8 files changed, 43 insertions, 24 deletions
diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c
index 0999ac536d86..8024cd5febd2 100644
--- a/tools/perf/bench/futex-hash.c
+++ b/tools/perf/bench/futex-hash.c
@@ -8,18 +8,23 @@
  * many threads and futexes as possible.
  */
 
-#include "../perf.h"
-#include "../util/util.h"
+/* For the CLR_() macros */
+#include <pthread.h>
+
+#include <errno.h>
+#include <signal.h>
+#include <stdlib.h>
+#include <linux/compiler.h>
+#include <linux/kernel.h>
+#include <sys/time.h>
+
 #include "../util/stat.h"
 #include <subcmd/parse-options.h>
-#include "../util/header.h"
 #include "bench.h"
 #include "futex.h"
 
 #include <err.h>
-#include <stdlib.h>
 #include <sys/time.h>
-#include <pthread.h>
 
 static unsigned int nthreads = 0;
 static unsigned int nsecs    = 10;
diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c
index 6952db65508a..936d89d30483 100644
--- a/tools/perf/bench/futex-lock-pi.c
+++ b/tools/perf/bench/futex-lock-pi.c
@@ -2,18 +2,21 @@
  * Copyright (C) 2015 Davidlohr Bueso.
  */
 
-#include "../perf.h"
-#include "../util/util.h"
+/* For the CLR_() macros */
+#include <pthread.h>
+
+#include <signal.h>
 #include "../util/stat.h"
 #include <subcmd/parse-options.h>
-#include "../util/header.h"
+#include <linux/compiler.h>
+#include <linux/kernel.h>
+#include <errno.h>
 #include "bench.h"
 #include "futex.h"
 
 #include <err.h>
 #include <stdlib.h>
 #include <sys/time.h>
-#include <pthread.h>
 
 struct worker {
 	int tid;
diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c
index 718238683013..f96e22ed9f87 100644
--- a/tools/perf/bench/futex-requeue.c
+++ b/tools/perf/bench/futex-requeue.c
@@ -8,18 +8,21 @@
  * requeues without waking up any tasks -- thus mimicking a regular futex_wait.
  */
 
-#include "../perf.h"
-#include "../util/util.h"
+/* For the CLR_() macros */
+#include <pthread.h>
+
+#include <signal.h>
 #include "../util/stat.h"
 #include <subcmd/parse-options.h>
-#include "../util/header.h"
+#include <linux/compiler.h>
+#include <linux/kernel.h>
+#include <errno.h>
 #include "bench.h"
 #include "futex.h"
 
 #include <err.h>
 #include <stdlib.h>
 #include <sys/time.h>
-#include <pthread.h>
 
 static u_int32_t futex1 = 0, futex2 = 0;
 
diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c
index 91aaf2a1fa90..4a2ecd7438ca 100644
--- a/tools/perf/bench/futex-wake-parallel.c
+++ b/tools/perf/bench/futex-wake-parallel.c
@@ -7,18 +7,21 @@
  * it can be used to measure futex_wake() changes.
  */
 
-#include "../perf.h"
-#include "../util/util.h"
+/* For the CLR_() macros */
+#include <pthread.h>
+
+#include <signal.h>
 #include "../util/stat.h"
 #include <subcmd/parse-options.h>
-#include "../util/header.h"
+#include <linux/compiler.h>
+#include <linux/kernel.h>
+#include <errno.h>
 #include "bench.h"
 #include "futex.h"
 
 #include <err.h>
 #include <stdlib.h>
 #include <sys/time.h>
-#include <pthread.h>
 
 struct thread_data {
 	pthread_t worker;
diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c
index f416bd705f66..87d8f4f292d9 100644
--- a/tools/perf/bench/futex-wake.c
+++ b/tools/perf/bench/futex-wake.c
@@ -8,18 +8,21 @@
  * one or more tasks, and thus the waitqueue is never empty.
  */
 
-#include "../perf.h"
-#include "../util/util.h"
+/* For the CLR_() macros */
+#include <pthread.h>
+
+#include <signal.h>
 #include "../util/stat.h"
 #include <subcmd/parse-options.h>
-#include "../util/header.h"
+#include <linux/compiler.h>
+#include <linux/kernel.h>
+#include <errno.h>
 #include "bench.h"
 #include "futex.h"
 
 #include <err.h>
 #include <stdlib.h>
 #include <sys/time.h>
-#include <pthread.h>
 
 /* all threads will block on the same futex */
 static u_int32_t futex1 = 0;
diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm.S b/tools/perf/bench/mem-memcpy-x86-64-asm.S
index 5c3cce082cb8..f700369bb0f6 100644
--- a/tools/perf/bench/mem-memcpy-x86-64-asm.S
+++ b/tools/perf/bench/mem-memcpy-x86-64-asm.S
@@ -6,7 +6,7 @@
 #define globl p2align 4; .globl
 #define _ASM_EXTABLE_FAULT(x, y)
 
-#include "../../../arch/x86/lib/memcpy_64.S"
+#include "../../arch/x86/lib/memcpy_64.S"
 /*
  * We need to provide note.GNU-stack section, saying that we want
  * NOT executable stack. Otherwise the final linking will assume that
diff --git a/tools/perf/bench/mem-memset-x86-64-asm.S b/tools/perf/bench/mem-memset-x86-64-asm.S
index de278784c866..58407aa24c1b 100644
--- a/tools/perf/bench/mem-memset-x86-64-asm.S
+++ b/tools/perf/bench/mem-memset-x86-64-asm.S
@@ -1,7 +1,7 @@
 #define memset MEMSET /* don't hide glibc's memset() */
 #define altinstr_replacement text
 #define globl p2align 4; .globl
-#include "../../../arch/x86/lib/memset_64.S"
+#include "../../arch/x86/lib/memset_64.S"
 
 /*
  * We need to provide note.GNU-stack section, saying that we want
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index 7500d959d7eb..f7f530081aa9 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -4,6 +4,9 @@
  * numa: Simulate NUMA-sensitive workload and measure their NUMA performance
  */
 
+/* For the CLR_() macros */
+#include <pthread.h>
+
 #include "../perf.h"
 #include "../builtin.h"
 #include "../util/util.h"
@@ -21,7 +24,6 @@
 #include <stdlib.h>
 #include <string.h>
 #include <unistd.h>
-#include <pthread.h>
 #include <sys/mman.h>
 #include <sys/time.h>
 #include <sys/resource.h>