Merge tag 'perf-core-for-mingo-20160712' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

User visible changes:

- Add demangling of symbols in programs written in the Rust language (David Tolnay)

- Add support for tracepoints in the python binding, including an example, that
  sets up and parses sched:sched_switch events, tools/perf/python/tracepoint.py
  (Jiri Olsa)

- Introduce --stdio-color to set up the color output mode selection in
  'annotate' and 'report', allowing emit color escape sequences when
  redirecting the output of these tools (Arnaldo Carvalho de Melo)

Infrastructure changes:

- Various tweaks to allow the 'perf trace' beautifiers to build without using
  kernel headers and in a wider range of Linux distributions/releases
  (Arnaldo Carvalho de Melo)

- Stop using kernel source files, instead copy what is needed and
  check when the original kernel source file gets modified, warning
  the developers about it. This helps in building the tool in older
  systems and even in recent ones, for just added kernel features
  for which ABI details (struct changes, defines, etc) still are not
  available on system headers (Arnaldo Carvalho de Melo)

- Be consistent in how to use strerror_r, adding a wrapper that makes sure that
  it returns a pointer to passed buffer, and using the XSI variant, that is
  available in more libc implementations (Arnaldo Carvalho de Melo)

- Avoid checking code drift on busibox's diff perf intel-pt-decoder, as it
  doesn't have the '-I' command line switch to check for regexps
  (Arnaldo Carvalho de Melo)

- Add missing headers in various places (Arnaldo Carvalho de Melo)

- Remove unneeded headers from various other places (Arnaldo Carvalho de Melo)

- Add feature detection for gelf_getnote(), disabling SDT support if not
  present (Arnaldo Carvalho de Melo)

- Fix oddities with GCC 5.3.0 by initializing some variables
  (Arnaldo Carvalho de Melo)

- With those changes in place perf now builds on Alpine Linux 3.4, in addition to
  on centos (5, 6, 7), debian (7, 8, experimental), fedora (21, 22, 23, 24, rawhide),
  mageia 5, opensuse (13.2, 42.1) and ubuntu (12.04.5, 14.04.4, 15.10, 16.04) and
  will be test build on those systems prior to future pull requests.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

11 files changed, 1514 insertions, 26 deletions

diff --git a/tools/include/asm-generic/bitops/__ffs.h b/tools/include/asm-generic/bitops/__ffs.h
index c94175015a82..b3accfdf24b9 100644
--- a/tools/include/asm-generic/bitops/__ffs.h
+++ b/tools/include/asm-generic/bitops/__ffs.h
@@ -2,6 +2,7 @@
 #define _TOOLS_LINUX_ASM_GENERIC_BITOPS___FFS_H_
 
 #include <asm/types.h>
+#include <asm/bitsperlong.h>
 
 /**
  * __ffs - find first bit in word.
diff --git a/tools/include/asm-generic/bitops/atomic.h b/tools/include/asm-generic/bitops/atomic.h
index 4bccd7c3d5d6..18663f59d72f 100644
--- a/tools/include/asm-generic/bitops/atomic.h
+++ b/tools/include/asm-generic/bitops/atomic.h
@@ -2,6 +2,7 @@
 #define _TOOLS_LINUX_ASM_GENERIC_BITOPS_ATOMIC_H_
 
 #include <asm/types.h>
+#include <asm/bitsperlong.h>
 
 static inline void set_bit(int nr, unsigned long *addr)
 {
diff --git a/tools/include/asm-generic/bitsperlong.h b/tools/include/asm-generic/bitsperlong.h
new file mode 100644
index 000000000000..d1d70aa19021
--- /dev/null
+++ b/tools/include/asm-generic/bitsperlong.h
@@ -0,0 +1,25 @@
+#ifndef __ASM_GENERIC_BITS_PER_LONG
+#define __ASM_GENERIC_BITS_PER_LONG
+
+#include <uapi/asm-generic/bitsperlong.h>
+
+
+#ifdef CONFIG_64BIT
+#define BITS_PER_LONG 64
+#else
+#define BITS_PER_LONG 32
+#endif /* CONFIG_64BIT */
+
+/*
+ * FIXME: The check currently breaks x86-64 build, so it's
+ * temporarily disabled. Please fix x86-64 and reenable
+ */
+#if 0 && 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
+
+#endif /* __ASM_GENERIC_BITS_PER_LONG */
diff --git a/tools/include/asm/alternative-asm.h b/tools/include/asm/alternative-asm.h
new file mode 100644
index 000000000000..2a4d1bfa2988
--- /dev/null
+++ b/tools/include/asm/alternative-asm.h
@@ -0,0 +1,9 @@
+#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 altinstruction_entry #
+#define ALTERNATIVE_2 #
+
+#endif
diff --git a/tools/include/linux/kernel.h b/tools/include/linux/kernel.h
index 76df53539c2a..28607db02bd3 100644
--- a/tools/include/linux/kernel.h
+++ b/tools/include/linux/kernel.h
@@ -2,8 +2,7 @@
 #define __TOOLS_LINUX_KERNEL_H
 
 #include <stdarg.h>
-#include <stdio.h>
-#include <stdlib.h>
+#include <stddef.h>
 #include <assert.h>
 
 #define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d))
@@ -70,29 +69,8 @@
 #define cpu_to_le64(x)	(x)
 #define cpu_to_le32(x)	(x)
 
-static inline int
-vscnprintf(char *buf, size_t size, const char *fmt, va_list args)
-{
-	int i;
-	ssize_t ssize = size;
-
-	i = vsnprintf(buf, size, fmt, args);
-
-	return (i >= ssize) ? (ssize - 1) : i;
-}
-
-static inline int scnprintf(char * buf, size_t size, const char * fmt, ...)
-{
-	va_list args;
-	ssize_t ssize = size;
-	int i;
-
-	va_start(args, fmt);
-	i = vsnprintf(buf, size, fmt, args);
-	va_end(args);
-
-	return (i >= ssize) ? (ssize - 1) : i;
-}
+int vscnprintf(char *buf, size_t size, const char *fmt, va_list args);
+int scnprintf(char * buf, size_t size, const char * fmt, ...);
 
 /*
  * This looks more complex than it should be. But we need to
diff --git a/tools/include/linux/string.h b/tools/include/linux/string.h
index e26223f1f287..b96879477311 100644
--- a/tools/include/linux/string.h
+++ b/tools/include/linux/string.h
@@ -8,8 +8,10 @@ void *memdup(const void *src, size_t len);
 
 int strtobool(const char *s, bool *res);
 
-#ifndef __UCLIBC__
+#ifdef __GLIBC__
 extern size_t strlcpy(char *dest, const char *src, size_t size);
 #endif
 
+char *str_error_r(int errnum, char *buf, size_t buflen);
+
 #endif /* _LINUX_STRING_H_ */
diff --git a/tools/include/uapi/asm-generic/bitsperlong.h b/tools/include/uapi/asm-generic/bitsperlong.h
new file mode 100644
index 000000000000..23e6c416b85f
--- /dev/null
+++ b/tools/include/uapi/asm-generic/bitsperlong.h
@@ -0,0 +1,15 @@
+#ifndef _UAPI__ASM_GENERIC_BITS_PER_LONG
+#define _UAPI__ASM_GENERIC_BITS_PER_LONG
+
+/*
+ * 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.
+ */
+#ifndef __BITS_PER_LONG
+#define __BITS_PER_LONG 32
+#endif
+
+#endif /* _UAPI__ASM_GENERIC_BITS_PER_LONG */
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
new file mode 100644
index 000000000000..406459b935a2
--- /dev/null
+++ b/tools/include/uapi/linux/bpf.h
@@ -0,0 +1,389 @@
+/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#ifndef _UAPI__LINUX_BPF_H__
+#define _UAPI__LINUX_BPF_H__
+
+#include <linux/types.h>
+#include <linux/bpf_common.h>
+
+/* Extended instruction set based on top of classic BPF */
+
+/* instruction classes */
+#define BPF_ALU64	0x07	/* alu mode in double word width */
+
+/* ld/ldx fields */
+#define BPF_DW		0x18	/* double word */
+#define BPF_XADD	0xc0	/* exclusive add */
+
+/* alu/jmp fields */
+#define BPF_MOV		0xb0	/* mov reg to reg */
+#define BPF_ARSH	0xc0	/* sign extending arithmetic shift right */
+
+/* change endianness of a register */
+#define BPF_END		0xd0	/* flags for endianness conversion: */
+#define BPF_TO_LE	0x00	/* convert to little-endian */
+#define BPF_TO_BE	0x08	/* convert to big-endian */
+#define BPF_FROM_LE	BPF_TO_LE
+#define BPF_FROM_BE	BPF_TO_BE
+
+#define BPF_JNE		0x50	/* jump != */
+#define BPF_JSGT	0x60	/* SGT is signed '>', GT in x86 */
+#define BPF_JSGE	0x70	/* SGE is signed '>=', GE in x86 */
+#define BPF_CALL	0x80	/* function call */
+#define BPF_EXIT	0x90	/* function return */
+
+/* Register numbers */
+enum {
+	BPF_REG_0 = 0,
+	BPF_REG_1,
+	BPF_REG_2,
+	BPF_REG_3,
+	BPF_REG_4,
+	BPF_REG_5,
+	BPF_REG_6,
+	BPF_REG_7,
+	BPF_REG_8,
+	BPF_REG_9,
+	BPF_REG_10,
+	__MAX_BPF_REG,
+};
+
+/* BPF has 10 general purpose 64-bit registers and stack frame. */
+#define MAX_BPF_REG	__MAX_BPF_REG
+
+struct bpf_insn {
+	__u8	code;		/* opcode */
+	__u8	dst_reg:4;	/* dest register */
+	__u8	src_reg:4;	/* source register */
+	__s16	off;		/* signed offset */
+	__s32	imm;		/* signed immediate constant */
+};
+
+/* BPF syscall commands, see bpf(2) man-page for details. */
+enum bpf_cmd {
+	BPF_MAP_CREATE,
+	BPF_MAP_LOOKUP_ELEM,
+	BPF_MAP_UPDATE_ELEM,
+	BPF_MAP_DELETE_ELEM,
+	BPF_MAP_GET_NEXT_KEY,
+	BPF_PROG_LOAD,
+	BPF_OBJ_PIN,
+	BPF_OBJ_GET,
+};
+
+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,
+};
+
+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,
+};
+
+#define BPF_PSEUDO_MAP_FD	1
+
+/* flags for BPF_MAP_UPDATE_ELEM command */
+#define BPF_ANY		0 /* create new element or update existing */
+#define BPF_NOEXIST	1 /* create new element if it didn't exist */
+#define BPF_EXIST	2 /* update existing element */
+
+#define BPF_F_NO_PREALLOC	(1U << 0)
+
+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;	/* prealloc or not */
+	};
+
+	struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
+		__u32		map_fd;
+		__aligned_u64	key;
+		union {
+			__aligned_u64 value;
+			__aligned_u64 next_key;
+		};
+		__u64		flags;
+	};
+
+	struct { /* anonymous struct used by BPF_PROG_LOAD command */
+		__u32		prog_type;	/* one of enum bpf_prog_type */
+		__u32		insn_cnt;
+		__aligned_u64	insns;
+		__aligned_u64	license;
+		__u32		log_level;	/* verbosity level of verifier */
+		__u32		log_size;	/* size of user buffer */
+		__aligned_u64	log_buf;	/* user supplied buffer */
+		__u32		kern_version;	/* checked when prog_type=kprobe */
+	};
+
+	struct { /* anonymous struct used by BPF_OBJ_* commands */
+		__aligned_u64	pathname;
+		__u32		bpf_fd;
+	};
+} __attribute__((aligned(8)));
+
+/* integer value in 'imm' field of BPF_CALL instruction selects which helper
+ * function eBPF program intends to call
+ */
+enum bpf_func_id {
+	BPF_FUNC_unspec,
+	BPF_FUNC_map_lookup_elem, /* void *map_lookup_elem(&map, &key) */
+	BPF_FUNC_map_update_elem, /* int map_update_elem(&map, &key, &value, flags) */
+	BPF_FUNC_map_delete_elem, /* int map_delete_elem(&map, &key) */
+	BPF_FUNC_probe_read,      /* int bpf_probe_read(void *dst, int size, void *src) */
+	BPF_FUNC_ktime_get_ns,    /* u64 bpf_ktime_get_ns(void) */
+	BPF_FUNC_trace_printk,    /* int bpf_trace_printk(const char *fmt, int fmt_size, ...) */
+	BPF_FUNC_get_prandom_u32, /* u32 prandom_u32(void) */
+	BPF_FUNC_get_smp_processor_id, /* u32 raw_smp_processor_id(void) */
+
+	/**
+	 * skb_store_bytes(skb, offset, from, len, flags) - store bytes into packet
+	 * @skb: pointer to skb
+	 * @offset: offset within packet from skb->mac_header
+	 * @from: pointer where to copy bytes from
+	 * @len: number of bytes to store into packet
+	 * @flags: bit 0 - if true, recompute skb->csum
+	 *         other bits - reserved
+	 * Return: 0 on success
+	 */
+	BPF_FUNC_skb_store_bytes,
+
+	/**
+	 * l3_csum_replace(skb, offset, from, to, flags) - recompute IP checksum
+	 * @skb: pointer to skb
+	 * @offset: offset within packet where IP checksum is located
+	 * @from: old value of header field
+	 * @to: new value of header field
+	 * @flags: bits 0-3 - size of header field
+	 *         other bits - reserved
