diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile
index 586d1b2595d16..7ed9390ecad46 100644
--- a/tools/bpf/bpftool/Makefile
+++ b/tools/bpf/bpftool/Makefile
@@ -64,11 +64,21 @@ $(LIBBPF_BOOTSTRAP)-clean: FORCE | $(LIBBPF_BOOTSTRAP_OUTPUT)
 prefix ?= /usr/local
 bash_compdir ?= /usr/share/bash-completion/completions
 
+try-run = $(shell set -e;		\
+	if ($(1)) >/dev/null 2>&1;	\
+	then echo "$(2)";		\
+	else echo "$(3)";		\
+	fi)
+
+__cc-option = $(call try-run,\
+	$(1) -Werror $(2) -c -x c /dev/null -o /dev/null,$(2),)
+cc-option = $(call __cc-option, $(CC),$(1))
+
 CFLAGS += -O2
 CFLAGS += -W
 CFLAGS += -Wall
 CFLAGS += -Wextra
-CFLAGS += -Wformat-signedness
+CFLAGS += $(call cc-option,-Wformat-signedness)
 CFLAGS += -Wno-unused-parameter
 CFLAGS += -Wno-missing-field-initializers
 CFLAGS += $(filter-out -Wswitch-enum -Wnested-externs,$(EXTRA_WARNINGS))
diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile
index b41a42818d8ac..bd615a708a0aa 100644
--- a/tools/build/feature/Makefile
+++ b/tools/build/feature/Makefile
@@ -316,10 +316,10 @@ $(OUTPUT)test-libcapstone.bin:
 	$(BUILD) # -lcapstone provided by $(FEATURE_CHECK_LDFLAGS-libcapstone)
 
 $(OUTPUT)test-compile-32.bin:
-	$(CC) -m32 -o $@ test-compile.c
+	$(CC) -m32 -Wall -Werror -o $@ test-compile.c
 
 $(OUTPUT)test-compile-x32.bin:
-	$(CC) -mx32 -o $@ test-compile.c
+	$(CC) -mx32 -Wall -Werror -o $@ test-compile.c
 
 $(OUTPUT)test-zlib.bin:
 	$(BUILD) -lz
diff --git a/tools/perf/Documentation/Build.txt b/tools/perf/Documentation/Build.txt
index 83dc87c662b63..3e4104e605ac0 100644
--- a/tools/perf/Documentation/Build.txt
+++ b/tools/perf/Documentation/Build.txt
@@ -99,3 +99,21 @@ configuration paths for cross building:
 In this case, the variable PKG_CONFIG_SYSROOT_DIR can be used alongside the
 variable PKG_CONFIG_LIBDIR or PKG_CONFIG_PATH to prepend the sysroot path to
 the library paths for cross compilation.
+
+5) Build with clang
+===================
+By default, the makefile uses GCC as compiler. With specifying environment
+variables HOSTCC, CC and CXX, it allows to build perf with clang.
+
+Using clang for native build:
+
+  $ HOSTCC=clang CC=clang CXX=clang++ make -C tools/perf
+
+Using clang for cross compilation:
+
+  $ HOSTCC=clang CC=clang CXX=clang++ \
+    make ARCH=arm64 CROSS_COMPILE=aarch64-linux-gnu- -C tools/perf \
+    NO_LIBELF=1 NO_LIBTRACEEVENT=1 NO_JEVENTS=1
+
+In the example above, due to lack libelf, python and libtraceevent for
+cross comiplation, disable the features accordingly.
diff --git a/tools/perf/Documentation/android.txt b/tools/perf/Documentation/android.txt
index 24a59998fc91e..e65204cf2921f 100644
--- a/tools/perf/Documentation/android.txt
+++ b/tools/perf/Documentation/android.txt
@@ -1,78 +1,12 @@
 How to compile perf for Android
-=========================================
+===============================
 
-I. Set the Android NDK environment
-------------------------------------------------
+There have two ways to build perf and run it on Android.
 
-(a). Use the Android NDK
-------------------------------------------------
-1. You need to download and install the Android Native Development Kit (NDK).
-Set the NDK variable to point to the path where you installed the NDK:
-  export NDK=/path/to/android-ndk
+- The first method is to build perf with static linking, please refer to
+  Build.txt, section "4) Cross compilation" for how to build a static
+  perf binary.
 
