTION_MODE_INVALID 0 /* never used */
+#define FS_ENCRYPTION_MODE_AES_256_XTS FSCRYPT_MODE_AES_256_XTS
+#define FS_ENCRYPTION_MODE_AES_256_GCM 2 /* never used */
+#define FS_ENCRYPTION_MODE_AES_256_CBC 3 /* never used */
+#define FS_ENCRYPTION_MODE_AES_256_CTS FSCRYPT_MODE_AES_256_CTS
+#define FS_ENCRYPTION_MODE_AES_128_CBC FSCRYPT_MODE_AES_128_CBC
+#define FS_ENCRYPTION_MODE_AES_128_CTS FSCRYPT_MODE_AES_128_CTS
+#define FS_ENCRYPTION_MODE_ADIANTUM FSCRYPT_MODE_ADIANTUM
+#define FS_KEY_DESC_PREFIX FSCRYPT_KEY_DESC_PREFIX
+#define FS_KEY_DESC_PREFIX_SIZE FSCRYPT_KEY_DESC_PREFIX_SIZE
+#define FS_MAX_KEY_SIZE FSCRYPT_MAX_KEY_SIZE
+#endif /* !__KERNEL__ */
+
+#endif /* _UAPI_LINUX_FSCRYPT_H */
diff --git a/tools/include/uapi/linux/hw_breakpoint.h b/tools/include/uapi/linux/hw_breakpoint.h
new file mode 100644
index 0000000000..1575d3ca6f
--- /dev/null
+++ b/tools/include/uapi/linux/hw_breakpoint.h
@@ -0,0 +1,25 @@
+/* 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,
+};
+
+#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 0000000000..39e659c83c
--- /dev/null
+++ b/tools/include/uapi/linux/if_link.h
@@ -0,0 +1,1284 @@
+/* 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;
+ __u32 tx_packets;
+ __u32 rx_bytes;
+ __u32 tx_bytes;
+ __u32 rx_errors;
+ __u32 tx_errors;
+ __u32 rx_dropped;
+ __u32 tx_dropped;
+ __u32 multicast;
+ __u32 collisions;
+ /* detailed rx_errors: */
+ __u32 rx_length_errors;
+ __u32 rx_over_errors;
+ __u32 rx_crc_errors;
+ __u32 rx_frame_errors;
+ __u32 rx_fifo_errors;
+ __u32 rx_missed_errors;
+
+ /* 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;
+};
+
+/**
+ * struct rtnl_link_stats64 - The main device statistics structure.
+ *
+ * @rx_packets: Number of good packets received by the interface.
+ * For hardware interfaces counts all good packets received from the device
+ * by the host, including packets which host had to drop at various stages
+ * of processing (even in the driver).
+ *
+ * @tx_packets: Number of packets successfully transmitted.
+ * For hardware interfaces counts packets which host was able to successfully
+ * hand over to the device, which does not necessarily mean that packets
+ * had been successfully transmitted out of the device, only that device
+ * acknowledged it copied them out of host memory.
+ *
+ * @rx_bytes: Number of good received bytes, corresponding to @rx_packets.
+ *
+ * For IEEE 802.3 devices should count the length of Ethernet Frames
+ * excluding the FCS.
+ *
+ * @tx_bytes: Number of good transmitted bytes, corresponding to @tx_packets.
+ *
+ * For IEEE 802.3 devices should count the length of Ethernet Frames
+ * excluding the FCS.
+ *
+ * @rx_errors: Total number of bad packets received on this network device.
+ * This counter must include events counted by @rx_length_errors,
+ * @rx_crc_errors, @rx_frame_errors and other errors not otherwise
+ * counted.
+ *
+ * @tx_errors: Total number of transmit problems.
+ * This counter must include events counter by @tx_aborted_errors,
+ * @tx_carrier_errors, @tx_fifo_errors, @tx_heartbeat_errors,
+ * @tx_window_errors and other errors not otherwise counted.
+ *
+ * @rx_dropped: Number of packets received but not processed,
+ * e.g. due to lack of resources or unsupported protocol.
+ * For hardware interfaces this counter may include packets discarded
+ * due to L2 address filtering but should not include packets dropped
+ * by the device due to buffer exhaustion which are counted separately in
+ * @rx_missed_errors (since procfs folds those two counters together).
+ *
+ * @tx_dropped: Number of packets dropped on their way to transmission,
+ * e.g. due to lack of resources.
+ *
+ * @multicast: Multicast packets received.
+ * For hardware interfaces this statistic is commonly calculated
+ * at the device level (unlike @rx_packets) and therefore may include
+ * packets which did not reach the host.
+ *
+ * For IEEE 802.3 devices this counter may be equivalent to:
+ *
+ * - 30.3.1.1.21 aMulticastFramesReceivedOK
+ *
+ * @collisions: Number of collisions during packet transmissions.
+ *
+ * @rx_length_errors: Number of packets dropped due to invalid length.
+ * Part of aggregate "frame" errors in `/proc/net/dev`.
+ *
+ * For IEEE 802.3 devices this counter should be equivalent to a sum
+ * of the following attributes:
+ *
+ * - 30.3.1.1.23 aInRangeLengthErrors
+ * - 30.3.1.1.24 aOutOfRangeLengthField
+ * - 30.3.1.1.25 aFrameTooLongErrors
+ *
+ * @rx_over_errors: Receiver FIFO overflow event counter.
+ *
+ * Historically the count of overflow events. Such events may be
+ * reported in the receive descriptors or via interrupts, and may
+ * not correspond one-to-one with dropped packets.
+ *
+ * The recommended interpretation for high speed interfaces is -
+ * number of packets dropped because they did not fit into buffers
+ * provided by the host, e.g. packets larger than MTU or next buffer
+ * in the ring was not available for a scatter transfer.
+ *
+ * Part of aggregate "frame" errors in `/proc/net/dev`.
+ *
+ * This statistics was historically used interchangeably with
+ * @rx_fifo_errors.
+ *
+ * This statistic corresponds to hardware events and is not commonly used
+ * on software devices.
+ *
+ * @rx_crc_errors: Number of packets received with a CRC error.
+ * Part of aggregate "frame" errors in `/proc/net/dev`.
+ *
+ * For IEEE 802.3 devices this counter must be equivalent to:
+ *
+ * - 30.3.1.1.6 aFrameCheckSequenceErrors
+ *
+ * @rx_frame_errors: Receiver frame alignment errors.
+ * Part of aggregate "frame" errors in `/proc/net/dev`.
+ *
+ * For IEEE 802.3 devices this counter should be equivalent to:
+ *
+ * - 30.3.1.1.7 aAlignmentErrors
+ *
+ * @rx_fifo_errors: Receiver FIFO error counter.
+ *
+ * Historically the count of overflow events. Those events may be
+ * reported in the receive descriptors or via interrupts, and may
+ * not correspond one-to-one with dropped packets.
+ *
+ * This statistics was used interchangeably with @rx_over_errors.
+ * Not recommended for use in drivers for high speed interfaces.
+ *
+ * This statistic is used on software devices, e.g. to count software
+ * packet queue overflow (can) or sequencing errors (GRE).
+ *
+ * @rx_missed_errors: Count of packets missed by the host.
+ * Folded into the "drop" counter in `/proc/net/dev`.
+ *
+ * Counts number of packets dropped by the device due to lack
+ * of buffer space. This usually indicates that the host interface
+ * is slower than the network interface, or host is not keeping up
+ * with the receive packet rate.
+ *
+ * This statistic corresponds to hardware events and is not used
+ * on software devices.
+ *
+ * @tx_aborted_errors:
+ * Part of aggregate "carrier" errors in `/proc/net/dev`.
+ * For IEEE 802.3 devices capable of half-duplex operation this counter
+ * must be equivalent to:
+ *
+ * - 30.3.1.1.11 aFramesAbortedDueToXSColls
+ *
+ * High speed interfaces may use this counter as a general device
+ * discard counter.
+ *
+ * @tx_carrier_errors: Number of frame transmission errors due to loss
+ * of carrier during transmission.
+ * Part of aggregate "carrier" errors in `/proc/net/dev`.
+ *
+ * For IEEE 802.3 devices this counter must be equivalent to:
+ *
+ * - 30.3.1.1.13 aCarrierSenseErrors
+ *
+ * @tx_fifo_errors: Number of frame transmission errors due to device
+ * FIFO underrun / underflow. This condition occurs when the device
+ * begins transmission of a frame but is unable to deliver the
+ * entire frame to the transmitter in time for transmission.
+ * Part of aggregate "carrier" errors in `/proc/net/dev`.
+ *
+ * @tx_heartbeat_errors: Number of Heartbeat / SQE Test errors for
+ * old half-duplex Ethernet.
+ * Part of aggregate "carrier" errors in `/proc/net/dev`.
+ *
+ * For IEEE 802.3 devices possibly equivalent to:
+ *
+ * - 30.3.2.1.4 aSQETestErrors
+ *
+ * @tx_window_errors: Number of frame transmission errors due
+ * to late collisions (for Ethernet - after the first 64B of transmission).
+ * Part of aggregate "carrier" errors in `/proc/net/dev`.
+ *
+ * For IEEE 802.3 devices this counter must be equivalent to:
+ *
+ * - 30.3.1.1.10 aLateCollisions
+ *
+ * @rx_compressed: Number of correctly received compressed packets.
+ * This counters is only meaningful for interfaces which support
+ * packet compression (e.g. CSLIP, PPP).
+ *
+ * @tx_compressed: Number of transmitted compressed packets.
+ * This counters is only meaningful for interfaces which support
+ * packet compression (e.g. CSLIP, PPP).
+ *
+ * @rx_nohandler: Number of packets received on the interface
+ * but dropped by the networking stack because the device is
+ * not designated to receive packets (e.g. backup link in a bond).
+ */
+struct rtnl_link_stats64 {
+ __u64 rx_packets;
+ __u64 tx_packets;
+ __u64 rx_bytes;
+ __u64 tx_bytes;
+ __u64 rx_errors;
+ __u64 tx_errors;
+ __u64 rx_dropped;
+ __u64 tx_dropped;
+ __u64 multicast;
+ __u64 collisions;
+
+ /* detailed rx_errors: */
+ __u64 rx_length_errors;
+ __u64 rx_over_errors;
+ __u64 rx_crc_errors;
+ __u64 rx_frame_errors;
+ __u64 rx_fifo_errors;
+ __u64 rx_missed_errors;
+
+ /* 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;
+};
+
+/* 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_TARGET_NETNSID = IFLA_IF_NETNSID, /* new alias */
+ IFLA_CARRIER_UP_COUNT,
+ IFLA_CARRIER_DOWN_COUNT,
+ IFLA_NEW_IFINDEX,
+ IFLA_MIN_MTU,
+ IFLA_MAX_MTU,
+ IFLA_PROP_LIST,
+ IFLA_ALT_IFNAME, /* Alternative ifname */
+ IFLA_PERM_ADDRESS,
+ IFLA_PROTO_DOWN_REASON,
+
+ /* device (sysfs) name as parent, used instead
+ * of IFLA_LINK where there's no parent netdev
+ */
+ IFLA_PARENT_DEV_NAME,
+ IFLA_PARENT_DEV_BUS_NAME,
+ IFLA_GRO_MAX_SIZE,
+ IFLA_TSO_MAX_SIZE,
+ IFLA_TSO_MAX_SEGS,
+
+ __IFLA_MAX
+};
+
+
+#define IFLA_MAX (__IFLA_MAX - 1)
+
+enum {
+ IFLA_PROTO_DOWN_REASON_UNSPEC,
+ IFLA_PROTO_DOWN_REASON_MASK, /* u32, mask for reason bits */
+ IFLA_PROTO_DOWN_REASON_VALUE, /* u32, reason bit value */
+
+ __IFLA_PROTO_DOWN_REASON_CNT,
+ IFLA_PROTO_DOWN_REASON_MAX = __IFLA_PROTO_DOWN_REASON_CNT - 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_RA_MTU, /* mtu carried in the RA message */
+ __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_VLAN_STATS_PER_PORT,
+ IFLA_BR_MULTI_BOOLOPT,
+ IFLA_BR_MCAST_QUERIER_STATE,
+ __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_MRP_RING_OPEN,
+ IFLA_BRPORT_MRP_IN_OPEN,
+ IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT,
+ IFLA_BRPORT_MCAST_EHT_HOSTS_CNT,
+ __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_BC_QUEUE_LEN,
+ IFLA_MACVLAN_BC_QUEUE_LEN_USED,
+ IFLA_MACVLAN_BC_CUTOFF,
+ __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
+#define MACVLAN_FLAG_NODST 2 /* skip dst macvlan if matching src macvlan */
+
+/* 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_OFFLOAD,
+ __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_COLLECT_METADATA,
+ __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,
+};
+
+enum macsec_offload {
+ MACSEC_OFFLOAD_OFF = 0,
+ MACSEC_OFFLOAD_PHY = 1,
+ MACSEC_OFFLOAD_MAC = 2,
+ __MACSEC_OFFLOAD_END,
+ MACSEC_OFFLOAD_MAX = __MACSEC_OFFLOAD_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_DF,
+ __IFLA_VXLAN_MAX
+};
+#define IFLA_VXLAN_MAX (__IFLA_VXLAN_MAX - 1)
+
+struct ifla_vxlan_port_range {
+ __be16 low;
+ __be16 high;
+};
+
+enum ifla_vxlan_df {
+ VXLAN_DF_UNSET = 0,
+ VXLAN_DF_SET,
+ VXLAN_DF_INHERIT,
+ __VXLAN_DF_END,
+ VXLAN_DF_MAX = __VXLAN_DF_END - 1,
+};
+
+/* 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_TTL_INHERIT,
+ IFLA_GENEVE_DF,
+ __IFLA_GENEVE_MAX
+};
+#define IFLA_GENEVE_MAX (__IFLA_GENEVE_MAX - 1)
+
+enum ifla_geneve_df {
+ GENEVE_DF_UNSET = 0,
+ GENEVE_DF_SET,
+ GENEVE_DF_INHERIT,
+ __GENEVE_DF_END,
+ GENEVE_DF_MAX = __GENEVE_DF_END - 1,
+};
+
+/* Bareudp section */
+enum {
+ IFLA_BAREUDP_UNSPEC,
+ IFLA_BAREUDP_PORT,
+ IFLA_BAREUDP_ETHERTYPE,
+ IFLA_BAREUDP_SRCPORT_MIN,
+ IFLA_BAREUDP_MULTIPROTO_MODE,
+ __IFLA_BAREUDP_MAX
+};
+
+#define IFLA_BAREUDP_MAX (__IFLA_BAREUDP_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_PEER_NOTIF_DELAY,
+ IFLA_BOND_AD_LACP_ACTIVE,
+ IFLA_BOND_MISSED_MAX,
+ IFLA_BOND_NS_IP6_TARGET,
+ __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_PRIO,
+ __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_BROADCAST, /* VF broadcast */
+ __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_broadcast {
+ __u8 broadcast[32];
+};
+
+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/PRP section, both uses same interface */
+
+/* Different redundancy protocols for hsr device */
+enum {
+ HSR_PROTOCOL_HSR,
+ HSR_PROTOCOL_PRP,
+ HSR_PROTOCOL_MAX,
+};
+
+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_PROTOCOL, /* Indicate different protocol than
+ * HSR. For example PRP.
+ */
+ __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_BOND,
+ __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_REPLACE (1U << 4)
+#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 | XDP_FLAGS_REPLACE)
+
+/* 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_EXPECTED_FD,
+ __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)
+#define RMNET_FLAGS_INGRESS_MAP_CKSUMV5 (1U << 4)
+#define RMNET_FLAGS_EGRESS_MAP_CKSUMV5 (1U << 5)
+
+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;
+};
+
+/* MCTP section */
+
+enum {
+ IFLA_MCTP_UNSPEC,
+ IFLA_MCTP_NET,
+ __IFLA_MCTP_MAX,
+};
+
+#define IFLA_MCTP_MAX (__IFLA_MCTP_MAX - 1)
+
+#endif /* _UAPI_LINUX_IF_LINK_H */
diff --git a/tools/include/uapi/linux/if_tun.h b/tools/include/uapi/linux/if_tun.h
new file mode 100644
index 0000000000..2ec07de1d7
--- /dev/null
+++ b/tools/include/uapi/linux/if_tun.h
@@ -0,0 +1,114 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ * Universal TUN/TAP device driver.
+ * Copyright (C) 1999-2000 Maxim Krasnyansky <max_mk@yahoo.com>
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _UAPI__IF_TUN_H
+#define _UAPI__IF_TUN_H
+
+#include <linux/types.h>
+#include <linux/if_ether.h>
+#include <linux/filter.h>
+
+/* Read queue size */
+#define TUN_READQ_SIZE 500
+/* TUN device type flags: deprecated. Use IFF_TUN/IFF_TAP instead. */
+#define TUN_TUN_DEV IFF_TUN
+#define TUN_TAP_DEV IFF_TAP
+#define TUN_TYPE_MASK 0x000f
+
+/* Ioctl defines */
+#define TUNSETNOCSUM _IOW('T', 200, int)
+#define TUNSETDEBUG _IOW('T', 201, int)
+#define TUNSETIFF _IOW('T', 202, int)
+#define TUNSETPERSIST _IOW('T', 203, int)
+#define TUNSETOWNER _IOW('T', 204, int)
+#define TUNSETLINK _IOW('T', 205, int)
+#define TUNSETGROUP _IOW('T', 206, int)
+#define TUNGETFEATURES _IOR('T', 207, unsigned int)
+#define TUNSETOFFLOAD _IOW('T', 208, unsigned int)
+#define TUNSETTXFILTER _IOW('T', 209, unsigned int)
+#define TUNGETIFF _IOR('T', 210, unsigned int)
+#define TUNGETSNDBUF _IOR('T', 211, int)
+#define TUNSETSNDBUF _IOW('T', 212, int)
+#define TUNATTACHFILTER _IOW('T', 213, struct sock_fprog)
+#define TUNDETACHFILTER _IOW('T', 214, struct sock_fprog)
+#define TUNGETVNETHDRSZ _IOR('T', 215, int)
+#define TUNSETVNETHDRSZ _IOW('T', 216, int)
+#define TUNSETQUEUE _IOW('T', 217, int)
+#define TUNSETIFINDEX _IOW('T', 218, unsigned int)
+#define TUNGETFILTER _IOR('T', 219, struct sock_fprog)
+#define TUNSETVNETLE _IOW('T', 220, int)
+#define TUNGETVNETLE _IOR('T', 221, int)
+/* The TUNSETVNETBE and TUNGETVNETBE ioctls are for cross-endian support on
+ * little-endian hosts. Not all kernel configurations support them, but all
+ * configurations that support SET also support GET.
+ */
+#define TUNSETVNETBE _IOW('T', 222, int)
+#define TUNGETVNETBE _IOR('T', 223, int)
+#define TUNSETSTEERINGEBPF _IOR('T', 224, int)
+#define TUNSETFILTEREBPF _IOR('T', 225, int)
+#define TUNSETCARRIER _IOW('T', 226, int)
+#define TUNGETDEVNETNS _IO('T', 227)
+
+/* TUNSETIFF ifr flags */
+#define IFF_TUN 0x0001
+#define IFF_TAP 0x0002
+#define IFF_NAPI 0x0010
+#define IFF_NAPI_FRAGS 0x0020
+#define IFF_NO_PI 0x1000
+/* This flag has no real effect */
+#define IFF_ONE_QUEUE 0x2000
+#define IFF_VNET_HDR 0x4000
+#define IFF_TUN_EXCL 0x8000
+#define IFF_MULTI_QUEUE 0x0100
+#define IFF_ATTACH_QUEUE 0x0200
+#define IFF_DETACH_QUEUE 0x0400
+/* read-only flag */
+#define IFF_PERSIST 0x0800
+#define IFF_NOFILTER 0x1000
+
+/* Socket options */
+#define TUN_TX_TIMESTAMP 1
+
+/* Features for GSO (TUNSETOFFLOAD). */
+#define TUN_F_CSUM 0x01 /* You can hand me unchecksummed packets. */
+#define TUN_F_TSO4 0x02 /* I can handle TSO for IPv4 packets */
+#define TUN_F_TSO6 0x04 /* I can handle TSO for IPv6 packets */
+#define TUN_F_TSO_ECN 0x08 /* I can handle TSO with ECN bits. */
+#define TUN_F_UFO 0x10 /* I can handle UFO packets */
+
+/* Protocol info prepended to the packets (when IFF_NO_PI is not set) */
+#define TUN_PKT_STRIP 0x0001
+struct tun_pi {
+ __u16 flags;
+ __be16 proto;
+};
+
+/*
+ * Filter spec (used for SETXXFILTER ioctls)
+ * This stuff is applicable only to the TAP (Ethernet) devices.
+ * If the count is zero the filter is disabled and the driver accepts
+ * all packets (promisc mode).
+ * If the filter is enabled in order to accept broadcast packets
+ * broadcast addr must be explicitly included in the addr list.
+ */
+#define TUN_FLT_ALLMULTI 0x0001 /* Accept all multicast packets */
+struct tun_filter {
+ __u16 flags; /* TUN_FLT_ flags see above */
+ __u16 count; /* Number of addresses */
+ __u8 addr[][ETH_ALEN];
+};
+
+#endif /* _UAPI__IF_TUN_H */
diff --git a/tools/include/uapi/linux/if_xdp.h b/tools/include/uapi/linux/if_xdp.h
new file mode 100644
index 0000000000..73a47da885
--- /dev/null
+++ b/tools/include/uapi/linux/if_xdp.h
@@ -0,0 +1,120 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * if_xdp: XDP socket user-space interface
+ * Copyright(c) 2018 Intel Corporation.
+ *
+ * Author(s): Björn Töpel <bjorn.topel@intel.com>
+ * Magnus Karlsson <magnus.karlsson@intel.com>
+ */
+
+#ifndef _LINUX_IF_XDP_H
+#define _LINUX_IF_XDP_H
+
+#include <linux/types.h>
+
+/* Options for the sxdp_flags field */
+#define XDP_SHARED_UMEM (1 << 0)
+#define XDP_COPY (1 << 1) /* Force copy-mode */
+#define XDP_ZEROCOPY (1 << 2) /* Force zero-copy mode */
+/* If this option is set, the driver might go sleep and in that case
+ * the XDP_RING_NEED_WAKEUP flag in the fill and/or Tx rings will be
+ * set. If it is set, the application need to explicitly wake up the
+ * driver with a poll() (Rx and Tx) or sendto() (Tx only). If you are
+ * running the driver and the application on the same core, you should
+ * use this option so that the kernel will yield to the user space
+ * application.
+ */
+#define XDP_USE_NEED_WAKEUP (1 << 3)
+/* By setting this option, userspace application indicates that it can
+ * handle multiple descriptors per packet thus enabling xsk core to split
+ * multi-buffer XDP frames into multiple Rx descriptors. Without this set
+ * such frames will be dropped by xsk.
+ */
+#define XDP_USE_SG (1 << 4)
+
+/* Flags for xsk_umem_config flags */
+#define XDP_UMEM_UNALIGNED_CHUNK_FLAG (1 << 0)
+
+struct sockaddr_xdp {
+ __u16 sxdp_family;
+ __u16 sxdp_flags;
+ __u32 sxdp_ifindex;
+ __u32 sxdp_queue_id;
+ __u32 sxdp_shared_umem_fd;
+};
+
+/* XDP_RING flags */
+#define XDP_RING_NEED_WAKEUP (1 << 0)
+
+struct xdp_ring_offset {
+ __u64 producer;
+ __u64 consumer;
+ __u64 desc;
+ __u64 flags;
+};
+
+struct xdp_mmap_offsets {
+ struct xdp_ring_offset rx;
+ struct xdp_ring_offset tx;
+ struct xdp_ring_offset fr; /* Fill */
+ struct xdp_ring_offset cr; /* Completion */
+};
+
+/* XDP socket options */
+#define XDP_MMAP_OFFSETS 1
+#define XDP_RX_RING 2
+#define XDP_TX_RING 3
+#define XDP_UMEM_REG 4
+#define XDP_UMEM_FILL_RING 5
+#define XDP_UMEM_COMPLETION_RING 6
+#define XDP_STATISTICS 7
+#define XDP_OPTIONS 8
+
+struct xdp_umem_reg {
+ __u64 addr; /* Start of packet data area */
+ __u64 len; /* Length of packet data area */
+ __u32 chunk_size;
+ __u32 headroom;
+ __u32 flags;
+};
+
+struct xdp_statistics {
+ __u64 rx_dropped; /* Dropped for other reasons */
+ __u64 rx_invalid_descs; /* Dropped due to invalid descriptor */
+ __u64 tx_invalid_descs; /* Dropped due to invalid descriptor */
+ __u64 rx_ring_full; /* Dropped due to rx ring being full */
+ __u64 rx_fill_ring_empty_descs; /* Failed to retrieve item from fill ring */
+ __u64 tx_ring_empty_descs; /* Failed to retrieve item from tx ring */
+};
+
+struct xdp_options {
+ __u32 flags;
+};
+
+/* Flags for the flags field of struct xdp_options */
+#define XDP_OPTIONS_ZEROCOPY (1 << 0)
+
+/* Pgoff for mmaping the rings */
+#define XDP_PGOFF_RX_RING 0
+#define XDP_PGOFF_TX_RING 0x80000000
+#define XDP_UMEM_PGOFF_FILL_RING 0x100000000ULL
+#define XDP_UMEM_PGOFF_COMPLETION_RING 0x180000000ULL
+
+/* Masks for unaligned chunks mode */
+#define XSK_UNALIGNED_BUF_OFFSET_SHIFT 48
+#define XSK_UNALIGNED_BUF_ADDR_MASK \
+ ((1ULL << XSK_UNALIGNED_BUF_OFFSET_SHIFT) - 1)
+
+/* Rx/Tx descriptor */
+struct xdp_desc {
+ __u64 addr;
+ __u32 len;
+ __u32 options;
+};
+
+/* Flag indicating packet constitutes of multiple buffers*/
+#define XDP_PKT_CONTD (1 << 0)
+
+/* UMEM descriptor is __u64 */
+
+#endif /* _LINUX_IF_XDP_H */
diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h
new file mode 100644
index 0000000000..e682ab628d
--- /dev/null
+++ b/tools/include/uapi/linux/in.h
@@ -0,0 +1,333 @@
+/* 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/stddef.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_L2TP = 115, /* Layer 2 Tunnelling Protocol */
+#define IPPROTO_L2TP IPPROTO_L2TP
+ 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_ETHERNET = 143, /* Ethernet-within-IPv6 Encapsulation */
+#define IPPROTO_ETHERNET IPPROTO_ETHERNET
+ IPPROTO_RAW = 255, /* Raw IP packets */
+#define IPPROTO_RAW IPPROTO_RAW
+ IPPROTO_MPTCP = 262, /* Multipath TCP connection */
+#define IPPROTO_MPTCP IPPROTO_MPTCP
+ 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
+#define IP_RECVERR_RFC4884 26
+
+/* 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 allows 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 IP_LOCAL_PORT_RANGE 51
+#define IP_PROTOCOL 52
+
+#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;
+ union {
+ __be32 imsf_slist[1];
+ __DECLARE_FLEX_ARRAY(__be32, imsf_slist_flex);
+ };
+};
+
+#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 {
+ union {
+ struct {
+ __u32 gf_interface_aux; /* interface index */
+ struct __kernel_sockaddr_storage gf_group_aux; /* multicast address */
+ __u32 gf_fmode_aux; /* filter mode */
+ __u32 gf_numsrc_aux; /* number of sources */
+ struct __kernel_sockaddr_storage gf_slist[1]; /* interface index */
+ };
+ struct {
+ __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_flex[]; /* 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 0xe0000000
+
+#define IN_BADCLASS(a) (((long int) (a) ) == (long int)0xffffffff)
+#define IN_EXPERIMENTAL(a) IN_BADCLASS((a))
+
+#define IN_CLASSE(a) ((((long int) (a)) & 0xf0000000) == 0xf0000000)
+#define IN_CLASSE_NET 0xffffffff
+#define IN_CLASSE_NSHIFT 0
+
+/* 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)
+
+/* Dummy address for src of ICMP replies if no real address is set (RFC7600). */
+#define INADDR_DUMMY ((unsigned long int) 0xc0000008)
+
+/* 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_ALLSNOOPERS_GROUP 0xe000006aU /* 224.0.0.106 */
+#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 0000000000..ef13050109
--- /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 0000000000..f089ab2909
--- /dev/null
+++ b/tools/include/uapi/linux/kvm.h
@@ -0,0 +1,2252 @@
+/* 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/const.h>
+#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_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_userspace_memory_region::flags are visible for
+ * userspace, other bits are reserved for kvm internal use which are defined
+ * in include/linux/kvm_host.h.
+ */
+#define KVM_MEM_LOG_DIRTY_PAGES (1UL << 0)
+#define KVM_MEM_READONLY (1UL << 1)
+
+/* 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/virt/kvm/api.rst
+ */
+ 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
+#define KVM_EXIT_HYPERV_SYNDBG 3
+ __u32 type;
+ __u32 pad1;
+ union {
+ struct {
+ __u32 msr;
+ __u32 pad2;
+ __u64 control;
+ __u64 evt_page;
+ __u64 msg_page;
+ } synic;
+ struct {
+ __u64 input;
+ __u64 result;
+ __u64 params[2];
+ } hcall;
+ struct {
+ __u32 msr;
+ __u32 pad2;
+ __u64 control;
+ __u64 status;
+ __u64 send_page;
+ __u64 recv_page;
+ __u64 pending_page;
+ } syndbg;
+ } u;
+};
+
+struct kvm_xen_exit {
+#define KVM_EXIT_XEN_HCALL 1
+ __u32 type;
+ union {
+ struct {
+ __u32 longmode;
+ __u32 cpl;
+ __u64 input;
+ __u64 result;
+ __u64 params[6];
+ } 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
+#define KVM_EXIT_ARM_NISV 28
+#define KVM_EXIT_X86_RDMSR 29
+#define KVM_EXIT_X86_WRMSR 30
+#define KVM_EXIT_DIRTY_RING_FULL 31
+#define KVM_EXIT_AP_RESET_HOLD 32
+#define KVM_EXIT_X86_BUS_LOCK 33
+#define KVM_EXIT_XEN 34
+#define KVM_EXIT_RISCV_SBI 35
+#define KVM_EXIT_RISCV_CSR 36
+#define KVM_EXIT_NOTIFY 37
+
+/* 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
+/* Encounter unexpected vm-exit reason */
+#define KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON 4
+
+/* Flags that describe what fields in emulation_failure hold valid data. */
+#define KVM_INTERNAL_ERROR_EMULATION_FLAG_INSTRUCTION_BYTES (1ULL << 0)
+
+/* 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;
+ __u32 cpu;
+ } 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;
+
+ union {
+#ifndef __KERNEL__
+ __u32 longmode;
+#endif
+ __u64 flags;
+ };
+ } 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_INTERNAL_ERROR_EMULATION
+ *
+ * "struct emulation_failure" is an overlay of "struct internal"
+ * that is used for the KVM_INTERNAL_ERROR_EMULATION sub-type of
+ * KVM_EXIT_INTERNAL_ERROR. Note, unlike other internal error
+ * sub-types, this struct is ABI! It also needs to be backwards
+ * compatible with "struct internal". Take special care that
+ * "ndata" is correct, that new fields are enumerated in "flags",
+ * and that each flag enumerates fields that are 64-bit aligned
+ * and sized (so that ndata+internal.data[] is valid/accurate).
+ *
+ * Space beyond the defined fields may be used to store arbitrary
+ * debug information relating to the emulation failure. It is
+ * accounted for in "ndata" but the format is unspecified and is
+ * not represented in "flags". Any such information is *not* ABI!
+ */
+ struct {
+ __u32 suberror;
+ __u32 ndata;
+ __u64 flags;
+ union {
+ struct {
+ __u8 insn_size;
+ __u8 insn_bytes[15];
+ };
+ };
+ /* Arbitrary debug data may follow. */
+ } emulation_failure;
+ /* 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
+#define KVM_SYSTEM_EVENT_WAKEUP 4
+#define KVM_SYSTEM_EVENT_SUSPEND 5
+#define KVM_SYSTEM_EVENT_SEV_TERM 6
+ __u32 type;
+ __u32 ndata;
+ union {
+#ifndef __KERNEL__
+ __u64 flags;
+#endif
+ __u64 data[16];
+ };
+ } 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;
+ /* KVM_EXIT_ARM_NISV */
+ struct {
+ __u64 esr_iss;
+ __u64 fault_ipa;
+ } arm_nisv;
+ /* KVM_EXIT_X86_RDMSR / KVM_EXIT_X86_WRMSR */
+ struct {
+ __u8 error; /* user -> kernel */
+ __u8 pad[7];
+#define KVM_MSR_EXIT_REASON_INVAL (1 << 0)
+#define KVM_MSR_EXIT_REASON_UNKNOWN (1 << 1)
+#define KVM_MSR_EXIT_REASON_FILTER (1 << 2)
+#define KVM_MSR_EXIT_REASON_VALID_MASK (KVM_MSR_EXIT_REASON_INVAL | \
+ KVM_MSR_EXIT_REASON_UNKNOWN | \
+ KVM_MSR_EXIT_REASON_FILTER)
+ __u32 reason; /* kernel -> user */
+ __u32 index; /* kernel -> user */
+ __u64 data; /* kernel <-> user */
+ } msr;
+ /* KVM_EXIT_XEN */
+ struct kvm_xen_exit xen;
+ /* KVM_EXIT_RISCV_SBI */
+ struct {
+ unsigned long extension_id;
+ unsigned long function_id;
+ unsigned long args[6];
+ unsigned long ret[2];
+ } riscv_sbi;
+ /* KVM_EXIT_RISCV_CSR */
+ struct {
+ unsigned long csr_num;
+ unsigned long new_value;
+ unsigned long write_mask;
+ unsigned long ret_value;
+ } riscv_csr;
+ /* KVM_EXIT_NOTIFY */
+ struct {
+#define KVM_NOTIFY_CONTEXT_INVALID (1 << 0)
+ __u32 flags;
+ } notify;
+ /* 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;
+ union {
+ __u32 pad;
+ __u32 pio;
+ };
+};
+
+struct kvm_coalesced_mmio {
+ __u64 phys_addr;
+ __u32 len;
+ union {
+ __u32 pad;
+ __u32 pio;
+ };
+ __u8 data[8];
+};
+
+struct kvm_coalesced_mmio_ring {
+ __u32 first, last;
+ struct kvm_coalesced_mmio coalesced_mmio[];
+};
+
+#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 */
+ union {
+ struct {
+ __u8 ar; /* the access register number */
+ __u8 key; /* access key, ignored if flag unset */
+ __u8 pad1[6]; /* ignored */
+ __u64 old_addr; /* ignored if cmpxchg flag unset */
+ };
+ __u32 sida_offset; /* offset into the sida */
+ __u8 reserved[32]; /* ignored */
+ };
+};
+/* types for kvm_s390_mem_op->op */
+#define KVM_S390_MEMOP_LOGICAL_READ 0
+#define KVM_S390_MEMOP_LOGICAL_WRITE 1
+#define KVM_S390_MEMOP_SIDA_READ 2
+#define KVM_S390_MEMOP_SIDA_WRITE 3
+#define KVM_S390_MEMOP_ABSOLUTE_READ 4
+#define KVM_S390_MEMOP_ABSOLUTE_WRITE 5
+#define KVM_S390_MEMOP_ABSOLUTE_CMPXCHG 6
+
+/* 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)
+#define KVM_S390_MEMOP_F_SKEY_PROTECTION (1ULL << 2)
+
+/* flags specifying extension support via KVM_CAP_S390_MEM_OP_EXTENSION */
+#define KVM_S390_MEMOP_EXTENSION_CAP_BASE (1 << 0)
+#define KVM_S390_MEMOP_EXTENSION_CAP_CMPXCHG (1 << 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_CLEAR_DIRTY_LOG */
+struct kvm_clear_dirty_log {
+ __u32 slot;
+ __u32 num_pages;
+ __u64 first_page;
+ union {
+ void __user *dirty_bitmap; /* one bit per page */
+ __u64 padding2;
+ };
+};
+
+/* for KVM_SET_SIGNAL_MASK */
+struct kvm_signal_mask {
+ __u32 len;
+ __u8 sigset[];
+};
+
+/* 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
+#define KVM_MP_STATE_AP_RESET_HOLD 9
+#define KVM_MP_STATE_SUSPENDED 10
+
+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_EXITS_CSTATE (1 << 3)
+#define KVM_X86_DISABLE_VALID_EXITS (KVM_X86_DISABLE_EXITS_MWAIT | \
+ KVM_X86_DISABLE_EXITS_HLT | \
+ KVM_X86_DISABLE_EXITS_PAUSE | \
+ KVM_X86_DISABLE_EXITS_CSTATE)
+
+/* 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
+#define KVM_PPC_NO_HASH 0x00000004
+
+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 indicates auto, 1 forces VZ ASE, 2 forces trap & emulate */
+#define KVM_VM_MIPS_AUTO 0
+#define KVM_VM_MIPS_VZ 1
+#define KVM_VM_MIPS_TE 2
+
+#define KVM_S390_SIE_PAGE_OFFSET 1
+
+/*
+ * On arm64, machine type can be used to request the physical
+ * address size for the VM. Bits[7-0] are reserved for the guest
+ * PA size shift (i.e, log2(PA_Size)). For backward compatibility,
+ * value 0 implies the default IPA size, 40bits.