+	 * Return: 0 on success
+	 */
+	BPF_FUNC_l3_csum_replace,
+
+	/**
+	 * l4_csum_replace(skb, offset, from, to, flags) - recompute TCP/UDP checksum
+	 * @skb: pointer to skb
+	 * @offset: offset within packet where TCP/UDP checksum is located
+	 * @from: old value of header field
+	 * @to: new value of header field
+	 * @flags: bits 0-3 - size of header field
+	 *         bit 4 - is pseudo header
+	 *         other bits - reserved
+	 * Return: 0 on success
+	 */
+	BPF_FUNC_l4_csum_replace,
+
+	/**
+	 * bpf_tail_call(ctx, prog_array_map, index) - jump into another BPF program
+	 * @ctx: context pointer passed to next program
+	 * @prog_array_map: pointer to map which type is BPF_MAP_TYPE_PROG_ARRAY
+	 * @index: index inside array that selects specific program to run
+	 * Return: 0 on success
+	 */
+	BPF_FUNC_tail_call,
+
+	/**
+	 * bpf_clone_redirect(skb, ifindex, flags) - redirect to another netdev
+	 * @skb: pointer to skb
+	 * @ifindex: ifindex of the net device
+	 * @flags: bit 0 - if set, redirect to ingress instead of egress
+	 *         other bits - reserved
+	 * Return: 0 on success
+	 */
+	BPF_FUNC_clone_redirect,
+
+	/**
+	 * u64 bpf_get_current_pid_tgid(void)
+	 * Return: current->tgid << 32 | current->pid
+	 */
+	BPF_FUNC_get_current_pid_tgid,
+
+	/**
+	 * u64 bpf_get_current_uid_gid(void)
+	 * Return: current_gid << 32 | current_uid
+	 */
+	BPF_FUNC_get_current_uid_gid,
+
+	/**
+	 * bpf_get_current_comm(char *buf, int size_of_buf)
+	 * stores current->comm into buf
+	 * Return: 0 on success
+	 */
+	BPF_FUNC_get_current_comm,
+
+	/**
+	 * bpf_get_cgroup_classid(skb) - retrieve a proc's classid
+	 * @skb: pointer to skb
+	 * Return: classid if != 0
+	 */
+	BPF_FUNC_get_cgroup_classid,
+	BPF_FUNC_skb_vlan_push, /* bpf_skb_vlan_push(skb, vlan_proto, vlan_tci) */
+	BPF_FUNC_skb_vlan_pop,  /* bpf_skb_vlan_pop(skb) */
+
+	/**
+	 * bpf_skb_[gs]et_tunnel_key(skb, key, size, flags)
+	 * retrieve or populate tunnel metadata
+	 * @skb: pointer to skb
+	 * @key: pointer to 'struct bpf_tunnel_key'
+	 * @size: size of 'struct bpf_tunnel_key'
+	 * @flags: room for future extensions
+	 * Retrun: 0 on success
+	 */
+	BPF_FUNC_skb_get_tunnel_key,
+	BPF_FUNC_skb_set_tunnel_key,
+	BPF_FUNC_perf_event_read,	/* u64 bpf_perf_event_read(&map, index) */
+	/**
+	 * bpf_redirect(ifindex, flags) - redirect to another netdev
+	 * @ifindex: ifindex of the net device
+	 * @flags: bit 0 - if set, redirect to ingress instead of egress
+	 *         other bits - reserved
+	 * Return: TC_ACT_REDIRECT
+	 */
+	BPF_FUNC_redirect,
+
+	/**
+	 * bpf_get_route_realm(skb) - retrieve a dst's tclassid
+	 * @skb: pointer to skb
+	 * Return: realm if != 0
+	 */
+	BPF_FUNC_get_route_realm,
+
+	/**
+	 * bpf_perf_event_output(ctx, map, index, data, size) - output perf raw sample
+	 * @ctx: struct pt_regs*
+	 * @map: pointer to perf_event_array map
+	 * @index: index of event in the map
+	 * @data: data on stack to be output as raw data
+	 * @size: size of data
+	 * Return: 0 on success
+	 */
+	BPF_FUNC_perf_event_output,
+	BPF_FUNC_skb_load_bytes,
+
+	/**
+	 * bpf_get_stackid(ctx, map, flags) - walk user or kernel stack and return id
+	 * @ctx: struct pt_regs*
+	 * @map: pointer to stack_trace map
+	 * @flags: bits 0-7 - numer of stack frames to skip
+	 *         bit 8 - collect user stack instead of kernel
+	 *         bit 9 - compare stacks by hash only
+	 *         bit 10 - if two different stacks hash into the same stackid
+	 *                  discard old
+	 *         other bits - reserved
+	 * Return: >= 0 stackid on success or negative error
+	 */
+	BPF_FUNC_get_stackid,
+
+	/**
+	 * bpf_csum_diff(from, from_size, to, to_size, seed) - calculate csum diff
+	 * @from: raw from buffer
+	 * @from_size: length of from buffer
+	 * @to: raw to buffer
+	 * @to_size: length of to buffer
+	 * @seed: optional seed
+	 * Return: csum result
+	 */
+	BPF_FUNC_csum_diff,
+
+	/**
+	 * bpf_skb_[gs]et_tunnel_opt(skb, opt, size)
+	 * retrieve or populate tunnel options metadata
+	 * @skb: pointer to skb
+	 * @opt: pointer to raw tunnel option data
+	 * @size: size of @opt
+	 * Return: 0 on success for set, option size for get
+	 */
+	BPF_FUNC_skb_get_tunnel_opt,
+	BPF_FUNC_skb_set_tunnel_opt,
+	__BPF_FUNC_MAX_ID,
+};
+
+/* All flags used by eBPF helper functions, placed here. */
+
+/* BPF_FUNC_skb_store_bytes flags. */
+#define BPF_F_RECOMPUTE_CSUM		(1ULL << 0)
+#define BPF_F_INVALIDATE_HASH		(1ULL << 1)
+
+/* BPF_FUNC_l3_csum_replace and BPF_FUNC_l4_csum_replace flags.
+ * First 4 bits are for passing the header field size.
+ */
+#define BPF_F_HDR_FIELD_MASK		0xfULL
+
+/* BPF_FUNC_l4_csum_replace flags. */
+#define BPF_F_PSEUDO_HDR		(1ULL << 4)
+#define BPF_F_MARK_MANGLED_0		(1ULL << 5)
+
+/* BPF_FUNC_clone_redirect and BPF_FUNC_redirect flags. */
+#define BPF_F_INGRESS			(1ULL << 0)
+
+/* BPF_FUNC_skb_set_tunnel_key and BPF_FUNC_skb_get_tunnel_key flags. */
+#define BPF_F_TUNINFO_IPV6		(1ULL << 0)
+
+/* BPF_FUNC_get_stackid flags. */
+#define BPF_F_SKIP_FIELD_MASK		0xffULL
+#define BPF_F_USER_STACK		(1ULL << 8)
+#define BPF_F_FAST_STACK_CMP		(1ULL << 9)
+#define BPF_F_REUSE_STACKID		(1ULL << 10)
+
+/* BPF_FUNC_skb_set_tunnel_key flags. */
+#define BPF_F_ZERO_CSUM_TX		(1ULL << 1)
+#define BPF_F_DONT_FRAGMENT		(1ULL << 2)
+
+/* BPF_FUNC_perf_event_output flags. */
+#define BPF_F_INDEX_MASK		0xffffffffULL
+#define BPF_F_CURRENT_CPU		BPF_F_INDEX_MASK
+
+/* 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;
+};
+
+struct bpf_tunnel_key {
+	__u32 tunnel_id;
+	union {
+		__u32 remote_ipv4;
+		__u32 remote_ipv6[4];
+	};
+	__u8 tunnel_tos;
+	__u8 tunnel_ttl;
+	__u16 tunnel_ext;
+	__u32 tunnel_label;
+};
+
+#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 000000000000..a5c220e0828f
--- /dev/null
+++ b/tools/include/uapi/linux/bpf_common.h
@@ -0,0 +1,55 @@
+#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
+#define		BPF_H		0x08
+#define		BPF_B		0x10
+#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/hw_breakpoint.h b/tools/include/uapi/linux/hw_breakpoint.h
new file mode 100644
index 000000000000..b04000a2296a
--- /dev/null
+++ b/tools/include/uapi/linux/hw_breakpoint.h
@@ -0,0 +1,30 @@
+#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_4 = 4,
+	HW_BREAKPOINT_LEN_8 = 8,
+};
+
+enum {
+	HW_BREAKPOINT_EMPTY	= 0,
+	HW_BREAKPOINT_R		= 1,
+	HW_BREAKPOINT_W		= 2,
+	HW_BREAKPOINT_RW	= HW_BREAKPOINT_R | HW_BREAKPOINT_W,
+	HW_BREAKPOINT_X		= 4,
+	HW_BREAKPOINT_INVALID   = HW_BREAKPOINT_RW | HW_BREAKPOINT_X,
+};
+
+enum bp_type_idx {
+	TYPE_INST 	= 0,
+#ifdef CONFIG_HAVE_MIXED_BREAKPOINTS_REGS
+	TYPE_DATA	= 0,
+#else
+	TYPE_DATA	= 1,
+#endif
+	TYPE_MAX
+};
+
+#endif /* _UAPI_LINUX_HW_BREAKPOINT_H */
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
new file mode 100644
index 000000000000..c66a485a24ac
--- /dev/null
+++ b/tools/include/uapi/linux/perf_event.h
@@ -0,0 +1,983 @@
+/*
+ * Performance events:
+ *
+ *    Copyright (C) 2008-2009, Thomas Gleixner <tglx@linutronix.de>
+ *    Copyright (C) 2008-2011, Red Hat, Inc., Ingo Molnar
+ *    Copyright (C) 2008-2011, Red Hat, Inc., Peter Zijlstra
+ *
+ * Data type definitions, declarations, prototypes.
+ *
+ *    Started by: Thomas Gleixner and Ingo Molnar
+ *
+ * For licencing details see kernel-base/COPYING
+ */
+#ifndef _UAPI_LINUX_PERF_EVENT_H
+#define _UAPI_LINUX_PERF_EVENT_H
+
+#include <linux/types.h>
+#include <linux/ioctl.h>
+#include <asm/byteorder.h>
+
+/*
+ * User-space ABI bits:
+ */
+
+/*
+ * attr.type
+ */
+enum perf_type_id {
+	PERF_TYPE_HARDWARE			= 0,
+	PERF_TYPE_SOFTWARE			= 1,
+	PERF_TYPE_TRACEPOINT			= 2,
+	PERF_TYPE_HW_CACHE			= 3,
+	PERF_TYPE_RAW				= 4,
+	PERF_TYPE_BREAKPOINT			= 5,
+
+	PERF_TYPE_MAX,				/* non-ABI */
+};
+
+/*
+ * Generalized performance event event_id types, used by the
+ * attr.event_id parameter of the sys_perf_event_open()
+ * syscall:
+ */
+enum perf_hw_id {
+	/*
+	 * Common hardware events, generalized by the kernel:
+	 */
+	PERF_COUNT_HW_CPU_CYCLES		= 0,
+	PERF_COUNT_HW_INSTRUCTIONS		= 1,
+	PERF_COUNT_HW_CACHE_REFERENCES		= 2,
+	PERF_COUNT_HW_CACHE_MISSES		= 3,
+	PERF_COUNT_HW_BRANCH_INSTRUCTIONS	= 4,
+	PERF_COUNT_HW_BRANCH_MISSES		= 5,
+	PERF_COUNT_HW_BUS_CYCLES		= 6,
+	PERF_COUNT_HW_STALLED_CYCLES_FRONTEND	= 7,
+	PERF_COUNT_HW_STALLED_CYCLES_BACKEND	= 8,
+	PERF_COUNT_HW_REF_CPU_CYCLES		= 9,
+
+	PERF_COUNT_HW_MAX,			/* non-ABI */
+};
+
+/*
+ * Generalized hardware cache events:
+ *
+ *       { L1-D, L1-I, LLC, ITLB, DTLB, BPU, NODE } x
+ *       { read, write, prefetch } x
+ *       { accesses, misses }
+ */
+enum perf_hw_cache_id {
+	PERF_COUNT_HW_CACHE_L1D			= 0,
+	PERF_COUNT_HW_CACHE_L1I			= 1,
+	PERF_COUNT_HW_CACHE_LL			= 2,
+	PERF_COUNT_HW_CACHE_DTLB		= 3,
+	PERF_COUNT_HW_CACHE_ITLB		= 4,
+	PERF_COUNT_HW_CACHE_BPU			= 5,
+	PERF_COUNT_HW_CACHE_NODE		= 6,
+
+	PERF_COUNT_HW_CACHE_MAX,		/* non-ABI */
+};
+
+enum perf_hw_cache_op_id {
+	PERF_COUNT_HW_CACHE_OP_READ		= 0,
+	PERF_COUNT_HW_CACHE_OP_WRITE		= 1,
+	PERF_COUNT_HW_CACHE_OP_PREFETCH		= 2,
+
+	PERF_COUNT_HW_CACHE_OP_MAX,		/* non-ABI */
+};
+
+enum perf_hw_cache_op_result_id {
+	PERF_COUNT_HW_CACHE_RESULT_ACCESS	= 0,
+	PERF_COUNT_HW_CACHE_RESULT_MISS		= 1,
+
+	PERF_COUNT_HW_CACHE_RESULT_MAX,		/* non-ABI */
+};
+
+/*
+ * Special "software" events provided by the kernel, even if the hardware
+ * does not support performance events. These events measure various
+ * physical and sw events of the kernel (and allow the profiling of them as
+ * well):
+ */
+enum perf_sw_ids {
+	PERF_COUNT_SW_CPU_CLOCK			= 0,
+	PERF_COUNT_SW_TASK_CLOCK		= 1,
+	PERF_COUNT_SW_PAGE_FAULTS		= 2,
+	PERF_COUNT_SW_CONTEXT_SWITCHES		= 3,
+	PERF_COUNT_SW_CPU_MIGRATIONS		= 4,
+	PERF_COUNT_SW_PAGE_FAULTS_MIN		= 5,
+	PERF_COUNT_SW_PAGE_FAULTS_MAJ		= 6,
+	PERF_COUNT_SW_ALIGNMENT_FAULTS		= 7,
+	PERF_COUNT_SW_EMULATION_FAULTS		= 8,
+	PERF_COUNT_SW_DUMMY			= 9,
+	PERF_COUNT_SW_BPF_OUTPUT		= 10,
+
+	PERF_COUNT_SW_MAX,			/* non-ABI */
+};
+
+/*
+ * Bits that can be set in attr.sample_type to request information
+ * in the overflow packets.
+ */
+enum perf_event_sample_format {
+	PERF_SAMPLE_IP				= 1U << 0,
+	PERF_SAMPLE_TID				= 1U << 1,
+	PERF_SAMPLE_TIME			= 1U << 2,
+	PERF_SAMPLE_ADDR			= 1U << 3,
+	PERF_SAMPLE_READ			= 1U << 4,
+	PERF_SAMPLE_CALLCHAIN			= 1U << 5,
+	PERF_SAMPLE_ID				= 1U << 6,
+	PERF_SAMPLE_CPU				= 1U << 7,
+	PERF_SAMPLE_PERIOD			= 1U << 8,
+	PERF_SAMPLE_STREAM_ID			= 1U << 9,
+	PERF_SAMPLE_RAW				= 1U << 10,
+	PERF_SAMPLE_BRANCH_STACK		= 1U << 11,
+	PERF_SAMPLE_REGS_USER			= 1U << 12,
+	PERF_SAMPLE_STACK_USER			= 1U << 13,
+	PERF_SAMPLE_WEIGHT			= 1U << 14,
+	PERF_SAMPLE_DATA_SRC			= 1U << 15,
+	PERF_SAMPLE_IDENTIFIER			= 1U << 16,
+	PERF_SAMPLE_TRANSACTION			= 1U << 17,
+	PERF_SAMPLE_REGS_INTR			= 1U << 18,
+
+	PERF_SAMPLE_MAX = 1U << 19,		/* non-ABI */
+};
+
+/*
+ * 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_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_MAX		= 1U << PERF_SAMPLE_BRANCH_MAX_SHIFT,
+};
+
+#define PERF_SAMPLE_BRANCH_PLM_ALL \
+	(PERF_SAMPLE_BRANCH_USER|\
+	 PERF_SAMPLE_BRANCH_KERNEL|\
+	 PERF_SAMPLE_BRANCH_HV)
+
+/*
+ * Values to determine ABI of the registers dump.
+ */
+enum perf_sample_regs_abi {
+	PERF_SAMPLE_REGS_ABI_NONE	= 0,
+	PERF_SAMPLE_REGS_ABI_32		= 1,
+	PERF_SAMPLE_REGS_ABI_64		= 2,
+};
+
+/*
+ * Values for the memory transaction event qualifier, mostly for
+ * abort events. Multiple bits can be set.
+ */
+enum {
+	PERF_TXN_ELISION        = (1 << 0), /* From elision */
+	PERF_TXN_TRANSACTION    = (1 << 1), /* From transaction */
+	PERF_TXN_SYNC           = (1 << 2), /* Instruction is related */
+	PERF_TXN_ASYNC          = (1 << 3), /* Instruction not related */
+	PERF_TXN_RETRY          = (1 << 4), /* Retry possible */
+	PERF_TXN_CONFLICT       = (1 << 5), /* Conflict abort */
+	PERF_TXN_CAPACITY_WRITE = (1 << 6), /* Capacity write abort */
+	PERF_TXN_CAPACITY_READ  = (1 << 7), /* Capacity read abort */
+
+	PERF_TXN_MAX	        = (1 << 8), /* non-ABI */
+
+	/* bits 32..63 are reserved for the abort code */
+
+	PERF_TXN_ABORT_MASK  = (0xffffffffULL << 32),
+	PERF_TXN_ABORT_SHIFT = 32,
+};
+
+/*
+ * The format of the data returned by read() on a perf event fd,
+ * as specified by attr.read_format:
+ *
+ * struct read_format {
+ *	{ u64		value;
+ *	  { u64		time_enabled; } && PERF_FORMAT_TOTAL_TIME_ENABLED
+ *	  { u64		time_running; } && PERF_FORMAT_TOTAL_TIME_RUNNING
+ *	  { u64		id;           } && PERF_FORMAT_ID
+ *	} && !PERF_FORMAT_GROUP
+ *
+ *	{ u64		nr;
+ *	  { u64		time_enabled; } && PERF_FORMAT_TOTAL_TIME_ENABLED
+ *	  { u64		time_running; } && PERF_FORMAT_TOTAL_TIME_RUNNING
+ *	  { u64		value;
+ *	    { u64	id;           } && PERF_FORMAT_ID
+ *	  }		cntr[nr];
+ *	} && PERF_FORMAT_GROUP
+ * };
+ */
+enum perf_event_read_format {
+	PERF_FORMAT_TOTAL_TIME_ENABLED		= 1U << 0,
+	PERF_FORMAT_TOTAL_TIME_RUNNING		= 1U << 1,
+	PERF_FORMAT_ID				= 1U << 2,
+	PERF_FORMAT_GROUP			= 1U << 3,
+
+	PERF_FORMAT_MAX = 1U << 4,		/* non-ABI */
+};
+
+#define PERF_ATTR_SIZE_VER0	64	/* sizeof first published struct */
+#define PERF_ATTR_SIZE_VER1	72	/* add: config2 */
+#define PERF_ATTR_SIZE_VER2	80	/* add: branch_sample_type */
+#define PERF_ATTR_SIZE_VER3	96	/* add: sample_regs_user */
+					/* add: sample_stack_user */
+#define PERF_ATTR_SIZE_VER4	104	/* add: sample_regs_intr */
+#define PERF_ATTR_SIZE_VER5	112	/* add: aux_watermark */
+
+/*
+ * Hardware event_id to monitor via a performance monitoring event:
+ *
+ * @sample_max_stack: Max number of frame pointers in a callchain,
+ *		      should be < /proc/sys/kernel/perf_event_max_stack
+ */
+struct perf_event_attr {
+
+	/*
+	 * Major type: hardware/software/tracepoint/etc.
+	 */
+	__u32			type;
+
+	/*
+	 * Size of the attr structure, for fwd/bwd compat.
+	 */
+	__u32			size;
+
+	/*
+	 * Type specific configuration information.
+	 */
+	__u64			config;
+
+	union {
+		__u64		sample_period;
+		__u64		sample_freq;
+	};
+
+	__u64			sample_type;
+	__u64			read_format;
+
+	__u64			disabled       :  1, /* off by default        */
+				inherit	       :  1, /* children inherit it   */
+				pinned	       :  1, /* must always be on PMU */
+				exclusive      :  1, /* only group on PMU     */
+				exclude_user   :  1, /* don't count user      */
+				exclude_kernel :  1, /* ditto kernel          */
+				exclude_hv     :  1, /* ditto hypervisor      */
+				exclude_idle   :  1, /* don't count when idle */
+				mmap           :  1, /* include mmap data     */
+				comm	       :  1, /* include comm data     */
+				freq           :  1, /* use freq, not period  */
+				inherit_stat   :  1, /* per task counts       */
+				enable_on_exec :  1, /* next exec enables     */
+				task           :  1, /* trace fork/exit       */
+				watermark      :  1, /* wakeup_watermark      */
+				/*
+				 * precise_ip:
+				 *
+				 *  0 - SAMPLE_IP can have arbitrary skid
+				 *  1 - SAMPLE_IP must have constant skid
+				 *  2 - SAMPLE_IP requested to have 0 skid
+				 *  3 - SAMPLE_IP must have 0 skid
+				 *
+				 *  See also PERF_RECORD_MISC_EXACT_IP
+				 */
+				precise_ip     :  2, /* skid constraint       */
+				mmap_data      :  1, /* non-exec mmap data    */
+				sample_id_all  :  1, /* sample_type all events */
+
+				exclude_host   :  1, /* don't count in host   */
+				exclude_guest  :  1, /* don't count in guest  */
+
+				exclude_callchain_kernel : 1, /* exclude kernel callchains */
+				exclude_callchain_user   : 1, /* exclude user callchains */
+				mmap2          :  1, /* include mmap with inode data     */
+				comm_exec      :  1, /* flag comm events that are due to an exec */
+				use_clockid    :  1, /* use @clockid for time fields */
+				context_switch :  1, /* context switch data */
+				write_backward :  1, /* Write ring buffer from end to beginning */
+				__reserved_1   : 36;
+
+	union {
+		__u32		wakeup_events;	  /* wakeup every n events */
+		__u32		wakeup_watermark; /* bytes before wakeup   */
+	};
+
+	__u32			bp_type;
+	union {
+		__u64		bp_addr;
+		__u64		config1; /* extension of config */
+	};
+	union {
+		__u64		bp_len;
+		__u64		config2; /* extension of config1 */