-2. Set cross-compiling environment variables for NDK toolchain and sysroot.
-For arm:
-  export NDK_TOOLCHAIN=${NDK}/toolchains/arm-linux-androideabi-4.9/prebuilt/linux-x86_64/bin/arm-linux-androideabi-
-  export NDK_SYSROOT=${NDK}/platforms/android-24/arch-arm
-For x86:
-  export NDK_TOOLCHAIN=${NDK}/toolchains/x86-4.9/prebuilt/linux-x86_64/bin/i686-linux-android-
-  export NDK_SYSROOT=${NDK}/platforms/android-24/arch-x86
-
-This method is only tested for Android NDK versions Revision 11b and later.
-perf uses some bionic enhancements that are not included in prior NDK versions.
-You can use method (b) described below instead.
-
-(b). Use the Android source tree
------------------------------------------------
-1. Download the master branch of the Android source tree.
-Set the environment for the target you want using:
-  source build/envsetup.sh
-  lunch
-
-2. Build your own NDK sysroot to contain latest bionic changes and set the
-NDK sysroot environment variable.
-  cd ${ANDROID_BUILD_TOP}/ndk
-For arm:
-  ./build/tools/build-ndk-sysroot.sh --abi=arm
-  export NDK_SYSROOT=${ANDROID_BUILD_TOP}/ndk/build/platforms/android-3/arch-arm
-For x86:
-  ./build/tools/build-ndk-sysroot.sh --abi=x86
-  export NDK_SYSROOT=${ANDROID_BUILD_TOP}/ndk/build/platforms/android-3/arch-x86
-
-3. Set the NDK toolchain environment variable.
-For arm:
-  export NDK_TOOLCHAIN=${ANDROID_TOOLCHAIN}/arm-linux-androideabi-
-For x86:
-  export NDK_TOOLCHAIN=${ANDROID_TOOLCHAIN}/i686-linux-android-
-
-II. Compile perf for Android
-------------------------------------------------
-You need to run make with the NDK toolchain and sysroot defined above:
-For arm:
-  make WERROR=0 ARCH=arm CROSS_COMPILE=${NDK_TOOLCHAIN} EXTRA_CFLAGS="-pie --sysroot=${NDK_SYSROOT}"
-For x86:
-  make WERROR=0 ARCH=x86 CROSS_COMPILE=${NDK_TOOLCHAIN} EXTRA_CFLAGS="-pie --sysroot=${NDK_SYSROOT}"
-
-III. Install perf
------------------------------------------------
-You need to connect to your Android device/emulator using adb.
-Install perf using:
-  adb push perf /data/perf
-
-If you also want to use perf-archive you need busybox tools for Android.
-For installing perf-archive, you first need to replace #!/bin/bash with #!/system/bin/sh:
-  sed 's/#!\/bin\/bash/#!\/system\/bin\/sh/g' perf-archive >> /tmp/perf-archive
-  chmod +x /tmp/perf-archive
-  adb push /tmp/perf-archive /data/perf-archive
-
-IV. Environment settings for running perf
-------------------------------------------------
-Some perf features need environment variables to run properly.
-You need to set these before running perf on the target:
-  adb shell
-  # PERF_PAGER=cat
-
-IV. Run perf
-------------------------------------------------
-Run perf on your device/emulator to which you previously connected using adb:
-  # ./data/perf
+- The second method is to download Android NDK, then use the contained
+  clang compiler for building perf. Please refer to Build.txt, section
+  "5) Build with clang" for details.
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 5a5832ee7b53c..a2b5c291a364c 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -23,8 +23,38 @@ HOSTCFLAGS := $(filter-out -Wnested-externs,$(EXTRA_WARNINGS))
 # borrowed from kernel headers depends on it, e.g. put_unaligned_*().
 CFLAGS += -fno-strict-aliasing
 
-# Enabled Wthread-safety analysis for clang builds.
+# Set target flag and options when using clang as compiler.
 ifeq ($(CC_NO_CLANG), 0)
+  CLANG_TARGET_FLAGS_arm	:= arm-linux-gnueabi
+  CLANG_TARGET_FLAGS_arm64	:= aarch64-linux-gnu
+  CLANG_TARGET_FLAGS_m68k	:= m68k-linux-gnu
+  CLANG_TARGET_FLAGS_mips	:= mipsel-linux-gnu
+  CLANG_TARGET_FLAGS_powerpc	:= powerpc64le-linux-gnu
+  CLANG_TARGET_FLAGS_riscv	:= riscv64-linux-gnu
+  CLANG_TARGET_FLAGS_s390	:= s390x-linux-gnu
+  CLANG_TARGET_FLAGS_x86	:= x86_64-linux-gnu
+
+  # Default to host architecture if ARCH is not explicitly given.
+  ifeq ($(ARCH),)
+    CLANG_TARGET_FLAGS := $(shell $(CLANG) -print-target-triple)
+  else
+    CLANG_TARGET_FLAGS := $(CLANG_TARGET_FLAGS_$(ARCH))
+  endif
+
+  ifeq ($(CROSS_COMPILE),)
+    ifeq ($(CLANG_TARGET_FLAGS),)
+      $(error Specify CROSS_COMPILE or add CLANG_TARGET_FLAGS for $(ARCH))
+    else
+      CLANG_FLAGS += --target=$(CLANG_TARGET_FLAGS)
+    endif # CLANG_TARGET_FLAGS
+  else
+    CLANG_FLAGS += --target=$(notdir $(CROSS_COMPILE:%-=%))
+  endif # CROSS_COMPILE
+
+  CC := $(CLANG) $(CLANG_FLAGS) -fintegrated-as
+  CXX := $(CXX) $(CLANG_FLAGS) -fintegrated-as
+
+  # Enabled Wthread-safety analysis for clang builds.
   CFLAGS += -Wthread-safety
 endif
 