+ */
+#define KVM_VM_TYPE_ARM_IPA_SIZE_MASK 0xffULL
+#define KVM_VM_TYPE_ARM_IPA_SIZE(x) \
+ ((x) & KVM_VM_TYPE_ARM_IPA_SIZE_MASK)
+/*
+ * 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
+#define KVM_CAP_PPC_NESTED_HV 160
+#define KVM_CAP_HYPERV_SEND_IPI 161
+#define KVM_CAP_COALESCED_PIO 162
+#define KVM_CAP_HYPERV_ENLIGHTENED_VMCS 163
+#define KVM_CAP_EXCEPTION_PAYLOAD 164
+#define KVM_CAP_ARM_VM_IPA_SIZE 165
+#define KVM_CAP_MANUAL_DIRTY_LOG_PROTECT 166 /* Obsolete */
+#define KVM_CAP_HYPERV_CPUID 167
+#define KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 168
+#define KVM_CAP_PPC_IRQ_XIVE 169
+#define KVM_CAP_ARM_SVE 170
+#define KVM_CAP_ARM_PTRAUTH_ADDRESS 171
+#define KVM_CAP_ARM_PTRAUTH_GENERIC 172
+#define KVM_CAP_PMU_EVENT_FILTER 173
+#define KVM_CAP_ARM_IRQ_LINE_LAYOUT_2 174
+#define KVM_CAP_HYPERV_DIRECT_TLBFLUSH 175
+#define KVM_CAP_PPC_GUEST_DEBUG_SSTEP 176
+#define KVM_CAP_ARM_NISV_TO_USER 177
+#define KVM_CAP_ARM_INJECT_EXT_DABT 178
+#define KVM_CAP_S390_VCPU_RESETS 179
+#define KVM_CAP_S390_PROTECTED 180
+#define KVM_CAP_PPC_SECURE_GUEST 181
+#define KVM_CAP_HALT_POLL 182
+#define KVM_CAP_ASYNC_PF_INT 183
+#define KVM_CAP_LAST_CPU 184
+#define KVM_CAP_SMALLER_MAXPHYADDR 185
+#define KVM_CAP_S390_DIAG318 186
+#define KVM_CAP_STEAL_TIME 187
+#define KVM_CAP_X86_USER_SPACE_MSR 188
+#define KVM_CAP_X86_MSR_FILTER 189
+#define KVM_CAP_ENFORCE_PV_FEATURE_CPUID 190
+#define KVM_CAP_SYS_HYPERV_CPUID 191
+#define KVM_CAP_DIRTY_LOG_RING 192
+#define KVM_CAP_X86_BUS_LOCK_EXIT 193
+#define KVM_CAP_PPC_DAWR1 194
+#define KVM_CAP_SET_GUEST_DEBUG2 195
+#define KVM_CAP_SGX_ATTRIBUTE 196
+#define KVM_CAP_VM_COPY_ENC_CONTEXT_FROM 197
+#define KVM_CAP_PTP_KVM 198
+#define KVM_CAP_HYPERV_ENFORCE_CPUID 199
+#define KVM_CAP_SREGS2 200
+#define KVM_CAP_EXIT_HYPERCALL 201
+#define KVM_CAP_PPC_RPT_INVALIDATE 202
+#define KVM_CAP_BINARY_STATS_FD 203
+#define KVM_CAP_EXIT_ON_EMULATION_FAILURE 204
+#define KVM_CAP_ARM_MTE 205
+#define KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM 206
+#define KVM_CAP_VM_GPA_BITS 207
+#define KVM_CAP_XSAVE2 208
+#define KVM_CAP_SYS_ATTRIBUTES 209
+#define KVM_CAP_PPC_AIL_MODE_3 210
+#define KVM_CAP_S390_MEM_OP_EXTENSION 211
+#define KVM_CAP_PMU_CAPABILITY 212
+#define KVM_CAP_DISABLE_QUIRKS2 213
+#define KVM_CAP_VM_TSC_CONTROL 214
+#define KVM_CAP_SYSTEM_EVENT_DATA 215
+#define KVM_CAP_ARM_SYSTEM_SUSPEND 216
+#define KVM_CAP_S390_PROTECTED_DUMP 217
+#define KVM_CAP_X86_TRIPLE_FAULT_EVENT 218
+#define KVM_CAP_X86_NOTIFY_VMEXIT 219
+#define KVM_CAP_VM_DISABLE_NX_HUGE_PAGES 220
+#define KVM_CAP_S390_ZPCI_OP 221
+#define KVM_CAP_S390_CPU_TOPOLOGY 222
+#define KVM_CAP_DIRTY_LOG_RING_ACQ_REL 223
+#define KVM_CAP_S390_PROTECTED_ASYNC_DISABLE 224
+#define KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP 225
+#define KVM_CAP_PMU_EVENT_MASKED_EVENTS 226
+#define KVM_CAP_COUNTER_OFFSET 227
+#define KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE 228
+#define KVM_CAP_ARM_SUPPORTED_BLOCK_SIZES 229
+
+#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;
+};
+
+struct kvm_irq_routing_xen_evtchn {
+ __u32 port;
+ __u32 vcpu;
+ __u32 priority;
+};
+
+#define KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL ((__u32)(-1))
+
+/* 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
+#define KVM_IRQ_ROUTING_XEN_EVTCHN 5
+
+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;
+ struct kvm_irq_routing_xen_evtchn xen_evtchn;
+ __u32 pad[8];
+ } u;
+};
+
+struct kvm_irq_routing {
+ __u32 nr;
+ __u32 flags;
+ struct kvm_irq_routing_entry entries[];
+};
+
+#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
+#define KVM_XEN_HVM_CONFIG_HYPERCALL_MSR (1 << 0)
+#define KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL (1 << 1)
+#define KVM_XEN_HVM_CONFIG_SHARED_INFO (1 << 2)
+#define KVM_XEN_HVM_CONFIG_RUNSTATE (1 << 3)
+#define KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL (1 << 4)
+#define KVM_XEN_HVM_CONFIG_EVTCHN_SEND (1 << 5)
+#define KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG (1 << 6)
+
+struct kvm_xen_hvm_config {
+ __u32 flags;
+ __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/virt/kvm/api.rst.
+ */
+#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
+#define KVM_CLOCK_REALTIME (1 << 2)
+#define KVM_CLOCK_HOST_TSC (1 << 3)
+
+struct kvm_clock_data {
+ __u64 clock;
+ __u32 flags;
+ __u32 pad0;
+ __u64 realtime;
+ __u64 host_tsc;
+ __u32 pad[4];
+};
+
+/* 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_RISCV 0x8000000000000000ULL
+
+#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
+#define KVM_REG_SIZE_U2048 0x0080000000000000ULL
+
+struct kvm_reg_list {
+ __u64 n; /* number of regs */
+ __u64 reg[];
+};
+
+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_XIVE,
+#define KVM_DEV_TYPE_XIVE KVM_DEV_TYPE_XIVE
+ KVM_DEV_TYPE_ARM_PV_TIME,
+#define KVM_DEV_TYPE_ARM_PV_TIME KVM_DEV_TYPE_ARM_PV_TIME
+ KVM_DEV_TYPE_RISCV_AIA,
+#define KVM_DEV_TYPE_RISCV_AIA KVM_DEV_TYPE_RISCV_AIA
+ KVM_DEV_TYPE_MAX,
+};
+
+struct kvm_vfio_spapr_tce {
+ __s32 groupfd;
+ __s32 tablefd;
+};
+
+/*
+ * 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)
+#define KVM_SET_NR_MMU_PAGES _IO(KVMIO, 0x44)
+#define KVM_GET_NR_MMU_PAGES _IO(KVMIO, 0x45) /* deprecated */
+#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 for a vCPU, or with
+* KVM_CAP_VM_TSC_CONTROL to set defaults for a VM */
+#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)
+/* Available with KVM_CAP_PMU_EVENT_FILTER */
+#define KVM_SET_PMU_EVENT_FILTER _IOW(KVMIO, 0xb2, struct kvm_pmu_event_filter)
+#define KVM_PPC_SVM_OFF _IO(KVMIO, 0xb3)
+#define KVM_ARM_MTE_COPY_TAGS _IOR(KVMIO, 0xb4, struct kvm_arm_copy_mte_tags)
+/* Available with KVM_CAP_COUNTER_OFFSET */
+#define KVM_ARM_SET_COUNTER_OFFSET _IOW(KVMIO, 0xb5, struct kvm_arm_counter_offset)
+
+/* 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_CAP_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)
+
+/* Available with KVM_CAP_MANUAL_DIRTY_LOG_PROTECT_2 */
+#define KVM_CLEAR_DIRTY_LOG _IOWR(KVMIO, 0xc0, struct kvm_clear_dirty_log)
+
+/* Available with KVM_CAP_HYPERV_CPUID (vcpu) / KVM_CAP_SYS_HYPERV_CPUID (system) */
+#define KVM_GET_SUPPORTED_HV_CPUID _IOWR(KVMIO, 0xc1, struct kvm_cpuid2)
+
+/* Available with KVM_CAP_ARM_SVE */
+#define KVM_ARM_VCPU_FINALIZE _IOW(KVMIO, 0xc2, int)
+
+/* Available with KVM_CAP_S390_VCPU_RESETS */
+#define KVM_S390_NORMAL_RESET _IO(KVMIO, 0xc3)
+#define KVM_S390_CLEAR_RESET _IO(KVMIO, 0xc4)
+
+struct kvm_s390_pv_sec_parm {
+ __u64 origin;
+ __u64 length;
+};
+
+struct kvm_s390_pv_unp {
+ __u64 addr;
+ __u64 size;
+ __u64 tweak;
+};
+
+enum pv_cmd_dmp_id {
+ KVM_PV_DUMP_INIT,
+ KVM_PV_DUMP_CONFIG_STOR_STATE,
+ KVM_PV_DUMP_COMPLETE,
+ KVM_PV_DUMP_CPU,
+};
+
+struct kvm_s390_pv_dmp {
+ __u64 subcmd;
+ __u64 buff_addr;
+ __u64 buff_len;
+ __u64 gaddr; /* For dump storage state */
+ __u64 reserved[4];
+};
+
+enum pv_cmd_info_id {
+ KVM_PV_INFO_VM,
+ KVM_PV_INFO_DUMP,
+};
+
+struct kvm_s390_pv_info_dump {
+ __u64 dump_cpu_buffer_len;
+ __u64 dump_config_mem_buffer_per_1m;
+ __u64 dump_config_finalize_len;
+};
+
+struct kvm_s390_pv_info_vm {
+ __u64 inst_calls_list[4];
+ __u64 max_cpus;
+ __u64 max_guests;
+ __u64 max_guest_addr;
+ __u64 feature_indication;
+};
+
+struct kvm_s390_pv_info_header {
+ __u32 id;
+ __u32 len_max;
+ __u32 len_written;
+ __u32 reserved;
+};
+
+struct kvm_s390_pv_info {
+ struct kvm_s390_pv_info_header header;
+ union {
+ struct kvm_s390_pv_info_dump dump;
+ struct kvm_s390_pv_info_vm vm;
+ };
+};
+
+enum pv_cmd_id {
+ KVM_PV_ENABLE,
+ KVM_PV_DISABLE,
+ KVM_PV_SET_SEC_PARMS,
+ KVM_PV_UNPACK,
+ KVM_PV_VERIFY,
+ KVM_PV_PREP_RESET,
+ KVM_PV_UNSHARE_ALL,
+ KVM_PV_INFO,
+ KVM_PV_DUMP,
+ KVM_PV_ASYNC_CLEANUP_PREPARE,
+ KVM_PV_ASYNC_CLEANUP_PERFORM,
+};
+
+struct kvm_pv_cmd {
+ __u32 cmd; /* Command to be executed */
+ __u16 rc; /* Ultravisor return code */
+ __u16 rrc; /* Ultravisor return reason code */
+ __u64 data; /* Data or address */
+ __u32 flags; /* flags for future extensions. Must be 0 for now */
+ __u32 reserved[3];
+};
+
+/* Available with KVM_CAP_S390_PROTECTED */
+#define KVM_S390_PV_COMMAND _IOWR(KVMIO, 0xc5, struct kvm_pv_cmd)
+
+/* Available with KVM_CAP_X86_MSR_FILTER */
+#define KVM_X86_SET_MSR_FILTER _IOW(KVMIO, 0xc6, struct kvm_msr_filter)
+
+/* Available with KVM_CAP_DIRTY_LOG_RING */
+#define KVM_RESET_DIRTY_RINGS _IO(KVMIO, 0xc7)
+
+/* Per-VM Xen attributes */
+#define KVM_XEN_HVM_GET_ATTR _IOWR(KVMIO, 0xc8, struct kvm_xen_hvm_attr)
+#define KVM_XEN_HVM_SET_ATTR _IOW(KVMIO, 0xc9, struct kvm_xen_hvm_attr)
+
+struct kvm_xen_hvm_attr {
+ __u16 type;
+ __u16 pad[3];
+ union {
+ __u8 long_mode;
+ __u8 vector;
+ __u8 runstate_update_flag;
+ struct {
+ __u64 gfn;
+#define KVM_XEN_INVALID_GFN ((__u64)-1)
+ } shared_info;
+ struct {
+ __u32 send_port;
+ __u32 type; /* EVTCHNSTAT_ipi / EVTCHNSTAT_interdomain */
+ __u32 flags;
+#define KVM_XEN_EVTCHN_DEASSIGN (1 << 0)
+#define KVM_XEN_EVTCHN_UPDATE (1 << 1)
+#define KVM_XEN_EVTCHN_RESET (1 << 2)
+ /*
+ * Events sent by the guest are either looped back to
+ * the guest itself (potentially on a different port#)
+ * or signalled via an eventfd.
+ */
+ union {
+ struct {
+ __u32 port;
+ __u32 vcpu;
+ __u32 priority;
+ } port;
+ struct {
+ __u32 port; /* Zero for eventfd */
+ __s32 fd;
+ } eventfd;
+ __u32 padding[4];
+ } deliver;
+ } evtchn;
+ __u32 xen_version;
+ __u64 pad[8];
+ } u;
+};
+
+
+/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */
+#define KVM_XEN_ATTR_TYPE_LONG_MODE 0x0
+#define KVM_XEN_ATTR_TYPE_SHARED_INFO 0x1
+#define KVM_XEN_ATTR_TYPE_UPCALL_VECTOR 0x2
+/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */
+#define KVM_XEN_ATTR_TYPE_EVTCHN 0x3
+#define KVM_XEN_ATTR_TYPE_XEN_VERSION 0x4
+/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG */
+#define KVM_XEN_ATTR_TYPE_RUNSTATE_UPDATE_FLAG 0x5
+
+/* Per-vCPU Xen attributes */
+#define KVM_XEN_VCPU_GET_ATTR _IOWR(KVMIO, 0xca, struct kvm_xen_vcpu_attr)
+#define KVM_XEN_VCPU_SET_ATTR _IOW(KVMIO, 0xcb, struct kvm_xen_vcpu_attr)
+
+/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */
+#define KVM_XEN_HVM_EVTCHN_SEND _IOW(KVMIO, 0xd0, struct kvm_irq_routing_xen_evtchn)
+
+#define KVM_GET_SREGS2 _IOR(KVMIO, 0xcc, struct kvm_sregs2)
+#define KVM_SET_SREGS2 _IOW(KVMIO, 0xcd, struct kvm_sregs2)
+
+struct kvm_xen_vcpu_attr {
+ __u16 type;
+ __u16 pad[3];
+ union {
+ __u64 gpa;
+#define KVM_XEN_INVALID_GPA ((__u64)-1)
+ __u64 pad[8];
+ struct {
+ __u64 state;
+ __u64 state_entry_time;
+ __u64 time_running;
+ __u64 time_runnable;
+ __u64 time_blocked;
+ __u64 time_offline;
+ } runstate;
+ __u32 vcpu_id;
+ struct {
+ __u32 port;
+ __u32 priority;
+ __u64 expires_ns;
+ } timer;
+ __u8 vector;
+ } u;
+};
+
+/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */
+#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO 0x0
+#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO 0x1
+#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR 0x2
+#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT 0x3
+#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA 0x4
+#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST 0x5
+/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */
+#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_ID 0x6
+#define KVM_XEN_VCPU_ATTR_TYPE_TIMER 0x7
+#define KVM_XEN_VCPU_ATTR_TYPE_UPCALL_VECTOR 0x8
+
+/* 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,
+ /* Attestation report */
+ KVM_SEV_GET_ATTESTATION_REPORT,
+ /* Guest Migration Extension */
+ KVM_SEV_SEND_CANCEL,
+
+ 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;
+};
+
+struct kvm_sev_attestation_report {
+ __u8 mnonce[16];
+ __u64 uaddr;
+ __u32 len;
+};
+
+struct kvm_sev_send_start {
+ __u32 policy;
+ __u64 pdh_cert_uaddr;
+ __u32 pdh_cert_len;
+ __u64 plat_certs_uaddr;
+ __u32 plat_certs_len;
+ __u64 amd_certs_uaddr;
+ __u32 amd_certs_len;
+ __u64 session_uaddr;
+ __u32 session_len;
+};
+
+struct kvm_sev_send_update_data {
+ __u64 hdr_uaddr;
+ __u32 hdr_len;
+ __u64 guest_uaddr;
+ __u32 guest_len;
+ __u64 trans_uaddr;
+ __u32 trans_len;
+};
+
+struct kvm_sev_receive_start {
+ __u32 handle;
+ __u32 policy;
+ __u64 pdh_uaddr;
+ __u32 pdh_len;
+ __u64 session_uaddr;
+ __u32 session_len;
+};
+
+struct kvm_sev_receive_update_data {
+ __u64 hdr_uaddr;
+ __u32 hdr_len;
+ __u64 guest_uaddr;
+ __u32 guest_len;
+ __u64 trans_uaddr;
+ __u32 trans_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)
+
+#define KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE (1 << 0)
+#define KVM_DIRTY_LOG_INITIALLY_SET (1 << 1)
+
+/*
+ * Arch needs to define the macro after implementing the dirty ring
+ * feature. KVM_DIRTY_LOG_PAGE_OFFSET should be defined as the
+ * starting page offset of the dirty ring structures.
+ */
+#ifndef KVM_DIRTY_LOG_PAGE_OFFSET
+#define KVM_DIRTY_LOG_PAGE_OFFSET 0
+#endif
+
+/*
+ * KVM dirty GFN flags, defined as:
+ *
+ * |---------------+---------------+--------------|
+ * | bit 1 (reset) | bit 0 (dirty) | Status |
+ * |---------------+---------------+--------------|
+ * | 0 | 0 | Invalid GFN |
+ * | 0 | 1 | Dirty GFN |
+ * | 1 | X | GFN to reset |
+ * |---------------+---------------+--------------|
+ *
+ * Lifecycle of a dirty GFN goes like:
+ *
+ * dirtied harvested reset
+ * 00 -----------> 01 -------------> 1X -------+
+ * ^ |
+ * | |
+ * +------------------------------------------+
+ *
+ * The userspace program is only responsible for the 01->1X state
+ * conversion after harvesting an entry. Also, it must not skip any
+ * dirty bits, so that dirty bits are always harvested in sequence.
+ */
+#define KVM_DIRTY_GFN_F_DIRTY _BITUL(0)
+#define KVM_DIRTY_GFN_F_RESET _BITUL(1)
+#define KVM_DIRTY_GFN_F_MASK 0x3
+
+/*
+ * KVM dirty rings should be mapped at KVM_DIRTY_LOG_PAGE_OFFSET of
+ * per-vcpu mmaped regions as an array of struct kvm_dirty_gfn. The
+ * size of the gfn buffer is decided by the first argument when
+ * enabling KVM_CAP_DIRTY_LOG_RING.
+ */
+struct kvm_dirty_gfn {
+ __u32 flags;
+ __u32 slot;
+ __u64 offset;
+};
+
+#define KVM_BUS_LOCK_DETECTION_OFF (1 << 0)
+#define KVM_BUS_LOCK_DETECTION_EXIT (1 << 1)
+
+#define KVM_PMU_CAP_DISABLE (1 << 0)
+
+/**
+ * struct kvm_stats_header - Header of per vm/vcpu binary statistics data.
+ * @flags: Some extra information for header, always 0 for now.
+ * @name_size: The size in bytes of the memory which contains statistics
+ * name string including trailing '\0'. The memory is allocated
+ * at the send of statistics descriptor.
+ * @num_desc: The number of statistics the vm or vcpu has.
+ * @id_offset: The offset of the vm/vcpu stats' id string in the file pointed
+ * by vm/vcpu stats fd.
+ * @desc_offset: The offset of the vm/vcpu stats' descriptor block in the file
+ * pointd by vm/vcpu stats fd.
+ * @data_offset: The offset of the vm/vcpu stats' data block in the file
+ * pointed by vm/vcpu stats fd.
+ *
+ * This is the header userspace needs to read from stats fd before any other
+ * readings. It is used by userspace to discover all the information about the
+ * vm/vcpu's binary statistics.
+ * Userspace reads this header from the start of the vm/vcpu's stats fd.
+ */
+struct kvm_stats_header {
+ __u32 flags;
+ __u32 name_size;
+ __u32 num_desc;
+ __u32 id_offset;
+ __u32 desc_offset;
+ __u32 data_offset;
+};
+
+#define KVM_STATS_TYPE_SHIFT 0
+#define KVM_STATS_TYPE_MASK (0xF << KVM_STATS_TYPE_SHIFT)
+#define KVM_STATS_TYPE_CUMULATIVE (0x0 << KVM_STATS_TYPE_SHIFT)
+#define KVM_STATS_TYPE_INSTANT (0x1 << KVM_STATS_TYPE_SHIFT)
+#define KVM_STATS_TYPE_PEAK (0x2 << KVM_STATS_TYPE_SHIFT)
+#define KVM_STATS_TYPE_LINEAR_HIST (0x3 << KVM_STATS_TYPE_SHIFT)
+#define KVM_STATS_TYPE_LOG_HIST (0x4 << KVM_STATS_TYPE_SHIFT)
+#define KVM_STATS_TYPE_MAX KVM_STATS_TYPE_LOG_HIST
+
+#define KVM_STATS_UNIT_SHIFT 4
+#define KVM_STATS_UNIT_MASK (0xF << KVM_STATS_UNIT_SHIFT)
+#define KVM_STATS_UNIT_NONE (0x0 << KVM_STATS_UNIT_SHIFT)
+#define KVM_STATS_UNIT_BYTES (0x1 << KVM_STATS_UNIT_SHIFT)
+#define KVM_STATS_UNIT_SECONDS (0x2 << KVM_STATS_UNIT_SHIFT)
+#define KVM_STATS_UNIT_CYCLES (0x3 << KVM_STATS_UNIT_SHIFT)
+#define KVM_STATS_UNIT_BOOLEAN (0x4 << KVM_STATS_UNIT_SHIFT)
+#define KVM_STATS_UNIT_MAX KVM_STATS_UNIT_BOOLEAN
+
+#define KVM_STATS_BASE_SHIFT 8
+#define KVM_STATS_BASE_MASK (0xF << KVM_STATS_BASE_SHIFT)
+#define KVM_STATS_BASE_POW10 (0x0 << KVM_STATS_BASE_SHIFT)
+#define KVM_STATS_BASE_POW2 (0x1 << KVM_STATS_BASE_SHIFT)
+#define KVM_STATS_BASE_MAX KVM_STATS_BASE_POW2
+
+/**
+ * struct kvm_stats_desc - Descriptor of a KVM statistics.
+ * @flags: Annotations of the stats, like type, unit, etc.
+ * @exponent: Used together with @flags to determine the unit.
+ * @size: The number of data items for this stats.
+ * Every data item is of type __u64.
+ * @offset: The offset of the stats to the start of stat structure in
+ * structure kvm or kvm_vcpu.
+ * @bucket_size: A parameter value used for histogram stats. It is only used
+ * for linear histogram stats, specifying the size of the bucket;
+ * @name: The name string for the stats. Its size is indicated by the
+ * &kvm_stats_header->name_size.
+ */
+struct kvm_stats_desc {
+ __u32 flags;
+ __s16 exponent;
+ __u16 size;
+ __u32 offset;
+ __u32 bucket_size;
+ char name[];
+};
+
+#define KVM_GET_STATS_FD _IO(KVMIO, 0xce)
+
+/* Available with KVM_CAP_XSAVE2 */
+#define KVM_GET_XSAVE2 _IOR(KVMIO, 0xcf, struct kvm_xsave)
+
+/* Available with KVM_CAP_S390_PROTECTED_DUMP */
+#define KVM_S390_PV_CPU_COMMAND _IOWR(KVMIO, 0xd0, struct kvm_pv_cmd)
+
+/* Available with KVM_CAP_X86_NOTIFY_VMEXIT */
+#define KVM_X86_NOTIFY_VMEXIT_ENABLED (1ULL << 0)
+#define KVM_X86_NOTIFY_VMEXIT_USER (1ULL << 1)
+
+/* Available with KVM_CAP_S390_ZPCI_OP */
+#define KVM_S390_ZPCI_OP _IOW(KVMIO, 0xd1, struct kvm_s390_zpci_op)
+
+struct kvm_s390_zpci_op {
+ /* in */
+ __u32 fh; /* target device */
+ __u8 op; /* operation to perform */
+ __u8 pad[3];
+ union {
+ /* for KVM_S390_ZPCIOP_REG_AEN */
+ struct {
+ __u64 ibv; /* Guest addr of interrupt bit vector */
+ __u64 sb; /* Guest addr of summary bit */
+ __u32 flags;
+ __u32 noi; /* Number of interrupts */
+ __u8 isc; /* Guest interrupt subclass */
+ __u8 sbo; /* Offset of guest summary bit vector */
+ __u16 pad;
+ } reg_aen;
+ __u64 reserved[8];
+ } u;
+};
+
+/* types for kvm_s390_zpci_op->op */
+#define KVM_S390_ZPCIOP_REG_AEN 0
+#define KVM_S390_ZPCIOP_DEREG_AEN 1
+
+/* flags for kvm_s390_zpci_op->u.reg_aen.flags */
+#define KVM_S390_ZPCIOP_REGAEN_HOST (1 << 0)
+
+#endif /* __LINUX_KVM_H */
diff --git a/tools/include/uapi/linux/mman.h b/tools/include/uapi/linux/mman.h
new file mode 100644
index 0000000000..a246e11988
--- /dev/null
+++ b/tools/include/uapi/linux/mman.h
@@ -0,0 +1,58 @@
+/* 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>
+#include <linux/types.h>
+
+#define MREMAP_MAYMOVE 1
+#define MREMAP_FIXED 2
+#define MREMAP_DONTUNMAP 4
+
+#define OVERCOMMIT_GUESS 0
+#define OVERCOMMIT_ALWAYS 1
+#define OVERCOMMIT_NEVER 2
+
+#define MAP_SHARED 0x01 /* Share changes */
+#define MAP_PRIVATE 0x02 /* Changes are private */
+#define MAP_SHARED_VALIDATE 0x03 /* share + validate extension flags */
+
+/*
+ * 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_16KB HUGETLB_FLAG_ENCODE_16KB
+#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_32MB HUGETLB_FLAG_ENCODE_32MB
+#define MAP_HUGE_256MB HUGETLB_FLAG_ENCODE_256MB
+#define MAP_HUGE_512MB HUGETLB_FLAG_ENCODE_512MB
+#define MAP_HUGE_1GB HUGETLB_FLAG_ENCODE_1GB
+#define MAP_HUGE_2GB HUGETLB_FLAG_ENCODE_2GB
+#define MAP_HUGE_16GB HUGETLB_FLAG_ENCODE_16GB
+
+struct cachestat_range {
+ __u64 off;
+ __u64 len;
+};
+
+struct cachestat {
+ __u64 nr_cache;
+ __u64 nr_dirty;
+ __u64 nr_writeback;
+ __u64 nr_evicted;
+ __u64 nr_recently_evicted;
+};
+
+#endif /* _UAPI_LINUX_MMAN_H */
diff --git a/tools/include/uapi/linux/mount.h b/tools/include/uapi/linux/mount.h
new file mode 100644
index 0000000000..8eb0d7b758
--- /dev/null
+++ b/tools/include/uapi/linux/mount.h
@@ -0,0 +1,140 @@
+#ifndef _UAPI_LINUX_MOUNT_H
+#define _UAPI_LINUX_MOUNT_H
+
+#include <linux/types.h>
+
+/*
+ * These are the fs-independent mount-flags: up to 32 flags are supported
+ *
+ * Usage of these is restricted within the kernel to core mount(2) code and
+ * callers of sys_mount() only. Filesystems should be using the SB_*
+ * equivalent instead.
+ */
+#define MS_RDONLY 1 /* Mount read-only */
+#define MS_NOSUID 2 /* Ignore suid and sgid bits */
+#define MS_NODEV 4 /* Disallow access to device special files */
+#define MS_NOEXEC 8 /* Disallow program execution */
+#define MS_SYNCHRONOUS 16 /* Writes are synced at once */
+#define MS_REMOUNT 32 /* Alter flags of a mounted FS */
+#define MS_MANDLOCK 64 /* Allow mandatory locks on an FS */
+#define MS_DIRSYNC 128 /* Directory modifications are synchronous */
+#define MS_NOSYMFOLLOW 256 /* Do not follow symlinks */
+#define MS_NOATIME 1024 /* Do not update access times. */
+#define MS_NODIRATIME 2048 /* Do not update directory access times */
+#define MS_BIND 4096
+#define MS_MOVE 8192
+#define MS_REC 16384
+#define MS_VERBOSE 32768 /* War is peace. Verbosity is silence.
+ MS_VERBOSE is deprecated. */
+#define MS_SILENT 32768
+#define MS_POSIXACL (1<<16) /* VFS does not apply the umask */
+#define MS_UNBINDABLE (1<<17) /* change to unbindable */
+#define MS_PRIVATE (1<<18) /* change to private */
+#define MS_SLAVE (1<<19) /* change to slave */
+#define MS_SHARED (1<<20) /* change to shared */
+#define MS_RELATIME (1<<21) /* Update atime relative to mtime/ctime. */
+#define MS_KERNMOUNT (1<<22) /* this is a kern_mount call */
+#define MS_I_VERSION (1<<23) /* Update inode I_version field */
+#define MS_STRICTATIME (1<<24) /* Always perform atime updates */
+#define MS_LAZYTIME (1<<25) /* Update the on-disk [acm]times lazily */
+
+/* These sb flags are internal to the kernel */
+#define MS_SUBMOUNT (1<<26)
+#define MS_NOREMOTELOCK (1<<27)
+#define MS_NOSEC (1<<28)
+#define MS_BORN (1<<29)
+#define MS_ACTIVE (1<<30)
+#define MS_NOUSER (1<<31)
+
+/*
+ * Superblock flags that can be altered by MS_REMOUNT
+ */
+#define MS_RMT_MASK (MS_RDONLY|MS_SYNCHRONOUS|MS_MANDLOCK|MS_I_VERSION|\
+ MS_LAZYTIME)
+
+/*
+ * Old magic mount flag and mask
+ */
+#define MS_MGC_VAL 0xC0ED0000
+#define MS_MGC_MSK 0xffff0000
+
+/*
+ * open_tree() flags.
+ */
+#define OPEN_TREE_CLONE 1 /* Clone the target tree and attach the clone */
+#define OPEN_TREE_CLOEXEC O_CLOEXEC /* Close the file on execve() */
+
+/*
+ * move_mount() flags.
+ */
+#define MOVE_MOUNT_F_SYMLINKS 0x00000001 /* Follow symlinks on from path */
+#define MOVE_MOUNT_F_AUTOMOUNTS 0x00000002 /* Follow automounts on from path */
+#define MOVE_MOUNT_F_EMPTY_PATH 0x00000004 /* Empty from path permitted */
+#define MOVE_MOUNT_T_SYMLINKS 0x00000010 /* Follow symlinks on to path */
+#define MOVE_MOUNT_T_AUTOMOUNTS 0x00000020 /* Follow automounts on to path */
+#define MOVE_MOUNT_T_EMPTY_PATH 0x00000040 /* Empty to path permitted */
+#define MOVE_MOUNT_SET_GROUP 0x00000100 /* Set sharing group instead */
+#define MOVE_MOUNT_BENEATH 0x00000200 /* Mount beneath top mount */
+#define MOVE_MOUNT__MASK 0x00000377
+
+/*
+ * fsopen() flags.
+ */
+#define FSOPEN_CLOEXEC 0x00000001
+
+/*
+ * fspick() flags.
+ */
+#define FSPICK_CLOEXEC 0x00000001
+#define FSPICK_SYMLINK_NOFOLLOW 0x00000002
+#define FSPICK_NO_AUTOMOUNT 0x00000004
+#define FSPICK_EMPTY_PATH 0x00000008
+
+/*
+ * The type of fsconfig() call made.
+ */
+enum fsconfig_command {
+ FSCONFIG_SET_FLAG = 0, /* Set parameter, supplying no value */
+ FSCONFIG_SET_STRING = 1, /* Set parameter, supplying a string value */
+ FSCONFIG_SET_BINARY = 2, /* Set parameter, supplying a binary blob value */
+ FSCONFIG_SET_PATH = 3, /* Set parameter, supplying an object by path */
+ FSCONFIG_SET_PATH_EMPTY = 4, /* Set parameter, supplying an object by (empty) path */
+ FSCONFIG_SET_FD = 5, /* Set parameter, supplying an object by fd */
+ FSCONFIG_CMD_CREATE = 6, /* Invoke superblock creation */
+ FSCONFIG_CMD_RECONFIGURE = 7, /* Invoke superblock reconfiguration */
+};
+
+/*
+ * fsmount() flags.
+ */
+#define FSMOUNT_CLOEXEC 0x00000001
+
+/*
+ * Mount attributes.
+ */
+#define MOUNT_ATTR_RDONLY 0x00000001 /* Mount read-only */
+#define MOUNT_ATTR_NOSUID 0x00000002 /* Ignore suid and sgid bits */
+#define MOUNT_ATTR_NODEV 0x00000004 /* Disallow access to device special files */
+#define MOUNT_ATTR_NOEXEC 0x00000008 /* Disallow program execution */
+#define MOUNT_ATTR__ATIME 0x00000070 /* Setting on how atime should be updated */
+#define MOUNT_ATTR_RELATIME 0x00000000 /* - Update atime relative to mtime/ctime. */
+#define MOUNT_ATTR_NOATIME 0x00000010 /* - Do not update access times. */
+#define MOUNT_ATTR_STRICTATIME 0x00000020 /* - Always perform atime updates */
+#define MOUNT_ATTR_NODIRATIME 0x00000080 /* Do not update directory access times */
+#define MOUNT_ATTR_IDMAP 0x00100000 /* Idmap mount to @userns_fd in struct mount_attr. */
+#define MOUNT_ATTR_NOSYMFOLLOW 0x00200000 /* Do not follow symlinks */
+
+/*
+ * mount_setattr()
+ */
+struct mount_attr {
+ __u64 attr_set;
+ __u64 attr_clr;
+ __u64 propagation;
+ __u64 userns_fd;
+};
+
+/* List of all mount_attr versions. */
+#define MOUNT_ATTR_SIZE_VER0 32 /* sizeof first published struct */
+
+#endif /* _UAPI_LINUX_MOUNT_H */
diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h
new file mode 100644
index 0000000000..c1634b95c2
--- /dev/null
+++ b/tools/include/uapi/linux/netdev.h
@@ -0,0 +1,63 @@
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
+/* Do not edit directly, auto-generated from: */
+/* Documentation/netlink/specs/netdev.yaml */
+/* YNL-GEN uapi header */
+
+#ifndef _UAPI_LINUX_NETDEV_H
+#define _UAPI_LINUX_NETDEV_H
+
+#define NETDEV_FAMILY_NAME "netdev"
+#define NETDEV_FAMILY_VERSION 1
+
+/**
+ * enum netdev_xdp_act
+ * @NETDEV_XDP_ACT_BASIC: XDP features set supported by all drivers
+ * (XDP_ABORTED, XDP_DROP, XDP_PASS, XDP_TX)
+ * @NETDEV_XDP_ACT_REDIRECT: The netdev supports XDP_REDIRECT
+ * @NETDEV_XDP_ACT_NDO_XMIT: This feature informs if netdev implements
+ * ndo_xdp_xmit callback.
+ * @NETDEV_XDP_ACT_XSK_ZEROCOPY: This feature informs if netdev supports AF_XDP
+ * in zero copy mode.
+ * @NETDEV_XDP_ACT_HW_OFFLOAD: This feature informs if netdev supports XDP hw
+ * offloading.
+ * @NETDEV_XDP_ACT_RX_SG: This feature informs if netdev implements non-linear
+ * XDP buffer support in the driver napi callback.
+ * @NETDEV_XDP_ACT_NDO_XMIT_SG: This feature informs if netdev implements
+ * non-linear XDP buffer support in ndo_xdp_xmit callback.
+ */
+enum netdev_xdp_act {
+ NETDEV_XDP_ACT_BASIC = 1,
+ NETDEV_XDP_ACT_REDIRECT = 2,
+ NETDEV_XDP_ACT_NDO_XMIT = 4,
+ NETDEV_XDP_ACT_XSK_ZEROCOPY = 8,
+ NETDEV_XDP_ACT_HW_OFFLOAD = 16,
+ NETDEV_XDP_ACT_RX_SG = 32,
+ NETDEV_XDP_ACT_NDO_XMIT_SG = 64,
+
+ /* private: */
+ NETDEV_XDP_ACT_MASK = 127,
+};
+
+enum {
+ NETDEV_A_DEV_IFINDEX = 1,
+ NETDEV_A_DEV_PAD,
+ NETDEV_A_DEV_XDP_FEATURES,
+ NETDEV_A_DEV_XDP_ZC_MAX_SEGS,
+
+ __NETDEV_A_DEV_MAX,
+ NETDEV_A_DEV_MAX = (__NETDEV_A_DEV_MAX - 1)
+};
+
+enum {
+ NETDEV_CMD_DEV_GET = 1,
+ NETDEV_CMD_DEV_ADD_NTF,
+ NETDEV_CMD_DEV_DEL_NTF,
+ NETDEV_CMD_DEV_CHANGE_NTF,
+
+ __NETDEV_CMD_MAX,
+ NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1)
+};
+
+#define NETDEV_MCGRP_MGMT "mgmt"
+
+#endif /* _UAPI_LINUX_NETDEV_H */
diff --git a/tools/include/uapi/linux/netlink.h b/tools/include/uapi/linux/netlink.h
new file mode 100644
index 0000000000..0a4d733177
--- /dev/null
+++ b/tools/include/uapi/linux/netlink.h
@@ -0,0 +1,252 @@
+/* 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
+#define NETLINK_GET_STRICT_CHK 12
+
+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/openat2.h b/tools/include/uapi/linux/openat2.h
new file mode 100644
index 0000000000..a5feb76049
--- /dev/null
+++ b/tools/include/uapi/linux/openat2.h
@@ -0,0 +1,43 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_LINUX_OPENAT2_H
+#define _UAPI_LINUX_OPENAT2_H
+
+#include <linux/types.h>
+
+/*
+ * Arguments for how openat2(2) should open the target path. If only @flags and
+ * @mode are non-zero, then openat2(2) operates very similarly to openat(2).
+ *
+ * However, unlike openat(2), unknown or invalid bits in @flags result in
+ * -EINVAL rather than being silently ignored. @mode must be zero unless one of
+ * {O_CREAT, O_TMPFILE} are set.
+ *
+ * @flags: O_* flags.
+ * @mode: O_CREAT/O_TMPFILE file mode.
+ * @resolve: RESOLVE_* flags.
+ */
+struct open_how {
+ __u64 flags;
+ __u64 mode;
+ __u64 resolve;
+};
+
+/* how->resolve flags for openat2(2). */
+#define RESOLVE_NO_XDEV 0x01 /* Block mount-point crossings
+ (includes bind-mounts). */
+#define RESOLVE_NO_MAGICLINKS 0x02 /* Block traversal through procfs-style
+ "magic-links". */
+#define RESOLVE_NO_SYMLINKS 0x04 /* Block traversal through all symlinks
+ (implies OEXT_NO_MAGICLINKS) */
+#define RESOLVE_BENEATH 0x08 /* Block "lexical" trickery like
+ "..", symlinks, and absolute
+ paths which escape the dirfd. */
+#define RESOLVE_IN_ROOT 0x10 /* Make all jumps to "/" and ".."
+ be scoped inside the dirfd
+ (similar to chroot(2)). */
+#define RESOLVE_CACHED 0x20 /* Only complete if resolution can be
+ completed through cached lookup. May
+ return -EAGAIN if that's not
+ possible. */
+
+#endif /* _UAPI_LINUX_OPENAT2_H */
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
new file mode 100644
index 0000000000..39c6a250dd
--- /dev/null
+++ b/tools/include/uapi/linux/perf_event.h
@@ -0,0 +1,1449 @@
+/* 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 */
+};
+
+/*
+ * attr.config layout for type PERF_TYPE_HARDWARE and PERF_TYPE_HW_CACHE
+ * PERF_TYPE_HARDWARE: 0xEEEEEEEE000000AA
+ * AA: hardware event ID
+ * EEEEEEEE: PMU type ID
+ * PERF_TYPE_HW_CACHE: 0xEEEEEEEE00DDCCBB
+ * BB: hardware cache ID
+ * CC: hardware cache op ID
+ * DD: hardware cache op result ID
+ * EEEEEEEE: PMU type ID
+ * If the PMU type ID is 0, the PERF_TYPE_RAW will be applied.
+ */
+#define PERF_PMU_TYPE_SHIFT 32
+#define PERF_HW_EVENT_MASK 0xffffffff
+
+/*
+ * 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_CGROUP_SWITCHES = 11,
+
+ 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_AUX = 1U << 20,
+ PERF_SAMPLE_CGROUP = 1U << 21,
+ PERF_SAMPLE_DATA_PAGE_SIZE = 1U << 22,
+ PERF_SAMPLE_CODE_PAGE_SIZE = 1U << 23,
+ PERF_SAMPLE_WEIGHT_STRUCT = 1U << 24,
+
+ PERF_SAMPLE_MAX = 1U << 25, /* non-ABI */
+};
+
+#define PERF_SAMPLE_WEIGHT_TYPE (PERF_SAMPLE_WEIGHT | PERF_SAMPLE_WEIGHT_STRUCT)
+/*
+ * 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_HW_INDEX_SHIFT = 17, /* save low level index of raw branch records */
+
+ PERF_SAMPLE_BRANCH_PRIV_SAVE_SHIFT = 18, /* save privilege mode */
+
+ 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_HW_INDEX = 1U << PERF_SAMPLE_BRANCH_HW_INDEX_SHIFT,
+
+ PERF_SAMPLE_BRANCH_PRIV_SAVE = 1U << PERF_SAMPLE_BRANCH_PRIV_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_ERET = 11, /* exception return */
+ PERF_BR_IRQ = 12, /* irq */
+ PERF_BR_SERROR = 13, /* system error */
+ PERF_BR_NO_TX = 14, /* not in transaction */
+ PERF_BR_EXTEND_ABI = 15, /* extend ABI */
+ PERF_BR_MAX,
+};
+
+/*
+ * Common branch speculation outcome classification
+ */
+enum {
+ PERF_BR_SPEC_NA = 0, /* Not available */
+ PERF_BR_SPEC_WRONG_PATH = 1, /* Speculative but on wrong path */
+ PERF_BR_NON_SPEC_CORRECT_PATH = 2, /* Non-speculative but on correct path */
+ PERF_BR_SPEC_CORRECT_PATH = 3, /* Speculative and on correct path */
+ PERF_BR_SPEC_MAX,
+};
+
+enum {
+ PERF_BR_NEW_FAULT_ALGN = 0, /* Alignment fault */
+ PERF_BR_NEW_FAULT_DATA = 1, /* Data fault */
+ PERF_BR_NEW_FAULT_INST = 2, /* Inst fault */
+ PERF_BR_NEW_ARCH_1 = 3, /* Architecture specific */
+ PERF_BR_NEW_ARCH_2 = 4, /* Architecture specific */
+ PERF_BR_NEW_ARCH_3 = 5, /* Architecture specific */
+ PERF_BR_NEW_ARCH_4 = 6, /* Architecture specific */
+ PERF_BR_NEW_ARCH_5 = 7, /* Architecture specific */
+ PERF_BR_NEW_MAX,
+};
+
+enum {
+ PERF_BR_PRIV_UNKNOWN = 0,
+ PERF_BR_PRIV_USER = 1,
+ PERF_BR_PRIV_KERNEL = 2,
+ PERF_BR_PRIV_HV = 3,
+};
+
+#define PERF_BR_ARM64_FIQ PERF_BR_NEW_ARCH_1
+#define PERF_BR_ARM64_DEBUG_HALT PERF_BR_NEW_ARCH_2
+#define PERF_BR_ARM64_DEBUG_EXIT PERF_BR_NEW_ARCH_3
+#define PERF_BR_ARM64_DEBUG_INST PERF_BR_NEW_ARCH_4
+#define PERF_BR_ARM64_DEBUG_DATA PERF_BR_NEW_ARCH_5
+
+#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
+ * { u64 lost; } && PERF_FORMAT_LOST
+ * } && !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
+ * { u64 lost; } && PERF_FORMAT_LOST
+ * } 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_LOST = 1U << 4,
+
+ PERF_FORMAT_MAX = 1U << 5, /* 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 */
+#define PERF_ATTR_SIZE_VER6 120 /* add: aux_sample_size */
+#define PERF_ATTR_SIZE_VER7 128 /* add: sig_data */
+#define PERF_ATTR_SIZE_VER8 136 /* add: config3 */
+
+/*
+ * 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 */
+ ksymbol : 1, /* include ksymbol events */
+ bpf_event : 1, /* include bpf events */
+ aux_output : 1, /* generate AUX records instead of events */
+ cgroup : 1, /* include cgroup events */
+ text_poke : 1, /* include text poke events */
+ build_id : 1, /* use build id in mmap2 events */
+ inherit_thread : 1, /* children only inherit if cloned with CLONE_THREAD */
+ remove_on_exec : 1, /* event is removed from task on exec */
+ sigtrap : 1, /* send synchronous SIGTRAP on event */
+ __reserved_1 : 26;
+
+ 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;
+ __u32 aux_sample_size;
+ __u32 __reserved_3;
+
+ /*
+ * User provided data if sigtrap=1, passed back to user via
+ * siginfo_t::si_perf_data, e.g. to permit user to identify the event.
+ * Note, siginfo_t::si_perf_data is long-sized, and sig_data will be
+ * truncated accordingly on 32 bit architectures.
+ */
+ __u64 sig_data;
+
+ __u64 config3; /* extension of config2 */
+};
+
+/*
+ * 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[];
+};
+
+/*
+ * 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_{shift,mult,offset} fields are used */
+ cap_user_time_zero : 1, /* The time_zero field is used */
+ cap_user_time_short : 1, /* the time_{cycle,mask} fields are used */
+ cap_____res : 58;
+ };
+ };
+
+ /*
+ * 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. */
+ __u32 __reserved_1;
+
+ /*
+ * If cap_usr_time_short, the hardware clock is less than 64bit wide
+ * and we must compute the 'cyc' value, as used by cap_usr_time, as:
+ *
+ * cyc = time_cycles + ((cyc - time_cycles) & time_mask)
+ *
+ * NOTE: this form is explicitly chosen such that cap_usr_time_short
+ * is a correction on top of cap_usr_time, and code that doesn't
+ * know about cap_usr_time_short still works under the assumption
+ * the counter doesn't wrap.
+ */
+ __u64 time_cycles;
+ __u64 time_mask;
+
+ /*
+ * Hole for extension of the self monitor capabilities
+ */
+
+ __u8 __reserved[116*8]; /* 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;
+};
+
+/*
+ * The current state of perf_event_header::misc bits usage:
+ * ('|' used bit, '-' unused bit)
+ *
+ * 012 CDEF
+ * |||---------||||
+ *
+ * Where:
+ * 0-2 CPUMODE_MASK
+ *
+ * C PROC_MAP_PARSE_TIMEOUT
+ * D MMAP_DATA / COMM_EXEC / FORK_EXEC / SWITCH_OUT
+ * E MMAP_BUILD_ID / EXACT_IP / SCHED_OUT_PREEMPT
+ * F (reserved)
+ */
+
+#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_FORK_EXEC - PERF_RECORD_FORK event (perf internal)
+ * 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_FORK_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_MMAP_BUILD_ID - PERF_RECORD_MMAP2 event
+ *
+ *
+ * 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.
+ *
+ * PERF_RECORD_MISC_MMAP_BUILD_ID:
+ * Indicates that mmap2 event carries build id data.
+ */
+#define PERF_RECORD_MISC_EXACT_IP (1 << 14)
+#define PERF_RECORD_MISC_SWITCH_OUT_PREEMPT (1 << 14)
+#define PERF_RECORD_MISC_MMAP_BUILD_ID (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 hw_idx; } && PERF_SAMPLE_BRANCH_HW_INDEX
+ * { 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
+ *
+ * { union perf_sample_weight
+ * {
+ * u64 full; && PERF_SAMPLE_WEIGHT
+ * #if defined(__LITTLE_ENDIAN_BITFIELD)
+ * struct {
+ * u32 var1_dw;
+ * u16 var2_w;
+ * u16 var3_w;
+ * } && PERF_SAMPLE_WEIGHT_STRUCT
+ * #elif defined(__BIG_ENDIAN_BITFIELD)
+ * struct {
+ * u16 var3_w;
+ * u16 var2_w;
+ * u32 var1_dw;
+ * } && PERF_SAMPLE_WEIGHT_STRUCT
+ * #endif
+ * }
+ * }
+ * { 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
+ * { u64 size;
+ * char data[size]; } && PERF_SAMPLE_AUX
+ * { u64 data_page_size;} && PERF_SAMPLE_DATA_PAGE_SIZE
+ * { u64 code_page_size;} && PERF_SAMPLE_CODE_PAGE_SIZE
+ * };
+ */
+ 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;
+ * union {
+ * struct {
+ * u32 maj;
+ * u32 min;
+ * u64 ino;
+ * u64 ino_generation;
+ * };
+ * struct {
+ * u8 build_id_size;
+ * u8 __reserved_1;
+ * u16 __reserved_2;
+ * u8 build_id[20];
+ * };
+ * };
+ * 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,
+
+ /*
+ * Record ksymbol register/unregister events:
+ *
+ * struct {
+ * struct perf_event_header header;
+ * u64 addr;
+ * u32 len;
+ * u16 ksym_type;
+ * u16 flags;
+ * char name[];
+ * struct sample_id sample_id;
+ * };
+ */
+ PERF_RECORD_KSYMBOL = 17,
+
+ /*
+ * Record bpf events:
+ * enum perf_bpf_event_type {
+ * PERF_BPF_EVENT_UNKNOWN = 0,
+ * PERF_BPF_EVENT_PROG_LOAD = 1,
+ * PERF_BPF_EVENT_PROG_UNLOAD = 2,
+ * };
+ *
+ * struct {
+ * struct perf_event_header header;
+ * u16 type;
+ * u16 flags;
+ * u32 id;
+ * u8 tag[BPF_TAG_SIZE];
+ * struct sample_id sample_id;
+ * };
+ */
+ PERF_RECORD_BPF_EVENT = 18,
+
+ /*
+ * struct {
+ * struct perf_event_header header;
+ * u64 id;
+ * char path[];
+ * struct sample_id sample_id;
+ * };
+ */
+ PERF_RECORD_CGROUP = 19,
+
+ /*
+ * Records changes to kernel text i.e. self-modified code. 'old_len' is
+ * the number of old bytes, 'new_len' is the number of new bytes. Either
+ * 'old_len' or 'new_len' may be zero to indicate, for example, the
+ * addition or removal of a trampoline. 'bytes' contains the old bytes
+ * followed immediately by the new bytes.
+ *
+ * struct {
+ * struct perf_event_header header;
+ * u64 addr;
+ * u16 old_len;
+ * u16 new_len;
+ * u8 bytes[];
+ * struct sample_id sample_id;
+ * };
+ */
+ PERF_RECORD_TEXT_POKE = 20,
+
+ /*
+ * Data written to the AUX area by hardware due to aux_output, may need
+ * to be matched to the event by an architecture-specific hardware ID.
+ * This records the hardware ID, but requires sample_id to provide the
+ * event ID. e.g. Intel PT uses this record to disambiguate PEBS-via-PT
+ * records from multiple events.
+ *
+ * struct {
+ * struct perf_event_header header;
+ * u64 hw_id;
+ * struct sample_id sample_id;
+ * };
+ */
+ PERF_RECORD_AUX_OUTPUT_HW_ID = 21,
+
+ PERF_RECORD_MAX, /* non-ABI */
+};
+
+enum perf_record_ksymbol_type {
+ PERF_RECORD_KSYMBOL_TYPE_UNKNOWN = 0,
+ PERF_RECORD_KSYMBOL_TYPE_BPF = 1,
+ /*
+ * Out of line code such as kprobe-replaced instructions or optimized
+ * kprobes or ftrace trampolines.
+ */
+ PERF_RECORD_KSYMBOL_TYPE_OOL = 2,
+ PERF_RECORD_KSYMBOL_TYPE_MAX /* non-ABI */
+};
+
+#define PERF_RECORD_KSYMBOL_FLAGS_UNREGISTER (1 << 0)
+
+enum perf_bpf_event_type {
+ PERF_BPF_EVENT_UNKNOWN = 0,
+ PERF_BPF_EVENT_PROG_LOAD = 1,
+ PERF_BPF_EVENT_PROG_UNLOAD = 2,
+ PERF_BPF_EVENT_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_AUX_FLAG_PMU_FORMAT_TYPE_MASK 0xff00 /* PMU specific trace format type */
+
+/* CoreSight PMU AUX buffer formats */
+#define PERF_AUX_FLAG_CORESIGHT_FORMAT_CORESIGHT 0x0000 /* Default for backward compatibility */
+#define PERF_AUX_FLAG_CORESIGHT_FORMAT_RAW 0x0100 /* Raw format of the source */
+
+#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_blk:3, /* access blocked */
+ mem_hops:3, /* hop level */
+ mem_rsvd:18;
+ };
+};
+#elif defined(__BIG_ENDIAN_BITFIELD)
+union perf_mem_data_src {
+ __u64 val;
+ struct {
+ __u64 mem_rsvd:18,
+ mem_hops:3, /* hop level */
+ mem_blk:3, /* access blocked */
+ 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
+
+/*
+ * PERF_MEM_LVL_* namespace being depricated to some extent in the
+ * favour of newer composite PERF_MEM_{LVLNUM_,REMOTE_,SNOOPX_} fields.
+ * Supporting this namespace inorder to not break defined ABIs.
+ *
+ * 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 */
+/* 5-0x7 available */
+#define PERF_MEM_LVLNUM_UNC 0x08 /* Uncached */
+#define PERF_MEM_LVLNUM_CXL 0x09 /* CXL */
+#define PERF_MEM_LVLNUM_IO 0x0a /* I/O */
+#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 */
+#define PERF_MEM_SNOOPX_PEER 0x02 /* xfer from peer */
+#define PERF_MEM_SNOOPX_SHIFT 38
+
+/* 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
+
+/* Access blocked */
+#define PERF_MEM_BLK_NA 0x01 /* not available */
+#define PERF_MEM_BLK_DATA 0x02 /* data could not be forwarded */
+#define PERF_MEM_BLK_ADDR 0x04 /* address conflict */
+#define PERF_MEM_BLK_SHIFT 40
+
+/* hop level */
+#define PERF_MEM_HOPS_0 0x01 /* remote core, same node */
+#define PERF_MEM_HOPS_1 0x02 /* remote node, same socket */
+#define PERF_MEM_HOPS_2 0x03 /* remote socket, same board */
+#define PERF_MEM_HOPS_3 0x04 /* remote board */
+/* 5-7 available */
+#define PERF_MEM_HOPS_SHIFT 43
+
+#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
+ * spec: branch speculation info (or 0 if not supported)
+ */
+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 */
+ spec:2, /* branch speculation info */
+ new_type:4, /* additional branch type */
+ priv:3, /* privilege level */
+ reserved:31;
+};
+
+union perf_sample_weight {
+ __u64 full;
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+ struct {
+ __u32 var1_dw;
+ __u16 var2_w;
+ __u16 var3_w;
+ };
+#elif defined(__BIG_ENDIAN_BITFIELD)
+ struct {
+ __u16 var3_w;
+ __u16 var2_w;
+ __u32 var1_dw;
+ };
+#else
+#error "Unknown endianness"
+#endif
+};
+
+#endif /* _UAPI_LINUX_PERF_EVENT_H */
diff --git a/tools/include/uapi/linux/pkt_cls.h b/tools/include/uapi/linux/pkt_cls.h
new file mode 100644
index 0000000000..3faee0199a
--- /dev/null
+++ b/tools/include/uapi/linux/pkt_cls.h
@@ -0,0 +1,612 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __LINUX_PKT_CLS_H
+#define __LINUX_PKT_CLS_H
+
+#include <linux/types.h>
+#include <linux/pkt_sched.h>
+
+#define TC_COOKIE_MAX_SIZE 16
+
+/* Action attributes */
+enum {
+ TCA_ACT_UNSPEC,
+ TCA_ACT_KIND,
+ TCA_ACT_OPTIONS,
+ TCA_ACT_INDEX,
+ TCA_ACT_STATS,
+ TCA_ACT_PAD,
+ TCA_ACT_COOKIE,
+ __TCA_ACT_MAX
+};
+
+#define TCA_ACT_MAX __TCA_ACT_MAX
+#define TCA_OLD_COMPAT (TCA_ACT_MAX+1)
+#define TCA_ACT_MAX_PRIO 32
+#define TCA_ACT_BIND 1
+#define TCA_ACT_NOBIND 0
+#define TCA_ACT_UNBIND 1
+#define TCA_ACT_NOUNBIND 0
+#define TCA_ACT_REPLACE 1
+#define TCA_ACT_NOREPLACE 0
+
+#define TC_ACT_UNSPEC (-1)
+#define TC_ACT_OK 0
+#define TC_ACT_RECLASSIFY 1
+#define TC_ACT_SHOT 2
+#define TC_ACT_PIPE 3
+#define TC_ACT_STOLEN 4
+#define TC_ACT_QUEUED 5
+#define TC_ACT_REPEAT 6
+#define TC_ACT_REDIRECT 7
+#define TC_ACT_TRAP 8 /* For hw path, this means "trap to cpu"
+ * and don't further process the frame
+ * in hardware. For sw path, this is
+ * equivalent of TC_ACT_STOLEN - drop
+ * the skb and act like everything
+ * is alright.
+ */
+#define TC_ACT_VALUE_MAX TC_ACT_TRAP
+
+/* There is a special kind of actions called "extended actions",
+ * which need a value parameter. These have a local opcode located in
+ * the highest nibble, starting from 1. The rest of the bits
+ * are used to carry the value. These two parts together make
+ * a combined opcode.
+ */
+#define __TC_ACT_EXT_SHIFT 28
+#define __TC_ACT_EXT(local) ((local) << __TC_ACT_EXT_SHIFT)
+#define TC_ACT_EXT_VAL_MASK ((1 << __TC_ACT_EXT_SHIFT) - 1)
+#define TC_ACT_EXT_OPCODE(combined) ((combined) & (~TC_ACT_EXT_VAL_MASK))
+#define TC_ACT_EXT_CMP(combined, opcode) (TC_ACT_EXT_OPCODE(combined) == opcode)
+
+#define TC_ACT_JUMP __TC_ACT_EXT(1)
+#define TC_ACT_GOTO_CHAIN __TC_ACT_EXT(2)
+#define TC_ACT_EXT_OPCODE_MAX TC_ACT_GOTO_CHAIN
+
+/* Action type identifiers*/
+enum {
+ TCA_ID_UNSPEC=0,
+ TCA_ID_POLICE=1,
+ /* other actions go here */
+ __TCA_ID_MAX=255
+};
+
+#define TCA_ID_MAX __TCA_ID_MAX
+
+struct tc_police {
+ __u32 index;
+ int action;
+#define TC_POLICE_UNSPEC TC_ACT_UNSPEC
+#define TC_POLICE_OK TC_ACT_OK
+#define TC_POLICE_RECLASSIFY TC_ACT_RECLASSIFY
+#define TC_POLICE_SHOT TC_ACT_SHOT
+#define TC_POLICE_PIPE TC_ACT_PIPE
+
+ __u32 limit;
+ __u32 burst;
+ __u32 mtu;
+ struct tc_ratespec rate;
+ struct tc_ratespec peakrate;
+ int refcnt;
+ int bindcnt;
+ __u32 capab;
+};
+
+struct tcf_t {
+ __u64 install;
+ __u64 lastuse;
+ __u64 expires;
+ __u64 firstuse;
+};
+
+struct tc_cnt {
+ int refcnt;
+ int bindcnt;
+};
+
+#define tc_gen \
+ __u32 index; \
+ __u32 capab; \
+ int action; \
+ int refcnt; \
+ int bindcnt
+
+enum {
+ TCA_POLICE_UNSPEC,
+ TCA_POLICE_TBF,
+ TCA_POLICE_RATE,
+ TCA_POLICE_PEAKRATE,
+ TCA_POLICE_AVRATE,
+ TCA_POLICE_RESULT,
+ TCA_POLICE_TM,
+ TCA_POLICE_PAD,
+ __TCA_POLICE_MAX
+#define TCA_POLICE_RESULT TCA_POLICE_RESULT
+};
+
+#define TCA_POLICE_MAX (__TCA_POLICE_MAX - 1)
+
+/* tca flags definitions */
+#define TCA_CLS_FLAGS_SKIP_HW (1 << 0) /* don't offload filter to HW */
+#define TCA_CLS_FLAGS_SKIP_SW (1 << 1) /* don't use filter in SW */
+#define TCA_CLS_FLAGS_IN_HW (1 << 2) /* filter is offloaded to HW */
+#define TCA_CLS_FLAGS_NOT_IN_HW (1 << 3) /* filter isn't offloaded to HW */
+#define TCA_CLS_FLAGS_VERBOSE (1 << 4) /* verbose logging */
+
+/* U32 filters */
+
+#define TC_U32_HTID(h) ((h)&0xFFF00000)
+#define TC_U32_USERHTID(h) (TC_U32_HTID(h)>>20)
+#define TC_U32_HASH(h) (((h)>>12)&0xFF)
+#define TC_U32_NODE(h) ((h)&0xFFF)
+#define TC_U32_KEY(h) ((h)&0xFFFFF)
+#define TC_U32_UNSPEC 0
+#define TC_U32_ROOT (0xFFF00000)
+
+enum {
+ TCA_U32_UNSPEC,
+ TCA_U32_CLASSID,
+ TCA_U32_HASH,
+ TCA_U32_LINK,
+ TCA_U32_DIVISOR,
+ TCA_U32_SEL,
+ TCA_U32_POLICE,
+ TCA_U32_ACT,
+ TCA_U32_INDEV,
+ TCA_U32_PCNT,
+ TCA_U32_MARK,
+ TCA_U32_FLAGS,
+ TCA_U32_PAD,
+ __TCA_U32_MAX
+};
+
+#define TCA_U32_MAX (__TCA_U32_MAX - 1)
+
+struct tc_u32_key {
+ __be32 mask;
+ __be32 val;
+ int off;
+ int offmask;
+};
+
+struct tc_u32_sel {
+ unsigned char flags;
+ unsigned char offshift;
+ unsigned char nkeys;
+
+ __be16 offmask;
+ __u16 off;
+ short offoff;
+
+ short hoff;
+ __be32 hmask;
+ struct tc_u32_key keys[];
+};
+
+struct tc_u32_mark {
+ __u32 val;
+ __u32 mask;
+ __u32 success;
+};
+
+struct tc_u32_pcnt {
+ __u64 rcnt;
+ __u64 rhit;
+ __u64 kcnts[];
+};
+
+/* Flags */
+
+#define TC_U32_TERMINAL 1
+#define TC_U32_OFFSET 2
+#define TC_U32_VAROFFSET 4
+#define TC_U32_EAT 8
+
+#define TC_U32_MAXDEPTH 8
+
+
+/* RSVP filter */
+
+enum {
+ TCA_RSVP_UNSPEC,
+ TCA_RSVP_CLASSID,
+ TCA_RSVP_DST,
+ TCA_RSVP_SRC,
+ TCA_RSVP_PINFO,
+ TCA_RSVP_POLICE,
+ TCA_RSVP_ACT,
+ __TCA_RSVP_MAX
+};
+
+#define TCA_RSVP_MAX (__TCA_RSVP_MAX - 1 )
+
+struct tc_rsvp_gpi {
+ __u32 key;
+ __u32 mask;
+ int offset;
+};
+
+struct tc_rsvp_pinfo {
+ struct tc_rsvp_gpi dpi;
+ struct tc_rsvp_gpi spi;
+ __u8 protocol;
+ __u8 tunnelid;
+ __u8 tunnelhdr;
+ __u8 pad;
+};
+
+/* ROUTE filter */
+
+enum {
+ TCA_ROUTE4_UNSPEC,
+ TCA_ROUTE4_CLASSID,
+ TCA_ROUTE4_TO,
+ TCA_ROUTE4_FROM,
+ TCA_ROUTE4_IIF,
+ TCA_ROUTE4_POLICE,
+ TCA_ROUTE4_ACT,
+ __TCA_ROUTE4_MAX
+};
+
+#define TCA_ROUTE4_MAX (__TCA_ROUTE4_MAX - 1)
+
+
+/* FW filter */
+
+enum {
+ TCA_FW_UNSPEC,
+ TCA_FW_CLASSID,
+ TCA_FW_POLICE,
+ TCA_FW_INDEV,
+ TCA_FW_ACT, /* used by CONFIG_NET_CLS_ACT */
+ TCA_FW_MASK,
+ __TCA_FW_MAX
+};
+
+#define TCA_FW_MAX (__TCA_FW_MAX - 1)
+
+/* TC index filter */
+
+enum {
+ TCA_TCINDEX_UNSPEC,
+ TCA_TCINDEX_HASH,
+ TCA_TCINDEX_MASK,
+ TCA_TCINDEX_SHIFT,
+ TCA_TCINDEX_FALL_THROUGH,
+ TCA_TCINDEX_CLASSID,
+ TCA_TCINDEX_POLICE,
+ TCA_TCINDEX_ACT,
+ __TCA_TCINDEX_MAX
+};
+
+#define TCA_TCINDEX_MAX (__TCA_TCINDEX_MAX - 1)
+
+/* Flow filter */
+
+enum {
+ FLOW_KEY_SRC,
+ FLOW_KEY_DST,
+ FLOW_KEY_PROTO,
+ FLOW_KEY_PROTO_SRC,
+ FLOW_KEY_PROTO_DST,
+ FLOW_KEY_IIF,
+ FLOW_KEY_PRIORITY,
+ FLOW_KEY_MARK,
+ FLOW_KEY_NFCT,
+ FLOW_KEY_NFCT_SRC,
+ FLOW_KEY_NFCT_DST,
+ FLOW_KEY_NFCT_PROTO_SRC,
+ FLOW_KEY_NFCT_PROTO_DST,
+ FLOW_KEY_RTCLASSID,
+ FLOW_KEY_SKUID,
+ FLOW_KEY_SKGID,
+ FLOW_KEY_VLAN_TAG,
+ FLOW_KEY_RXHASH,
+ __FLOW_KEY_MAX,
+};
+
+#define FLOW_KEY_MAX (__FLOW_KEY_MAX - 1)
+
+enum {
+ FLOW_MODE_MAP,
+ FLOW_MODE_HASH,
+};
+
+enum {
+ TCA_FLOW_UNSPEC,
+ TCA_FLOW_KEYS,
+ TCA_FLOW_MODE,
+ TCA_FLOW_BASECLASS,
+ TCA_FLOW_RSHIFT,
+ TCA_FLOW_ADDEND,
+ TCA_FLOW_MASK,
+ TCA_FLOW_XOR,
+ TCA_FLOW_DIVISOR,
+ TCA_FLOW_ACT,
+ TCA_FLOW_POLICE,
+ TCA_FLOW_EMATCHES,
+ TCA_FLOW_PERTURB,
+ __TCA_FLOW_MAX
+};
+
+#define TCA_FLOW_MAX (__TCA_FLOW_MAX - 1)
+
+/* Basic filter */
+
+enum {
+ TCA_BASIC_UNSPEC,
+ TCA_BASIC_CLASSID,
+ TCA_BASIC_EMATCHES,
+ TCA_BASIC_ACT,
+ TCA_BASIC_POLICE,
+ __TCA_BASIC_MAX
+};
+
+#define TCA_BASIC_MAX (__TCA_BASIC_MAX - 1)
+
+
+/* Cgroup classifier */
+
+enum {
+ TCA_CGROUP_UNSPEC,
+ TCA_CGROUP_ACT,
+ TCA_CGROUP_POLICE,
+ TCA_CGROUP_EMATCHES,
+ __TCA_CGROUP_MAX,
+};
+
+#define TCA_CGROUP_MAX (__TCA_CGROUP_MAX - 1)
+
+/* BPF classifier */
+
+#define TCA_BPF_FLAG_ACT_DIRECT (1 << 0)
+
+enum {
+ TCA_BPF_UNSPEC,
+ TCA_BPF_ACT,
+ TCA_BPF_POLICE,
+ TCA_BPF_CLASSID,
+ TCA_BPF_OPS_LEN,
+ TCA_BPF_OPS,
+ TCA_BPF_FD,
+ TCA_BPF_NAME,
+ TCA_BPF_FLAGS,
+ TCA_BPF_FLAGS_GEN,
+ TCA_BPF_TAG,
+ TCA_BPF_ID,
+ __TCA_BPF_MAX,
+};
+
+#define TCA_BPF_MAX (__TCA_BPF_MAX - 1)
+
+/* Flower classifier */
+
+enum {
+ TCA_FLOWER_UNSPEC,
+ TCA_FLOWER_CLASSID,
+ TCA_FLOWER_INDEV,
+ TCA_FLOWER_ACT,
+ TCA_FLOWER_KEY_ETH_DST, /* ETH_ALEN */
+ TCA_FLOWER_KEY_ETH_DST_MASK, /* ETH_ALEN */
+ TCA_FLOWER_KEY_ETH_SRC, /* ETH_ALEN */
+ TCA_FLOWER_KEY_ETH_SRC_MASK, /* ETH_ALEN */
+ TCA_FLOWER_KEY_ETH_TYPE, /* be16 */
+ TCA_FLOWER_KEY_IP_PROTO, /* u8 */
+ TCA_FLOWER_KEY_IPV4_SRC, /* be32 */
+ TCA_FLOWER_KEY_IPV4_SRC_MASK, /* be32 */
+ TCA_FLOWER_KEY_IPV4_DST, /* be32 */
+ TCA_FLOWER_KEY_IPV4_DST_MASK, /* be32 */
+ TCA_FLOWER_KEY_IPV6_SRC, /* struct in6_addr */
+ TCA_FLOWER_KEY_IPV6_SRC_MASK, /* struct in6_addr */
+ TCA_FLOWER_KEY_IPV6_DST, /* struct in6_addr */
+ TCA_FLOWER_KEY_IPV6_DST_MASK, /* struct in6_addr */
+ TCA_FLOWER_KEY_TCP_SRC, /* be16 */
+ TCA_FLOWER_KEY_TCP_DST, /* be16 */
+ TCA_FLOWER_KEY_UDP_SRC, /* be16 */
+ TCA_FLOWER_KEY_UDP_DST, /* be16 */
+
+ TCA_FLOWER_FLAGS,
+ TCA_FLOWER_KEY_VLAN_ID, /* be16 */
+ TCA_FLOWER_KEY_VLAN_PRIO, /* u8 */
+ TCA_FLOWER_KEY_VLAN_ETH_TYPE, /* be16 */
+
+ TCA_FLOWER_KEY_ENC_KEY_ID, /* be32 */
+ TCA_FLOWER_KEY_ENC_IPV4_SRC, /* be32 */
+ TCA_FLOWER_KEY_ENC_IPV4_SRC_MASK,/* be32 */
+ TCA_FLOWER_KEY_ENC_IPV4_DST, /* be32 */
+ TCA_FLOWER_KEY_ENC_IPV4_DST_MASK,/* be32 */
+ TCA_FLOWER_KEY_ENC_IPV6_SRC, /* struct in6_addr */
+ TCA_FLOWER_KEY_ENC_IPV6_SRC_MASK,/* struct in6_addr */
+ TCA_FLOWER_KEY_ENC_IPV6_DST, /* struct in6_addr */
+ TCA_FLOWER_KEY_ENC_IPV6_DST_MASK,/* struct in6_addr */
+
+ TCA_FLOWER_KEY_TCP_SRC_MASK, /* be16 */
+ TCA_FLOWER_KEY_TCP_DST_MASK, /* be16 */
+ TCA_FLOWER_KEY_UDP_SRC_MASK, /* be16 */
+ TCA_FLOWER_KEY_UDP_DST_MASK, /* be16 */
+ TCA_FLOWER_KEY_SCTP_SRC_MASK, /* be16 */
+ TCA_FLOWER_KEY_SCTP_DST_MASK, /* be16 */
+
+ TCA_FLOWER_KEY_SCTP_SRC, /* be16 */
+ TCA_FLOWER_KEY_SCTP_DST, /* be16 */
+
+ TCA_FLOWER_KEY_ENC_UDP_SRC_PORT, /* be16 */
+ TCA_FLOWER_KEY_ENC_UDP_SRC_PORT_MASK, /* be16 */
+ TCA_FLOWER_KEY_ENC_UDP_DST_PORT, /* be16 */
+ TCA_FLOWER_KEY_ENC_UDP_DST_PORT_MASK, /* be16 */
+
+ TCA_FLOWER_KEY_FLAGS, /* be32 */
+ TCA_FLOWER_KEY_FLAGS_MASK, /* be32 */
+
+ TCA_FLOWER_KEY_ICMPV4_CODE, /* u8 */
+ TCA_FLOWER_KEY_ICMPV4_CODE_MASK,/* u8 */
+ TCA_FLOWER_KEY_ICMPV4_TYPE, /* u8 */
+ TCA_FLOWER_KEY_ICMPV4_TYPE_MASK,/* u8 */
+ TCA_FLOWER_KEY_ICMPV6_CODE, /* u8 */
+ TCA_FLOWER_KEY_ICMPV6_CODE_MASK,/* u8 */
+ TCA_FLOWER_KEY_ICMPV6_TYPE, /* u8 */
+ TCA_FLOWER_KEY_ICMPV6_TYPE_MASK,/* u8 */
+
+ TCA_FLOWER_KEY_ARP_SIP, /* be32 */
+ TCA_FLOWER_KEY_ARP_SIP_MASK, /* be32 */
+ TCA_FLOWER_KEY_ARP_TIP, /* be32 */
+ TCA_FLOWER_KEY_ARP_TIP_MASK, /* be32 */
+ TCA_FLOWER_KEY_ARP_OP, /* u8 */
+ TCA_FLOWER_KEY_ARP_OP_MASK, /* u8 */
+ TCA_FLOWER_KEY_ARP_SHA, /* ETH_ALEN */
+ TCA_FLOWER_KEY_ARP_SHA_MASK, /* ETH_ALEN */
+ TCA_FLOWER_KEY_ARP_THA, /* ETH_ALEN */
+ TCA_FLOWER_KEY_ARP_THA_MASK, /* ETH_ALEN */
+
+ TCA_FLOWER_KEY_MPLS_TTL, /* u8 - 8 bits */
+ TCA_FLOWER_KEY_MPLS_BOS, /* u8 - 1 bit */
+ TCA_FLOWER_KEY_MPLS_TC, /* u8 - 3 bits */
+ TCA_FLOWER_KEY_MPLS_LABEL, /* be32 - 20 bits */
+
+ TCA_FLOWER_KEY_TCP_FLAGS, /* be16 */
+ TCA_FLOWER_KEY_TCP_FLAGS_MASK, /* be16 */
+
+ TCA_FLOWER_KEY_IP_TOS, /* u8 */
+ TCA_FLOWER_KEY_IP_TOS_MASK, /* u8 */
+ TCA_FLOWER_KEY_IP_TTL, /* u8 */
+ TCA_FLOWER_KEY_IP_TTL_MASK, /* u8 */
+
+ TCA_FLOWER_KEY_CVLAN_ID, /* be16 */
+ TCA_FLOWER_KEY_CVLAN_PRIO, /* u8 */
+ TCA_FLOWER_KEY_CVLAN_ETH_TYPE, /* be16 */
+
+ TCA_FLOWER_KEY_ENC_IP_TOS, /* u8 */
+ TCA_FLOWER_KEY_ENC_IP_TOS_MASK, /* u8 */
+ TCA_FLOWER_KEY_ENC_IP_TTL, /* u8 */
+ TCA_FLOWER_KEY_ENC_IP_TTL_MASK, /* u8 */
+
+ TCA_FLOWER_KEY_ENC_OPTS,
+ TCA_FLOWER_KEY_ENC_OPTS_MASK,
+
+ TCA_FLOWER_IN_HW_COUNT,
+
+ __TCA_FLOWER_MAX,
+};
+
+#define TCA_FLOWER_MAX (__TCA_FLOWER_MAX - 1)
+
+enum {
+ TCA_FLOWER_KEY_ENC_OPTS_UNSPEC,
+ TCA_FLOWER_KEY_ENC_OPTS_GENEVE, /* Nested
+ * TCA_FLOWER_KEY_ENC_OPT_GENEVE_
+ * attributes
+ */
+ __TCA_FLOWER_KEY_ENC_OPTS_MAX,
+};
+
+#define TCA_FLOWER_KEY_ENC_OPTS_MAX (__TCA_FLOWER_KEY_ENC_OPTS_MAX - 1)
+
+enum {
+ TCA_FLOWER_KEY_ENC_OPT_GENEVE_UNSPEC,
+ TCA_FLOWER_KEY_ENC_OPT_GENEVE_CLASS, /* u16 */
+ TCA_FLOWER_KEY_ENC_OPT_GENEVE_TYPE, /* u8 */
+ TCA_FLOWER_KEY_ENC_OPT_GENEVE_DATA, /* 4 to 128 bytes */
+
+ __TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX,
+};
+
+#define TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX \
+ (__TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX - 1)
+
+enum {
+ TCA_FLOWER_KEY_FLAGS_IS_FRAGMENT = (1 << 0),
+ TCA_FLOWER_KEY_FLAGS_FRAG_IS_FIRST = (1 << 1),
+};
+
+/* Match-all classifier */
+
+enum {
+ TCA_MATCHALL_UNSPEC,
+ TCA_MATCHALL_CLASSID,
+ TCA_MATCHALL_ACT,
+ TCA_MATCHALL_FLAGS,
+ __TCA_MATCHALL_MAX,
+};
+
+#define TCA_MATCHALL_MAX (__TCA_MATCHALL_MAX - 1)
+
+/* Extended Matches */
+
+struct tcf_ematch_tree_hdr {
+ __u16 nmatches;
+ __u16 progid;
+};
+
+enum {
+ TCA_EMATCH_TREE_UNSPEC,
+ TCA_EMATCH_TREE_HDR,
+ TCA_EMATCH_TREE_LIST,
+ __TCA_EMATCH_TREE_MAX
+};
+#define TCA_EMATCH_TREE_MAX (__TCA_EMATCH_TREE_MAX - 1)
+
+struct tcf_ematch_hdr {
+ __u16 matchid;
+ __u16 kind;
+ __u16 flags;
+ __u16 pad; /* currently unused */
+};
+
+/* 0 1
+ * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5
+ * +-----------------------+-+-+---+
+ * | Unused |S|I| R |
+ * +-----------------------+-+-+---+
+ *
+ * R(2) ::= relation to next ematch
+ * where: 0 0 END (last ematch)
+ * 0 1 AND
+ * 1 0 OR
+ * 1 1 Unused (invalid)
+ * I(1) ::= invert result
+ * S(1) ::= simple payload
+ */
+#define TCF_EM_REL_END 0
+#define TCF_EM_REL_AND (1<<0)
+#define TCF_EM_REL_OR (1<<1)
+#define TCF_EM_INVERT (1<<2)
+#define TCF_EM_SIMPLE (1<<3)
+
+#define TCF_EM_REL_MASK 3
+#define TCF_EM_REL_VALID(v) (((v) & TCF_EM_REL_MASK) != TCF_EM_REL_MASK)
+
+enum {
+ TCF_LAYER_LINK,
+ TCF_LAYER_NETWORK,
+ TCF_LAYER_TRANSPORT,
+ __TCF_LAYER_MAX
+};
+#define TCF_LAYER_MAX (__TCF_LAYER_MAX - 1)
+
+/* Ematch type assignments
+ * 1..32767 Reserved for ematches inside kernel tree
+ * 32768..65535 Free to use, not reliable
+ */
+#define TCF_EM_CONTAINER 0
+#define TCF_EM_CMP 1
+#define TCF_EM_NBYTE 2
+#define TCF_EM_U32 3
+#define TCF_EM_META 4
+#define TCF_EM_TEXT 5
+#define TCF_EM_VLAN 6
+#define TCF_EM_CANID 7
+#define TCF_EM_IPSET 8
+#define TCF_EM_IPT 9
+#define TCF_EM_MAX 9
+
+enum {
+ TCF_EM_PROG_TC
+};
+
+enum {
+ TCF_EM_OPND_EQ,
+ TCF_EM_OPND_GT,
+ TCF_EM_OPND_LT
+};
+
+#endif
diff --git a/tools/include/uapi/linux/pkt_sched.h b/tools/include/uapi/linux/pkt_sched.h
new file mode 100644
index 0000000000..5c903abc9f
--- /dev/null
+++ b/tools/include/uapi/linux/pkt_sched.h
@@ -0,0 +1,1164 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __LINUX_PKT_SCHED_H
+#define __LINUX_PKT_SCHED_H
+
+#include <linux/types.h>
+
+/* Logical priority bands not depending on specific packet scheduler.
+ Every scheduler will map them to real traffic classes, if it has
+ no more precise mechanism to classify packets.
+
+ These numbers have no special meaning, though their coincidence
+ with obsolete IPv6 values is not occasional :-). New IPv6 drafts
+ preferred full anarchy inspired by diffserv group.
+
+ Note: TC_PRIO_BESTEFFORT does not mean that it is the most unhappy
+ class, actually, as rule it will be handled with more care than
+ filler or even bulk.
+ */
+
+#define TC_PRIO_BESTEFFORT 0
+#define TC_PRIO_FILLER 1
+#define TC_PRIO_BULK 2
+#define TC_PRIO_INTERACTIVE_BULK 4
+#define TC_PRIO_INTERACTIVE 6
+#define TC_PRIO_CONTROL 7
+
+#define TC_PRIO_MAX 15
+
+/* Generic queue statistics, available for all the elements.
+ Particular schedulers may have also their private records.
+ */
+
+struct tc_stats {
+ __u64 bytes; /* Number of enqueued bytes */
+ __u32 packets; /* Number of enqueued packets */
+ __u32 drops; /* Packets dropped because of lack of resources */
+ __u32 overlimits; /* Number of throttle events when this
+ * flow goes out of allocated bandwidth */
+ __u32 bps; /* Current flow byte rate */
+ __u32 pps; /* Current flow packet rate */
+ __u32 qlen;
+ __u32 backlog;
+};
+
+struct tc_estimator {
+ signed char interval;
+ unsigned char ewma_log;
+};
+
+/* "Handles"
+ ---------
+
+ All the traffic control objects have 32bit identifiers, or "handles".
+
+ They can be considered as opaque numbers from user API viewpoint,
+ but actually they always consist of two fields: major and
+ minor numbers, which are interpreted by kernel specially,
+ that may be used by applications, though not recommended.
+
+ F.e. qdisc handles always have minor number equal to zero,
+ classes (or flows) have major equal to parent qdisc major, and
+ minor uniquely identifying class inside qdisc.
+
+ Macros to manipulate handles:
+ */
+
+#define TC_H_MAJ_MASK (0xFFFF0000U)
+#define TC_H_MIN_MASK (0x0000FFFFU)
+#define TC_H_MAJ(h) ((h)&TC_H_MAJ_MASK)
+#define TC_H_MIN(h) ((h)&TC_H_MIN_MASK)
+#define TC_H_MAKE(maj,min) (((maj)&TC_H_MAJ_MASK)|((min)&TC_H_MIN_MASK))
+
+#define TC_H_UNSPEC (0U)
+#define TC_H_ROOT (0xFFFFFFFFU)
+#define TC_H_INGRESS (0xFFFFFFF1U)
+#define TC_H_CLSACT TC_H_INGRESS
+
+#define TC_H_MIN_PRIORITY 0xFFE0U
+#define TC_H_MIN_INGRESS 0xFFF2U
+#define TC_H_MIN_EGRESS 0xFFF3U
+
+/* Need to corrospond to iproute2 tc/tc_core.h "enum link_layer" */
+enum tc_link_layer {
+ TC_LINKLAYER_UNAWARE, /* Indicate unaware old iproute2 util */
+ TC_LINKLAYER_ETHERNET,
+ TC_LINKLAYER_ATM,
+};
+#define TC_LINKLAYER_MASK 0x0F /* limit use to lower 4 bits */
+
+struct tc_ratespec {
+ unsigned char cell_log;
+ __u8 linklayer; /* lower 4 bits */
+ unsigned short overhead;
+ short cell_align;
+ unsigned short mpu;
+ __u32 rate;
+};
+
+#define TC_RTAB_SIZE 1024
+
+struct tc_sizespec {
+ unsigned char cell_log;
+ unsigned char size_log;
+ short cell_align;
+ int overhead;
+ unsigned int linklayer;
+ unsigned int mpu;
+ unsigned int mtu;
+ unsigned int tsize;
+};
+
+enum {
+ TCA_STAB_UNSPEC,
+ TCA_STAB_BASE,
+ TCA_STAB_DATA,
+ __TCA_STAB_MAX
+};
+
+#define TCA_STAB_MAX (__TCA_STAB_MAX - 1)
+
+/* FIFO section */
+
+struct tc_fifo_qopt {
+ __u32 limit; /* Queue length: bytes for bfifo, packets for pfifo */
+};
+
+/* SKBPRIO section */
+
+/*
+ * Priorities go from zero to (SKBPRIO_MAX_PRIORITY - 1).
+ * SKBPRIO_MAX_PRIORITY should be at least 64 in order for skbprio to be able
+ * to map one to one the DS field of IPV4 and IPV6 headers.
+ * Memory allocation grows linearly with SKBPRIO_MAX_PRIORITY.
+ */
+
+#define SKBPRIO_MAX_PRIORITY 64
+
+struct tc_skbprio_qopt {
+ __u32 limit; /* Queue length in packets. */
+};
+
+/* PRIO section */
+
+#define TCQ_PRIO_BANDS 16
+#define TCQ_MIN_PRIO_BANDS 2
+
+struct tc_prio_qopt {
+ int bands; /* Number of bands */
+ __u8 priomap[TC_PRIO_MAX+1]; /* Map: logical priority -> PRIO band */
+};
+
+/* MULTIQ section */
+
+struct tc_multiq_qopt {
+ __u16 bands; /* Number of bands */
+ __u16 max_bands; /* Maximum number of queues */
+};
+
+/* PLUG section */
+
+#define TCQ_PLUG_BUFFER 0
+#define TCQ_PLUG_RELEASE_ONE 1
+#define TCQ_PLUG_RELEASE_INDEFINITE 2
+#define TCQ_PLUG_LIMIT 3
+
+struct tc_plug_qopt {
+ /* TCQ_PLUG_BUFFER: Inset a plug into the queue and
+ * buffer any incoming packets
+ * TCQ_PLUG_RELEASE_ONE: Dequeue packets from queue head
+ * to beginning of the next plug.
+ * TCQ_PLUG_RELEASE_INDEFINITE: Dequeue all packets from queue.
+ * Stop buffering packets until the next TCQ_PLUG_BUFFER
+ * command is received (just act as a pass-thru queue).
+ * TCQ_PLUG_LIMIT: Increase/decrease queue size
+ */
+ int action;
+ __u32 limit;
+};
+
+/* TBF section */
+
+struct tc_tbf_qopt {
+ struct tc_ratespec rate;
+ struct tc_ratespec peakrate;
+ __u32 limit;
+ __u32 buffer;
+ __u32 mtu;
+};
+
+enum {
+ TCA_TBF_UNSPEC,
+ TCA_TBF_PARMS,
+ TCA_TBF_RTAB,
+ TCA_TBF_PTAB,
+ TCA_TBF_RATE64,
+ TCA_TBF_PRATE64,
+ TCA_TBF_BURST,
+ TCA_TBF_PBURST,
+ TCA_TBF_PAD,
+ __TCA_TBF_MAX,
+};
+
+#define TCA_TBF_MAX (__TCA_TBF_MAX - 1)
+
+
+/* TEQL section */
+
+/* TEQL does not require any parameters */
+
+/* SFQ section */
+
+struct tc_sfq_qopt {
+ unsigned quantum; /* Bytes per round allocated to flow */
+ int perturb_period; /* Period of hash perturbation */
+ __u32 limit; /* Maximal packets in queue */
+ unsigned divisor; /* Hash divisor */
+ unsigned flows; /* Maximal number of flows */
+};
+
+struct tc_sfqred_stats {
+ __u32 prob_drop; /* Early drops, below max threshold */
+ __u32 forced_drop; /* Early drops, after max threshold */
+ __u32 prob_mark; /* Marked packets, below max threshold */
+ __u32 forced_mark; /* Marked packets, after max threshold */
+ __u32 prob_mark_head; /* Marked packets, below max threshold */
+ __u32 forced_mark_head;/* Marked packets, after max threshold */
+};
+
+struct tc_sfq_qopt_v1 {
+ struct tc_sfq_qopt v0;
+ unsigned int depth; /* max number of packets per flow */
+ unsigned int headdrop;
+/* SFQRED parameters */
+ __u32 limit; /* HARD maximal flow queue length (bytes) */
+ __u32 qth_min; /* Min average length threshold (bytes) */
+ __u32 qth_max; /* Max average length threshold (bytes) */
+ unsigned char Wlog; /* log(W) */
+ unsigned char Plog; /* log(P_max/(qth_max-qth_min)) */
+ unsigned char Scell_log; /* cell size for idle damping */
+ unsigned char flags;
+ __u32 max_P; /* probability, high resolution */
+/* SFQRED stats */
+ struct tc_sfqred_stats stats;
+};
+
+
+struct tc_sfq_xstats {
+ __s32 allot;
+};
+
+/* RED section */
+
+enum {
+ TCA_RED_UNSPEC,
+ TCA_RED_PARMS,
+ TCA_RED_STAB,
+ TCA_RED_MAX_P,
+ __TCA_RED_MAX,
+};
+
+#define TCA_RED_MAX (__TCA_RED_MAX - 1)
+
+struct tc_red_qopt {
+ __u32 limit; /* HARD maximal queue length (bytes) */
+ __u32 qth_min; /* Min average length threshold (bytes) */
+ __u32 qth_max; /* Max average length threshold (bytes) */
+ unsigned char Wlog; /* log(W) */
+ unsigned char Plog; /* log(P_max/(qth_max-qth_min)) */
+ unsigned char Scell_log; /* cell size for idle damping */
+ unsigned char flags;
+#define TC_RED_ECN 1
+#define TC_RED_HARDDROP 2
+#define TC_RED_ADAPTATIVE 4
+};
+
+struct tc_red_xstats {
+ __u32 early; /* Early drops */
+ __u32 pdrop; /* Drops due to queue limits */
+ __u32 other; /* Drops due to drop() calls */
+ __u32 marked; /* Marked packets */
+};
+
+/* GRED section */
+
+#define MAX_DPs 16
+
+enum {
+ TCA_GRED_UNSPEC,
+ TCA_GRED_PARMS,
+ TCA_GRED_STAB,
+ TCA_GRED_DPS,
+ TCA_GRED_MAX_P,
+ TCA_GRED_LIMIT,
+ TCA_GRED_VQ_LIST, /* nested TCA_GRED_VQ_ENTRY */
+ __TCA_GRED_MAX,
+};
+
+#define TCA_GRED_MAX (__TCA_GRED_MAX - 1)
+
+enum {
+ TCA_GRED_VQ_ENTRY_UNSPEC,
+ TCA_GRED_VQ_ENTRY, /* nested TCA_GRED_VQ_* */
+ __TCA_GRED_VQ_ENTRY_MAX,
+};
+#define TCA_GRED_VQ_ENTRY_MAX (__TCA_GRED_VQ_ENTRY_MAX - 1)
+
+enum {
+ TCA_GRED_VQ_UNSPEC,
+ TCA_GRED_VQ_PAD,
+ TCA_GRED_VQ_DP, /* u32 */
+ TCA_GRED_VQ_STAT_BYTES, /* u64 */
+ TCA_GRED_VQ_STAT_PACKETS, /* u32 */
+ TCA_GRED_VQ_STAT_BACKLOG, /* u32 */
+ TCA_GRED_VQ_STAT_PROB_DROP, /* u32 */
+ TCA_GRED_VQ_STAT_PROB_MARK, /* u32 */
+ TCA_GRED_VQ_STAT_FORCED_DROP, /* u32 */
+ TCA_GRED_VQ_STAT_FORCED_MARK, /* u32 */
+ TCA_GRED_VQ_STAT_PDROP, /* u32 */
+ TCA_GRED_VQ_STAT_OTHER, /* u32 */
+ TCA_GRED_VQ_FLAGS, /* u32 */
+ __TCA_GRED_VQ_MAX
+};
+
+#define TCA_GRED_VQ_MAX (__TCA_GRED_VQ_MAX - 1)
+
+struct tc_gred_qopt {
+ __u32 limit; /* HARD maximal queue length (bytes) */
+ __u32 qth_min; /* Min average length threshold (bytes) */
+ __u32 qth_max; /* Max average length threshold (bytes) */
+ __u32 DP; /* up to 2^32 DPs */
+ __u32 backlog;
+ __u32 qave;
+ __u32 forced;
+ __u32 early;
+ __u32 other;
+ __u32 pdrop;
+ __u8 Wlog; /* log(W) */
+ __u8 Plog; /* log(P_max/(qth_max-qth_min)) */
+ __u8 Scell_log; /* cell size for idle damping */
+ __u8 prio; /* prio of this VQ */
+ __u32 packets;
+ __u32 bytesin;
+};
+
+/* gred setup */
+struct tc_gred_sopt {
+ __u32 DPs;
+ __u32 def_DP;
+ __u8 grio;
+ __u8 flags;
+ __u16 pad1;
+};
+
+/* CHOKe section */
+
+enum {
+ TCA_CHOKE_UNSPEC,
+ TCA_CHOKE_PARMS,
+ TCA_CHOKE_STAB,
+ TCA_CHOKE_MAX_P,
+ __TCA_CHOKE_MAX,
+};
+
+#define TCA_CHOKE_MAX (__TCA_CHOKE_MAX - 1)
+
+struct tc_choke_qopt {
+ __u32 limit; /* Hard queue length (packets) */
+ __u32 qth_min; /* Min average threshold (packets) */
+ __u32 qth_max; /* Max average threshold (packets) */
+ unsigned char Wlog; /* log(W) */
+ unsigned char Plog; /* log(P_max/(qth_max-qth_min)) */
+ unsigned char Scell_log; /* cell size for idle damping */
+ unsigned char flags; /* see RED flags */
+};
+
+struct tc_choke_xstats {
+ __u32 early; /* Early drops */
+ __u32 pdrop; /* Drops due to queue limits */
+ __u32 other; /* Drops due to drop() calls */
+ __u32 marked; /* Marked packets */
+ __u32 matched; /* Drops due to flow match */
+};
+
+/* HTB section */
+#define TC_HTB_NUMPRIO 8
+#define TC_HTB_MAXDEPTH 8
+#define TC_HTB_PROTOVER 3 /* the same as HTB and TC's major */
+
+struct tc_htb_opt {
+ struct tc_ratespec rate;
+ struct tc_ratespec ceil;
+ __u32 buffer;
+ __u32 cbuffer;
+ __u32 quantum;
+ __u32 level; /* out only */
+ __u32 prio;
+};
+struct tc_htb_glob {
+ __u32 version; /* to match HTB/TC */
+ __u32 rate2quantum; /* bps->quantum divisor */
+ __u32 defcls; /* default class number */
+ __u32 debug; /* debug flags */
+
+ /* stats */
+ __u32 direct_pkts; /* count of non shaped packets */
+};
+enum {
+ TCA_HTB_UNSPEC,
+ TCA_HTB_PARMS,
+ TCA_HTB_INIT,
+ TCA_HTB_CTAB,
+ TCA_HTB_RTAB,
+ TCA_HTB_DIRECT_QLEN,
+ TCA_HTB_RATE64,
+ TCA_HTB_CEIL64,
+ TCA_HTB_PAD,
+ TCA_HTB_OFFLOAD,
+ __TCA_HTB_MAX,
+};
+
+#define TCA_HTB_MAX (__TCA_HTB_MAX - 1)
+
+struct tc_htb_xstats {
+ __u32 lends;
+ __u32 borrows;
+ __u32 giants; /* unused since 'Make HTB scheduler work with TSO.' */
+ __s32 tokens;
+ __s32 ctokens;
+};
+
+/* HFSC section */
+
+struct tc_hfsc_qopt {
+ __u16 defcls; /* default class */
+};
+
+struct tc_service_curve {
+ __u32 m1; /* slope of the first segment in bps */
+ __u32 d; /* x-projection of the first segment in us */
+ __u32 m2; /* slope of the second segment in bps */
+};
+
+struct tc_hfsc_stats {
+ __u64 work; /* total work done */
+ __u64 rtwork; /* work done by real-time criteria */
+ __u32 period; /* current period */
+ __u32 level; /* class level in hierarchy */
+};
+
+enum {
+ TCA_HFSC_UNSPEC,
+ TCA_HFSC_RSC,
+ TCA_HFSC_FSC,
+ TCA_HFSC_USC,
+ __TCA_HFSC_MAX,
+};
+
+#define TCA_HFSC_MAX (__TCA_HFSC_MAX - 1)
+
+
+/* CBQ section */
+
+#define TC_CBQ_MAXPRIO 8
+#define TC_CBQ_MAXLEVEL 8
+#define TC_CBQ_DEF_EWMA 5
+
+struct tc_cbq_lssopt {
+ unsigned char change;
+ unsigned char flags;
+#define TCF_CBQ_LSS_BOUNDED 1
+#define TCF_CBQ_LSS_ISOLATED 2
+ unsigned char ewma_log;
+ unsigned char level;
+#define TCF_CBQ_LSS_FLAGS 1
+#define TCF_CBQ_LSS_EWMA 2
+#define TCF_CBQ_LSS_MAXIDLE 4
+#define TCF_CBQ_LSS_MINIDLE 8
+#define TCF_CBQ_LSS_OFFTIME 0x10
+#define TCF_CBQ_LSS_AVPKT 0x20
+ __u32 maxidle;
+ __u32 minidle;
+ __u32 offtime;
+ __u32 avpkt;
+};
+
+struct tc_cbq_wrropt {
+ unsigned char flags;
+ unsigned char priority;
+ unsigned char cpriority;
+ unsigned char __reserved;
+ __u32 allot;
+ __u32 weight;
+};
+
+struct tc_cbq_ovl {
+ unsigned char strategy;
+#define TC_CBQ_OVL_CLASSIC 0
+#define TC_CBQ_OVL_DELAY 1
+#define TC_CBQ_OVL_LOWPRIO 2
+#define TC_CBQ_OVL_DROP 3
+#define TC_CBQ_OVL_RCLASSIC 4
+ unsigned char priority2;
+ __u16 pad;
+ __u32 penalty;
+};
+
+struct tc_cbq_police {
+ unsigned char police;
+ unsigned char __res1;
+ unsigned short __res2;
+};
+
+struct tc_cbq_fopt {
+ __u32 split;
+ __u32 defmap;
+ __u32 defchange;
+};
+
+struct tc_cbq_xstats {
+ __u32 borrows;
+ __u32 overactions;
+ __s32 avgidle;
+ __s32 undertime;
+};
+
+enum {
+ TCA_CBQ_UNSPEC,
+ TCA_CBQ_LSSOPT,
+ TCA_CBQ_WRROPT,
+ TCA_CBQ_FOPT,
+ TCA_CBQ_OVL_STRATEGY,
+ TCA_CBQ_RATE,
+ TCA_CBQ_RTAB,
+ TCA_CBQ_POLICE,
+ __TCA_CBQ_MAX,
+};
+
+#define TCA_CBQ_MAX (__TCA_CBQ_MAX - 1)
+
+/* dsmark section */
+
+enum {
+ TCA_DSMARK_UNSPEC,
+ TCA_DSMARK_INDICES,
+ TCA_DSMARK_DEFAULT_INDEX,
+ TCA_DSMARK_SET_TC_INDEX,
+ TCA_DSMARK_MASK,
+ TCA_DSMARK_VALUE,
+ __TCA_DSMARK_MAX,
+};
+
+#define TCA_DSMARK_MAX (__TCA_DSMARK_MAX - 1)
+
+/* ATM section */
+
+enum {
+ TCA_ATM_UNSPEC,
+ TCA_ATM_FD, /* file/socket descriptor */
+ TCA_ATM_PTR, /* pointer to descriptor - later */
+ TCA_ATM_HDR, /* LL header */
+ TCA_ATM_EXCESS, /* excess traffic class (0 for CLP) */
+ TCA_ATM_ADDR, /* PVC address (for output only) */
+ TCA_ATM_STATE, /* VC state (ATM_VS_*; for output only) */
+ __TCA_ATM_MAX,
+};
+
+#define TCA_ATM_MAX (__TCA_ATM_MAX - 1)
+
+/* Network emulator */
+
+enum {
+ TCA_NETEM_UNSPEC,
+ TCA_NETEM_CORR,
+ TCA_NETEM_DELAY_DIST,
+ TCA_NETEM_REORDER,
+ TCA_NETEM_CORRUPT,
+ TCA_NETEM_LOSS,
+ TCA_NETEM_RATE,
+ TCA_NETEM_ECN,
+ TCA_NETEM_RATE64,
+ TCA_NETEM_PAD,
+ TCA_NETEM_LATENCY64,
+ TCA_NETEM_JITTER64,
+ TCA_NETEM_SLOT,
+ TCA_NETEM_SLOT_DIST,
+ __TCA_NETEM_MAX,
+};
+
+#define TCA_NETEM_MAX (__TCA_NETEM_MAX - 1)
+
+struct tc_netem_qopt {
+ __u32 latency; /* added delay (us) */
+ __u32 limit; /* fifo limit (packets) */
+ __u32 loss; /* random packet loss (0=none ~0=100%) */
+ __u32 gap; /* re-ordering gap (0 for none) */
+ __u32 duplicate; /* random packet dup (0=none ~0=100%) */
+ __u32 jitter; /* random jitter in latency (us) */
+};
+
+struct tc_netem_corr {
+ __u32 delay_corr; /* delay correlation */
+ __u32 loss_corr; /* packet loss correlation */
+ __u32 dup_corr; /* duplicate correlation */
+};
+
+struct tc_netem_reorder {
+ __u32 probability;
+ __u32 correlation;
+};
+
+struct tc_netem_corrupt {
+ __u32 probability;
+ __u32 correlation;
+};
+
+struct tc_netem_rate {
+ __u32 rate; /* byte/s */
+ __s32 packet_overhead;
+ __u32 cell_size;
+ __s32 cell_overhead;
+};
+
+struct tc_netem_slot {
+ __s64 min_delay; /* nsec */
+ __s64 max_delay;
+ __s32 max_packets;
+ __s32 max_bytes;
+ __s64 dist_delay; /* nsec */
+ __s64 dist_jitter; /* nsec */
+};
+
+enum {
+ NETEM_LOSS_UNSPEC,
+ NETEM_LOSS_GI, /* General Intuitive - 4 state model */
+ NETEM_LOSS_GE, /* Gilbert Elliot models */
+ __NETEM_LOSS_MAX
+};
+#define NETEM_LOSS_MAX (__NETEM_LOSS_MAX - 1)
+
+/* State transition probabilities for 4 state model */
+struct tc_netem_gimodel {
+ __u32 p13;
+ __u32 p31;
+ __u32 p32;
+ __u32 p14;
+ __u32 p23;
+};
+
+/* Gilbert-Elliot models */
+struct tc_netem_gemodel {
+ __u32 p;
+ __u32 r;
+ __u32 h;
+ __u32 k1;
+};
+
+#define NETEM_DIST_SCALE 8192
+#define NETEM_DIST_MAX 16384
+
+/* DRR */
+
+enum {
+ TCA_DRR_UNSPEC,
+ TCA_DRR_QUANTUM,
+ __TCA_DRR_MAX
+};
+
+#define TCA_DRR_MAX (__TCA_DRR_MAX - 1)
+
+struct tc_drr_stats {
+ __u32 deficit;
+};
+
+/* MQPRIO */
+#define TC_QOPT_BITMASK 15
+#define TC_QOPT_MAX_QUEUE 16
+
+enum {
+ TC_MQPRIO_HW_OFFLOAD_NONE, /* no offload requested */
+ TC_MQPRIO_HW_OFFLOAD_TCS, /* offload TCs, no queue counts */
+ __TC_MQPRIO_HW_OFFLOAD_MAX
+};
+
+#define TC_MQPRIO_HW_OFFLOAD_MAX (__TC_MQPRIO_HW_OFFLOAD_MAX - 1)
+
+enum {
+ TC_MQPRIO_MODE_DCB,
+ TC_MQPRIO_MODE_CHANNEL,
+ __TC_MQPRIO_MODE_MAX
+};
+
+#define __TC_MQPRIO_MODE_MAX (__TC_MQPRIO_MODE_MAX - 1)
+
+enum {
+ TC_MQPRIO_SHAPER_DCB,
+ TC_MQPRIO_SHAPER_BW_RATE, /* Add new shapers below */
+ __TC_MQPRIO_SHAPER_MAX
+};
+
+#define __TC_MQPRIO_SHAPER_MAX (__TC_MQPRIO_SHAPER_MAX - 1)
+
+struct tc_mqprio_qopt {
+ __u8 num_tc;
+ __u8 prio_tc_map[TC_QOPT_BITMASK + 1];
+ __u8 hw;
+ __u16 count[TC_QOPT_MAX_QUEUE];
+ __u16 offset[TC_QOPT_MAX_QUEUE];
+};
+
+#define TC_MQPRIO_F_MODE 0x1
+#define TC_MQPRIO_F_SHAPER 0x2
+#define TC_MQPRIO_F_MIN_RATE 0x4
+#define TC_MQPRIO_F_MAX_RATE 0x8
+
+enum {
+ TCA_MQPRIO_UNSPEC,
+ TCA_MQPRIO_MODE,
+ TCA_MQPRIO_SHAPER,
+ TCA_MQPRIO_MIN_RATE64,
+ TCA_MQPRIO_MAX_RATE64,
+ __TCA_MQPRIO_MAX,
+};
+
+#define TCA_MQPRIO_MAX (__TCA_MQPRIO_MAX - 1)
+
+/* SFB */
+
+enum {
+ TCA_SFB_UNSPEC,
+ TCA_SFB_PARMS,
+ __TCA_SFB_MAX,
+};
+
+#define TCA_SFB_MAX (__TCA_SFB_MAX - 1)
+
+/*
+ * Note: increment, decrement are Q0.16 fixed-point values.
+ */
+struct tc_sfb_qopt {
+ __u32 rehash_interval; /* delay between hash move, in ms */
+ __u32 warmup_time; /* double buffering warmup time in ms (warmup_time < rehash_interval) */
+ __u32 max; /* max len of qlen_min */
+ __u32 bin_size; /* maximum queue length per bin */
+ __u32 increment; /* probability increment, (d1 in Blue) */
+ __u32 decrement; /* probability decrement, (d2 in Blue) */
+ __u32 limit; /* max SFB queue length */
+ __u32 penalty_rate; /* inelastic flows are rate limited to 'rate' pps */
+ __u32 penalty_burst;
+};
+
+struct tc_sfb_xstats {
+ __u32 earlydrop;
+ __u32 penaltydrop;
+ __u32 bucketdrop;
+ __u32 queuedrop;
+ __u32 childdrop; /* drops in child qdisc */
+ __u32 marked;
+ __u32 maxqlen;
+ __u32 maxprob;
+ __u32 avgprob;
+};
+
+#define SFB_MAX_PROB 0xFFFF
+
+/* QFQ */
+enum {
+ TCA_QFQ_UNSPEC,
+ TCA_QFQ_WEIGHT,
+ TCA_QFQ_LMAX,
+ __TCA_QFQ_MAX
+};
+
+#define TCA_QFQ_MAX (__TCA_QFQ_MAX - 1)
+
+struct tc_qfq_stats {
+ __u32 weight;
+ __u32 lmax;
+};
+
+/* CODEL */
+
+enum {
+ TCA_CODEL_UNSPEC,
+ TCA_CODEL_TARGET,
+ TCA_CODEL_LIMIT,
+ TCA_CODEL_INTERVAL,
+ TCA_CODEL_ECN,
+ TCA_CODEL_CE_THRESHOLD,
+ __TCA_CODEL_MAX
+};
+
+#define TCA_CODEL_MAX (__TCA_CODEL_MAX - 1)
+
+struct tc_codel_xstats {
+ __u32 maxpacket; /* largest packet we've seen so far */
+ __u32 count; /* how many drops we've done since the last time we
+ * entered dropping state
+ */
+ __u32 lastcount; /* count at entry to dropping state */
+ __u32 ldelay; /* in-queue delay seen by most recently dequeued packet */
+ __s32 drop_next; /* time to drop next packet */
+ __u32 drop_overlimit; /* number of time max qdisc packet limit was hit */
+ __u32 ecn_mark; /* number of packets we ECN marked instead of dropped */
+ __u32 dropping; /* are we in dropping state ? */
+ __u32 ce_mark; /* number of CE marked packets because of ce_threshold */
+};
+
+/* FQ_CODEL */
+
+enum {
+ TCA_FQ_CODEL_UNSPEC,
+ TCA_FQ_CODEL_TARGET,
+ TCA_FQ_CODEL_LIMIT,
+ TCA_FQ_CODEL_INTERVAL,
+ TCA_FQ_CODEL_ECN,
+ TCA_FQ_CODEL_FLOWS,
+ TCA_FQ_CODEL_QUANTUM,
+ TCA_FQ_CODEL_CE_THRESHOLD,
+ TCA_FQ_CODEL_DROP_BATCH_SIZE,
+ TCA_FQ_CODEL_MEMORY_LIMIT,
+ __TCA_FQ_CODEL_MAX
+};
+
+#define TCA_FQ_CODEL_MAX (__TCA_FQ_CODEL_MAX - 1)
+
+enum {
+ TCA_FQ_CODEL_XSTATS_QDISC,
+ TCA_FQ_CODEL_XSTATS_CLASS,
+};
+
+struct tc_fq_codel_qd_stats {
+ __u32 maxpacket; /* largest packet we've seen so far */
+ __u32 drop_overlimit; /* number of time max qdisc
+ * packet limit was hit
+ */
+ __u32 ecn_mark; /* number of packets we ECN marked
+ * instead of being dropped
+ */
+ __u32 new_flow_count; /* number of time packets
+ * created a 'new flow'
+ */
+ __u32 new_flows_len; /* count of flows in new list */
+ __u32 old_flows_len; /* count of flows in old list */
+ __u32 ce_mark; /* packets above ce_threshold */
+ __u32 memory_usage; /* in bytes */
+ __u32 drop_overmemory;
+};
+
+struct tc_fq_codel_cl_stats {
+ __s32 deficit;
+ __u32 ldelay; /* in-queue delay seen by most recently
+ * dequeued packet
+ */
+ __u32 count;
+ __u32 lastcount;
+ __u32 dropping;
+ __s32 drop_next;
+};
+
+struct tc_fq_codel_xstats {
+ __u32 type;
+ union {
+ struct tc_fq_codel_qd_stats qdisc_stats;
+ struct tc_fq_codel_cl_stats class_stats;
+ };
+};
+
+/* FQ */
+
+enum {
+ TCA_FQ_UNSPEC,
+
+ TCA_FQ_PLIMIT, /* limit of total number of packets in queue */
+
+ TCA_FQ_FLOW_PLIMIT, /* limit of packets per flow */
+
+ TCA_FQ_QUANTUM, /* RR quantum */
+
+ TCA_FQ_INITIAL_QUANTUM, /* RR quantum for new flow */
+
+ TCA_FQ_RATE_ENABLE, /* enable/disable rate limiting */
+
+ TCA_FQ_FLOW_DEFAULT_RATE,/* obsolete, do not use */
+
+ TCA_FQ_FLOW_MAX_RATE, /* per flow max rate */
+
+ TCA_FQ_BUCKETS_LOG, /* log2(number of buckets) */
+
+ TCA_FQ_FLOW_REFILL_DELAY, /* flow credit refill delay in usec */
+
+ TCA_FQ_ORPHAN_MASK, /* mask applied to orphaned skb hashes */
+
+ TCA_FQ_LOW_RATE_THRESHOLD, /* per packet delay under this rate */
+
+ TCA_FQ_CE_THRESHOLD, /* DCTCP-like CE-marking threshold */
+
+ __TCA_FQ_MAX
+};
+
+#define TCA_FQ_MAX (__TCA_FQ_MAX - 1)
+
+struct tc_fq_qd_stats {
+ __u64 gc_flows;
+ __u64 highprio_packets;
+ __u64 tcp_retrans;
+ __u64 throttled;
+ __u64 flows_plimit;
+ __u64 pkts_too_long;
+ __u64 allocation_errors;
+ __s64 time_next_delayed_flow;
+ __u32 flows;
+ __u32 inactive_flows;
+ __u32 throttled_flows;
+ __u32 unthrottle_latency_ns;
+ __u64 ce_mark; /* packets above ce_threshold */
+};
+
+/* Heavy-Hitter Filter */
+
+enum {
+ TCA_HHF_UNSPEC,
+ TCA_HHF_BACKLOG_LIMIT,
+ TCA_HHF_QUANTUM,
+ TCA_HHF_HH_FLOWS_LIMIT,
+ TCA_HHF_RESET_TIMEOUT,
+ TCA_HHF_ADMIT_BYTES,
+ TCA_HHF_EVICT_TIMEOUT,
+ TCA_HHF_NON_HH_WEIGHT,
+ __TCA_HHF_MAX
+};
+
+#define TCA_HHF_MAX (__TCA_HHF_MAX - 1)
+
+struct tc_hhf_xstats {
+ __u32 drop_overlimit; /* number of times max qdisc packet limit
+ * was hit
+ */
+ __u32 hh_overlimit; /* number of times max heavy-hitters was hit */
+ __u32 hh_tot_count; /* number of captured heavy-hitters so far */
+ __u32 hh_cur_count; /* number of current heavy-hitters */
+};
+
+/* PIE */
+enum {
+ TCA_PIE_UNSPEC,
+ TCA_PIE_TARGET,
+ TCA_PIE_LIMIT,
+ TCA_PIE_TUPDATE,
+ TCA_PIE_ALPHA,
+ TCA_PIE_BETA,
+ TCA_PIE_ECN,
+ TCA_PIE_BYTEMODE,
+ __TCA_PIE_MAX
+};
+#define TCA_PIE_MAX (__TCA_PIE_MAX - 1)
+
+struct tc_pie_xstats {
+ __u32 prob; /* current probability */
+ __u32 delay; /* current delay in ms */
+ __u32 avg_dq_rate; /* current average dq_rate in bits/pie_time */
+ __u32 packets_in; /* total number of packets enqueued */
+ __u32 dropped; /* packets dropped due to pie_action */
+ __u32 overlimit; /* dropped due to lack of space in queue */
+ __u32 maxq; /* maximum queue size */
+ __u32 ecn_mark; /* packets marked with ecn*/
+};
+
+/* CBS */
+struct tc_cbs_qopt {
+ __u8 offload;
+ __u8 _pad[3];
+ __s32 hicredit;
+ __s32 locredit;
+ __s32 idleslope;
+ __s32 sendslope;
+};
+
+enum {
+ TCA_CBS_UNSPEC,
+ TCA_CBS_PARMS,
+ __TCA_CBS_MAX,
+};
+
+#define TCA_CBS_MAX (__TCA_CBS_MAX - 1)
+
+
+/* ETF */
+struct tc_etf_qopt {
+ __s32 delta;
+ __s32 clockid;
+ __u32 flags;
+#define TC_ETF_DEADLINE_MODE_ON BIT(0)
+#define TC_ETF_OFFLOAD_ON BIT(1)
+};
+
+enum {
+ TCA_ETF_UNSPEC,
+ TCA_ETF_PARMS,
+ __TCA_ETF_MAX,
+};
+
+#define TCA_ETF_MAX (__TCA_ETF_MAX - 1)
+
+
+/* CAKE */
+enum {
+ TCA_CAKE_UNSPEC,
+ TCA_CAKE_PAD,
+ TCA_CAKE_BASE_RATE64,
+ TCA_CAKE_DIFFSERV_MODE,
+ TCA_CAKE_ATM,
+ TCA_CAKE_FLOW_MODE,
+ TCA_CAKE_OVERHEAD,
+ TCA_CAKE_RTT,
+ TCA_CAKE_TARGET,
+ TCA_CAKE_AUTORATE,
+ TCA_CAKE_MEMORY,
+ TCA_CAKE_NAT,
+ TCA_CAKE_RAW,
+ TCA_CAKE_WASH,
+ TCA_CAKE_MPU,
+ TCA_CAKE_INGRESS,
+ TCA_CAKE_ACK_FILTER,
+ TCA_CAKE_SPLIT_GSO,
+ __TCA_CAKE_MAX
+};
+#define TCA_CAKE_MAX (__TCA_CAKE_MAX - 1)
+
+enum {
+ __TCA_CAKE_STATS_INVALID,
+ TCA_CAKE_STATS_PAD,
+ TCA_CAKE_STATS_CAPACITY_ESTIMATE64,
+ TCA_CAKE_STATS_MEMORY_LIMIT,
+ TCA_CAKE_STATS_MEMORY_USED,
+ TCA_CAKE_STATS_AVG_NETOFF,
+ TCA_CAKE_STATS_MIN_NETLEN,
+ TCA_CAKE_STATS_MAX_NETLEN,
+ TCA_CAKE_STATS_MIN_ADJLEN,
+ TCA_CAKE_STATS_MAX_ADJLEN,
+ TCA_CAKE_STATS_TIN_STATS,
+ TCA_CAKE_STATS_DEFICIT,
+ TCA_CAKE_STATS_COBALT_COUNT,
+ TCA_CAKE_STATS_DROPPING,
+ TCA_CAKE_STATS_DROP_NEXT_US,
+ TCA_CAKE_STATS_P_DROP,
+ TCA_CAKE_STATS_BLUE_TIMER_US,
+ __TCA_CAKE_STATS_MAX
+};
+#define TCA_CAKE_STATS_MAX (__TCA_CAKE_STATS_MAX - 1)
+
+enum {
+ __TCA_CAKE_TIN_STATS_INVALID,
+ TCA_CAKE_TIN_STATS_PAD,
+ TCA_CAKE_TIN_STATS_SENT_PACKETS,
+ TCA_CAKE_TIN_STATS_SENT_BYTES64,
+ TCA_CAKE_TIN_STATS_DROPPED_PACKETS,
+ TCA_CAKE_TIN_STATS_DROPPED_BYTES64,
+ TCA_CAKE_TIN_STATS_ACKS_DROPPED_PACKETS,
+ TCA_CAKE_TIN_STATS_ACKS_DROPPED_BYTES64,
+ TCA_CAKE_TIN_STATS_ECN_MARKED_PACKETS,
+ TCA_CAKE_TIN_STATS_ECN_MARKED_BYTES64,
+ TCA_CAKE_TIN_STATS_BACKLOG_PACKETS,
+ TCA_CAKE_TIN_STATS_BACKLOG_BYTES,
+ TCA_CAKE_TIN_STATS_THRESHOLD_RATE64,
+ TCA_CAKE_TIN_STATS_TARGET_US,
+ TCA_CAKE_TIN_STATS_INTERVAL_US,
+ TCA_CAKE_TIN_STATS_WAY_INDIRECT_HITS,
+ TCA_CAKE_TIN_STATS_WAY_MISSES,
+ TCA_CAKE_TIN_STATS_WAY_COLLISIONS,
+ TCA_CAKE_TIN_STATS_PEAK_DELAY_US,
+ TCA_CAKE_TIN_STATS_AVG_DELAY_US,
+ TCA_CAKE_TIN_STATS_BASE_DELAY_US,
+ TCA_CAKE_TIN_STATS_SPARSE_FLOWS,
+ TCA_CAKE_TIN_STATS_BULK_FLOWS,
+ TCA_CAKE_TIN_STATS_UNRESPONSIVE_FLOWS,
+ TCA_CAKE_TIN_STATS_MAX_SKBLEN,
+ TCA_CAKE_TIN_STATS_FLOW_QUANTUM,
+ __TCA_CAKE_TIN_STATS_MAX
+};
+#define TCA_CAKE_TIN_STATS_MAX (__TCA_CAKE_TIN_STATS_MAX - 1)
+#define TC_CAKE_MAX_TINS (8)
+
+enum {
+ CAKE_FLOW_NONE = 0,
+ CAKE_FLOW_SRC_IP,
+ CAKE_FLOW_DST_IP,
+ CAKE_FLOW_HOSTS, /* = CAKE_FLOW_SRC_IP | CAKE_FLOW_DST_IP */
+ CAKE_FLOW_FLOWS,
+ CAKE_FLOW_DUAL_SRC, /* = CAKE_FLOW_SRC_IP | CAKE_FLOW_FLOWS */
+ CAKE_FLOW_DUAL_DST, /* = CAKE_FLOW_DST_IP | CAKE_FLOW_FLOWS */
+ CAKE_FLOW_TRIPLE, /* = CAKE_FLOW_HOSTS | CAKE_FLOW_FLOWS */
+ CAKE_FLOW_MAX,
+};
+
+enum {
+ CAKE_DIFFSERV_DIFFSERV3 = 0,
+ CAKE_DIFFSERV_DIFFSERV4,
+ CAKE_DIFFSERV_DIFFSERV8,
+ CAKE_DIFFSERV_BESTEFFORT,
+ CAKE_DIFFSERV_PRECEDENCE,
+ CAKE_DIFFSERV_MAX
+};
+
+enum {
+ CAKE_ACK_NONE = 0,
+ CAKE_ACK_FILTER,
+ CAKE_ACK_AGGRESSIVE,
+ CAKE_ACK_MAX
+};
+
+enum {
+ CAKE_ATM_NONE = 0,
+ CAKE_ATM_ATM,
+ CAKE_ATM_PTM,
+ CAKE_ATM_MAX
+};
+
+
+/* TAPRIO */
+enum {
+ TC_TAPRIO_CMD_SET_GATES = 0x00,
+ TC_TAPRIO_CMD_SET_AND_HOLD = 0x01,
+ TC_TAPRIO_CMD_SET_AND_RELEASE = 0x02,
+};
+
+enum {
+ TCA_TAPRIO_SCHED_ENTRY_UNSPEC,
+ TCA_TAPRIO_SCHED_ENTRY_INDEX, /* u32 */
+ TCA_TAPRIO_SCHED_ENTRY_CMD, /* u8 */
+ TCA_TAPRIO_SCHED_ENTRY_GATE_MASK, /* u32 */
+ TCA_TAPRIO_SCHED_ENTRY_INTERVAL, /* u32 */
+ __TCA_TAPRIO_SCHED_ENTRY_MAX,
+};
+#define TCA_TAPRIO_SCHED_ENTRY_MAX (__TCA_TAPRIO_SCHED_ENTRY_MAX - 1)
+
+/* The format for schedule entry list is:
+ * [TCA_TAPRIO_SCHED_ENTRY_LIST]
+ * [TCA_TAPRIO_SCHED_ENTRY]
+ * [TCA_TAPRIO_SCHED_ENTRY_CMD]
+ * [TCA_TAPRIO_SCHED_ENTRY_GATES]
+ * [TCA_TAPRIO_SCHED_ENTRY_INTERVAL]
+ */
+enum {
+ TCA_TAPRIO_SCHED_UNSPEC,
+ TCA_TAPRIO_SCHED_ENTRY,
+ __TCA_TAPRIO_SCHED_MAX,
+};
+
+#define TCA_TAPRIO_SCHED_MAX (__TCA_TAPRIO_SCHED_MAX - 1)
+
+enum {
+ TCA_TAPRIO_ATTR_UNSPEC,
+ TCA_TAPRIO_ATTR_PRIOMAP, /* struct tc_mqprio_qopt */
+ TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST, /* nested of entry */
+ TCA_TAPRIO_ATTR_SCHED_BASE_TIME, /* s64 */
+ TCA_TAPRIO_ATTR_SCHED_SINGLE_ENTRY, /* single entry */
+ TCA_TAPRIO_ATTR_SCHED_CLOCKID, /* s32 */
+ TCA_TAPRIO_PAD,
+ __TCA_TAPRIO_ATTR_MAX,
+};
+
+#define TCA_TAPRIO_ATTR_MAX (__TCA_TAPRIO_ATTR_MAX - 1)
+
+#endif
diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h
new file mode 100644
index 0000000000..370ed14b1a
--- /dev/null
+++ b/tools/include/uapi/linux/prctl.h
@@ -0,0 +1,309 @@
+/* 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
+
+/*
+ * No longer implemented, but left here to ensure the numbers stay reserved:
+ */
+#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
+# define PR_SPEC_L1D_FLUSH 2
+/* 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)
+# define PR_SPEC_DISABLE_NOEXEC (1UL << 4)
+
+/* Reset arm64 pointer authentication keys */
+#define PR_PAC_RESET_KEYS 54
+# define PR_PAC_APIAKEY (1UL << 0)
+# define PR_PAC_APIBKEY (1UL << 1)
+# define PR_PAC_APDAKEY (1UL << 2)
+# define PR_PAC_APDBKEY (1UL << 3)
+# define PR_PAC_APGAKEY (1UL << 4)
+
+/* Tagged user address controls for arm64 */
+#define PR_SET_TAGGED_ADDR_CTRL 55
+#define PR_GET_TAGGED_ADDR_CTRL 56
+# define PR_TAGGED_ADDR_ENABLE (1UL << 0)
+/* MTE tag check fault modes */
+# define PR_MTE_TCF_NONE 0UL
+# define PR_MTE_TCF_SYNC (1UL << 1)
+# define PR_MTE_TCF_ASYNC (1UL << 2)
+# define PR_MTE_TCF_MASK (PR_MTE_TCF_SYNC | PR_MTE_TCF_ASYNC)
+/* MTE tag inclusion mask */
+# define PR_MTE_TAG_SHIFT 3
+# define PR_MTE_TAG_MASK (0xffffUL << PR_MTE_TAG_SHIFT)
+/* Unused; kept only for source compatibility */
+# define PR_MTE_TCF_SHIFT 1
+
+/* Control reclaim behavior when allocating memory */
+#define PR_SET_IO_FLUSHER 57
+#define PR_GET_IO_FLUSHER 58
+
+/* Dispatch syscalls to a userspace handler */
+#define PR_SET_SYSCALL_USER_DISPATCH 59
+# define PR_SYS_DISPATCH_OFF 0
+# define PR_SYS_DISPATCH_ON 1
+/* The control values for the user space selector when dispatch is enabled */
+# define SYSCALL_DISPATCH_FILTER_ALLOW 0
+# define SYSCALL_DISPATCH_FILTER_BLOCK 1
+
+/* Set/get enabled arm64 pointer authentication keys */
+#define PR_PAC_SET_ENABLED_KEYS 60
+#define PR_PAC_GET_ENABLED_KEYS 61
+
+/* Request the scheduler to share a core */
+#define PR_SCHED_CORE 62
+# define PR_SCHED_CORE_GET 0
+# define PR_SCHED_CORE_CREATE 1 /* create unique core_sched cookie */
+# define PR_SCHED_CORE_SHARE_TO 2 /* push core_sched cookie to pid */
+# define PR_SCHED_CORE_SHARE_FROM 3 /* pull core_sched cookie to pid */
+# define PR_SCHED_CORE_MAX 4
+# define PR_SCHED_CORE_SCOPE_THREAD 0
+# define PR_SCHED_CORE_SCOPE_THREAD_GROUP 1
+# define PR_SCHED_CORE_SCOPE_PROCESS_GROUP 2
+
+/* arm64 Scalable Matrix Extension controls */
+/* Flag values must be in sync with SVE versions */
+#define PR_SME_SET_VL 63 /* set task vector length */
+# define PR_SME_SET_VL_ONEXEC (1 << 18) /* defer effect until exec */
+#define PR_SME_GET_VL 64 /* get task vector length */
+/* Bits common to PR_SME_SET_VL and PR_SME_GET_VL */
+# define PR_SME_VL_LEN_MASK 0xffff
+# define PR_SME_VL_INHERIT (1 << 17) /* inherit across exec */
+
+/* Memory deny write / execute */
+#define PR_SET_MDWE 65
+# define PR_MDWE_REFUSE_EXEC_GAIN (1UL << 0)
+# define PR_MDWE_NO_INHERIT (1UL << 1)
+
+#define PR_GET_MDWE 66
+
+#define PR_SET_VMA 0x53564d41
+# define PR_SET_VMA_ANON_NAME 0
+
+#define PR_GET_AUXV 0x41555856
+
+#define PR_SET_MEMORY_MERGE 67
+#define PR_GET_MEMORY_MERGE 68
+
+#define PR_RISCV_V_SET_CONTROL 69
+#define PR_RISCV_V_GET_CONTROL 70
+# define PR_RISCV_V_VSTATE_CTRL_DEFAULT 0
+# define PR_RISCV_V_VSTATE_CTRL_OFF 1
+# define PR_RISCV_V_VSTATE_CTRL_ON 2
+# define PR_RISCV_V_VSTATE_CTRL_INHERIT (1 << 4)
+# define PR_RISCV_V_VSTATE_CTRL_CUR_MASK 0x3
+# define PR_RISCV_V_VSTATE_CTRL_NEXT_MASK 0xc
+# define PR_RISCV_V_VSTATE_CTRL_MASK 0x1f
+
+#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 0000000000..3bac0a8cea
--- /dev/null
+++ b/tools/include/uapi/linux/sched.h
@@ -0,0 +1,148 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_LINUX_SCHED_H
+#define _UAPI_LINUX_SCHED_H
+
+#include <linux/types.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_PIDFD 0x00001000 /* set if a pidfd should be placed in parent */
+#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 */
+
+/* Flags for the clone3() syscall. */
+#define CLONE_CLEAR_SIGHAND 0x100000000ULL /* Clear any signal handler and reset to SIG_DFL. */
+#define CLONE_INTO_CGROUP 0x200000000ULL /* Clone into a specific cgroup given the right permissions. */
+
+/*
+ * cloning flags intersect with CSIGNAL so can be used with unshare and clone3
+ * syscalls only:
+ */
+#define CLONE_NEWTIME 0x00000080 /* New time namespace */
+
+#ifndef __ASSEMBLY__
+/**
+ * struct clone_args - arguments for the clone3 syscall
+ * @flags: Flags for the new process as listed above.
+ * All flags are valid except for CSIGNAL and
+ * CLONE_DETACHED.
+ * @pidfd: If CLONE_PIDFD is set, a pidfd will be
+ * returned in this argument.
+ * @child_tid: If CLONE_CHILD_SETTID is set, the TID of the
+ * child process will be returned in the child's
+ * memory.
+ * @parent_tid: If CLONE_PARENT_SETTID is set, the TID of
+ * the child process will be returned in the
+ * parent's memory.
+ * @exit_signal: The exit_signal the parent process will be
+ * sent when the child exits.
+ * @stack: Specify the location of the stack for the
+ * child process.
+ * Note, @stack is expected to point to the
+ * lowest address. The stack direction will be
+ * determined by the kernel and set up
+ * appropriately based on @stack_size.
+ * @stack_size: The size of the stack for the child process.
+ * @tls: If CLONE_SETTLS is set, the tls descriptor
+ * is set to tls.
+ * @set_tid: Pointer to an array of type *pid_t. The size
+ * of the array is defined using @set_tid_size.
+ * This array is used to select PIDs/TIDs for
+ * newly created processes. The first element in
+ * this defines the PID in the most nested PID
+ * namespace. Each additional element in the array
+ * defines the PID in the parent PID namespace of
+ * the original PID namespace. If the array has
+ * less entries than the number of currently
+ * nested PID namespaces only the PIDs in the
+ * corresponding namespaces are set.
+ * @set_tid_size: This defines the size of the array referenced
+ * in @set_tid. This cannot be larger than the
+ * kernel's limit of nested PID namespaces.
+ * @cgroup: If CLONE_INTO_CGROUP is specified set this to
+ * a file descriptor for the cgroup.
+ *
+ * The structure is versioned by size and thus extensible.
+ * New struct members must go at the end of the struct and
+ * must be properly 64bit aligned.
+ */
+struct clone_args {
+ __aligned_u64 flags;
+ __aligned_u64 pidfd;
+ __aligned_u64 child_tid;
+ __aligned_u64 parent_tid;
+ __aligned_u64 exit_signal;
+ __aligned_u64 stack;
+ __aligned_u64 stack_size;
+ __aligned_u64 tls;
+ __aligned_u64 set_tid;
+ __aligned_u64 set_tid_size;
+ __aligned_u64 cgroup;
+};
+#endif
+
+#define CLONE_ARGS_SIZE_VER0 64 /* sizeof first published struct */
+#define CLONE_ARGS_SIZE_VER1 80 /* sizeof second published struct */
+#define CLONE_ARGS_SIZE_VER2 88 /* sizeof third published struct */
+
+/*
+ * 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_KEEP_POLICY 0x08
+#define SCHED_FLAG_KEEP_PARAMS 0x10
+#define SCHED_FLAG_UTIL_CLAMP_MIN 0x20
+#define SCHED_FLAG_UTIL_CLAMP_MAX 0x40
+
+#define SCHED_FLAG_KEEP_ALL (SCHED_FLAG_KEEP_POLICY | \
+ SCHED_FLAG_KEEP_PARAMS)
+
+#define SCHED_FLAG_UTIL_CLAMP (SCHED_FLAG_UTIL_CLAMP_MIN | \
+ SCHED_FLAG_UTIL_CLAMP_MAX)
+
+#define SCHED_FLAG_ALL (SCHED_FLAG_RESET_ON_FORK | \
+ SCHED_FLAG_RECLAIM | \
+ SCHED_FLAG_DL_OVERRUN | \
+ SCHED_FLAG_KEEP_ALL | \
+ SCHED_FLAG_UTIL_CLAMP)
+
+#endif /* _UAPI_LINUX_SCHED_H */
diff --git a/tools/include/uapi/linux/seccomp.h b/tools/include/uapi/linux/seccomp.h
new file mode 100644
index 0000000000..dbfc9b37fc
--- /dev/null
+++ b/tools/include/uapi/linux/seccomp.h
@@ -0,0 +1,157 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_LINUX_SECCOMP_H
+#define _UAPI_LINUX_SECCOMP_H
+
+#include <linux/compiler.h>
+#include <linux/types.h>
+
+
+/* Valid values for seccomp.mode and prctl(PR_SET_SECCOMP, <mode>) */
+#define SECCOMP_MODE_DISABLED 0 /* seccomp is not in use. */
+#define SECCOMP_MODE_STRICT 1 /* uses hard-coded filter. */
+#define SECCOMP_MODE_FILTER 2 /* uses user-supplied filter. */
+
+/* Valid operations for seccomp syscall. */
+#define SECCOMP_SET_MODE_STRICT 0
+#define SECCOMP_SET_MODE_FILTER 1
+#define SECCOMP_GET_ACTION_AVAIL 2
+#define SECCOMP_GET_NOTIF_SIZES 3
+
+/* Valid flags for SECCOMP_SET_MODE_FILTER */
+#define SECCOMP_FILTER_FLAG_TSYNC (1UL << 0)
+#define SECCOMP_FILTER_FLAG_LOG (1UL << 1)
+#define SECCOMP_FILTER_FLAG_SPEC_ALLOW (1UL << 2)
+#define SECCOMP_FILTER_FLAG_NEW_LISTENER (1UL << 3)
+#define SECCOMP_FILTER_FLAG_TSYNC_ESRCH (1UL << 4)
+/* Received notifications wait in killable state (only respond to fatal signals) */
+#define SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV (1UL << 5)
+
+/*
+ * All BPF programs must return a 32-bit value.
+ * The bottom 16-bits are for optional return data.
+ * The upper 16-bits are ordered from least permissive values to most,
+ * as a signed value (so 0x8000000 is negative).
+ *
+ * The ordering ensures that a min_t() over composed return values always
+ * selects the least permissive choice.
+ */
+#define SECCOMP_RET_KILL_PROCESS 0x80000000U /* kill the process */
+#define SECCOMP_RET_KILL_THREAD 0x00000000U /* kill the thread */
+#define SECCOMP_RET_KILL SECCOMP_RET_KILL_THREAD
+#define SECCOMP_RET_TRAP 0x00030000U /* disallow and force a SIGSYS */
+#define SECCOMP_RET_ERRNO 0x00050000U /* returns an errno */
+#define SECCOMP_RET_USER_NOTIF 0x7fc00000U /* notifies userspace */
+#define SECCOMP_RET_TRACE 0x7ff00000U /* pass to a tracer or disallow */
+#define SECCOMP_RET_LOG 0x7ffc0000U /* allow after logging */
+#define SECCOMP_RET_ALLOW 0x7fff0000U /* allow */
+
+/* Masks for the return value sections. */
+#define SECCOMP_RET_ACTION_FULL 0xffff0000U
+#define SECCOMP_RET_ACTION 0x7fff0000U
+#define SECCOMP_RET_DATA 0x0000ffffU
+
+/**
+ * struct seccomp_data - the format the BPF program executes over.
+ * @nr: the system call number
+ * @arch: indicates system call convention as an AUDIT_ARCH_* value
+ * as defined in <linux/audit.h>.
+ * @instruction_pointer: at the time of the system call.
+ * @args: up to 6 system call arguments always stored as 64-bit values
+ * regardless of the architecture.
+ */
+struct seccomp_data {
+ int nr;
+ __u32 arch;
+ __u64 instruction_pointer;
+ __u64 args[6];
+};
+
+struct seccomp_notif_sizes {
+ __u16 seccomp_notif;
+ __u16 seccomp_notif_resp;
+ __u16 seccomp_data;
+};
+
+struct seccomp_notif {
+ __u64 id;
+ __u32 pid;
+ __u32 flags;
+ struct seccomp_data data;
+};
+
+/*
+ * Valid flags for struct seccomp_notif_resp
+ *
+ * Note, the SECCOMP_USER_NOTIF_FLAG_CONTINUE flag must be used with caution!
+ * If set by the process supervising the syscalls of another process the
+ * syscall will continue. This is problematic because of an inherent TOCTOU.
+ * An attacker can exploit the time while the supervised process is waiting on
+ * a response from the supervising process to rewrite syscall arguments which
+ * are passed as pointers of the intercepted syscall.
+ * It should be absolutely clear that this means that the seccomp notifier
+ * _cannot_ be used to implement a security policy! It should only ever be used
+ * in scenarios where a more privileged process supervises the syscalls of a
+ * lesser privileged process to get around kernel-enforced security
+ * restrictions when the privileged process deems this safe. In other words,
+ * in order to continue a syscall the supervising process should be sure that
+ * another security mechanism or the kernel itself will sufficiently block
+ * syscalls if arguments are rewritten to something unsafe.
+ *
+ * Similar precautions should be applied when stacking SECCOMP_RET_USER_NOTIF
+ * or SECCOMP_RET_TRACE. For SECCOMP_RET_USER_NOTIF filters acting on the
+ * same syscall, the most recently added filter takes precedence. This means
+ * that the new SECCOMP_RET_USER_NOTIF filter can override any
+ * SECCOMP_IOCTL_NOTIF_SEND from earlier filters, essentially allowing all
+ * such filtered syscalls to be executed by sending the response
+ * SECCOMP_USER_NOTIF_FLAG_CONTINUE. Note that SECCOMP_RET_TRACE can equally
+ * be overriden by SECCOMP_USER_NOTIF_FLAG_CONTINUE.
+ */
+#define SECCOMP_USER_NOTIF_FLAG_CONTINUE (1UL << 0)
+
+struct seccomp_notif_resp {
+ __u64 id;
+ __s64 val;
+ __s32 error;
+ __u32 flags;
+};
+
+#define SECCOMP_USER_NOTIF_FD_SYNC_WAKE_UP (1UL << 0)
+
+/* valid flags for seccomp_notif_addfd */
+#define SECCOMP_ADDFD_FLAG_SETFD (1UL << 0) /* Specify remote fd */
+#define SECCOMP_ADDFD_FLAG_SEND (1UL << 1) /* Addfd and return it, atomically */
+
+/**
+ * struct seccomp_notif_addfd
+ * @id: The ID of the seccomp notification
+ * @flags: SECCOMP_ADDFD_FLAG_*
+ * @srcfd: The local fd number
+ * @newfd: Optional remote FD number if SETFD option is set, otherwise 0.
+ * @newfd_flags: The O_* flags the remote FD should have applied
+ */
+struct seccomp_notif_addfd {
+ __u64 id;
+ __u32 flags;
+ __u32 srcfd;
+ __u32 newfd;
+ __u32 newfd_flags;
+};
+
+#define SECCOMP_IOC_MAGIC '!'
+#define SECCOMP_IO(nr) _IO(SECCOMP_IOC_MAGIC, nr)
+#define SECCOMP_IOR(nr, type) _IOR(SECCOMP_IOC_MAGIC, nr, type)
+#define SECCOMP_IOW(nr, type) _IOW(SECCOMP_IOC_MAGIC, nr, type)
+#define SECCOMP_IOWR(nr, type) _IOWR(SECCOMP_IOC_MAGIC, nr, type)
+
+/* Flags for seccomp notification fd ioctl. */
+#define SECCOMP_IOCTL_NOTIF_RECV SECCOMP_IOWR(0, struct seccomp_notif)
+#define SECCOMP_IOCTL_NOTIF_SEND SECCOMP_IOWR(1, \
+ struct seccomp_notif_resp)
+#define SECCOMP_IOCTL_NOTIF_ID_VALID SECCOMP_IOW(2, __u64)
+/* On success, the return value is the remote process's added fd number */
+#define SECCOMP_IOCTL_NOTIF_ADDFD SECCOMP_IOW(3, \
+ struct seccomp_notif_addfd)
+
+#define SECCOMP_IOCTL_NOTIF_SET_FLAGS SECCOMP_IOW(4, __u64)
+
+#endif /* _UAPI_LINUX_SECCOMP_H */
diff --git a/tools/include/uapi/linux/seg6.h b/tools/include/uapi/linux/seg6.h
new file mode 100644
index 0000000000..f94baf154c
--- /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[];
+};
+
+#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[];
+};
+
+#endif
diff --git a/tools/include/uapi/linux/seg6_local.h b/tools/include/uapi/linux/seg6_local.h
new file mode 100644
index 0000000000..edc138bdc5
--- /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 0000000000..7cab2c65d3
--- /dev/null
+++ b/tools/include/uapi/linux/stat.h
@@ -0,0 +1,194 @@
+/* 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 stx_mnt_id;
+ __u32 stx_dio_mem_align; /* Memory buffer alignment for direct I/O */
+ __u32 stx_dio_offset_align; /* File offset alignment for direct I/O */
+ /* 0xa0 */
+ __u64 __spare3[12]; /* 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_MNT_ID 0x00001000U /* Got stx_mnt_id */
+#define STATX_DIOALIGN 0x00002000U /* Want/got direct I/O alignment info */
+
+#define STATX__RESERVED 0x80000000U /* Reserved for future struct statx expansion */
+
+#ifndef __KERNEL__
+/*
+ * This is deprecated, and shall remain the same value in the future. To avoid
+ * confusion please use the equivalent (STATX_BASIC_STATS | STATX_BTIME)
+ * instead.
+ */
+#define STATX_ALL 0x00000fffU
+#endif
+
+/*
+ * 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 the FS_IOC_SETFLAGS flags
+ * semantically. Where possible, the numerical value is picked to correspond
+ * also. Note that the DAX attribute indicates that the file is in the CPU
+ * direct access state. It does not correspond to the per-inode flag that
+ * some filesystems support.
+ *
+ */
+#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 */
+#define STATX_ATTR_MOUNT_ROOT 0x00002000 /* Root of a mount */
+#define STATX_ATTR_VERITY 0x00100000 /* [I] Verity protected file */
+#define STATX_ATTR_DAX 0x00200000 /* File is currently in DAX state */
+
+
+#endif /* _UAPI_LINUX_STAT_H */
diff --git a/tools/include/uapi/linux/stddef.h b/tools/include/uapi/linux/stddef.h
new file mode 100644
index 0000000000..bb6ea517ef
--- /dev/null
+++ b/tools/include/uapi/linux/stddef.h
@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _LINUX_STDDEF_H
+#define _LINUX_STDDEF_H
+
+
+
+#ifndef __always_inline
+#define __always_inline __inline__
+#endif
+
+/**
+ * __struct_group() - Create a mirrored named and anonyomous struct
+ *
+ * @TAG: The tag name for the named sub-struct (usually empty)
+ * @NAME: The identifier name of the mirrored sub-struct
+ * @ATTRS: Any struct attributes (usually empty)
+ * @MEMBERS: The member declarations for the mirrored structs
+ *
+ * Used to create an anonymous union of two structs with identical layout
+ * and size: one anonymous and one named. The former's members can be used
+ * normally without sub-struct naming, and the latter can be used to
+ * reason about the start, end, and size of the group of struct members.
+ * The named struct can also be explicitly tagged for layer reuse, as well
+ * as both having struct attributes appended.
+ */
+#define __struct_group(TAG, NAME, ATTRS, MEMBERS...) \
+ union { \
+ struct { MEMBERS } ATTRS; \
+ struct TAG { MEMBERS } ATTRS NAME; \
+ }
+
+/**
+ * __DECLARE_FLEX_ARRAY() - Declare a flexible array usable in a union
+ *
+ * @TYPE: The type of each flexible array element
+ * @NAME: The name of the flexible array member
+ *
+ * In order to have a flexible array member in a union or alone in a
+ * struct, it needs to be wrapped in an anonymous struct with at least 1
+ * named member, but that member can be empty.
+ */
+#define __DECLARE_FLEX_ARRAY(TYPE, NAME) \
+ struct { \
+ struct { } __empty_ ## NAME; \
+ TYPE NAME[]; \
+ }
+#endif
diff --git a/tools/include/uapi/linux/tc_act/tc_bpf.h b/tools/include/uapi/linux/tc_act/tc_bpf.h
new file mode 100644
index 0000000000..fe6c8f8f3e
--- /dev/null
+++ b/tools/include/uapi/linux/tc_act/tc_bpf.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ * Copyright (c) 2015 Jiri Pirko <jiri@resnulli.us>
+ */
+
+#ifndef __LINUX_TC_BPF_H
+#define __LINUX_TC_BPF_H
+
+#include <linux/pkt_cls.h>
+
+struct tc_act_bpf {
+ tc_gen;
+};
+
+enum {
+ TCA_ACT_BPF_UNSPEC,
+ TCA_ACT_BPF_TM,
+ TCA_ACT_BPF_PARMS,
+ TCA_ACT_BPF_OPS_LEN,
+ TCA_ACT_BPF_OPS,
+ TCA_ACT_BPF_FD,
+ TCA_ACT_BPF_NAME,
+ TCA_ACT_BPF_PAD,
+ TCA_ACT_BPF_TAG,
+ TCA_ACT_BPF_ID,
+ __TCA_ACT_BPF_MAX,
+};
+#define TCA_ACT_BPF_MAX (__TCA_ACT_BPF_MAX - 1)
+
+#endif
diff --git a/tools/include/uapi/linux/tcp.h b/tools/include/uapi/linux/tcp.h
new file mode 100644
index 0000000000..13ceeb395e
--- /dev/null
+++ b/tools/include/uapi/linux/tcp.h
@@ -0,0 +1,357 @@
+/* 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 for the TCP protocol.
+ *
+ * Version: @(#)tcp.h 1.0.2 04/28/93
+ *
+ * Author: 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_TCP_H
+#define _UAPI_LINUX_TCP_H
+
+#include <linux/types.h>
+#include <asm/byteorder.h>
+#include <linux/socket.h>
+
+struct tcphdr {
+ __be16 source;
+ __be16 dest;
+ __be32 seq;
+ __be32 ack_seq;
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+ __u16 res1:4,
+ doff:4,
+ fin:1,
+ syn:1,
+ rst:1,
+ psh:1,
+ ack:1,
+ urg:1,
+ ece:1,
+ cwr:1;
+#elif defined(__BIG_ENDIAN_BITFIELD)
+ __u16 doff:4,
+ res1:4,
+ cwr:1,
+ ece:1,
+ urg:1,
+ ack:1,
+ psh:1,
+ rst:1,
+ syn:1,
+ fin:1;
+#else
+#error "Adjust your <asm/byteorder.h> defines"
+#endif
+ __be16 window;
+ __sum16 check;
+ __be16 urg_ptr;
+};
+
+/*
+ * The union cast uses a gcc extension to avoid aliasing problems
+ * (union is compatible to any of its members)
+ * This means this part of the code is -fstrict-aliasing safe now.