+	};
+	__u64	branch_sample_type; /* enum perf_branch_sample_type */
+
+	/*
+	 * Defines set of user regs to dump on samples.
+	 * See asm/perf_regs.h for details.
+	 */
+	__u64	sample_regs_user;
+
+	/*
+	 * Defines size of the user stack to dump on samples.
+	 */
+	__u32	sample_stack_user;
+
+	__s32	clockid;
+	/*
+	 * Defines set of regs to dump for each sample
+	 * state captured on:
+	 *  - precise = 0: PMU interrupt
+	 *  - precise > 0: sampled instruction
+	 *
+	 * See asm/perf_regs.h for details.
+	 */
+	__u64	sample_regs_intr;
+
+	/*
+	 * Wakeup watermark for AUX area
+	 */
+	__u32	aux_watermark;
+	__u16	sample_max_stack;
+	__u16	__reserved_2;	/* align to __u64 */
+};
+
+#define perf_flags(attr)	(*(&(attr)->read_format + 1))
+
+/*
+ * Ioctls that can be done on a perf event fd:
+ */
+#define PERF_EVENT_IOC_ENABLE		_IO ('$', 0)
+#define PERF_EVENT_IOC_DISABLE		_IO ('$', 1)
+#define PERF_EVENT_IOC_REFRESH		_IO ('$', 2)
+#define PERF_EVENT_IOC_RESET		_IO ('$', 3)
+#define PERF_EVENT_IOC_PERIOD		_IOW('$', 4, __u64)
+#define PERF_EVENT_IOC_SET_OUTPUT	_IO ('$', 5)
+#define PERF_EVENT_IOC_SET_FILTER	_IOW('$', 6, char *)
+#define PERF_EVENT_IOC_ID		_IOR('$', 7, __u64 *)
+#define PERF_EVENT_IOC_SET_BPF		_IOW('$', 8, __u32)
+#define PERF_EVENT_IOC_PAUSE_OUTPUT	_IOW('$', 9, __u32)
+
+enum perf_event_ioc_flags {
+	PERF_IOC_FLAG_GROUP		= 1U << 0,
+};
+
+/*
+ * Structure of the page that can be mapped via mmap
+ */
+struct perf_event_mmap_page {
+	__u32	version;		/* version number of this structure */
+	__u32	compat_version;		/* lowest version this is compat with */
+
+	/*
+	 * Bits needed to read the hw events in user-space.
+	 *
+	 *   u32 seq, time_mult, time_shift, index, width;
+	 *   u64 count, enabled, running;
+	 *   u64 cyc, time_offset;
+	 *   s64 pmc = 0;
+	 *
+	 *   do {
+	 *     seq = pc->lock;
+	 *     barrier()
+	 *
+	 *     enabled = pc->time_enabled;
+	 *     running = pc->time_running;
+	 *
+	 *     if (pc->cap_usr_time && enabled != running) {
+	 *       cyc = rdtsc();
+	 *       time_offset = pc->time_offset;
+	 *       time_mult   = pc->time_mult;
+	 *       time_shift  = pc->time_shift;
+	 *     }
+	 *
+	 *     index = pc->index;
+	 *     count = pc->offset;
+	 *     if (pc->cap_user_rdpmc && index) {
+	 *       width = pc->pmc_width;
+	 *       pmc = rdpmc(index - 1);
+	 *     }
+	 *
+	 *     barrier();
+	 *   } while (pc->lock != seq);
+	 *
+	 * NOTE: for obvious reason this only works on self-monitoring
+	 *       processes.
+	 */
+	__u32	lock;			/* seqlock for synchronization */
+	__u32	index;			/* hardware event identifier */
+	__s64	offset;			/* add to hardware event value */
+	__u64	time_enabled;		/* time event active */
+	__u64	time_running;		/* time event on cpu */
+	union {
+		__u64	capabilities;
+		struct {
+			__u64	cap_bit0		: 1, /* Always 0, deprecated, see commit 860f085b74e9 */
+				cap_bit0_is_deprecated	: 1, /* Always 1, signals that bit 0 is zero */
+
+				cap_user_rdpmc		: 1, /* The RDPMC instruction can be used to read counts */
+				cap_user_time		: 1, /* The time_* fields are used */
+				cap_user_time_zero	: 1, /* The time_zero field is used */
+				cap_____res		: 59;
+		};
+	};
+
+	/*
+	 * If cap_user_rdpmc this field provides the bit-width of the value
+	 * read using the rdpmc() or equivalent instruction. This can be used
+	 * to sign extend the result like:
+	 *
+	 *   pmc <<= 64 - width;
+	 *   pmc >>= 64 - width; // signed shift right
+	 *   count += pmc;
+	 */
+	__u16	pmc_width;
+
+	/*
+	 * If cap_usr_time the below fields can be used to compute the time
+	 * delta since time_enabled (in ns) using rdtsc or similar.
+	 *
+	 *   u64 quot, rem;
+	 *   u64 delta;
+	 *
+	 *   quot = (cyc >> time_shift);
+	 *   rem = cyc & (((u64)1 << time_shift) - 1);
+	 *   delta = time_offset + quot * time_mult +
+	 *              ((rem * time_mult) >> time_shift);
+	 *
+	 * Where time_offset,time_mult,time_shift and cyc are read in the
+	 * seqcount loop described above. This delta can then be added to
+	 * enabled and possible running (if index), improving the scaling:
+	 *
+	 *   enabled += delta;
+	 *   if (index)
+	 *     running += delta;
+	 *
+	 *   quot = count / running;
+	 *   rem  = count % running;
+	 *   count = quot * enabled + (rem * enabled) / running;
+	 */
+	__u16	time_shift;
+	__u32	time_mult;
+	__u64	time_offset;
+	/*
+	 * If cap_usr_time_zero, the hardware clock (e.g. TSC) can be calculated
+	 * from sample timestamps.
+	 *
+	 *   time = timestamp - time_zero;
+	 *   quot = time / time_mult;
+	 *   rem  = time % time_mult;
+	 *   cyc = (quot << time_shift) + (rem << time_shift) / time_mult;
+	 *
+	 * And vice versa:
+	 *
+	 *   quot = cyc >> time_shift;
+	 *   rem  = cyc & (((u64)1 << time_shift) - 1);
+	 *   timestamp = time_zero + quot * time_mult +
+	 *               ((rem * time_mult) >> time_shift);
+	 */
+	__u64	time_zero;
+	__u32	size;			/* Header size up to __reserved[] fields. */
+
+		/*
+		 * Hole for extension of the self monitor capabilities
+		 */
+
+	__u8	__reserved[118*8+4];	/* align to 1k. */
+
+	/*
+	 * Control data for the mmap() data buffer.
+	 *
+	 * User-space reading the @data_head value should issue an smp_rmb(),
+	 * after reading this value.
+	 *
+	 * When the mapping is PROT_WRITE the @data_tail value should be
+	 * written by userspace to reflect the last read data, after issueing