diff --git a/tools/perf/tests/shell/coresight/memcpy_thread/memcpy_thread.c b/tools/perf/tests/shell/coresight/memcpy_thread/memcpy_thread.c
index 5f886cd09e6b3..7e879217be30a 100644
--- a/tools/perf/tests/shell/coresight/memcpy_thread/memcpy_thread.c
+++ b/tools/perf/tests/shell/coresight/memcpy_thread/memcpy_thread.c
@@ -27,6 +27,8 @@ static void *thrfn(void *arg)
 	}
 	for (i = 0; i < len; i++)
 		memcpy(dst, src, a->size * 1024);
+
+	return NULL;
 }
 
 static pthread_t new_thr(void *(*fn) (void *arg), void *arg)
diff --git a/tools/perf/tests/shell/coresight/thread_loop/thread_loop.c b/tools/perf/tests/shell/coresight/thread_loop/thread_loop.c
index e05a559253ca9..86f3f548b0063 100644
--- a/tools/perf/tests/shell/coresight/thread_loop/thread_loop.c
+++ b/tools/perf/tests/shell/coresight/thread_loop/thread_loop.c
@@ -34,8 +34,8 @@ static void *thrfn(void *arg)
 	}
 	asm volatile(
 		"loop:\n"
-		"add %[i], %[i], #1\n"
-		"cmp %[i], %[len]\n"
+		"add %w[i], %w[i], #1\n"
+		"cmp %w[i], %w[len]\n"
 		"blt loop\n"
 		: /* out */
 		: /* in */ [i] "r" (i), [len] "r" (len)
diff --git a/tools/perf/tests/shell/coresight/unroll_loop_thread/unroll_loop_thread.c b/tools/perf/tests/shell/coresight/unroll_loop_thread/unroll_loop_thread.c
index 0fc7bf1a25af3..8f4e1c985ca38 100644
--- a/tools/perf/tests/shell/coresight/unroll_loop_thread/unroll_loop_thread.c
+++ b/tools/perf/tests/shell/coresight/unroll_loop_thread/unroll_loop_thread.c
@@ -20,7 +20,7 @@ static void *thrfn(void *arg)
 	for (i = 0; i < 10000; i++) {
 		asm volatile (
 // force an unroll of thia add instruction so we can test long runs of code
-#define SNIP1 "add %[in], %[in], #1\n"
+#define SNIP1 "add %w[in], %w[in], #1\n"
 // 10
 #define SNIP2 SNIP1 SNIP1 SNIP1 SNIP1 SNIP1 SNIP1 SNIP1 SNIP1 SNIP1 SNIP1
 // 100
@@ -36,6 +36,8 @@ static void *thrfn(void *arg)
 			: /* clobber */
 		);
 	}
+
+	return NULL;
 }
 
 static pthread_t new_thr(void *(*fn) (void *arg), void *arg)
diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
index dd289d15acfd6..9cae2c472f4ad 100644
--- a/tools/perf/util/setup.py
+++ b/tools/perf/util/setup.py
@@ -1,6 +1,7 @@
 from os import getenv, path
 from subprocess import Popen, PIPE
 from re import sub
+import shlex
 
 cc = getenv("CC")
 assert cc, "Environment variable CC not set"
@@ -22,7 +23,9 @@
 src_feature_tests  = f'{srctree}/tools/build/feature'
 
 def clang_has_option(option):
-    cc_output = Popen([cc, cc_options + option, path.join(src_feature_tests, "test-hello.c") ], stderr=PIPE).stderr.readlines()
+    cmd = shlex.split(f"{cc} {cc_options} {option}")
+    cmd.append(path.join(src_feature_tests, "test-hello.c"))
+    cc_output = Popen(cmd, stderr=PIPE).stderr.readlines()
     return [o for o in cc_output if ((b"unknown argument" in o) or (b"is not supported" in o) or (b"unknown warning option" in o))] == [ ]
 
 if cc_is_clang: