Merge tag 'perf-core-for-mingo-20161114' 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:

New features:

 - Allow querying and setting .perfconfig variables (Taeung Song)

 - Show branch information in callchains (predicted, TSX aborts, loop
   iteractions, etc) (Jin Yao)

Infrastructure changes:

 - Support kbuild's CFLAGS_REMOVE_ in tools/build (Jiri Olsa)

 - Plug building jvmti to the main perf Makefile (Jiri Olsa)

Documentation changes:

 - Update Intel PT documentation about context switch events (Arnaldo Carvalho de Melo)

 - Fix 'perf record --call-graph dwarf' help/config in builds not linking
   with a unwind library, mentioning that is a possible record option (Rabin Vincent)

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

tools/build/Build.include

@@ -89,7 +89,9 @@ if_changed = $(if $(strip $(any-prereq) $(arg-check)),             \
 # - per target C flags
 # - per object C flags
 # - BUILD_STR macro to allow '-D"$(variable)"' constructs
-c_flags = -Wp,-MD,$(depfile),-MT,$@ $(CFLAGS) -D"BUILD_STR(s)=\#s" $(CFLAGS_$(basetarget).o) $(CFLAGS_$(obj))
+c_flags_1 = -Wp,-MD,$(depfile),-MT,$@ $(CFLAGS) -D"BUILD_STR(s)=\#s" $(CFLAGS_$(basetarget).o) $(CFLAGS_$(obj))
+c_flags_2 = $(filter-out $(CFLAGS_REMOVE_$(basetarget).o), $(c_flags_1))
+c_flags   = $(filter-out $(CFLAGS_REMOVE_$(obj)), $(c_flags_2))
 cxx_flags = -Wp,-MD,$(depfile),-MT,$@ $(CXXFLAGS) -D"BUILD_STR(s)=\#s" $(CXXFLAGS_$(basetarget).o) $(CXXFLAGS_$(obj))
 
 ###

tools/build/Documentation/Build.txt

@@ -135,8 +135,10 @@ CFLAGS
 
 It's possible to alter the standard object C flags in the following way:
 
-  CFLAGS_perf.o += '...' - alters CFLAGS for perf.o object
-  CFLAGS_gtk += '...'    - alters CFLAGS for gtk build object
+  CFLAGS_perf.o        += '...'  - adds CFLAGS for perf.o object
+  CFLAGS_gtk           += '...'  - adds CFLAGS for gtk build object
+  CFLAGS_REMOVE_perf.o += '...'  - removes CFLAGS for perf.o object
+  CFLAGS_REMOVE_gtk    += '...'  - removes CFLAGS for gtk build object
 
 This C flags changes has the scope of the Build makefile they are defined in.
 

tools/build/feature/Makefile

@@ -47,7 +47,8 @@ FILES=					\
 	test-bpf.bin			\
 	test-get_cpuid.bin		\
 	test-sdt.bin			\
-	test-cxx.bin
+	test-cxx.bin			\
+	test-jvmti.bin
 
 FILES := $(addprefix $(OUTPUT),$(FILES))
 
@@ -225,6 +226,9 @@ $(OUTPUT)test-sdt.bin:
 $(OUTPUT)test-cxx.bin:
 	$(BUILDXX) -std=gnu++11
 
+$(OUTPUT)test-jvmti.bin:
+	$(BUILD)
+
 -include $(OUTPUT)*.d
 
 ###############################

tools/build/feature/test-jvmti.c

@@ -0,0 +1,13 @@
+#include <jvmti.h>
+#include <jvmticmlr.h>
+
+int main(void)
+{
+	JavaVM			jvm	__attribute__((unused));
+	jvmtiEventCallbacks	cb	__attribute__((unused));
+	jvmtiCapabilities	caps	__attribute__((unused));
+	jvmtiJlocationFormat	format	__attribute__((unused));
+	jvmtiEnv		jvmti	__attribute__((unused));
+
+	return 0;
+}

tools/perf/Documentation/intel-pt.txt

@@ -550,6 +550,18 @@ Unless /proc/sys/kernel/perf_event_paranoid is set to -1, unprivileged users
 have memory limits imposed upon them.  That affects what buffer sizes they can
 have as outlined above.
 
+The v4.2 kernel introduced support for a context switch metadata event,
+PERF_RECORD_SWITCH, which allows unprivileged users to see when their processes
+are scheduled out and in, just not by whom, which is left for the
+PERF_RECORD_SWITCH_CPU_WIDE, that is only accessible in system wide context,
+which in turn requires CAP_SYS_ADMIN.
+
+Please see the 45ac1403f564 ("perf: Add PERF_RECORD_SWITCH to indicate context
+switches") commit, that introduces these metadata events for further info.
+
+When working with kernels < v4.2, the following considerations must be taken,
+as the sched:sched_switch tracepoints will be used to receive such information:
+
 Unless /proc/sys/kernel/perf_event_paranoid is set to -1, unprivileged users are
 not permitted to use tracepoints which means there is insufficient side-band
 information to decode Intel PT in per-cpu mode, and potentially workload-only
@@ -564,8 +576,11 @@ sched_switch tracepoint
 -----------------------
 
 The sched_switch tracepoint is used to provide side-band data for Intel PT
-decoding.  sched_switch events are automatically added. e.g. the second event
-shown below
+decoding in kernels where the PERF_RECORD_SWITCH metadata event isn't
+available.
+
+The sched_switch events are automatically added. e.g. the second event shown
+below:
 
 	$ perf record -vv -e intel_pt//u uname
 	------------------------------------------------------------

tools/perf/Documentation/perf-config.txt

@@ -8,6 +8,8 @@ perf-config - Get and set variables in a configuration file.
 SYNOPSIS
 --------
 [verse]
+'perf config' [<file-option>] [section.name[=value] ...]
+or
 'perf config' [<file-option>] -l | --list
 
 DESCRIPTION
@@ -118,6 +120,39 @@ Given a $HOME/.perfconfig like this:
 		children = true
 		group = true
 
+You can hide source code of annotate feature setting the config to false with
+
+	% perf config annotate.hide_src_code=true
+
+If you want to add or modify several config items, you can do like
+
+	% perf config ui.show-headers=false kmem.default=slab
+
+To modify the sort order of report functionality in user config file(i.e. `~/.perfconfig`), do
+
+	% perf config --user report sort-order=srcline
+
+To change colors of selected line to other foreground and background colors
+in system config file (i.e. `$(sysconf)/perfconfig`), do
+
+	% perf config --system colors.selected=yellow,green
+
+To query the record mode of call graph, do
+
+	% perf config call-graph.record-mode
+
+If you want to know multiple config key/value pairs, you can do like
+
+	% perf config report.queue-size call-graph.order report.children
+
+To query the config value of sort order of call graph in user config file (i.e. `~/.perfconfig`), do
+
+	% perf config --user call-graph.sort-order
+
+To query the config value of buildid directory in system config file (i.e. `$(sysconf)/perfconfig`), do
+
+	% perf config --system buildid.dir
+
 Variables
 ~~~~~~~~~
 

tools/perf/Makefile.config

@@ -758,6 +758,31 @@ ifndef NO_AUXTRACE
   endif
 endif
 
+ifndef NO_JVMTI
+  ifneq (,$(wildcard /usr/sbin/update-java-alternatives))
+    JDIR=$(shell /usr/sbin/update-java-alternatives -l | head -1 | awk '{print $$3}')
+  else
+    ifneq (,$(wildcard /usr/sbin/alternatives))
+      JDIR=$(shell alternatives --display java | tail -1 | cut -d' ' -f 5 | sed 's%/jre/bin/java.%%g')
+    endif
+  endif
+  ifndef JDIR
+    $(warning No alternatives command found, you need to set JDIR= to point to the root of your Java directory)
+    NO_JVMTI := 1
+  endif
+endif
+
+ifndef NO_JVMTI
+  FEATURE_CHECK_CFLAGS-jvmti := -I$(JDIR)/include -I$(JDIR)/include/linux
+  $(call feature_check,jvmti)
+  ifeq ($(feature-jvmti), 1)
+    $(call detected_var,JDIR)
+  else
+    $(warning No openjdk development package found, please install JDK package)
+    NO_JVMTI := 1
+  endif
+endif
+
 # Among the variables below, these:
 #   perfexecdir
 #   template_dir
@@ -850,6 +875,7 @@ ifeq ($(VF),1)
   $(call print_var,sysconfdir)
   $(call print_var,LIBUNWIND_DIR)
   $(call print_var,LIBDW_DIR)
+  $(call print_var,JDIR)
 
   ifeq ($(dwarf-post-unwind),1)
     $(call feature_print_text,"DWARF post unwind library", $(dwarf-post-unwind-text))

tools/perf/Makefile.perf

@@ -86,6 +86,8 @@ include ../scripts/utilities.mak
 #
 # Define FEATURES_DUMP to provide features detection dump file
 # and bypass the feature detection
+#
+# Define NO_JVMTI if you do not want jvmti agent built
 
 # As per kernel Makefile, avoid funny character set dependencies
 unexport LC_ALL
@@ -283,6 +285,12 @@ ifndef NO_PERF_READ_VDSOX32
 PROGRAMS += $(OUTPUT)perf-read-vdsox32
 endif
 
+LIBJVMTI = libperf-jvmti.so
+
+ifndef NO_JVMTI
+PROGRAMS += $(OUTPUT)$(LIBJVMTI)
+endif
+
 # what 'all' will build and 'install' will install, in perfexecdir
 ALL_PROGRAMS = $(PROGRAMS) $(SCRIPTS)
 
@@ -551,6 +559,16 @@ $(OUTPUT)perf-read-vdsox32: perf-read-vdso.c util/find-vdso-map.c
 	$(QUIET_CC)$(CC) -mx32 $(filter -static,$(LDFLAGS)) -Wall -Werror -o $@ perf-read-vdso.c
 endif
 
+ifndef NO_JVMTI
+LIBJVMTI_IN := $(OUTPUT)jvmti/jvmti-in.o
+
+$(LIBJVMTI_IN): FORCE
+	$(Q)$(MAKE) -f $(srctree)/tools/build/Makefile.build dir=jvmti obj=jvmti
+
+$(OUTPUT)$(LIBJVMTI): $(LIBJVMTI_IN)
+	$(QUIET_LINK)$(CC) -shared -Wl,-soname -Wl,$(LIBJVMTI) -o $@ $< -lelf -lrt
+endif
+
 $(patsubst perf-%,%.o,$(PROGRAMS)): $(wildcard */*.h)
 
 LIBPERF_IN := $(OUTPUT)libperf-in.o
@@ -687,6 +705,10 @@ endif
 ifndef NO_PERF_READ_VDSOX32
 	$(call QUIET_INSTALL, perf-read-vdsox32) \
 		$(INSTALL) $(OUTPUT)perf-read-vdsox32 '$(DESTDIR_SQ)$(bindir_SQ)';
+endif
+ifndef NO_JVMTI
+	$(call QUIET_INSTALL, $(LIBJVMTI)) \
+		$(INSTALL) $(OUTPUT)$(LIBJVMTI) '$(DESTDIR_SQ)$(libdir_SQ)';
 endif
 	$(call QUIET_INSTALL, libexec) \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
@@ -754,7 +776,7 @@ clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clea
 	$(call QUIET_CLEAN, core-objs)  $(RM) $(LIB_FILE) $(OUTPUT)perf-archive $(OUTPUT)perf-with-kcore $(LANG_BINDINGS)
 	$(Q)find $(if $(OUTPUT),$(OUTPUT),.) -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete
 	$(Q)$(RM) $(OUTPUT).config-detected
-	$(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf perf-read-vdso32 perf-read-vdsox32 $(OUTPUT)pmu-events/jevents
+	$(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf perf-read-vdso32 perf-read-vdsox32 $(OUTPUT)pmu-events/jevents $(OUTPUT)$(LIBJVMTI).so
 	$(call QUIET_CLEAN, core-gen)   $(RM)  *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)FEATURE-DUMP $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex* \
 		$(OUTPUT)util/intel-pt-decoder/inat-tables.c $(OUTPUT)fixdep \
 		$(OUTPUT)tests/llvm-src-{base,kbuild,prologue,relocation}.c \