+ */
+union tcp_word_hdr {
+ struct tcphdr hdr;
+ __be32 words[5];
+};
+
+#define tcp_flag_word(tp) ( ((union tcp_word_hdr *)(tp))->words [3])
+
+enum {
+ TCP_FLAG_CWR = __constant_cpu_to_be32(0x00800000),
+ TCP_FLAG_ECE = __constant_cpu_to_be32(0x00400000),
+ TCP_FLAG_URG = __constant_cpu_to_be32(0x00200000),
+ TCP_FLAG_ACK = __constant_cpu_to_be32(0x00100000),
+ TCP_FLAG_PSH = __constant_cpu_to_be32(0x00080000),
+ TCP_FLAG_RST = __constant_cpu_to_be32(0x00040000),
+ TCP_FLAG_SYN = __constant_cpu_to_be32(0x00020000),
+ TCP_FLAG_FIN = __constant_cpu_to_be32(0x00010000),
+ TCP_RESERVED_BITS = __constant_cpu_to_be32(0x0F000000),
+ TCP_DATA_OFFSET = __constant_cpu_to_be32(0xF0000000)
+};
+
+/*
+ * TCP general constants
+ */
+#define TCP_MSS_DEFAULT 536U /* IPv4 (RFC1122, RFC2581) */
+#define TCP_MSS_DESIRED 1220U /* IPv6 (tunneled), EDNS0 (RFC3226) */
+
+/* TCP socket options */
+#define TCP_NODELAY 1 /* Turn off Nagle's algorithm. */
+#define TCP_MAXSEG 2 /* Limit MSS */
+#define TCP_CORK 3 /* Never send partially complete segments */
+#define TCP_KEEPIDLE 4 /* Start keeplives after this period */
+#define TCP_KEEPINTVL 5 /* Interval between keepalives */
+#define TCP_KEEPCNT 6 /* Number of keepalives before death */
+#define TCP_SYNCNT 7 /* Number of SYN retransmits */
+#define TCP_LINGER2 8 /* Life time of orphaned FIN-WAIT-2 state */
+#define TCP_DEFER_ACCEPT 9 /* Wake up listener only when data arrive */
+#define TCP_WINDOW_CLAMP 10 /* Bound advertised window */
+#define TCP_INFO 11 /* Information about this connection. */
+#define TCP_QUICKACK 12 /* Block/reenable quick acks */
+#define TCP_CONGESTION 13 /* Congestion control algorithm */
+#define TCP_MD5SIG 14 /* TCP MD5 Signature (RFC2385) */
+#define TCP_THIN_LINEAR_TIMEOUTS 16 /* Use linear timeouts for thin streams*/
+#define TCP_THIN_DUPACK 17 /* Fast retrans. after 1 dupack */
+#define TCP_USER_TIMEOUT 18 /* How long for loss retry before timeout */
+#define TCP_REPAIR 19 /* TCP sock is under repair right now */
+#define TCP_REPAIR_QUEUE 20
+#define TCP_QUEUE_SEQ 21
+#define TCP_REPAIR_OPTIONS 22
+#define TCP_FASTOPEN 23 /* Enable FastOpen on listeners */
+#define TCP_TIMESTAMP 24
+#define TCP_NOTSENT_LOWAT 25 /* limit number of unsent bytes in write queue */
+#define TCP_CC_INFO 26 /* Get Congestion Control (optional) info */
+#define TCP_SAVE_SYN 27 /* Record SYN headers for new connections */
+#define TCP_SAVED_SYN 28 /* Get SYN headers recorded for connection */
+#define TCP_REPAIR_WINDOW 29 /* Get/set window parameters */
+#define TCP_FASTOPEN_CONNECT 30 /* Attempt FastOpen with connect */
+#define TCP_ULP 31 /* Attach a ULP to a TCP connection */
+#define TCP_MD5SIG_EXT 32 /* TCP MD5 Signature with extensions */
+#define TCP_FASTOPEN_KEY 33 /* Set the key for Fast Open (cookie) */
+#define TCP_FASTOPEN_NO_COOKIE 34 /* Enable TFO without a TFO cookie */
+#define TCP_ZEROCOPY_RECEIVE 35
+#define TCP_INQ 36 /* Notify bytes available to read as a cmsg on read */
+
+#define TCP_CM_INQ TCP_INQ
+
+#define TCP_TX_DELAY 37 /* delay outgoing packets by XX usec */
+
+
+#define TCP_REPAIR_ON 1
+#define TCP_REPAIR_OFF 0
+#define TCP_REPAIR_OFF_NO_WP -1 /* Turn off without window probes */
+
+struct tcp_repair_opt {
+ __u32 opt_code;
+ __u32 opt_val;
+};
+
+struct tcp_repair_window {
+ __u32 snd_wl1;
+ __u32 snd_wnd;
+ __u32 max_window;
+
+ __u32 rcv_wnd;
+ __u32 rcv_wup;
+};
+
+enum {
+ TCP_NO_QUEUE,
+ TCP_RECV_QUEUE,
+ TCP_SEND_QUEUE,
+ TCP_QUEUES_NR,
+};
+
+/* why fastopen failed from client perspective */
+enum tcp_fastopen_client_fail {
+ TFO_STATUS_UNSPEC, /* catch-all */
+ TFO_COOKIE_UNAVAILABLE, /* if not in TFO_CLIENT_NO_COOKIE mode */
+ TFO_DATA_NOT_ACKED, /* SYN-ACK did not ack SYN data */
+ TFO_SYN_RETRANSMITTED, /* SYN-ACK did not ack SYN data after timeout */
+};
+
+/* for TCP_INFO socket option */
+#define TCPI_OPT_TIMESTAMPS 1
+#define TCPI_OPT_SACK 2
+#define TCPI_OPT_WSCALE 4
+#define TCPI_OPT_ECN 8 /* ECN was negociated at TCP session init */
+#define TCPI_OPT_ECN_SEEN 16 /* we received at least one packet with ECT */
+#define TCPI_OPT_SYN_DATA 32 /* SYN-ACK acked data in SYN sent or rcvd */
+
+/*
+ * Sender's congestion state indicating normal or abnormal situations
+ * in the last round of packets sent. The state is driven by the ACK
+ * information and timer events.
+ */
+enum tcp_ca_state {
+ /*
+ * Nothing bad has been observed recently.
+ * No apparent reordering, packet loss, or ECN marks.
+ */
+ TCP_CA_Open = 0,
+#define TCPF_CA_Open (1<<TCP_CA_Open)
+ /*
+ * The sender enters disordered state when it has received DUPACKs or
+ * SACKs in the last round of packets sent. This could be due to packet
+ * loss or reordering but needs further information to confirm packets
+ * have been lost.
+ */
+ TCP_CA_Disorder = 1,
+#define TCPF_CA_Disorder (1<<TCP_CA_Disorder)
+ /*
+ * The sender enters Congestion Window Reduction (CWR) state when it
+ * has received ACKs with ECN-ECE marks, or has experienced congestion
+ * or packet discard on the sender host (e.g. qdisc).
+ */
+ TCP_CA_CWR = 2,
+#define TCPF_CA_CWR (1<<TCP_CA_CWR)
+ /*
+ * The sender is in fast recovery and retransmitting lost packets,
+ * typically triggered by ACK events.
+ */
+ TCP_CA_Recovery = 3,
+#define TCPF_CA_Recovery (1<<TCP_CA_Recovery)
+ /*
+ * The sender is in loss recovery triggered by retransmission timeout.
+ */
+ TCP_CA_Loss = 4
+#define TCPF_CA_Loss (1<<TCP_CA_Loss)
+};
+
+struct tcp_info {
+ __u8 tcpi_state;
+ __u8 tcpi_ca_state;
+ __u8 tcpi_retransmits;
+ __u8 tcpi_probes;
+ __u8 tcpi_backoff;
+ __u8 tcpi_options;
+ __u8 tcpi_snd_wscale : 4, tcpi_rcv_wscale : 4;
+ __u8 tcpi_delivery_rate_app_limited:1, tcpi_fastopen_client_fail:2;
+
+ __u32 tcpi_rto;
+ __u32 tcpi_ato;
+ __u32 tcpi_snd_mss;
+ __u32 tcpi_rcv_mss;
+
+ __u32 tcpi_unacked;
+ __u32 tcpi_sacked;
+ __u32 tcpi_lost;
+ __u32 tcpi_retrans;
+ __u32 tcpi_fackets;
+
+ /* Times. */
+ __u32 tcpi_last_data_sent;
+ __u32 tcpi_last_ack_sent; /* Not remembered, sorry. */
+ __u32 tcpi_last_data_recv;
+ __u32 tcpi_last_ack_recv;
+
+ /* Metrics. */
+ __u32 tcpi_pmtu;
+ __u32 tcpi_rcv_ssthresh;
+ __u32 tcpi_rtt;
+ __u32 tcpi_rttvar;
+ __u32 tcpi_snd_ssthresh;
+ __u32 tcpi_snd_cwnd;
+ __u32 tcpi_advmss;
+ __u32 tcpi_reordering;
+
+ __u32 tcpi_rcv_rtt;
+ __u32 tcpi_rcv_space;
+
+ __u32 tcpi_total_retrans;
+
+ __u64 tcpi_pacing_rate;
+ __u64 tcpi_max_pacing_rate;
+ __u64 tcpi_bytes_acked; /* RFC4898 tcpEStatsAppHCThruOctetsAcked */
+ __u64 tcpi_bytes_received; /* RFC4898 tcpEStatsAppHCThruOctetsReceived */
+ __u32 tcpi_segs_out; /* RFC4898 tcpEStatsPerfSegsOut */
+ __u32 tcpi_segs_in; /* RFC4898 tcpEStatsPerfSegsIn */
+
+ __u32 tcpi_notsent_bytes;
+ __u32 tcpi_min_rtt;
+ __u32 tcpi_data_segs_in; /* RFC4898 tcpEStatsDataSegsIn */
+ __u32 tcpi_data_segs_out; /* RFC4898 tcpEStatsDataSegsOut */
+
+ __u64 tcpi_delivery_rate;
+
+ __u64 tcpi_busy_time; /* Time (usec) busy sending data */
+ __u64 tcpi_rwnd_limited; /* Time (usec) limited by receive window */
+ __u64 tcpi_sndbuf_limited; /* Time (usec) limited by send buffer */
+
+ __u32 tcpi_delivered;
+ __u32 tcpi_delivered_ce;
+
+ __u64 tcpi_bytes_sent; /* RFC4898 tcpEStatsPerfHCDataOctetsOut */
+ __u64 tcpi_bytes_retrans; /* RFC4898 tcpEStatsPerfOctetsRetrans */
+ __u32 tcpi_dsack_dups; /* RFC4898 tcpEStatsStackDSACKDups */
+ __u32 tcpi_reord_seen; /* reordering events seen */
+
+ __u32 tcpi_rcv_ooopack; /* Out-of-order packets received */
+
+ __u32 tcpi_snd_wnd; /* peer's advertised receive window after
+ * scaling (bytes)
+ */
+};
+
+/* netlink attributes types for SCM_TIMESTAMPING_OPT_STATS */
+enum {
+ TCP_NLA_PAD,
+ TCP_NLA_BUSY, /* Time (usec) busy sending data */
+ TCP_NLA_RWND_LIMITED, /* Time (usec) limited by receive window */
+ TCP_NLA_SNDBUF_LIMITED, /* Time (usec) limited by send buffer */
+ TCP_NLA_DATA_SEGS_OUT, /* Data pkts sent including retransmission */
+ TCP_NLA_TOTAL_RETRANS, /* Data pkts retransmitted */
+ TCP_NLA_PACING_RATE, /* Pacing rate in bytes per second */
+ TCP_NLA_DELIVERY_RATE, /* Delivery rate in bytes per second */
+ TCP_NLA_SND_CWND, /* Sending congestion window */
+ TCP_NLA_REORDERING, /* Reordering metric */
+ TCP_NLA_MIN_RTT, /* minimum RTT */
+ TCP_NLA_RECUR_RETRANS, /* Recurring retransmits for the current pkt */
+ TCP_NLA_DELIVERY_RATE_APP_LMT, /* delivery rate application limited ? */
+ TCP_NLA_SNDQ_SIZE, /* Data (bytes) pending in send queue */
+ TCP_NLA_CA_STATE, /* ca_state of socket */
+ TCP_NLA_SND_SSTHRESH, /* Slow start size threshold */
+ TCP_NLA_DELIVERED, /* Data pkts delivered incl. out-of-order */
+ TCP_NLA_DELIVERED_CE, /* Like above but only ones w/ CE marks */
+ TCP_NLA_BYTES_SENT, /* Data bytes sent including retransmission */
+ TCP_NLA_BYTES_RETRANS, /* Data bytes retransmitted */
+ TCP_NLA_DSACK_DUPS, /* DSACK blocks received */
+ TCP_NLA_REORD_SEEN, /* reordering events seen */
+ TCP_NLA_SRTT, /* smoothed RTT in usecs */
+ TCP_NLA_TIMEOUT_REHASH, /* Timeout-triggered rehash attempts */
+ TCP_NLA_BYTES_NOTSENT, /* Bytes in write queue not yet sent */
+ TCP_NLA_EDT, /* Earliest departure time (CLOCK_MONOTONIC) */
+};
+
+/* for TCP_MD5SIG socket option */
+#define TCP_MD5SIG_MAXKEYLEN 80
+
+/* tcp_md5sig extension flags for TCP_MD5SIG_EXT */
+#define TCP_MD5SIG_FLAG_PREFIX 0x1 /* address prefix length */
+#define TCP_MD5SIG_FLAG_IFINDEX 0x2 /* ifindex set */
+
+struct tcp_md5sig {
+ struct __kernel_sockaddr_storage tcpm_addr; /* address associated */
+ __u8 tcpm_flags; /* extension flags */
+ __u8 tcpm_prefixlen; /* address prefix */
+ __u16 tcpm_keylen; /* key length */
+ int tcpm_ifindex; /* device index for scope */
+ __u8 tcpm_key[TCP_MD5SIG_MAXKEYLEN]; /* key (binary) */
+};
+
+/* INET_DIAG_MD5SIG */
+struct tcp_diag_md5sig {
+ __u8 tcpm_family;
+ __u8 tcpm_prefixlen;
+ __u16 tcpm_keylen;
+ __be32 tcpm_addr[4];
+ __u8 tcpm_key[TCP_MD5SIG_MAXKEYLEN];
+};
+
+/* setsockopt(fd, IPPROTO_TCP, TCP_ZEROCOPY_RECEIVE, ...) */
+
+#define TCP_RECEIVE_ZEROCOPY_FLAG_TLB_CLEAN_HINT 0x1
+struct tcp_zerocopy_receive {
+ __u64 address; /* in: address of mapping */
+ __u32 length; /* in/out: number of bytes to map/mapped */
+ __u32 recv_skip_hint; /* out: amount of bytes to skip */
+ __u32 inq; /* out: amount of bytes in read queue */
+ __s32 err; /* out: socket error */
+ __u64 copybuf_address; /* in: copybuf address (small reads) */
+ __s32 copybuf_len; /* in/out: copybuf bytes avail/used or error */
+ __u32 flags; /* in: flags */
+};
+#endif /* _UAPI_LINUX_TCP_H */
diff --git a/tools/include/uapi/linux/tls.h b/tools/include/uapi/linux/tls.h
new file mode 100644
index 0000000000..ff02287495
--- /dev/null
+++ b/tools/include/uapi/linux/tls.h
@@ -0,0 +1,78 @@
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
+/*
+ * Copyright (c) 2016-2017, Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses. You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or
+ * without modification, are permitted provided that the following
+ * conditions are met:
+ *
+ * - Redistributions of source code must retain the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer in the documentation and/or other materials
+ * provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef _UAPI_LINUX_TLS_H
+#define _UAPI_LINUX_TLS_H
+
+#include <linux/types.h>
+
+/* TLS socket options */
+#define TLS_TX 1 /* Set transmit parameters */
+#define TLS_RX 2 /* Set receive parameters */
+
+/* Supported versions */
+#define TLS_VERSION_MINOR(ver) ((ver) & 0xFF)
+#define TLS_VERSION_MAJOR(ver) (((ver) >> 8) & 0xFF)
+
+#define TLS_VERSION_NUMBER(id) ((((id##_VERSION_MAJOR) & 0xFF) << 8) | \
+ ((id##_VERSION_MINOR) & 0xFF))
+
+#define TLS_1_2_VERSION_MAJOR 0x3
+#define TLS_1_2_VERSION_MINOR 0x3
+#define TLS_1_2_VERSION TLS_VERSION_NUMBER(TLS_1_2)
+
+/* Supported ciphers */
+#define TLS_CIPHER_AES_GCM_128 51
+#define TLS_CIPHER_AES_GCM_128_IV_SIZE 8
+#define TLS_CIPHER_AES_GCM_128_KEY_SIZE 16
+#define TLS_CIPHER_AES_GCM_128_SALT_SIZE 4
+#define TLS_CIPHER_AES_GCM_128_TAG_SIZE 16
+#define TLS_CIPHER_AES_GCM_128_REC_SEQ_SIZE 8
+
+#define TLS_SET_RECORD_TYPE 1
+#define TLS_GET_RECORD_TYPE 2
+
+struct tls_crypto_info {
+ __u16 version;
+ __u16 cipher_type;
+};
+
+struct tls12_crypto_info_aes_gcm_128 {
+ struct tls_crypto_info info;
+ unsigned char iv[TLS_CIPHER_AES_GCM_128_IV_SIZE];
+ unsigned char key[TLS_CIPHER_AES_GCM_128_KEY_SIZE];
+ unsigned char salt[TLS_CIPHER_AES_GCM_128_SALT_SIZE];
+ unsigned char rec_seq[TLS_CIPHER_AES_GCM_128_REC_SEQ_SIZE];
+};
+
+#endif /* _UAPI_LINUX_TLS_H */
diff --git a/tools/include/uapi/linux/types.h b/tools/include/uapi/linux/types.h
new file mode 100644
index 0000000000..91fa51a9c3
--- /dev/null
+++ b/tools/include/uapi/linux/types.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _UAPI_LINUX_TYPES_H
+#define _UAPI_LINUX_TYPES_H
+
+#include <asm-generic/int-ll64.h>
+
+/* copied from linux:include/uapi/linux/types.h */
+#define __bitwise
+typedef __u16 __bitwise __le16;
+typedef __u16 __bitwise __be16;
+typedef __u32 __bitwise __le32;
+typedef __u32 __bitwise __be32;
+typedef __u64 __bitwise __le64;
+typedef __u64 __bitwise __be64;
+
+typedef __u16 __bitwise __sum16;
+typedef __u32 __bitwise __wsum;
+
+#define __aligned_u64 __u64 __attribute__((aligned(8)))
+#define __aligned_be64 __be64 __attribute__((aligned(8)))
+#define __aligned_le64 __le64 __attribute__((aligned(8)))
+
+#endif /* _UAPI_LINUX_TYPES_H */
diff --git a/tools/include/uapi/linux/usbdevice_fs.h b/tools/include/uapi/linux/usbdevice_fs.h
new file mode 100644
index 0000000000..74a84e0242
--- /dev/null
+++ b/tools/include/uapi/linux/usbdevice_fs.h
@@ -0,0 +1,231 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*****************************************************************************/
+
+/*
+ * usbdevice_fs.h -- USB device file system.
+ *
+ * Copyright (C) 2000
+ * Thomas Sailer (sailer@ife.ee.ethz.ch)
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * History:
+ * 0.1 04.01.2000 Created
+ */
+
+/*****************************************************************************/
+
+#ifndef _UAPI_LINUX_USBDEVICE_FS_H
+#define _UAPI_LINUX_USBDEVICE_FS_H
+
+#include <linux/types.h>
+#include <linux/magic.h>
+
+/* --------------------------------------------------------------------- */
+
+/* usbdevfs ioctl codes */
+
+struct usbdevfs_ctrltransfer {
+ __u8 bRequestType;
+ __u8 bRequest;
+ __u16 wValue;
+ __u16 wIndex;
+ __u16 wLength;
+ __u32 timeout; /* in milliseconds */
+ void __user *data;
+};
+
+struct usbdevfs_bulktransfer {
+ unsigned int ep;
+ unsigned int len;
+ unsigned int timeout; /* in milliseconds */
+ void __user *data;
+};
+
+struct usbdevfs_setinterface {
+ unsigned int interface;
+ unsigned int altsetting;
+};
+
+struct usbdevfs_disconnectsignal {
+ unsigned int signr;
+ void __user *context;
+};
+
+#define USBDEVFS_MAXDRIVERNAME 255
+
+struct usbdevfs_getdriver {
+ unsigned int interface;
+ char driver[USBDEVFS_MAXDRIVERNAME + 1];
+};
+
+struct usbdevfs_connectinfo {
+ unsigned int devnum;
+ unsigned char slow;
+};
+
+struct usbdevfs_conninfo_ex {
+ __u32 size; /* Size of the structure from the kernel's */
+ /* point of view. Can be used by userspace */
+ /* to determine how much data can be */
+ /* used/trusted. */
+ __u32 busnum; /* USB bus number, as enumerated by the */
+ /* kernel, the device is connected to. */
+ __u32 devnum; /* Device address on the bus. */
+ __u32 speed; /* USB_SPEED_* constants from ch9.h */
+ __u8 num_ports; /* Number of ports the device is connected */
+ /* to on the way to the root hub. It may */
+ /* be bigger than size of 'ports' array so */
+ /* userspace can detect overflows. */
+ __u8 ports[7]; /* List of ports on the way from the root */
+ /* hub to the device. Current limit in */
+ /* USB specification is 7 tiers (root hub, */
+ /* 5 intermediate hubs, device), which */
+ /* gives at most 6 port entries. */
+};
+
+#define USBDEVFS_URB_SHORT_NOT_OK 0x01
+#define USBDEVFS_URB_ISO_ASAP 0x02
+#define USBDEVFS_URB_BULK_CONTINUATION 0x04
+#define USBDEVFS_URB_NO_FSBR 0x20 /* Not used */
+#define USBDEVFS_URB_ZERO_PACKET 0x40
+#define USBDEVFS_URB_NO_INTERRUPT 0x80
+
+#define USBDEVFS_URB_TYPE_ISO 0
+#define USBDEVFS_URB_TYPE_INTERRUPT 1
+#define USBDEVFS_URB_TYPE_CONTROL 2
+#define USBDEVFS_URB_TYPE_BULK 3
+
+struct usbdevfs_iso_packet_desc {
+ unsigned int length;
+ unsigned int actual_length;
+ unsigned int status;
+};
+
+struct usbdevfs_urb {
+ unsigned char type;
+ unsigned char endpoint;
+ int status;
+ unsigned int flags;
+ void __user *buffer;
+ int buffer_length;
+ int actual_length;
+ int start_frame;
+ union {
+ int number_of_packets; /* Only used for isoc urbs */
+ unsigned int stream_id; /* Only used with bulk streams */
+ };
+ int error_count;
+ unsigned int signr; /* signal to be sent on completion,
+ or 0 if none should be sent. */
+ void __user *usercontext;
+ struct usbdevfs_iso_packet_desc iso_frame_desc[];
+};
+
+/* ioctls for talking directly to drivers */
+struct usbdevfs_ioctl {
+ int ifno; /* interface 0..N ; negative numbers reserved */
+ int ioctl_code; /* MUST encode size + direction of data so the
+ * macros in <asm/ioctl.h> give correct values */
+ void __user *data; /* param buffer (in, or out) */
+};
+
+/* You can do most things with hubs just through control messages,
+ * except find out what device connects to what port. */
+struct usbdevfs_hub_portinfo {
+ char nports; /* number of downstream ports in this hub */
+ char port [127]; /* e.g. port 3 connects to device 27 */
+};
+
+/* System and bus capability flags */
+#define USBDEVFS_CAP_ZERO_PACKET 0x01
+#define USBDEVFS_CAP_BULK_CONTINUATION 0x02
+#define USBDEVFS_CAP_NO_PACKET_SIZE_LIM 0x04
+#define USBDEVFS_CAP_BULK_SCATTER_GATHER 0x08
+#define USBDEVFS_CAP_REAP_AFTER_DISCONNECT 0x10
+#define USBDEVFS_CAP_MMAP 0x20
+#define USBDEVFS_CAP_DROP_PRIVILEGES 0x40
+#define USBDEVFS_CAP_CONNINFO_EX 0x80
+#define USBDEVFS_CAP_SUSPEND 0x100
+
+/* USBDEVFS_DISCONNECT_CLAIM flags & struct */
+
+/* disconnect-and-claim if the driver matches the driver field */
+#define USBDEVFS_DISCONNECT_CLAIM_IF_DRIVER 0x01
+/* disconnect-and-claim except when the driver matches the driver field */
+#define USBDEVFS_DISCONNECT_CLAIM_EXCEPT_DRIVER 0x02
+
+struct usbdevfs_disconnect_claim {
+ unsigned int interface;
+ unsigned int flags;
+ char driver[USBDEVFS_MAXDRIVERNAME + 1];
+};
+
+struct usbdevfs_streams {
+ unsigned int num_streams; /* Not used by USBDEVFS_FREE_STREAMS */
+ unsigned int num_eps;
+ unsigned char eps[];
+};
+
+/*
+ * USB_SPEED_* values returned by USBDEVFS_GET_SPEED are defined in
+ * linux/usb/ch9.h
+ */
+
+#define USBDEVFS_CONTROL _IOWR('U', 0, struct usbdevfs_ctrltransfer)
+#define USBDEVFS_CONTROL32 _IOWR('U', 0, struct usbdevfs_ctrltransfer32)
+#define USBDEVFS_BULK _IOWR('U', 2, struct usbdevfs_bulktransfer)
+#define USBDEVFS_BULK32 _IOWR('U', 2, struct usbdevfs_bulktransfer32)
+#define USBDEVFS_RESETEP _IOR('U', 3, unsigned int)
+#define USBDEVFS_SETINTERFACE _IOR('U', 4, struct usbdevfs_setinterface)
+#define USBDEVFS_SETCONFIGURATION _IOR('U', 5, unsigned int)
+#define USBDEVFS_GETDRIVER _IOW('U', 8, struct usbdevfs_getdriver)
+#define USBDEVFS_SUBMITURB _IOR('U', 10, struct usbdevfs_urb)
+#define USBDEVFS_SUBMITURB32 _IOR('U', 10, struct usbdevfs_urb32)
+#define USBDEVFS_DISCARDURB _IO('U', 11)
+#define USBDEVFS_REAPURB _IOW('U', 12, void *)
+#define USBDEVFS_REAPURB32 _IOW('U', 12, __u32)
+#define USBDEVFS_REAPURBNDELAY _IOW('U', 13, void *)
+#define USBDEVFS_REAPURBNDELAY32 _IOW('U', 13, __u32)
+#define USBDEVFS_DISCSIGNAL _IOR('U', 14, struct usbdevfs_disconnectsignal)
+#define USBDEVFS_DISCSIGNAL32 _IOR('U', 14, struct usbdevfs_disconnectsignal32)
+#define USBDEVFS_CLAIMINTERFACE _IOR('U', 15, unsigned int)
+#define USBDEVFS_RELEASEINTERFACE _IOR('U', 16, unsigned int)
+#define USBDEVFS_CONNECTINFO _IOW('U', 17, struct usbdevfs_connectinfo)
+#define USBDEVFS_IOCTL _IOWR('U', 18, struct usbdevfs_ioctl)
+#define USBDEVFS_IOCTL32 _IOWR('U', 18, struct usbdevfs_ioctl32)
+#define USBDEVFS_HUB_PORTINFO _IOR('U', 19, struct usbdevfs_hub_portinfo)
+#define USBDEVFS_RESET _IO('U', 20)
+#define USBDEVFS_CLEAR_HALT _IOR('U', 21, unsigned int)
+#define USBDEVFS_DISCONNECT _IO('U', 22)
+#define USBDEVFS_CONNECT _IO('U', 23)
+#define USBDEVFS_CLAIM_PORT _IOR('U', 24, unsigned int)
+#define USBDEVFS_RELEASE_PORT _IOR('U', 25, unsigned int)
+#define USBDEVFS_GET_CAPABILITIES _IOR('U', 26, __u32)
+#define USBDEVFS_DISCONNECT_CLAIM _IOR('U', 27, struct usbdevfs_disconnect_claim)
+#define USBDEVFS_ALLOC_STREAMS _IOR('U', 28, struct usbdevfs_streams)
+#define USBDEVFS_FREE_STREAMS _IOR('U', 29, struct usbdevfs_streams)
+#define USBDEVFS_DROP_PRIVILEGES _IOW('U', 30, __u32)
+#define USBDEVFS_GET_SPEED _IO('U', 31)
+/*
+ * Returns struct usbdevfs_conninfo_ex; length is variable to allow
+ * extending size of the data returned.
+ */
+#define USBDEVFS_CONNINFO_EX(len) _IOC(_IOC_READ, 'U', 32, len)
+#define USBDEVFS_FORBID_SUSPEND _IO('U', 33)
+#define USBDEVFS_ALLOW_SUSPEND _IO('U', 34)
+#define USBDEVFS_WAIT_FOR_RESUME _IO('U', 35)
+
+#endif /* _UAPI_LINUX_USBDEVICE_FS_H */
diff --git a/tools/include/uapi/linux/vhost.h b/tools/include/uapi/linux/vhost.h
new file mode 100644
index 0000000000..f5c48b61ab
--- /dev/null
+++ b/tools/include/uapi/linux/vhost.h
@@ -0,0 +1,222 @@
+/* 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/vhost_types.h>
+#include <linux/types.h>
+#include <linux/ioctl.h>
+
+#define VHOST_FILE_UNBIND -1
+
+/* 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)
+/* By default, a device gets one vhost_worker that its virtqueues share. This
+ * command allows the owner of the device to create an additional vhost_worker
+ * for the device. It can later be bound to 1 or more of its virtqueues using
+ * the VHOST_ATTACH_VRING_WORKER command.
+ *
+ * This must be called after VHOST_SET_OWNER and the caller must be the owner
+ * of the device. The new thread will inherit caller's cgroups and namespaces,
+ * and will share the caller's memory space. The new thread will also be
+ * counted against the caller's RLIMIT_NPROC value.
+ *
+ * The worker's ID used in other commands will be returned in
+ * vhost_worker_state.
+ */
+#define VHOST_NEW_WORKER _IOR(VHOST_VIRTIO, 0x8, struct vhost_worker_state)
+/* Free a worker created with VHOST_NEW_WORKER if it's not attached to any
+ * virtqueue. If userspace is not able to call this for workers its created,
+ * the kernel will free all the device's workers when the device is closed.
+ */
+#define VHOST_FREE_WORKER _IOW(VHOST_VIRTIO, 0x9, struct vhost_worker_state)
+
+/* 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)
+/* Attach a vhost_worker created with VHOST_NEW_WORKER to one of the device's
+ * virtqueues.
+ *
+ * This will replace the virtqueue's existing worker. If the replaced worker
+ * is no longer attached to any virtqueues, it can be freed with
+ * VHOST_FREE_WORKER.
+ */
+#define VHOST_ATTACH_VRING_WORKER _IOW(VHOST_VIRTIO, 0x15, \
+ struct vhost_vring_worker)
+/* Return the vring worker's ID */
+#define VHOST_GET_VRING_WORKER _IOWR(VHOST_VIRTIO, 0x16, \
+ struct vhost_vring_worker)
+
+/* 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 */
+
+#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)
+
+/* VHOST_SCSI specific defines */
+
+#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)
+
+/* VHOST_VDPA specific defines */
+
+/* Get the device id. The device ids follow the same definition of
+ * the device id defined in virtio-spec.
+ */
+#define VHOST_VDPA_GET_DEVICE_ID _IOR(VHOST_VIRTIO, 0x70, __u32)
+/* Get and set the status. The status bits follow the same definition
+ * of the device status defined in virtio-spec.
+ */
+#define VHOST_VDPA_GET_STATUS _IOR(VHOST_VIRTIO, 0x71, __u8)
+#define VHOST_VDPA_SET_STATUS _IOW(VHOST_VIRTIO, 0x72, __u8)
+/* Get and set the device config. The device config follows the same
+ * definition of the device config defined in virtio-spec.
+ */
+#define VHOST_VDPA_GET_CONFIG _IOR(VHOST_VIRTIO, 0x73, \
+ struct vhost_vdpa_config)
+#define VHOST_VDPA_SET_CONFIG _IOW(VHOST_VIRTIO, 0x74, \
+ struct vhost_vdpa_config)
+/* Enable/disable the ring. */
+#define VHOST_VDPA_SET_VRING_ENABLE _IOW(VHOST_VIRTIO, 0x75, \
+ struct vhost_vring_state)
+/* Get the max ring size. */
+#define VHOST_VDPA_GET_VRING_NUM _IOR(VHOST_VIRTIO, 0x76, __u16)
+
+/* Set event fd for config interrupt*/
+#define VHOST_VDPA_SET_CONFIG_CALL _IOW(VHOST_VIRTIO, 0x77, int)
+
+/* Get the valid iova range */
+#define VHOST_VDPA_GET_IOVA_RANGE _IOR(VHOST_VIRTIO, 0x78, \
+ struct vhost_vdpa_iova_range)
+/* Get the config size */
+#define VHOST_VDPA_GET_CONFIG_SIZE _IOR(VHOST_VIRTIO, 0x79, __u32)
+
+/* Get the count of all virtqueues */
+#define VHOST_VDPA_GET_VQS_COUNT _IOR(VHOST_VIRTIO, 0x80, __u32)
+
+/* Get the number of virtqueue groups. */
+#define VHOST_VDPA_GET_GROUP_NUM _IOR(VHOST_VIRTIO, 0x81, __u32)
+
+/* Get the number of address spaces. */
+#define VHOST_VDPA_GET_AS_NUM _IOR(VHOST_VIRTIO, 0x7A, unsigned int)
+
+/* Get the group for a virtqueue: read index, write group in num,
+ * The virtqueue index is stored in the index field of
+ * vhost_vring_state. The group for this specific virtqueue is
+ * returned via num field of vhost_vring_state.
+ */
+#define VHOST_VDPA_GET_VRING_GROUP _IOWR(VHOST_VIRTIO, 0x7B, \
+ struct vhost_vring_state)
+/* Set the ASID for a virtqueue group. The group index is stored in
+ * the index field of vhost_vring_state, the ASID associated with this
+ * group is stored at num field of vhost_vring_state.
+ */
+#define VHOST_VDPA_SET_GROUP_ASID _IOW(VHOST_VIRTIO, 0x7C, \
+ struct vhost_vring_state)
+
+/* Suspend a device so it does not process virtqueue requests anymore
+ *
+ * After the return of ioctl the device must preserve all the necessary state
+ * (the virtqueue vring base plus the possible device specific states) that is
+ * required for restoring in the future. The device must not change its
+ * configuration after that point.
+ */
+#define VHOST_VDPA_SUSPEND _IO(VHOST_VIRTIO, 0x7D)
+
+/* Resume a device so it can resume processing virtqueue requests
+ *
+ * After the return of this ioctl the device will have restored all the
+ * necessary states and it is fully operational to continue processing the
+ * virtqueue descriptors.
+ */
+#define VHOST_VDPA_RESUME _IO(VHOST_VIRTIO, 0x7E)
+
+#endif
diff --git a/tools/include/uapi/sound/asound.h b/tools/include/uapi/sound/asound.h
new file mode 100644
index 0000000000..f9939da411
--- /dev/null
+++ b/tools/include/uapi/sound/asound.h
@@ -0,0 +1,1249 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ * Advanced Linux Sound Architecture - ALSA - Driver
+ * Copyright (c) 1994-2003 by Jaroslav Kysela <perex@perex.cz>,
+ * Abramo Bagnara <abramo@alsa-project.org>
+ */
+
+#ifndef _UAPI__SOUND_ASOUND_H
+#define _UAPI__SOUND_ASOUND_H
+
+#if defined(__KERNEL__) || defined(__linux__)
+#include <linux/types.h>
+#include <asm/byteorder.h>
+#else
+#include <endian.h>
+#include <sys/ioctl.h>
+#endif
+
+#ifndef __KERNEL__
+#include <stdlib.h>
+#include <time.h>
+#endif
+
+/*
+ * protocol version
+ */
+
+#define SNDRV_PROTOCOL_VERSION(major, minor, subminor) (((major)<<16)|((minor)<<8)|(subminor))
+#define SNDRV_PROTOCOL_MAJOR(version) (((version)>>16)&0xffff)
+#define SNDRV_PROTOCOL_MINOR(version) (((version)>>8)&0xff)
+#define SNDRV_PROTOCOL_MICRO(version) ((version)&0xff)
+#define SNDRV_PROTOCOL_INCOMPATIBLE(kversion, uversion) \
+ (SNDRV_PROTOCOL_MAJOR(kversion) != SNDRV_PROTOCOL_MAJOR(uversion) || \
+ (SNDRV_PROTOCOL_MAJOR(kversion) == SNDRV_PROTOCOL_MAJOR(uversion) && \
+ SNDRV_PROTOCOL_MINOR(kversion) != SNDRV_PROTOCOL_MINOR(uversion)))
+
+/****************************************************************************
+ * *
+ * Digital audio interface *
+ * *
+ ****************************************************************************/
+
+#define AES_IEC958_STATUS_SIZE 24
+
+struct snd_aes_iec958 {
+ unsigned char status[AES_IEC958_STATUS_SIZE]; /* AES/IEC958 channel status bits */
+ unsigned char subcode[147]; /* AES/IEC958 subcode bits */
+ unsigned char pad; /* nothing */
+ unsigned char dig_subframe[4]; /* AES/IEC958 subframe bits */
+};
+
+/****************************************************************************
+ * *
+ * CEA-861 Audio InfoFrame. Used in HDMI and DisplayPort *
+ * *
+ ****************************************************************************/
+
+struct snd_cea_861_aud_if {
+ unsigned char db1_ct_cc; /* coding type and channel count */
+ unsigned char db2_sf_ss; /* sample frequency and size */
+ unsigned char db3; /* not used, all zeros */
+ unsigned char db4_ca; /* channel allocation code */
+ unsigned char db5_dminh_lsv; /* downmix inhibit & level-shit values */
+};
+
+/****************************************************************************
+ * *
+ * Section for driver hardware dependent interface - /dev/snd/hw? *
+ * *
+ ****************************************************************************/
+
+#define SNDRV_HWDEP_VERSION SNDRV_PROTOCOL_VERSION(1, 0, 1)
+
+enum {
+ SNDRV_HWDEP_IFACE_OPL2 = 0,
+ SNDRV_HWDEP_IFACE_OPL3,
+ SNDRV_HWDEP_IFACE_OPL4,
+ SNDRV_HWDEP_IFACE_SB16CSP, /* Creative Signal Processor */
+ SNDRV_HWDEP_IFACE_EMU10K1, /* FX8010 processor in EMU10K1 chip */
+ SNDRV_HWDEP_IFACE_YSS225, /* Yamaha FX processor */
+ SNDRV_HWDEP_IFACE_ICS2115, /* Wavetable synth */
+ SNDRV_HWDEP_IFACE_SSCAPE, /* Ensoniq SoundScape ISA card (MC68EC000) */
+ SNDRV_HWDEP_IFACE_VX, /* Digigram VX cards */
+ SNDRV_HWDEP_IFACE_MIXART, /* Digigram miXart cards */
+ SNDRV_HWDEP_IFACE_USX2Y, /* Tascam US122, US224 & US428 usb */
+ SNDRV_HWDEP_IFACE_EMUX_WAVETABLE, /* EmuX wavetable */
+ SNDRV_HWDEP_IFACE_BLUETOOTH, /* Bluetooth audio */
+ SNDRV_HWDEP_IFACE_USX2Y_PCM, /* Tascam US122, US224 & US428 rawusb pcm */
+ SNDRV_HWDEP_IFACE_PCXHR, /* Digigram PCXHR */
+ SNDRV_HWDEP_IFACE_SB_RC, /* SB Extigy/Audigy2NX remote control */
+ SNDRV_HWDEP_IFACE_HDA, /* HD-audio */
+ SNDRV_HWDEP_IFACE_USB_STREAM, /* direct access to usb stream */
+ SNDRV_HWDEP_IFACE_FW_DICE, /* TC DICE FireWire device */
+ SNDRV_HWDEP_IFACE_FW_FIREWORKS, /* Echo Audio Fireworks based device */
+ SNDRV_HWDEP_IFACE_FW_BEBOB, /* BridgeCo BeBoB based device */
+ SNDRV_HWDEP_IFACE_FW_OXFW, /* Oxford OXFW970/971 based device */
+ SNDRV_HWDEP_IFACE_FW_DIGI00X, /* Digidesign Digi 002/003 family */
+ SNDRV_HWDEP_IFACE_FW_TASCAM, /* TASCAM FireWire series */
+ SNDRV_HWDEP_IFACE_LINE6, /* Line6 USB processors */
+ SNDRV_HWDEP_IFACE_FW_MOTU, /* MOTU FireWire series */
+ SNDRV_HWDEP_IFACE_FW_FIREFACE, /* RME Fireface series */
+
+ /* Don't forget to change the following: */
+ SNDRV_HWDEP_IFACE_LAST = SNDRV_HWDEP_IFACE_FW_FIREFACE
+};
+
+struct snd_hwdep_info {
+ unsigned int device; /* WR: device number */
+ int card; /* R: card number */
+ unsigned char id[64]; /* ID (user selectable) */
+ unsigned char name[80]; /* hwdep name */
+ int iface; /* hwdep interface */
+ unsigned char reserved[64]; /* reserved for future */
+};
+
+/* generic DSP loader */
+struct snd_hwdep_dsp_status {
+ unsigned int version; /* R: driver-specific version */
+ unsigned char id[32]; /* R: driver-specific ID string */
+ unsigned int num_dsps; /* R: number of DSP images to transfer */
+ unsigned int dsp_loaded; /* R: bit flags indicating the loaded DSPs */
+ unsigned int chip_ready; /* R: 1 = initialization finished */
+ unsigned char reserved[16]; /* reserved for future use */
+};
+
+struct snd_hwdep_dsp_image {
+ unsigned int index; /* W: DSP index */
+ unsigned char name[64]; /* W: ID (e.g. file name) */
+ unsigned char __user *image; /* W: binary image */
+ size_t length; /* W: size of image in bytes */
+ unsigned long driver_data; /* W: driver-specific data */
+};
+
+#define SNDRV_HWDEP_IOCTL_PVERSION _IOR ('H', 0x00, int)
+#define SNDRV_HWDEP_IOCTL_INFO _IOR ('H', 0x01, struct snd_hwdep_info)
+#define SNDRV_HWDEP_IOCTL_DSP_STATUS _IOR('H', 0x02, struct snd_hwdep_dsp_status)
+#define SNDRV_HWDEP_IOCTL_DSP_LOAD _IOW('H', 0x03, struct snd_hwdep_dsp_image)
+
+/*****************************************************************************
+ * *
+ * Digital Audio (PCM) interface - /dev/snd/pcm?? *
+ * *
+ *****************************************************************************/
+
+#define SNDRV_PCM_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 15)
+
+typedef unsigned long snd_pcm_uframes_t;
+typedef signed long snd_pcm_sframes_t;
+
+enum {
+ SNDRV_PCM_CLASS_GENERIC = 0, /* standard mono or stereo device */
+ SNDRV_PCM_CLASS_MULTI, /* multichannel device */
+ SNDRV_PCM_CLASS_MODEM, /* software modem class */
+ SNDRV_PCM_CLASS_DIGITIZER, /* digitizer class */
+ /* Don't forget to change the following: */
+ SNDRV_PCM_CLASS_LAST = SNDRV_PCM_CLASS_DIGITIZER,
+};
+
+enum {
+ SNDRV_PCM_SUBCLASS_GENERIC_MIX = 0, /* mono or stereo subdevices are mixed together */
+ SNDRV_PCM_SUBCLASS_MULTI_MIX, /* multichannel subdevices are mixed together */
+ /* Don't forget to change the following: */
+ SNDRV_PCM_SUBCLASS_LAST = SNDRV_PCM_SUBCLASS_MULTI_MIX,
+};
+
+enum {
+ SNDRV_PCM_STREAM_PLAYBACK = 0,
+ SNDRV_PCM_STREAM_CAPTURE,
+ SNDRV_PCM_STREAM_LAST = SNDRV_PCM_STREAM_CAPTURE,
+};
+
+typedef int __bitwise snd_pcm_access_t;
+#define SNDRV_PCM_ACCESS_MMAP_INTERLEAVED ((__force snd_pcm_access_t) 0) /* interleaved mmap */
+#define SNDRV_PCM_ACCESS_MMAP_NONINTERLEAVED ((__force snd_pcm_access_t) 1) /* noninterleaved mmap */
+#define SNDRV_PCM_ACCESS_MMAP_COMPLEX ((__force snd_pcm_access_t) 2) /* complex mmap */
+#define SNDRV_PCM_ACCESS_RW_INTERLEAVED ((__force snd_pcm_access_t) 3) /* readi/writei */
+#define SNDRV_PCM_ACCESS_RW_NONINTERLEAVED ((__force snd_pcm_access_t) 4) /* readn/writen */
+#define SNDRV_PCM_ACCESS_LAST SNDRV_PCM_ACCESS_RW_NONINTERLEAVED
+
+typedef int __bitwise snd_pcm_format_t;
+#define SNDRV_PCM_FORMAT_S8 ((__force snd_pcm_format_t) 0)
+#define SNDRV_PCM_FORMAT_U8 ((__force snd_pcm_format_t) 1)
+#define SNDRV_PCM_FORMAT_S16_LE ((__force snd_pcm_format_t) 2)
+#define SNDRV_PCM_FORMAT_S16_BE ((__force snd_pcm_format_t) 3)
+#define SNDRV_PCM_FORMAT_U16_LE ((__force snd_pcm_format_t) 4)
+#define SNDRV_PCM_FORMAT_U16_BE ((__force snd_pcm_format_t) 5)
+#define SNDRV_PCM_FORMAT_S24_LE ((__force snd_pcm_format_t) 6) /* low three bytes */
+#define SNDRV_PCM_FORMAT_S24_BE ((__force snd_pcm_format_t) 7) /* low three bytes */
+#define SNDRV_PCM_FORMAT_U24_LE ((__force snd_pcm_format_t) 8) /* low three bytes */
+#define SNDRV_PCM_FORMAT_U24_BE ((__force snd_pcm_format_t) 9) /* low three bytes */
+/*
+ * For S32/U32 formats, 'msbits' hardware parameter is often used to deliver information about the
+ * available bit count in most significant bit. It's for the case of so-called 'left-justified' or
+ * `right-padding` sample which has less width than 32 bit.
+ */
+#define SNDRV_PCM_FORMAT_S32_LE ((__force snd_pcm_format_t) 10)
+#define SNDRV_PCM_FORMAT_S32_BE ((__force snd_pcm_format_t) 11)
+#define SNDRV_PCM_FORMAT_U32_LE ((__force snd_pcm_format_t) 12)
+#define SNDRV_PCM_FORMAT_U32_BE ((__force snd_pcm_format_t) 13)
+#define SNDRV_PCM_FORMAT_FLOAT_LE ((__force snd_pcm_format_t) 14) /* 4-byte float, IEEE-754 32-bit, range -1.0 to 1.0 */
+#define SNDRV_PCM_FORMAT_FLOAT_BE ((__force snd_pcm_format_t) 15) /* 4-byte float, IEEE-754 32-bit, range -1.0 to 1.0 */
+#define SNDRV_PCM_FORMAT_FLOAT64_LE ((__force snd_pcm_format_t) 16) /* 8-byte float, IEEE-754 64-bit, range -1.0 to 1.0 */
+#define SNDRV_PCM_FORMAT_FLOAT64_BE ((__force snd_pcm_format_t) 17) /* 8-byte float, IEEE-754 64-bit, range -1.0 to 1.0 */
+#define SNDRV_PCM_FORMAT_IEC958_SUBFRAME_LE ((__force snd_pcm_format_t) 18) /* IEC-958 subframe, Little Endian */
+#define SNDRV_PCM_FORMAT_IEC958_SUBFRAME_BE ((__force snd_pcm_format_t) 19) /* IEC-958 subframe, Big Endian */
+#define SNDRV_PCM_FORMAT_MU_LAW ((__force snd_pcm_format_t) 20)
+#define SNDRV_PCM_FORMAT_A_LAW ((__force snd_pcm_format_t) 21)
+#define SNDRV_PCM_FORMAT_IMA_ADPCM ((__force snd_pcm_format_t) 22)
+#define SNDRV_PCM_FORMAT_MPEG ((__force snd_pcm_format_t) 23)
+#define SNDRV_PCM_FORMAT_GSM ((__force snd_pcm_format_t) 24)
+#define SNDRV_PCM_FORMAT_S20_LE ((__force snd_pcm_format_t) 25) /* in four bytes, LSB justified */
+#define SNDRV_PCM_FORMAT_S20_BE ((__force snd_pcm_format_t) 26) /* in four bytes, LSB justified */
+#define SNDRV_PCM_FORMAT_U20_LE ((__force snd_pcm_format_t) 27) /* in four bytes, LSB justified */
+#define SNDRV_PCM_FORMAT_U20_BE ((__force snd_pcm_format_t) 28) /* in four bytes, LSB justified */
+/* gap in the numbering for a future standard linear format */
+#define SNDRV_PCM_FORMAT_SPECIAL ((__force snd_pcm_format_t) 31)
+#define SNDRV_PCM_FORMAT_S24_3LE ((__force snd_pcm_format_t) 32) /* in three bytes */
+#define SNDRV_PCM_FORMAT_S24_3BE ((__force snd_pcm_format_t) 33) /* in three bytes */
+#define SNDRV_PCM_FORMAT_U24_3LE ((__force snd_pcm_format_t) 34) /* in three bytes */
+#define SNDRV_PCM_FORMAT_U24_3BE ((__force snd_pcm_format_t) 35) /* in three bytes */
+#define SNDRV_PCM_FORMAT_S20_3LE ((__force snd_pcm_format_t) 36) /* in three bytes */
+#define SNDRV_PCM_FORMAT_S20_3BE ((__force snd_pcm_format_t) 37) /* in three bytes */
+#define SNDRV_PCM_FORMAT_U20_3LE ((__force snd_pcm_format_t) 38) /* in three bytes */
+#define SNDRV_PCM_FORMAT_U20_3BE ((__force snd_pcm_format_t) 39) /* in three bytes */
+#define SNDRV_PCM_FORMAT_S18_3LE ((__force snd_pcm_format_t) 40) /* in three bytes */
+#define SNDRV_PCM_FORMAT_S18_3BE ((__force snd_pcm_format_t) 41) /* in three bytes */
+#define SNDRV_PCM_FORMAT_U18_3LE ((__force snd_pcm_format_t) 42) /* in three bytes */
+#define SNDRV_PCM_FORMAT_U18_3BE ((__force snd_pcm_format_t) 43) /* in three bytes */
+#define SNDRV_PCM_FORMAT_G723_24 ((__force snd_pcm_format_t) 44) /* 8 samples in 3 bytes */
+#define SNDRV_PCM_FORMAT_G723_24_1B ((__force snd_pcm_format_t) 45) /* 1 sample in 1 byte */
+#define SNDRV_PCM_FORMAT_G723_40 ((__force snd_pcm_format_t) 46) /* 8 Samples in 5 bytes */
+#define SNDRV_PCM_FORMAT_G723_40_1B ((__force snd_pcm_format_t) 47) /* 1 sample in 1 byte */
+#define SNDRV_PCM_FORMAT_DSD_U8 ((__force snd_pcm_format_t) 48) /* DSD, 1-byte samples DSD (x8) */
+#define SNDRV_PCM_FORMAT_DSD_U16_LE ((__force snd_pcm_format_t) 49) /* DSD, 2-byte samples DSD (x16), little endian */
+#define SNDRV_PCM_FORMAT_DSD_U32_LE ((__force snd_pcm_format_t) 50) /* DSD, 4-byte samples DSD (x32), little endian */
+#define SNDRV_PCM_FORMAT_DSD_U16_BE ((__force snd_pcm_format_t) 51) /* DSD, 2-byte samples DSD (x16), big endian */
+#define SNDRV_PCM_FORMAT_DSD_U32_BE ((__force snd_pcm_format_t) 52) /* DSD, 4-byte samples DSD (x32), big endian */
+#define SNDRV_PCM_FORMAT_LAST SNDRV_PCM_FORMAT_DSD_U32_BE
+#define SNDRV_PCM_FORMAT_FIRST SNDRV_PCM_FORMAT_S8
+
+#ifdef SNDRV_LITTLE_ENDIAN
+#define SNDRV_PCM_FORMAT_S16 SNDRV_PCM_FORMAT_S16_LE
+#define SNDRV_PCM_FORMAT_U16 SNDRV_PCM_FORMAT_U16_LE
+#define SNDRV_PCM_FORMAT_S24 SNDRV_PCM_FORMAT_S24_LE
+#define SNDRV_PCM_FORMAT_U24 SNDRV_PCM_FORMAT_U24_LE
+#define SNDRV_PCM_FORMAT_S32 SNDRV_PCM_FORMAT_S32_LE
+#define SNDRV_PCM_FORMAT_U32 SNDRV_PCM_FORMAT_U32_LE
+#define SNDRV_PCM_FORMAT_FLOAT SNDRV_PCM_FORMAT_FLOAT_LE
+#define SNDRV_PCM_FORMAT_FLOAT64 SNDRV_PCM_FORMAT_FLOAT64_LE
+#define SNDRV_PCM_FORMAT_IEC958_SUBFRAME SNDRV_PCM_FORMAT_IEC958_SUBFRAME_LE
+#define SNDRV_PCM_FORMAT_S20 SNDRV_PCM_FORMAT_S20_LE
+#define SNDRV_PCM_FORMAT_U20 SNDRV_PCM_FORMAT_U20_LE
+#endif
+#ifdef SNDRV_BIG_ENDIAN
+#define SNDRV_PCM_FORMAT_S16 SNDRV_PCM_FORMAT_S16_BE
+#define SNDRV_PCM_FORMAT_U16 SNDRV_PCM_FORMAT_U16_BE
+#define SNDRV_PCM_FORMAT_S24 SNDRV_PCM_FORMAT_S24_BE
+#define SNDRV_PCM_FORMAT_U24 SNDRV_PCM_FORMAT_U24_BE
+#define SNDRV_PCM_FORMAT_S32 SNDRV_PCM_FORMAT_S32_BE
+#define SNDRV_PCM_FORMAT_U32 SNDRV_PCM_FORMAT_U32_BE
+#define SNDRV_PCM_FORMAT_FLOAT SNDRV_PCM_FORMAT_FLOAT_BE
+#define SNDRV_PCM_FORMAT_FLOAT64 SNDRV_PCM_FORMAT_FLOAT64_BE
+#define SNDRV_PCM_FORMAT_IEC958_SUBFRAME SNDRV_PCM_FORMAT_IEC958_SUBFRAME_BE
+#define SNDRV_PCM_FORMAT_S20 SNDRV_PCM_FORMAT_S20_BE
+#define SNDRV_PCM_FORMAT_U20 SNDRV_PCM_FORMAT_U20_BE
+#endif
+
+typedef int __bitwise snd_pcm_subformat_t;
+#define SNDRV_PCM_SUBFORMAT_STD ((__force snd_pcm_subformat_t) 0)
+#define SNDRV_PCM_SUBFORMAT_LAST SNDRV_PCM_SUBFORMAT_STD
+
+#define SNDRV_PCM_INFO_MMAP 0x00000001 /* hardware supports mmap */
+#define SNDRV_PCM_INFO_MMAP_VALID 0x00000002 /* period data are valid during transfer */
+#define SNDRV_PCM_INFO_DOUBLE 0x00000004 /* Double buffering needed for PCM start/stop */
+#define SNDRV_PCM_INFO_BATCH 0x00000010 /* double buffering */
+#define SNDRV_PCM_INFO_SYNC_APPLPTR 0x00000020 /* need the explicit sync of appl_ptr update */
+#define SNDRV_PCM_INFO_PERFECT_DRAIN 0x00000040 /* silencing at the end of stream is not required */
+#define SNDRV_PCM_INFO_INTERLEAVED 0x00000100 /* channels are interleaved */
+#define SNDRV_PCM_INFO_NONINTERLEAVED 0x00000200 /* channels are not interleaved */
+#define SNDRV_PCM_INFO_COMPLEX 0x00000400 /* complex frame organization (mmap only) */
+#define SNDRV_PCM_INFO_BLOCK_TRANSFER 0x00010000 /* hardware transfer block of samples */
+#define SNDRV_PCM_INFO_OVERRANGE 0x00020000 /* hardware supports ADC (capture) overrange detection */
+#define SNDRV_PCM_INFO_RESUME 0x00040000 /* hardware supports stream resume after suspend */
+#define SNDRV_PCM_INFO_PAUSE 0x00080000 /* pause ioctl is supported */
+#define SNDRV_PCM_INFO_HALF_DUPLEX 0x00100000 /* only half duplex */
+#define SNDRV_PCM_INFO_JOINT_DUPLEX 0x00200000 /* playback and capture stream are somewhat correlated */
+#define SNDRV_PCM_INFO_SYNC_START 0x00400000 /* pcm support some kind of sync go */
+#define SNDRV_PCM_INFO_NO_PERIOD_WAKEUP 0x00800000 /* period wakeup can be disabled */
+#define SNDRV_PCM_INFO_HAS_WALL_CLOCK 0x01000000 /* (Deprecated)has audio wall clock for audio/system time sync */
+#define SNDRV_PCM_INFO_HAS_LINK_ATIME 0x01000000 /* report hardware link audio time, reset on startup */
+#define SNDRV_PCM_INFO_HAS_LINK_ABSOLUTE_ATIME 0x02000000 /* report absolute hardware link audio time, not reset on startup */
+#define SNDRV_PCM_INFO_HAS_LINK_ESTIMATED_ATIME 0x04000000 /* report estimated link audio time */
+#define SNDRV_PCM_INFO_HAS_LINK_SYNCHRONIZED_ATIME 0x08000000 /* report synchronized audio/system time */
+#define SNDRV_PCM_INFO_EXPLICIT_SYNC 0x10000000 /* needs explicit sync of pointers and data */
+#define SNDRV_PCM_INFO_NO_REWINDS 0x20000000 /* hardware can only support monotonic changes of appl_ptr */
+#define SNDRV_PCM_INFO_DRAIN_TRIGGER 0x40000000 /* internal kernel flag - trigger in drain */
+#define SNDRV_PCM_INFO_FIFO_IN_FRAMES 0x80000000 /* internal kernel flag - FIFO size is in frames */
+
+#if (__BITS_PER_LONG == 32 && defined(__USE_TIME_BITS64)) || defined __KERNEL__
+#define __SND_STRUCT_TIME64
+#endif
+
+typedef int __bitwise snd_pcm_state_t;
+#define SNDRV_PCM_STATE_OPEN ((__force snd_pcm_state_t) 0) /* stream is open */
+#define SNDRV_PCM_STATE_SETUP ((__force snd_pcm_state_t) 1) /* stream has a setup */
+#define SNDRV_PCM_STATE_PREPARED ((__force snd_pcm_state_t) 2) /* stream is ready to start */
+#define SNDRV_PCM_STATE_RUNNING ((__force snd_pcm_state_t) 3) /* stream is running */
+#define SNDRV_PCM_STATE_XRUN ((__force snd_pcm_state_t) 4) /* stream reached an xrun */
+#define SNDRV_PCM_STATE_DRAINING ((__force snd_pcm_state_t) 5) /* stream is draining */
+#define SNDRV_PCM_STATE_PAUSED ((__force snd_pcm_state_t) 6) /* stream is paused */
+#define SNDRV_PCM_STATE_SUSPENDED ((__force snd_pcm_state_t) 7) /* hardware is suspended */
+#define SNDRV_PCM_STATE_DISCONNECTED ((__force snd_pcm_state_t) 8) /* hardware is disconnected */
+#define SNDRV_PCM_STATE_LAST SNDRV_PCM_STATE_DISCONNECTED
+
+enum {
+ SNDRV_PCM_MMAP_OFFSET_DATA = 0x00000000,
+ SNDRV_PCM_MMAP_OFFSET_STATUS_OLD = 0x80000000,
+ SNDRV_PCM_MMAP_OFFSET_CONTROL_OLD = 0x81000000,
+ SNDRV_PCM_MMAP_OFFSET_STATUS_NEW = 0x82000000,
+ SNDRV_PCM_MMAP_OFFSET_CONTROL_NEW = 0x83000000,
+#ifdef __SND_STRUCT_TIME64
+ SNDRV_PCM_MMAP_OFFSET_STATUS = SNDRV_PCM_MMAP_OFFSET_STATUS_NEW,
+ SNDRV_PCM_MMAP_OFFSET_CONTROL = SNDRV_PCM_MMAP_OFFSET_CONTROL_NEW,
+#else
+ SNDRV_PCM_MMAP_OFFSET_STATUS = SNDRV_PCM_MMAP_OFFSET_STATUS_OLD,
+ SNDRV_PCM_MMAP_OFFSET_CONTROL = SNDRV_PCM_MMAP_OFFSET_CONTROL_OLD,
+#endif
+};
+
+union snd_pcm_sync_id {
+ unsigned char id[16];
+ unsigned short id16[8];
+ unsigned int id32[4];
+};
+
+struct snd_pcm_info {
+ unsigned int device; /* RO/WR (control): device number */
+ unsigned int subdevice; /* RO/WR (control): subdevice number */
+ int stream; /* RO/WR (control): stream direction */
+ int card; /* R: card number */
+ unsigned char id[64]; /* ID (user selectable) */
+ unsigned char name[80]; /* name of this device */
+ unsigned char subname[32]; /* subdevice name */
+ int dev_class; /* SNDRV_PCM_CLASS_* */
+ int dev_subclass; /* SNDRV_PCM_SUBCLASS_* */
+ unsigned int subdevices_count;
+ unsigned int subdevices_avail;
+ union snd_pcm_sync_id sync; /* hardware synchronization ID */
+ unsigned char reserved[64]; /* reserved for future... */
+};
+
+typedef int snd_pcm_hw_param_t;
+#define SNDRV_PCM_HW_PARAM_ACCESS 0 /* Access type */
+#define SNDRV_PCM_HW_PARAM_FORMAT 1 /* Format */
+#define SNDRV_PCM_HW_PARAM_SUBFORMAT 2 /* Subformat */
+#define SNDRV_PCM_HW_PARAM_FIRST_MASK SNDRV_PCM_HW_PARAM_ACCESS
+#define SNDRV_PCM_HW_PARAM_LAST_MASK SNDRV_PCM_HW_PARAM_SUBFORMAT
+
+#define SNDRV_PCM_HW_PARAM_SAMPLE_BITS 8 /* Bits per sample */
+#define SNDRV_PCM_HW_PARAM_FRAME_BITS 9 /* Bits per frame */
+#define SNDRV_PCM_HW_PARAM_CHANNELS 10 /* Channels */
+#define SNDRV_PCM_HW_PARAM_RATE 11 /* Approx rate */
+#define SNDRV_PCM_HW_PARAM_PERIOD_TIME 12 /* Approx distance between
+ * interrupts in us
+ */
+#define SNDRV_PCM_HW_PARAM_PERIOD_SIZE 13 /* Approx frames between
+ * interrupts
+ */
+#define SNDRV_PCM_HW_PARAM_PERIOD_BYTES 14 /* Approx bytes between
+ * interrupts
+ */
+#define SNDRV_PCM_HW_PARAM_PERIODS 15 /* Approx interrupts per
+ * buffer
+ */
+#define SNDRV_PCM_HW_PARAM_BUFFER_TIME 16 /* Approx duration of buffer
+ * in us
+ */
+#define SNDRV_PCM_HW_PARAM_BUFFER_SIZE 17 /* Size of buffer in frames */
+#define SNDRV_PCM_HW_PARAM_BUFFER_BYTES 18 /* Size of buffer in bytes */
+#define SNDRV_PCM_HW_PARAM_TICK_TIME 19 /* Approx tick duration in us */
+#define SNDRV_PCM_HW_PARAM_FIRST_INTERVAL SNDRV_PCM_HW_PARAM_SAMPLE_BITS
+#define SNDRV_PCM_HW_PARAM_LAST_INTERVAL SNDRV_PCM_HW_PARAM_TICK_TIME
+
+#define SNDRV_PCM_HW_PARAMS_NORESAMPLE (1<<0) /* avoid rate resampling */
+#define SNDRV_PCM_HW_PARAMS_EXPORT_BUFFER (1<<1) /* export buffer */
+#define SNDRV_PCM_HW_PARAMS_NO_PERIOD_WAKEUP (1<<2) /* disable period wakeups */
+#define SNDRV_PCM_HW_PARAMS_NO_DRAIN_SILENCE (1<<3) /* suppress drain with the filling
+ * of the silence samples
+ */
+
+struct snd_interval {
+ unsigned int min, max;
+ unsigned int openmin:1,
+ openmax:1,
+ integer:1,
+ empty:1;
+};
+
+#define SNDRV_MASK_MAX 256
+
+struct snd_mask {
+ __u32 bits[(SNDRV_MASK_MAX+31)/32];
+};
+
+struct snd_pcm_hw_params {
+ unsigned int flags;
+ struct snd_mask masks[SNDRV_PCM_HW_PARAM_LAST_MASK -
+ SNDRV_PCM_HW_PARAM_FIRST_MASK + 1];
+ struct snd_mask mres[5]; /* reserved masks */
+ struct snd_interval intervals[SNDRV_PCM_HW_PARAM_LAST_INTERVAL -
+ SNDRV_PCM_HW_PARAM_FIRST_INTERVAL + 1];
+ struct snd_interval ires[9]; /* reserved intervals */
+ unsigned int rmask; /* W: requested masks */
+ unsigned int cmask; /* R: changed masks */
+ unsigned int info; /* R: Info flags for returned setup */
+ unsigned int msbits; /* R: used most significant bits */
+ unsigned int rate_num; /* R: rate numerator */
+ unsigned int rate_den; /* R: rate denominator */
+ snd_pcm_uframes_t fifo_size; /* R: chip FIFO size in frames */
+ unsigned char reserved[64]; /* reserved for future */
+};
+
+enum {
+ SNDRV_PCM_TSTAMP_NONE = 0,
+ SNDRV_PCM_TSTAMP_ENABLE,
+ SNDRV_PCM_TSTAMP_LAST = SNDRV_PCM_TSTAMP_ENABLE,
+};
+
+struct snd_pcm_sw_params {
+ int tstamp_mode; /* timestamp mode */
+ unsigned int period_step;
+ unsigned int sleep_min; /* min ticks to sleep */
+ snd_pcm_uframes_t avail_min; /* min avail frames for wakeup */
+ snd_pcm_uframes_t xfer_align; /* obsolete: xfer size need to be a multiple */
+ snd_pcm_uframes_t start_threshold; /* min hw_avail frames for automatic start */
+ /*
+ * The following two thresholds alleviate playback buffer underruns; when
+ * hw_avail drops below the threshold, the respective action is triggered:
+ */
+ snd_pcm_uframes_t stop_threshold; /* - stop playback */
+ snd_pcm_uframes_t silence_threshold; /* - pre-fill buffer with silence */
+ snd_pcm_uframes_t silence_size; /* max size of silence pre-fill; when >= boundary,
+ * fill played area with silence immediately */
+ snd_pcm_uframes_t boundary; /* pointers wrap point */
+ unsigned int proto; /* protocol version */
+ unsigned int tstamp_type; /* timestamp type (req. proto >= 2.0.12) */
+ unsigned char reserved[56]; /* reserved for future */
+};
+
+struct snd_pcm_channel_info {
+ unsigned int channel;
+ __kernel_off_t offset; /* mmap offset */
+ unsigned int first; /* offset to first sample in bits */
+ unsigned int step; /* samples distance in bits */
+};
+
+enum {
+ /*
+ * first definition for backwards compatibility only,
+ * maps to wallclock/link time for HDAudio playback and DEFAULT/DMA time for everything else
+ */
+ SNDRV_PCM_AUDIO_TSTAMP_TYPE_COMPAT = 0,
+
+ /* timestamp definitions */
+ SNDRV_PCM_AUDIO_TSTAMP_TYPE_DEFAULT = 1, /* DMA time, reported as per hw_ptr */
+ SNDRV_PCM_AUDIO_TSTAMP_TYPE_LINK = 2, /* link time reported by sample or wallclock counter, reset on startup */
+ SNDRV_PCM_AUDIO_TSTAMP_TYPE_LINK_ABSOLUTE = 3, /* link time reported by sample or wallclock counter, not reset on startup */
+ SNDRV_PCM_AUDIO_TSTAMP_TYPE_LINK_ESTIMATED = 4, /* link time estimated indirectly */
+ SNDRV_PCM_AUDIO_TSTAMP_TYPE_LINK_SYNCHRONIZED = 5, /* link time synchronized with system time */
+ SNDRV_PCM_AUDIO_TSTAMP_TYPE_LAST = SNDRV_PCM_AUDIO_TSTAMP_TYPE_LINK_SYNCHRONIZED
+};
+
+#ifndef __KERNEL__
+/* explicit padding avoids incompatibility between i386 and x86-64 */
+typedef struct { unsigned char pad[sizeof(time_t) - sizeof(int)]; } __time_pad;
+
+struct snd_pcm_status {
+ snd_pcm_state_t state; /* stream state */
+ __time_pad pad1; /* align to timespec */
+ struct timespec trigger_tstamp; /* time when stream was started/stopped/paused */
+ struct timespec tstamp; /* reference timestamp */
+ snd_pcm_uframes_t appl_ptr; /* appl ptr */
+ snd_pcm_uframes_t hw_ptr; /* hw ptr */
+ snd_pcm_sframes_t delay; /* current delay in frames */
+ snd_pcm_uframes_t avail; /* number of frames available */
+ snd_pcm_uframes_t avail_max; /* max frames available on hw since last status */
+ snd_pcm_uframes_t overrange; /* count of ADC (capture) overrange detections from last status */
+ snd_pcm_state_t suspended_state; /* suspended stream state */
+ __u32 audio_tstamp_data; /* needed for 64-bit alignment, used for configs/report to/from userspace */
+ struct timespec audio_tstamp; /* sample counter, wall clock, PHC or on-demand sync'ed */
+ struct timespec driver_tstamp; /* useful in case reference system tstamp is reported with delay */
+ __u32 audio_tstamp_accuracy; /* in ns units, only valid if indicated in audio_tstamp_data */
+ unsigned char reserved[52-2*sizeof(struct timespec)]; /* must be filled with zero */
+};
+#endif
+
+/*
+ * For mmap operations, we need the 64-bit layout, both for compat mode,
+ * and for y2038 compatibility. For 64-bit applications, the two definitions
+ * are identical, so we keep the traditional version.
+ */
+#ifdef __SND_STRUCT_TIME64
+#define __snd_pcm_mmap_status64 snd_pcm_mmap_status
+#define __snd_pcm_mmap_control64 snd_pcm_mmap_control
+#define __snd_pcm_sync_ptr64 snd_pcm_sync_ptr
+#ifdef __KERNEL__
+#define __snd_timespec64 __kernel_timespec
+#else
+#define __snd_timespec64 timespec
+#endif
+struct __snd_timespec {
+ __s32 tv_sec;
+ __s32 tv_nsec;
+};
+#else
+#define __snd_pcm_mmap_status snd_pcm_mmap_status
+#define __snd_pcm_mmap_control snd_pcm_mmap_control
+#define __snd_pcm_sync_ptr snd_pcm_sync_ptr
+#define __snd_timespec timespec
+struct __snd_timespec64 {
+ __s64 tv_sec;
+ __s64 tv_nsec;
+};
+
+#endif
+
+struct __snd_pcm_mmap_status {
+ snd_pcm_state_t state; /* RO: state - SNDRV_PCM_STATE_XXXX */
+ int pad1; /* Needed for 64 bit alignment */
+ snd_pcm_uframes_t hw_ptr; /* RO: hw ptr (0...boundary-1) */
+ struct __snd_timespec tstamp; /* Timestamp */
+ snd_pcm_state_t suspended_state; /* RO: suspended stream state */
+ struct __snd_timespec audio_tstamp; /* from sample counter or wall clock */
+};
+
+struct __snd_pcm_mmap_control {
+ snd_pcm_uframes_t appl_ptr; /* RW: appl ptr (0...boundary-1) */
+ snd_pcm_uframes_t avail_min; /* RW: min available frames for wakeup */
+};
+
+#define SNDRV_PCM_SYNC_PTR_HWSYNC (1<<0) /* execute hwsync */
+#define SNDRV_PCM_SYNC_PTR_APPL (1<<1) /* get appl_ptr from driver (r/w op) */
+#define SNDRV_PCM_SYNC_PTR_AVAIL_MIN (1<<2) /* get avail_min from driver */
+
+struct __snd_pcm_sync_ptr {
+ unsigned int flags;
+ union {
+ struct __snd_pcm_mmap_status status;
+ unsigned char reserved[64];
+ } s;
+ union {
+ struct __snd_pcm_mmap_control control;
+ unsigned char reserved[64];
+ } c;
+};
+
+#if defined(__BYTE_ORDER) ? __BYTE_ORDER == __BIG_ENDIAN : defined(__BIG_ENDIAN)
+typedef char __pad_before_uframe[sizeof(__u64) - sizeof(snd_pcm_uframes_t)];
+typedef char __pad_after_uframe[0];
+#endif
+
+#if defined(__BYTE_ORDER) ? __BYTE_ORDER == __LITTLE_ENDIAN : defined(__LITTLE_ENDIAN)
+typedef char __pad_before_uframe[0];
+typedef char __pad_after_uframe[sizeof(__u64) - sizeof(snd_pcm_uframes_t)];
+#endif
+
+struct __snd_pcm_mmap_status64 {
+ snd_pcm_state_t state; /* RO: state - SNDRV_PCM_STATE_XXXX */
+ __u32 pad1; /* Needed for 64 bit alignment */
+ __pad_before_uframe __pad1;
+ snd_pcm_uframes_t hw_ptr; /* RO: hw ptr (0...boundary-1) */
+ __pad_after_uframe __pad2;
+ struct __snd_timespec64 tstamp; /* Timestamp */
+ snd_pcm_state_t suspended_state;/* RO: suspended stream state */
+ __u32 pad3; /* Needed for 64 bit alignment */
+ struct __snd_timespec64 audio_tstamp; /* sample counter or wall clock */
+};
+
+struct __snd_pcm_mmap_control64 {
+ __pad_before_uframe __pad1;
+ snd_pcm_uframes_t appl_ptr; /* RW: appl ptr (0...boundary-1) */
+ __pad_before_uframe __pad2; // This should be __pad_after_uframe, but binary
+ // backwards compatibility constraints prevent a fix.