+	 * an smp_mb() to separate the data read from the ->data_tail store.
+	 * In this case the kernel will not over-write unread data.
+	 *
+	 * See perf_output_put_handle() for the data ordering.
+	 *
+	 * data_{offset,size} indicate the location and size of the perf record
+	 * buffer within the mmapped area.
+	 */
+	__u64   data_head;		/* head in the data section */
+	__u64	data_tail;		/* user-space written tail */
+	__u64	data_offset;		/* where the buffer starts */
+	__u64	data_size;		/* data buffer size */
+
+	/*
+	 * AUX area is defined by aux_{offset,size} fields that should be set
+	 * by the userspace, so that
+	 *
+	 *   aux_offset >= data_offset + data_size
+	 *
+	 * prior to mmap()ing it. Size of the mmap()ed area should be aux_size.
+	 *
+	 * Ring buffer pointers aux_{head,tail} have the same semantics as
+	 * data_{head,tail} and same ordering rules apply.
+	 */
+	__u64	aux_head;
+	__u64	aux_tail;
+	__u64	aux_offset;
+	__u64	aux_size;
+};
+
+#define PERF_RECORD_MISC_CPUMODE_MASK		(7 << 0)
+#define PERF_RECORD_MISC_CPUMODE_UNKNOWN	(0 << 0)
+#define PERF_RECORD_MISC_KERNEL			(1 << 0)
+#define PERF_RECORD_MISC_USER			(2 << 0)
+#define PERF_RECORD_MISC_HYPERVISOR		(3 << 0)
+#define PERF_RECORD_MISC_GUEST_KERNEL		(4 << 0)
+#define PERF_RECORD_MISC_GUEST_USER		(5 << 0)
+
+/*
+ * Indicates that /proc/PID/maps parsing are truncated by time out.
+ */
+#define PERF_RECORD_MISC_PROC_MAP_PARSE_TIMEOUT	(1 << 12)
+/*
+ * PERF_RECORD_MISC_MMAP_DATA and PERF_RECORD_MISC_COMM_EXEC are used on
+ * different events so can reuse the same bit position.
+ * Ditto PERF_RECORD_MISC_SWITCH_OUT.
+ */
+#define PERF_RECORD_MISC_MMAP_DATA		(1 << 13)
+#define PERF_RECORD_MISC_COMM_EXEC		(1 << 13)
+#define PERF_RECORD_MISC_SWITCH_OUT		(1 << 13)
+/*
+ * Indicates that the content of PERF_SAMPLE_IP points to
+ * the actual instruction that triggered the event. See also
+ * perf_event_attr::precise_ip.
+ */
+#define PERF_RECORD_MISC_EXACT_IP		(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;
+};
+
+enum perf_event_type {
+
+	/*
+	 * If perf_event_attr.sample_id_all is set then all event types will
+	 * have the sample_type selected fields related to where/when
+	 * (identity) an event took place (TID, TIME, ID, STREAM_ID, CPU,
+	 * IDENTIFIER) described in PERF_RECORD_SAMPLE below, it will be stashed
+	 * just after the perf_event_header and the fields already present for
+	 * the existing fields, i.e. at the end of the payload. That way a newer
+	 * perf.data file will be supported by older perf tools, with these new
+	 * optional fields being ignored.
+	 *
+	 * struct sample_id {
+	 * 	{ u32			pid, tid; } && PERF_SAMPLE_TID
+	 * 	{ u64			time;     } && PERF_SAMPLE_TIME
+	 * 	{ u64			id;       } && PERF_SAMPLE_ID
+	 * 	{ u64			stream_id;} && PERF_SAMPLE_STREAM_ID
+	 * 	{ u32			cpu, res; } && PERF_SAMPLE_CPU
+	 *	{ u64			id;	  } && PERF_SAMPLE_IDENTIFIER
+	 * } && perf_event_attr::sample_id_all
+	 *
+	 * Note that PERF_SAMPLE_IDENTIFIER duplicates PERF_SAMPLE_ID.  The
+	 * advantage of PERF_SAMPLE_IDENTIFIER is that its position is fixed
+	 * relative to header.size.
+	 */
+
+	/*
+	 * The MMAP events record the PROT_EXEC mappings so that we can
+	 * correlate userspace IPs to code. They have the following structure:
+	 *
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *
+	 *	u32				pid, tid;
+	 *	u64				addr;
+	 *	u64				len;
+	 *	u64				pgoff;
+	 *	char				filename[];
+	 * 	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_MMAP			= 1,
+
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u64				id;
+	 *	u64				lost;
+	 * 	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_LOST			= 2,
+
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *
+	 *	u32				pid, tid;
+	 *	char				comm[];
+	 * 	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_COMM			= 3,
+
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u32				pid, ppid;
+	 *	u32				tid, ptid;
+	 *	u64				time;
+	 * 	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_EXIT			= 4,
+
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u64				time;
+	 *	u64				id;
+	 *	u64				stream_id;
+	 * 	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_THROTTLE			= 5,
+	PERF_RECORD_UNTHROTTLE			= 6,
+
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u32				pid, ppid;
+	 *	u32				tid, ptid;
+	 *	u64				time;
+	 * 	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_FORK			= 7,
+
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u32				pid, tid;
+	 *
+	 *	struct read_format		values;
+	 * 	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_READ			= 8,
+
+	/*
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *
+	 *	#
+	 *	# Note that PERF_SAMPLE_IDENTIFIER duplicates PERF_SAMPLE_ID.
+	 *	# The advantage of PERF_SAMPLE_IDENTIFIER is that its position
+	 *	# is fixed relative to header.
+	 *	#
+	 *
+	 *	{ u64			id;	  } && PERF_SAMPLE_IDENTIFIER
+	 *	{ u64			ip;	  } && PERF_SAMPLE_IP
+	 *	{ u32			pid, tid; } && PERF_SAMPLE_TID
+	 *	{ u64			time;     } && PERF_SAMPLE_TIME
+	 *	{ u64			addr;     } && PERF_SAMPLE_ADDR
+	 *	{ u64			id;	  } && PERF_SAMPLE_ID
+	 *	{ u64			stream_id;} && PERF_SAMPLE_STREAM_ID
+	 *	{ u32			cpu, res; } && PERF_SAMPLE_CPU
+	 *	{ u64			period;   } && PERF_SAMPLE_PERIOD
+	 *
+	 *	{ struct read_format	values;	  } && PERF_SAMPLE_READ
+	 *
+	 *	{ u64			nr,