+
+ __pad_before_uframe __pad3;
+ snd_pcm_uframes_t avail_min; /* RW: min available frames for wakeup */
+ __pad_after_uframe __pad4;
+};
+
+struct __snd_pcm_sync_ptr64 {
+ __u32 flags;
+ __u32 pad1;
+ union {
+ struct __snd_pcm_mmap_status64 status;
+ unsigned char reserved[64];
+ } s;
+ union {
+ struct __snd_pcm_mmap_control64 control;
+ unsigned char reserved[64];
+ } c;
+};
+
+struct snd_xferi {
+ snd_pcm_sframes_t result;
+ void __user *buf;
+ snd_pcm_uframes_t frames;
+};
+
+struct snd_xfern {
+ snd_pcm_sframes_t result;
+ void __user * __user *bufs;
+ snd_pcm_uframes_t frames;
+};
+
+enum {
+ SNDRV_PCM_TSTAMP_TYPE_GETTIMEOFDAY = 0, /* gettimeofday equivalent */
+ SNDRV_PCM_TSTAMP_TYPE_MONOTONIC, /* posix_clock_monotonic equivalent */
+ SNDRV_PCM_TSTAMP_TYPE_MONOTONIC_RAW, /* monotonic_raw (no NTP) */
+ SNDRV_PCM_TSTAMP_TYPE_LAST = SNDRV_PCM_TSTAMP_TYPE_MONOTONIC_RAW,
+};
+
+/* channel positions */
+enum {
+ SNDRV_CHMAP_UNKNOWN = 0,
+ SNDRV_CHMAP_NA, /* N/A, silent */
+ SNDRV_CHMAP_MONO, /* mono stream */
+ /* this follows the alsa-lib mixer channel value + 3 */
+ SNDRV_CHMAP_FL, /* front left */
+ SNDRV_CHMAP_FR, /* front right */
+ SNDRV_CHMAP_RL, /* rear left */
+ SNDRV_CHMAP_RR, /* rear right */
+ SNDRV_CHMAP_FC, /* front center */
+ SNDRV_CHMAP_LFE, /* LFE */
+ SNDRV_CHMAP_SL, /* side left */
+ SNDRV_CHMAP_SR, /* side right */
+ SNDRV_CHMAP_RC, /* rear center */
+ /* new definitions */
+ SNDRV_CHMAP_FLC, /* front left center */
+ SNDRV_CHMAP_FRC, /* front right center */
+ SNDRV_CHMAP_RLC, /* rear left center */
+ SNDRV_CHMAP_RRC, /* rear right center */
+ SNDRV_CHMAP_FLW, /* front left wide */
+ SNDRV_CHMAP_FRW, /* front right wide */
+ SNDRV_CHMAP_FLH, /* front left high */
+ SNDRV_CHMAP_FCH, /* front center high */
+ SNDRV_CHMAP_FRH, /* front right high */
+ SNDRV_CHMAP_TC, /* top center */
+ SNDRV_CHMAP_TFL, /* top front left */
+ SNDRV_CHMAP_TFR, /* top front right */
+ SNDRV_CHMAP_TFC, /* top front center */
+ SNDRV_CHMAP_TRL, /* top rear left */
+ SNDRV_CHMAP_TRR, /* top rear right */
+ SNDRV_CHMAP_TRC, /* top rear center */
+ /* new definitions for UAC2 */
+ SNDRV_CHMAP_TFLC, /* top front left center */
+ SNDRV_CHMAP_TFRC, /* top front right center */
+ SNDRV_CHMAP_TSL, /* top side left */
+ SNDRV_CHMAP_TSR, /* top side right */
+ SNDRV_CHMAP_LLFE, /* left LFE */
+ SNDRV_CHMAP_RLFE, /* right LFE */
+ SNDRV_CHMAP_BC, /* bottom center */
+ SNDRV_CHMAP_BLC, /* bottom left center */
+ SNDRV_CHMAP_BRC, /* bottom right center */
+ SNDRV_CHMAP_LAST = SNDRV_CHMAP_BRC,
+};
+
+#define SNDRV_CHMAP_POSITION_MASK 0xffff
+#define SNDRV_CHMAP_PHASE_INVERSE (0x01 << 16)
+#define SNDRV_CHMAP_DRIVER_SPEC (0x02 << 16)
+
+#define SNDRV_PCM_IOCTL_PVERSION _IOR('A', 0x00, int)
+#define SNDRV_PCM_IOCTL_INFO _IOR('A', 0x01, struct snd_pcm_info)
+#define SNDRV_PCM_IOCTL_TSTAMP _IOW('A', 0x02, int)
+#define SNDRV_PCM_IOCTL_TTSTAMP _IOW('A', 0x03, int)
+#define SNDRV_PCM_IOCTL_USER_PVERSION _IOW('A', 0x04, int)
+#define SNDRV_PCM_IOCTL_HW_REFINE _IOWR('A', 0x10, struct snd_pcm_hw_params)
+#define SNDRV_PCM_IOCTL_HW_PARAMS _IOWR('A', 0x11, struct snd_pcm_hw_params)
+#define SNDRV_PCM_IOCTL_HW_FREE _IO('A', 0x12)
+#define SNDRV_PCM_IOCTL_SW_PARAMS _IOWR('A', 0x13, struct snd_pcm_sw_params)
+#define SNDRV_PCM_IOCTL_STATUS _IOR('A', 0x20, struct snd_pcm_status)
+#define SNDRV_PCM_IOCTL_DELAY _IOR('A', 0x21, snd_pcm_sframes_t)
+#define SNDRV_PCM_IOCTL_HWSYNC _IO('A', 0x22)
+#define __SNDRV_PCM_IOCTL_SYNC_PTR _IOWR('A', 0x23, struct __snd_pcm_sync_ptr)
+#define __SNDRV_PCM_IOCTL_SYNC_PTR64 _IOWR('A', 0x23, struct __snd_pcm_sync_ptr64)
+#define SNDRV_PCM_IOCTL_SYNC_PTR _IOWR('A', 0x23, struct snd_pcm_sync_ptr)
+#define SNDRV_PCM_IOCTL_STATUS_EXT _IOWR('A', 0x24, struct snd_pcm_status)
+#define SNDRV_PCM_IOCTL_CHANNEL_INFO _IOR('A', 0x32, struct snd_pcm_channel_info)
+#define SNDRV_PCM_IOCTL_PREPARE _IO('A', 0x40)
+#define SNDRV_PCM_IOCTL_RESET _IO('A', 0x41)
+#define SNDRV_PCM_IOCTL_START _IO('A', 0x42)
+#define SNDRV_PCM_IOCTL_DROP _IO('A', 0x43)
+#define SNDRV_PCM_IOCTL_DRAIN _IO('A', 0x44)
+#define SNDRV_PCM_IOCTL_PAUSE _IOW('A', 0x45, int)
+#define SNDRV_PCM_IOCTL_REWIND _IOW('A', 0x46, snd_pcm_uframes_t)
+#define SNDRV_PCM_IOCTL_RESUME _IO('A', 0x47)
+#define SNDRV_PCM_IOCTL_XRUN _IO('A', 0x48)
+#define SNDRV_PCM_IOCTL_FORWARD _IOW('A', 0x49, snd_pcm_uframes_t)
+#define SNDRV_PCM_IOCTL_WRITEI_FRAMES _IOW('A', 0x50, struct snd_xferi)
+#define SNDRV_PCM_IOCTL_READI_FRAMES _IOR('A', 0x51, struct snd_xferi)
+#define SNDRV_PCM_IOCTL_WRITEN_FRAMES _IOW('A', 0x52, struct snd_xfern)
+#define SNDRV_PCM_IOCTL_READN_FRAMES _IOR('A', 0x53, struct snd_xfern)
+#define SNDRV_PCM_IOCTL_LINK _IOW('A', 0x60, int)
+#define SNDRV_PCM_IOCTL_UNLINK _IO('A', 0x61)
+
+/*****************************************************************************
+ * *
+ * MIDI v1.0 interface *
+ * *
+ *****************************************************************************/
+
+/*
+ * Raw MIDI section - /dev/snd/midi??
+ */
+
+#define SNDRV_RAWMIDI_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 4)
+
+enum {
+ SNDRV_RAWMIDI_STREAM_OUTPUT = 0,
+ SNDRV_RAWMIDI_STREAM_INPUT,
+ SNDRV_RAWMIDI_STREAM_LAST = SNDRV_RAWMIDI_STREAM_INPUT,
+};
+
+#define SNDRV_RAWMIDI_INFO_OUTPUT 0x00000001
+#define SNDRV_RAWMIDI_INFO_INPUT 0x00000002
+#define SNDRV_RAWMIDI_INFO_DUPLEX 0x00000004
+#define SNDRV_RAWMIDI_INFO_UMP 0x00000008
+
+struct snd_rawmidi_info {
+ unsigned int device; /* RO/WR (control): device number */
+ unsigned int subdevice; /* RO/WR (control): subdevice number */
+ int stream; /* WR: stream */
+ int card; /* R: card number */
+ unsigned int flags; /* SNDRV_RAWMIDI_INFO_XXXX */
+ unsigned char id[64]; /* ID (user selectable) */
+ unsigned char name[80]; /* name of device */
+ unsigned char subname[32]; /* name of active or selected subdevice */
+ unsigned int subdevices_count;
+ unsigned int subdevices_avail;
+ unsigned char reserved[64]; /* reserved for future use */
+};
+
+#define SNDRV_RAWMIDI_MODE_FRAMING_MASK (7<<0)
+#define SNDRV_RAWMIDI_MODE_FRAMING_SHIFT 0
+#define SNDRV_RAWMIDI_MODE_FRAMING_NONE (0<<0)
+#define SNDRV_RAWMIDI_MODE_FRAMING_TSTAMP (1<<0)
+#define SNDRV_RAWMIDI_MODE_CLOCK_MASK (7<<3)
+#define SNDRV_RAWMIDI_MODE_CLOCK_SHIFT 3
+#define SNDRV_RAWMIDI_MODE_CLOCK_NONE (0<<3)
+#define SNDRV_RAWMIDI_MODE_CLOCK_REALTIME (1<<3)
+#define SNDRV_RAWMIDI_MODE_CLOCK_MONOTONIC (2<<3)
+#define SNDRV_RAWMIDI_MODE_CLOCK_MONOTONIC_RAW (3<<3)
+
+#define SNDRV_RAWMIDI_FRAMING_DATA_LENGTH 16
+
+struct snd_rawmidi_framing_tstamp {
+ /* For now, frame_type is always 0. Midi 2.0 is expected to add new
+ * types here. Applications are expected to skip unknown frame types.
+ */
+ __u8 frame_type;
+ __u8 length; /* number of valid bytes in data field */
+ __u8 reserved[2];
+ __u32 tv_nsec; /* nanoseconds */
+ __u64 tv_sec; /* seconds */
+ __u8 data[SNDRV_RAWMIDI_FRAMING_DATA_LENGTH];
+} __packed;
+
+struct snd_rawmidi_params {
+ int stream;
+ size_t buffer_size; /* queue size in bytes */
+ size_t avail_min; /* minimum avail bytes for wakeup */
+ unsigned int no_active_sensing: 1; /* do not send active sensing byte in close() */
+ unsigned int mode; /* For input data only, frame incoming data */
+ unsigned char reserved[12]; /* reserved for future use */
+};
+
+#ifndef __KERNEL__
+struct snd_rawmidi_status {
+ int stream;
+ __time_pad pad1;
+ struct timespec tstamp; /* Timestamp */
+ size_t avail; /* available bytes */
+ size_t xruns; /* count of overruns since last status (in bytes) */
+ unsigned char reserved[16]; /* reserved for future use */
+};
+#endif
+
+/* UMP EP info flags */
+#define SNDRV_UMP_EP_INFO_STATIC_BLOCKS 0x01
+
+/* UMP EP Protocol / JRTS capability bits */
+#define SNDRV_UMP_EP_INFO_PROTO_MIDI_MASK 0x0300
+#define SNDRV_UMP_EP_INFO_PROTO_MIDI1 0x0100 /* MIDI 1.0 */
+#define SNDRV_UMP_EP_INFO_PROTO_MIDI2 0x0200 /* MIDI 2.0 */
+#define SNDRV_UMP_EP_INFO_PROTO_JRTS_MASK 0x0003
+#define SNDRV_UMP_EP_INFO_PROTO_JRTS_TX 0x0001 /* JRTS Transmit */
+#define SNDRV_UMP_EP_INFO_PROTO_JRTS_RX 0x0002 /* JRTS Receive */
+
+/* UMP Endpoint information */
+struct snd_ump_endpoint_info {
+ int card; /* card number */
+ int device; /* device number */
+ unsigned int flags; /* additional info */
+ unsigned int protocol_caps; /* protocol capabilities */
+ unsigned int protocol; /* current protocol */
+ unsigned int num_blocks; /* # of function blocks */
+ unsigned short version; /* UMP major/minor version */
+ unsigned short family_id; /* MIDI device family ID */
+ unsigned short model_id; /* MIDI family model ID */
+ unsigned int manufacturer_id; /* MIDI manufacturer ID */
+ unsigned char sw_revision[4]; /* software revision */
+ unsigned short padding;
+ unsigned char name[128]; /* endpoint name string */
+ unsigned char product_id[128]; /* unique product id string */
+ unsigned char reserved[32];
+} __packed;
+
+/* UMP direction */
+#define SNDRV_UMP_DIR_INPUT 0x01
+#define SNDRV_UMP_DIR_OUTPUT 0x02
+#define SNDRV_UMP_DIR_BIDIRECTION 0x03
+
+/* UMP block info flags */
+#define SNDRV_UMP_BLOCK_IS_MIDI1 (1U << 0) /* MIDI 1.0 port w/o restrict */
+#define SNDRV_UMP_BLOCK_IS_LOWSPEED (1U << 1) /* 31.25Kbps B/W MIDI1 port */
+
+/* UMP block user-interface hint */
+#define SNDRV_UMP_BLOCK_UI_HINT_UNKNOWN 0x00
+#define SNDRV_UMP_BLOCK_UI_HINT_RECEIVER 0x01
+#define SNDRV_UMP_BLOCK_UI_HINT_SENDER 0x02
+#define SNDRV_UMP_BLOCK_UI_HINT_BOTH 0x03
+
+/* UMP groups and blocks */
+#define SNDRV_UMP_MAX_GROUPS 16
+#define SNDRV_UMP_MAX_BLOCKS 32
+
+/* UMP Block information */
+struct snd_ump_block_info {
+ int card; /* card number */
+ int device; /* device number */
+ unsigned char block_id; /* block ID (R/W) */
+ unsigned char direction; /* UMP direction */
+ unsigned char active; /* Activeness */
+ unsigned char first_group; /* first group ID */
+ unsigned char num_groups; /* number of groups */
+ unsigned char midi_ci_version; /* MIDI-CI support version */
+ unsigned char sysex8_streams; /* max number of sysex8 streams */
+ unsigned char ui_hint; /* user interface hint */
+ unsigned int flags; /* various info flags */
+ unsigned char name[128]; /* block name string */
+ unsigned char reserved[32];
+} __packed;
+
+#define SNDRV_RAWMIDI_IOCTL_PVERSION _IOR('W', 0x00, int)
+#define SNDRV_RAWMIDI_IOCTL_INFO _IOR('W', 0x01, struct snd_rawmidi_info)
+#define SNDRV_RAWMIDI_IOCTL_USER_PVERSION _IOW('W', 0x02, int)
+#define SNDRV_RAWMIDI_IOCTL_PARAMS _IOWR('W', 0x10, struct snd_rawmidi_params)
+#define SNDRV_RAWMIDI_IOCTL_STATUS _IOWR('W', 0x20, struct snd_rawmidi_status)
+#define SNDRV_RAWMIDI_IOCTL_DROP _IOW('W', 0x30, int)
+#define SNDRV_RAWMIDI_IOCTL_DRAIN _IOW('W', 0x31, int)
+/* Additional ioctls for UMP rawmidi devices */
+#define SNDRV_UMP_IOCTL_ENDPOINT_INFO _IOR('W', 0x40, struct snd_ump_endpoint_info)
+#define SNDRV_UMP_IOCTL_BLOCK_INFO _IOR('W', 0x41, struct snd_ump_block_info)
+
+/*
+ * Timer section - /dev/snd/timer
+ */
+
+#define SNDRV_TIMER_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 7)
+
+enum {
+ SNDRV_TIMER_CLASS_NONE = -1,
+ SNDRV_TIMER_CLASS_SLAVE = 0,
+ SNDRV_TIMER_CLASS_GLOBAL,
+ SNDRV_TIMER_CLASS_CARD,
+ SNDRV_TIMER_CLASS_PCM,
+ SNDRV_TIMER_CLASS_LAST = SNDRV_TIMER_CLASS_PCM,
+};
+
+/* slave timer classes */
+enum {
+ SNDRV_TIMER_SCLASS_NONE = 0,
+ SNDRV_TIMER_SCLASS_APPLICATION,
+ SNDRV_TIMER_SCLASS_SEQUENCER, /* alias */
+ SNDRV_TIMER_SCLASS_OSS_SEQUENCER, /* alias */
+ SNDRV_TIMER_SCLASS_LAST = SNDRV_TIMER_SCLASS_OSS_SEQUENCER,
+};
+
+/* global timers (device member) */
+#define SNDRV_TIMER_GLOBAL_SYSTEM 0
+#define SNDRV_TIMER_GLOBAL_RTC 1 /* unused */
+#define SNDRV_TIMER_GLOBAL_HPET 2
+#define SNDRV_TIMER_GLOBAL_HRTIMER 3
+
+/* info flags */
+#define SNDRV_TIMER_FLG_SLAVE (1<<0) /* cannot be controlled */
+
+struct snd_timer_id {
+ int dev_class;
+ int dev_sclass;
+ int card;
+ int device;
+ int subdevice;
+};
+
+struct snd_timer_ginfo {
+ struct snd_timer_id tid; /* requested timer ID */
+ unsigned int flags; /* timer flags - SNDRV_TIMER_FLG_* */
+ int card; /* card number */
+ unsigned char id[64]; /* timer identification */
+ unsigned char name[80]; /* timer name */
+ unsigned long reserved0; /* reserved for future use */
+ unsigned long resolution; /* average period resolution in ns */
+ unsigned long resolution_min; /* minimal period resolution in ns */
+ unsigned long resolution_max; /* maximal period resolution in ns */
+ unsigned int clients; /* active timer clients */
+ unsigned char reserved[32];
+};
+
+struct snd_timer_gparams {
+ struct snd_timer_id tid; /* requested timer ID */
+ unsigned long period_num; /* requested precise period duration (in seconds) - numerator */
+ unsigned long period_den; /* requested precise period duration (in seconds) - denominator */
+ unsigned char reserved[32];
+};
+
+struct snd_timer_gstatus {
+ struct snd_timer_id tid; /* requested timer ID */
+ unsigned long resolution; /* current period resolution in ns */
+ unsigned long resolution_num; /* precise current period resolution (in seconds) - numerator */
+ unsigned long resolution_den; /* precise current period resolution (in seconds) - denominator */
+ unsigned char reserved[32];
+};
+
+struct snd_timer_select {
+ struct snd_timer_id id; /* bind to timer ID */
+ unsigned char reserved[32]; /* reserved */
+};
+
+struct snd_timer_info {
+ unsigned int flags; /* timer flags - SNDRV_TIMER_FLG_* */
+ int card; /* card number */
+ unsigned char id[64]; /* timer identificator */
+ unsigned char name[80]; /* timer name */
+ unsigned long reserved0; /* reserved for future use */
+ unsigned long resolution; /* average period resolution in ns */
+ unsigned char reserved[64]; /* reserved */
+};
+
+#define SNDRV_TIMER_PSFLG_AUTO (1<<0) /* auto start, otherwise one-shot */
+#define SNDRV_TIMER_PSFLG_EXCLUSIVE (1<<1) /* exclusive use, precise start/stop/pause/continue */
+#define SNDRV_TIMER_PSFLG_EARLY_EVENT (1<<2) /* write early event to the poll queue */
+
+struct snd_timer_params {
+ unsigned int flags; /* flags - SNDRV_TIMER_PSFLG_* */
+ unsigned int ticks; /* requested resolution in ticks */
+ unsigned int queue_size; /* total size of queue (32-1024) */
+ unsigned int reserved0; /* reserved, was: failure locations */
+ unsigned int filter; /* event filter (bitmask of SNDRV_TIMER_EVENT_*) */
+ unsigned char reserved[60]; /* reserved */
+};
+
+#ifndef __KERNEL__
+struct snd_timer_status {
+ struct timespec tstamp; /* Timestamp - last update */
+ unsigned int resolution; /* current period resolution in ns */
+ unsigned int lost; /* counter of master tick lost */
+ unsigned int overrun; /* count of read queue overruns */
+ unsigned int queue; /* used queue size */
+ unsigned char reserved[64]; /* reserved */
+};
+#endif
+
+#define SNDRV_TIMER_IOCTL_PVERSION _IOR('T', 0x00, int)
+#define SNDRV_TIMER_IOCTL_NEXT_DEVICE _IOWR('T', 0x01, struct snd_timer_id)
+#define SNDRV_TIMER_IOCTL_TREAD_OLD _IOW('T', 0x02, int)
+#define SNDRV_TIMER_IOCTL_GINFO _IOWR('T', 0x03, struct snd_timer_ginfo)
+#define SNDRV_TIMER_IOCTL_GPARAMS _IOW('T', 0x04, struct snd_timer_gparams)
+#define SNDRV_TIMER_IOCTL_GSTATUS _IOWR('T', 0x05, struct snd_timer_gstatus)
+#define SNDRV_TIMER_IOCTL_SELECT _IOW('T', 0x10, struct snd_timer_select)
+#define SNDRV_TIMER_IOCTL_INFO _IOR('T', 0x11, struct snd_timer_info)
+#define SNDRV_TIMER_IOCTL_PARAMS _IOW('T', 0x12, struct snd_timer_params)
+#define SNDRV_TIMER_IOCTL_STATUS _IOR('T', 0x14, struct snd_timer_status)
+/* The following four ioctls are changed since 1.0.9 due to confliction */
+#define SNDRV_TIMER_IOCTL_START _IO('T', 0xa0)
+#define SNDRV_TIMER_IOCTL_STOP _IO('T', 0xa1)
+#define SNDRV_TIMER_IOCTL_CONTINUE _IO('T', 0xa2)
+#define SNDRV_TIMER_IOCTL_PAUSE _IO('T', 0xa3)
+#define SNDRV_TIMER_IOCTL_TREAD64 _IOW('T', 0xa4, int)
+
+#if __BITS_PER_LONG == 64
+#define SNDRV_TIMER_IOCTL_TREAD SNDRV_TIMER_IOCTL_TREAD_OLD
+#else
+#define SNDRV_TIMER_IOCTL_TREAD ((sizeof(__kernel_long_t) >= sizeof(time_t)) ? \
+ SNDRV_TIMER_IOCTL_TREAD_OLD : \
+ SNDRV_TIMER_IOCTL_TREAD64)
+#endif
+
+struct snd_timer_read {
+ unsigned int resolution;
+ unsigned int ticks;
+};
+
+enum {
+ SNDRV_TIMER_EVENT_RESOLUTION = 0, /* val = resolution in ns */
+ SNDRV_TIMER_EVENT_TICK, /* val = ticks */
+ SNDRV_TIMER_EVENT_START, /* val = resolution in ns */
+ SNDRV_TIMER_EVENT_STOP, /* val = 0 */
+ SNDRV_TIMER_EVENT_CONTINUE, /* val = resolution in ns */
+ SNDRV_TIMER_EVENT_PAUSE, /* val = 0 */
+ SNDRV_TIMER_EVENT_EARLY, /* val = 0, early event */
+ SNDRV_TIMER_EVENT_SUSPEND, /* val = 0 */
+ SNDRV_TIMER_EVENT_RESUME, /* val = resolution in ns */
+ /* master timer events for slave timer instances */
+ SNDRV_TIMER_EVENT_MSTART = SNDRV_TIMER_EVENT_START + 10,
+ SNDRV_TIMER_EVENT_MSTOP = SNDRV_TIMER_EVENT_STOP + 10,
+ SNDRV_TIMER_EVENT_MCONTINUE = SNDRV_TIMER_EVENT_CONTINUE + 10,
+ SNDRV_TIMER_EVENT_MPAUSE = SNDRV_TIMER_EVENT_PAUSE + 10,
+ SNDRV_TIMER_EVENT_MSUSPEND = SNDRV_TIMER_EVENT_SUSPEND + 10,
+ SNDRV_TIMER_EVENT_MRESUME = SNDRV_TIMER_EVENT_RESUME + 10,
+};
+
+#ifndef __KERNEL__
+struct snd_timer_tread {
+ int event;
+ __time_pad pad1;
+ struct timespec tstamp;
+ unsigned int val;
+ __time_pad pad2;
+};
+#endif
+
+/****************************************************************************
+ * *
+ * Section for driver control interface - /dev/snd/control? *
+ * *
+ ****************************************************************************/
+
+#define SNDRV_CTL_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 9)
+
+struct snd_ctl_card_info {
+ int card; /* card number */
+ int pad; /* reserved for future (was type) */
+ unsigned char id[16]; /* ID of card (user selectable) */
+ unsigned char driver[16]; /* Driver name */
+ unsigned char name[32]; /* Short name of soundcard */
+ unsigned char longname[80]; /* name + info text about soundcard */
+ unsigned char reserved_[16]; /* reserved for future (was ID of mixer) */
+ unsigned char mixername[80]; /* visual mixer identification */
+ unsigned char components[128]; /* card components / fine identification, delimited with one space (AC97 etc..) */
+};
+
+typedef int __bitwise snd_ctl_elem_type_t;
+#define SNDRV_CTL_ELEM_TYPE_NONE ((__force snd_ctl_elem_type_t) 0) /* invalid */
+#define SNDRV_CTL_ELEM_TYPE_BOOLEAN ((__force snd_ctl_elem_type_t) 1) /* boolean type */
+#define SNDRV_CTL_ELEM_TYPE_INTEGER ((__force snd_ctl_elem_type_t) 2) /* integer type */
+#define SNDRV_CTL_ELEM_TYPE_ENUMERATED ((__force snd_ctl_elem_type_t) 3) /* enumerated type */
+#define SNDRV_CTL_ELEM_TYPE_BYTES ((__force snd_ctl_elem_type_t) 4) /* byte array */
+#define SNDRV_CTL_ELEM_TYPE_IEC958 ((__force snd_ctl_elem_type_t) 5) /* IEC958 (S/PDIF) setup */
+#define SNDRV_CTL_ELEM_TYPE_INTEGER64 ((__force snd_ctl_elem_type_t) 6) /* 64-bit integer type */
+#define SNDRV_CTL_ELEM_TYPE_LAST SNDRV_CTL_ELEM_TYPE_INTEGER64
+
+typedef int __bitwise snd_ctl_elem_iface_t;
+#define SNDRV_CTL_ELEM_IFACE_CARD ((__force snd_ctl_elem_iface_t) 0) /* global control */
+#define SNDRV_CTL_ELEM_IFACE_HWDEP ((__force snd_ctl_elem_iface_t) 1) /* hardware dependent device */
+#define SNDRV_CTL_ELEM_IFACE_MIXER ((__force snd_ctl_elem_iface_t) 2) /* virtual mixer device */
+#define SNDRV_CTL_ELEM_IFACE_PCM ((__force snd_ctl_elem_iface_t) 3) /* PCM device */
+#define SNDRV_CTL_ELEM_IFACE_RAWMIDI ((__force snd_ctl_elem_iface_t) 4) /* RawMidi device */
+#define SNDRV_CTL_ELEM_IFACE_TIMER ((__force snd_ctl_elem_iface_t) 5) /* timer device */
+#define SNDRV_CTL_ELEM_IFACE_SEQUENCER ((__force snd_ctl_elem_iface_t) 6) /* sequencer client */
+#define SNDRV_CTL_ELEM_IFACE_LAST SNDRV_CTL_ELEM_IFACE_SEQUENCER
+
+#define SNDRV_CTL_ELEM_ACCESS_READ (1<<0)
+#define SNDRV_CTL_ELEM_ACCESS_WRITE (1<<1)
+#define SNDRV_CTL_ELEM_ACCESS_READWRITE (SNDRV_CTL_ELEM_ACCESS_READ|SNDRV_CTL_ELEM_ACCESS_WRITE)
+#define SNDRV_CTL_ELEM_ACCESS_VOLATILE (1<<2) /* control value may be changed without a notification */
+/* (1 << 3) is unused. */
+#define SNDRV_CTL_ELEM_ACCESS_TLV_READ (1<<4) /* TLV read is possible */
+#define SNDRV_CTL_ELEM_ACCESS_TLV_WRITE (1<<5) /* TLV write is possible */
+#define SNDRV_CTL_ELEM_ACCESS_TLV_READWRITE (SNDRV_CTL_ELEM_ACCESS_TLV_READ|SNDRV_CTL_ELEM_ACCESS_TLV_WRITE)
+#define SNDRV_CTL_ELEM_ACCESS_TLV_COMMAND (1<<6) /* TLV command is possible */
+#define SNDRV_CTL_ELEM_ACCESS_INACTIVE (1<<8) /* control does actually nothing, but may be updated */
+#define SNDRV_CTL_ELEM_ACCESS_LOCK (1<<9) /* write lock */
+#define SNDRV_CTL_ELEM_ACCESS_OWNER (1<<10) /* write lock owner */
+#define SNDRV_CTL_ELEM_ACCESS_TLV_CALLBACK (1<<28) /* kernel use a TLV callback */
+#define SNDRV_CTL_ELEM_ACCESS_USER (1<<29) /* user space element */
+/* bits 30 and 31 are obsoleted (for indirect access) */
+
+/* for further details see the ACPI and PCI power management specification */
+#define SNDRV_CTL_POWER_D0 0x0000 /* full On */
+#define SNDRV_CTL_POWER_D1 0x0100 /* partial On */
+#define SNDRV_CTL_POWER_D2 0x0200 /* partial On */
+#define SNDRV_CTL_POWER_D3 0x0300 /* Off */
+#define SNDRV_CTL_POWER_D3hot (SNDRV_CTL_POWER_D3|0x0000) /* Off, with power */
+#define SNDRV_CTL_POWER_D3cold (SNDRV_CTL_POWER_D3|0x0001) /* Off, without power */
+
+#define SNDRV_CTL_ELEM_ID_NAME_MAXLEN 44
+
+struct snd_ctl_elem_id {
+ unsigned int numid; /* numeric identifier, zero = invalid */
+ snd_ctl_elem_iface_t iface; /* interface identifier */
+ unsigned int device; /* device/client number */
+ unsigned int subdevice; /* subdevice (substream) number */
+ unsigned char name[SNDRV_CTL_ELEM_ID_NAME_MAXLEN]; /* ASCII name of item */
+ unsigned int index; /* index of item */
+};
+
+struct snd_ctl_elem_list {
+ unsigned int offset; /* W: first element ID to get */
+ unsigned int space; /* W: count of element IDs to get */
+ unsigned int used; /* R: count of element IDs set */
+ unsigned int count; /* R: count of all elements */
+ struct snd_ctl_elem_id __user *pids; /* R: IDs */
+ unsigned char reserved[50];
+};
+
+struct snd_ctl_elem_info {
+ struct snd_ctl_elem_id id; /* W: element ID */
+ snd_ctl_elem_type_t type; /* R: value type - SNDRV_CTL_ELEM_TYPE_* */
+ unsigned int access; /* R: value access (bitmask) - SNDRV_CTL_ELEM_ACCESS_* */
+ unsigned int count; /* count of values */
+ __kernel_pid_t owner; /* owner's PID of this control */
+ union {
+ struct {
+ long min; /* R: minimum value */
+ long max; /* R: maximum value */
+ long step; /* R: step (0 variable) */
+ } integer;
+ struct {
+ long long min; /* R: minimum value */
+ long long max; /* R: maximum value */
+ long long step; /* R: step (0 variable) */
+ } integer64;
+ struct {
+ unsigned int items; /* R: number of items */
+ unsigned int item; /* W: item number */
+ char name[64]; /* R: value name */
+ __u64 names_ptr; /* W: names list (ELEM_ADD only) */
+ unsigned int names_length;
+ } enumerated;
+ unsigned char reserved[128];
+ } value;
+ unsigned char reserved[64];
+};
+
+struct snd_ctl_elem_value {
+ struct snd_ctl_elem_id id; /* W: element ID */
+ unsigned int indirect: 1; /* W: indirect access - obsoleted */
+ union {
+ union {
+ long value[128];
+ long *value_ptr; /* obsoleted */
+ } integer;
+ union {
+ long long value[64];
+ long long *value_ptr; /* obsoleted */
+ } integer64;
+ union {
+ unsigned int item[128];
+ unsigned int *item_ptr; /* obsoleted */
+ } enumerated;
+ union {
+ unsigned char data[512];
+ unsigned char *data_ptr; /* obsoleted */
+ } bytes;
+ struct snd_aes_iec958 iec958;
+ } value; /* RO */
+ unsigned char reserved[128];
+};
+
+struct snd_ctl_tlv {
+ unsigned int numid; /* control element numeric identification */
+ unsigned int length; /* in bytes aligned to 4 */
+ unsigned int tlv[]; /* first TLV */
+};
+
+#define SNDRV_CTL_IOCTL_PVERSION _IOR('U', 0x00, int)
+#define SNDRV_CTL_IOCTL_CARD_INFO _IOR('U', 0x01, struct snd_ctl_card_info)
+#define SNDRV_CTL_IOCTL_ELEM_LIST _IOWR('U', 0x10, struct snd_ctl_elem_list)
+#define SNDRV_CTL_IOCTL_ELEM_INFO _IOWR('U', 0x11, struct snd_ctl_elem_info)
+#define SNDRV_CTL_IOCTL_ELEM_READ _IOWR('U', 0x12, struct snd_ctl_elem_value)
+#define SNDRV_CTL_IOCTL_ELEM_WRITE _IOWR('U', 0x13, struct snd_ctl_elem_value)
+#define SNDRV_CTL_IOCTL_ELEM_LOCK _IOW('U', 0x14, struct snd_ctl_elem_id)
+#define SNDRV_CTL_IOCTL_ELEM_UNLOCK _IOW('U', 0x15, struct snd_ctl_elem_id)
+#define SNDRV_CTL_IOCTL_SUBSCRIBE_EVENTS _IOWR('U', 0x16, int)
+#define SNDRV_CTL_IOCTL_ELEM_ADD _IOWR('U', 0x17, struct snd_ctl_elem_info)
+#define SNDRV_CTL_IOCTL_ELEM_REPLACE _IOWR('U', 0x18, struct snd_ctl_elem_info)
+#define SNDRV_CTL_IOCTL_ELEM_REMOVE _IOWR('U', 0x19, struct snd_ctl_elem_id)
+#define SNDRV_CTL_IOCTL_TLV_READ _IOWR('U', 0x1a, struct snd_ctl_tlv)
+#define SNDRV_CTL_IOCTL_TLV_WRITE _IOWR('U', 0x1b, struct snd_ctl_tlv)
+#define SNDRV_CTL_IOCTL_TLV_COMMAND _IOWR('U', 0x1c, struct snd_ctl_tlv)
+#define SNDRV_CTL_IOCTL_HWDEP_NEXT_DEVICE _IOWR('U', 0x20, int)
+#define SNDRV_CTL_IOCTL_HWDEP_INFO _IOR('U', 0x21, struct snd_hwdep_info)
+#define SNDRV_CTL_IOCTL_PCM_NEXT_DEVICE _IOR('U', 0x30, int)
+#define SNDRV_CTL_IOCTL_PCM_INFO _IOWR('U', 0x31, struct snd_pcm_info)
+#define SNDRV_CTL_IOCTL_PCM_PREFER_SUBDEVICE _IOW('U', 0x32, int)
+#define SNDRV_CTL_IOCTL_RAWMIDI_NEXT_DEVICE _IOWR('U', 0x40, int)
+#define SNDRV_CTL_IOCTL_RAWMIDI_INFO _IOWR('U', 0x41, struct snd_rawmidi_info)
+#define SNDRV_CTL_IOCTL_RAWMIDI_PREFER_SUBDEVICE _IOW('U', 0x42, int)
+#define SNDRV_CTL_IOCTL_UMP_NEXT_DEVICE _IOWR('U', 0x43, int)
+#define SNDRV_CTL_IOCTL_UMP_ENDPOINT_INFO _IOWR('U', 0x44, struct snd_ump_endpoint_info)
+#define SNDRV_CTL_IOCTL_UMP_BLOCK_INFO _IOWR('U', 0x45, struct snd_ump_block_info)
+#define SNDRV_CTL_IOCTL_POWER _IOWR('U', 0xd0, int)
+#define SNDRV_CTL_IOCTL_POWER_STATE _IOR('U', 0xd1, int)
+
+/*
+ * Read interface.
+ */
+
+enum sndrv_ctl_event_type {
+ SNDRV_CTL_EVENT_ELEM = 0,
+ SNDRV_CTL_EVENT_LAST = SNDRV_CTL_EVENT_ELEM,
+};
+
+#define SNDRV_CTL_EVENT_MASK_VALUE (1<<0) /* element value was changed */
+#define SNDRV_CTL_EVENT_MASK_INFO (1<<1) /* element info was changed */
+#define SNDRV_CTL_EVENT_MASK_ADD (1<<2) /* element was added */
+#define SNDRV_CTL_EVENT_MASK_TLV (1<<3) /* element TLV tree was changed */
+#define SNDRV_CTL_EVENT_MASK_REMOVE (~0U) /* element was removed */
+
+struct snd_ctl_event {
+ int type; /* event type - SNDRV_CTL_EVENT_* */
+ union {
+ struct {
+ unsigned int mask;
+ struct snd_ctl_elem_id id;
+ } elem;
+ unsigned char data8[60];
+ } data;
+};
+
+/*
+ * Control names
+ */
+
+#define SNDRV_CTL_NAME_NONE ""
+#define SNDRV_CTL_NAME_PLAYBACK "Playback "
+#define SNDRV_CTL_NAME_CAPTURE "Capture "
+
+#define SNDRV_CTL_NAME_IEC958_NONE ""
+#define SNDRV_CTL_NAME_IEC958_SWITCH "Switch"
+#define SNDRV_CTL_NAME_IEC958_VOLUME "Volume"
+#define SNDRV_CTL_NAME_IEC958_DEFAULT "Default"
+#define SNDRV_CTL_NAME_IEC958_MASK "Mask"
+#define SNDRV_CTL_NAME_IEC958_CON_MASK "Con Mask"
+#define SNDRV_CTL_NAME_IEC958_PRO_MASK "Pro Mask"
+#define SNDRV_CTL_NAME_IEC958_PCM_STREAM "PCM Stream"
+#define SNDRV_CTL_NAME_IEC958(expl,direction,what) "IEC958 " expl SNDRV_CTL_NAME_##direction SNDRV_CTL_NAME_IEC958_##what
+
+#endif /* _UAPI__SOUND_ASOUND_H */
diff --git a/tools/include/vdso/bits.h b/tools/include/vdso/bits.h
new file mode 100644
index 0000000000..388b212088
--- /dev/null
+++ b/tools/include/vdso/bits.h
@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __VDSO_BITS_H
+#define __VDSO_BITS_H
+
+#include <vdso/const.h>
+
+#define BIT(nr) (UL(1) << (nr))
+#define BIT_ULL(nr) (ULL(1) << (nr))
+
+#endif /* __VDSO_BITS_H */
diff --git a/tools/include/vdso/const.h b/tools/include/vdso/const.h
new file mode 100644
index 0000000000..94b385ad43
--- /dev/null
+++ b/tools/include/vdso/const.h
@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __VDSO_CONST_H
+#define __VDSO_CONST_H
+
+#include <uapi/linux/const.h>
+
+#define UL(x) (_UL(x))
+#define ULL(x) (_ULL(x))
+
+#endif /* __VDSO_CONST_H */