+	 *	  u64			ips[nr];  } && PERF_SAMPLE_CALLCHAIN
+	 *
+	 *	#
+	 *	# The RAW record below is opaque data wrt the ABI
+	 *	#
+	 *	# That is, the ABI doesn't make any promises wrt to
+	 *	# the stability of its content, it may vary depending
+	 *	# on event, hardware, kernel version and phase of
+	 *	# the moon.
+	 *	#
+	 *	# In other words, PERF_SAMPLE_RAW contents are not an ABI.
+	 *	#
+	 *
+	 *	{ u32			size;
+	 *	  char                  data[size];}&& PERF_SAMPLE_RAW
+	 *
+	 *	{ u64                   nr;
+	 *        { u64 from, to, flags } lbr[nr];} && PERF_SAMPLE_BRANCH_STACK
+	 *
+	 * 	{ u64			abi; # enum perf_sample_regs_abi
+	 * 	  u64			regs[weight(mask)]; } && PERF_SAMPLE_REGS_USER
+	 *
+	 * 	{ u64			size;
+	 * 	  char			data[size];
+	 * 	  u64			dyn_size; } && PERF_SAMPLE_STACK_USER
+	 *
+	 *	{ u64			weight;   } && PERF_SAMPLE_WEIGHT
+	 *	{ u64			data_src; } && PERF_SAMPLE_DATA_SRC
+	 *	{ u64			transaction; } && PERF_SAMPLE_TRANSACTION
+	 *	{ u64			abi; # enum perf_sample_regs_abi
+	 *	  u64			regs[weight(mask)]; } && PERF_SAMPLE_REGS_INTR
+	 * };
+	 */
+	PERF_RECORD_SAMPLE			= 9,
+
+	/*
+	 * The MMAP2 records are an augmented version of MMAP, they add
+	 * maj, min, ino numbers to be used to uniquely identify each mapping
+	 *
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *
+	 *	u32				pid, tid;
+	 *	u64				addr;
+	 *	u64				len;
+	 *	u64				pgoff;
+	 *	u32				maj;
+	 *	u32				min;
+	 *	u64				ino;
+	 *	u64				ino_generation;
+	 *	u32				prot, flags;
+	 *	char				filename[];
+	 * 	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_MMAP2			= 10,
+
+	/*
+	 * Records that new data landed in the AUX buffer part.
+	 *
+	 * struct {
+	 * 	struct perf_event_header	header;
+	 *
+	 * 	u64				aux_offset;
+	 * 	u64				aux_size;
+	 *	u64				flags;
+	 * 	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_AUX				= 11,
+
+	/*
+	 * Indicates that instruction trace has started
+	 *
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u32				pid;
+	 *	u32				tid;
+	 * };
+	 */
+	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,
+
+	PERF_RECORD_MAX,			/* non-ABI */
+};
+
+#define PERF_MAX_STACK_DEPTH		127
+#define PERF_MAX_CONTEXTS_PER_STACK	  8
+
+enum perf_callchain_context {
+	PERF_CONTEXT_HV			= (__u64)-32,
+	PERF_CONTEXT_KERNEL		= (__u64)-128,
+	PERF_CONTEXT_USER		= (__u64)-512,
+
+	PERF_CONTEXT_GUEST		= (__u64)-2048,
+	PERF_CONTEXT_GUEST_KERNEL	= (__u64)-2176,
+	PERF_CONTEXT_GUEST_USER		= (__u64)-2560,
+
+	PERF_CONTEXT_MAX		= (__u64)-4095,
+};
+
+/**
+ * PERF_RECORD_AUX::flags bits
+ */
+#define PERF_AUX_FLAG_TRUNCATED		0x01	/* record was truncated to fit */
+#define PERF_AUX_FLAG_OVERWRITE		0x02	/* snapshot from overwrite mode */
+
+#define PERF_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 */
+
+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_rsvd:31;
+	};
+};
+
+/* type of opcode (load/store/prefetch,code) */
+#define PERF_MEM_OP_NA		0x01 /* not available */
+#define PERF_MEM_OP_LOAD	0x02 /* load instruction */
+#define PERF_MEM_OP_STORE	0x04 /* store instruction */
+#define PERF_MEM_OP_PFETCH	0x08 /* prefetch */
+#define PERF_MEM_OP_EXEC	0x10 /* code (execution) */
+#define PERF_MEM_OP_SHIFT	0
+
+/* memory hierarchy (memory level, hit or miss) */
+#define PERF_MEM_LVL_NA		0x01  /* not available */
+#define PERF_MEM_LVL_HIT	0x02  /* hit level */
+#define PERF_MEM_LVL_MISS	0x04  /* miss level  */
+#define PERF_MEM_LVL_L1		0x08  /* L1 */
+#define PERF_MEM_LVL_LFB	0x10  /* Line Fill Buffer */
+#define PERF_MEM_LVL_L2		0x20  /* L2 */
+#define PERF_MEM_LVL_L3		0x40  /* L3 */
+#define PERF_MEM_LVL_LOC_RAM	0x80  /* Local DRAM */
+#define PERF_MEM_LVL_REM_RAM1	0x100 /* Remote DRAM (1 hop) */
+#define PERF_MEM_LVL_REM_RAM2	0x200 /* Remote DRAM (2 hops) */
+#define PERF_MEM_LVL_REM_CCE1	0x400 /* Remote Cache (1 hop) */
+#define PERF_MEM_LVL_REM_CCE2	0x800 /* Remote Cache (2 hops) */
+#define PERF_MEM_LVL_IO		0x1000 /* I/O memory */
+#define PERF_MEM_LVL_UNC	0x2000 /* Uncached memory */
+#define PERF_MEM_LVL_SHIFT	5
+
+/* 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
+
+/* locked instruction */
+#define PERF_MEM_LOCK_NA	0x01 /* not available */
+#define PERF_MEM_LOCK_LOCKED	0x02 /* locked transaction */
+#define PERF_MEM_LOCK_SHIFT	24
+
+/* TLB access */
+#define PERF_MEM_TLB_NA		0x01 /* not available */
+#define PERF_MEM_TLB_HIT	0x02 /* hit level */
+#define PERF_MEM_TLB_MISS	0x04 /* miss level */
+#define PERF_MEM_TLB_L1		0x08 /* L1 */
+#define PERF_MEM_TLB_L2		0x10 /* L2 */
+#define PERF_MEM_TLB_WK		0x20 /* Hardware Walker*/
+#define PERF_MEM_TLB_OS		0x40 /* OS fault handler */
+#define PERF_MEM_TLB_SHIFT	26
+
+#define PERF_MEM_S(a, s) \
+	(((__u64)PERF_MEM_##a##_##s) << PERF_MEM_##a##_SHIFT)
+
+/*
+ * single taken branch record layout:
+ *
+ *      from: source instruction (may not always be a branch insn)
+ *        to: branch target
+ *   mispred: branch target was mispredicted
+ * predicted: branch target was predicted
+ *
+ * support for mispred, predicted is optional. In case it
+ * is not supported mispred = predicted = 0.
+ *
+ *     in_tx: running in a hardware transaction
+ *     abort: aborting a hardware transaction
+ *    cycles: cycles from last branch (or 0 if not supported)
+ */
+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 */
+		reserved:44;
+};
+
+#endif /* _UAPI_LINUX_PERF_EVENT_H */