Merge tag 'perf-core-for-mingo-20161207' 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:

Improvements:

 - Improve error message when analyzing file with required events in
   'perf sched timehist' (David Ahern)

Fixes:

 - Force fixdep compilation to be done at the start of the build, fixing
   some build race conditions in high core count machines (Jiri Olsa)

 - Fix handling a zero sample->tid in 'perf sched timehist', as
   sometimes that isn't the idle thread (Namhyung Kim)

Infrastructure changes:

 - Check minimal accepted LLVM version in its feature check, 3.9 at this
   time (Wang Nan)

Documentation changes:

 - Explicitly document that --children is enabled by default (Yannick Brosseau)

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

10 files changed, 122 insertions, 38 deletions

diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile
index 303196c16019..b564a2eea039 100644
--- a/tools/build/feature/Makefile
+++ b/tools/build/feature/Makefile
@@ -231,14 +231,18 @@ $(OUTPUT)test-jvmti.bin:
         $(BUILD)
 
 $(OUTPUT)test-llvm.bin:
-        $(BUILDXX) -std=gnu++11                                         \
+        $(BUILDXX) -std=gnu++11                                 \
                 -I$(shell $(LLVM_CONFIG) --includedir)          \
                 -L$(shell $(LLVM_CONFIG) --libdir)              \
                 $(shell $(LLVM_CONFIG) --libs Core BPF)         \
                 $(shell $(LLVM_CONFIG) --system-libs)
 
+$(OUTPUT)test-llvm-version.bin:
+        $(BUILDXX) -std=gnu++11                                 \
+                -I$(shell $(LLVM_CONFIG) --includedir)
+
 $(OUTPUT)test-clang.bin:
-        $(BUILDXX) -std=gnu++11                                         \
+        $(BUILDXX) -std=gnu++11                                 \
                 -I$(shell $(LLVM_CONFIG) --includedir)          \
                 -L$(shell $(LLVM_CONFIG) --libdir)              \
                 -Wl,--start-group -lclangBasic -lclangDriver    \
diff --git a/tools/build/feature/test-llvm-version.cpp b/tools/build/feature/test-llvm-version.cpp
new file mode 100644
index 000000000000..896d31724568
--- /dev/null
+++ b/tools/build/feature/test-llvm-version.cpp
@@ -0,0 +1,11 @@
+#include <cstdio>
+#include "llvm/Config/llvm-config.h"
+
+#define NUM_VERSION (((LLVM_VERSION_MAJOR) << 16) + (LLVM_VERSION_MINOR << 8) + LLVM_VERSION_PATCH)
+#define pass int main() {printf("%x\n", NUM_VERSION); return 0;}
+
+#if NUM_VERSION >= 0x030900
+pass
+#else
+# error This LLVM is not tested yet.
+#endif
diff --git a/tools/build/feature/test-llvm.cpp b/tools/build/feature/test-llvm.cpp
index d8d2cee35345..455a332dc8a8 100644
--- a/tools/build/feature/test-llvm.cpp
+++ b/tools/build/feature/test-llvm.cpp
@@ -1,5 +1,10 @@
 #include "llvm/Support/ManagedStatic.h"
 #include "llvm/Support/raw_ostream.h"
+#define NUM_VERSION (((LLVM_VERSION_MAJOR) << 16) + (LLVM_VERSION_MINOR << 8) + LLVM_VERSION_PATCH)
+
+#if NUM_VERSION < 0x030900
+# error "LLVM version too low"
+#endif
 int main()
 {
         llvm::errs() << "Hello World!\n";
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 3a166ae4a4d3..f2914f03ae7b 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -239,7 +239,8 @@ OPTIONS
         Accumulate callchain of children to parent entry so that then can
         show up in the output.  The output will have a new "Children" column
         and will be sorted on the data.  It requires callchains are recorded.
-        See the `overhead calculation' section for more details.
+        See the `overhead calculation' section for more details. Enabled by
+        default, disable with --no-children.
 
 --max-stack::
         Set the stack depth limit when parsing the callchain, anything
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index 91d638df3a6b..e71d63843f45 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -170,6 +170,7 @@ Default is to monitor all CPUS.
         show up in the output.  The output will have a new "Children" column
         and will be sorted on the data.  It requires -g/--call-graph option
         enabled.  See the `overhead calculation' section for more details.
+        Enabled by default, disable with --no-children.
 
 --max-stack::
         Set the stack depth limit when parsing the callchain, anything
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 09c2a9874f2f..76c84f0eec52 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -802,12 +802,13 @@ ifdef LIBCLANGLLVM
     msg := $(warning No g++ found, disable clang and llvm support. Please install g++)
   else
     $(call feature_check,llvm)
+    $(call feature_check,llvm-version)
     ifneq ($(feature-llvm), 1)
-      msg := $(warning No libLLVM found, disable clang and llvm support. Please install llvm-dev)
+      msg := $(warning No suitable libLLVM found, disabling builtin clang and LLVM support. Please install llvm-dev(el) (>= 3.9.0))
     else
       $(call feature_check,clang)
       ifneq ($(feature-clang), 1)
-        msg := $(warning No libclang found, disable clang and llvm support. Please install libclang-dev)
+        msg := $(warning No suitable libclang found, disabling builtin clang and LLVM support. Please install libclang-dev(el) (>= 3.9.0))
       else
         CFLAGS += -DHAVE_LIBCLANGLLVM_SUPPORT
         CXXFLAGS += -DHAVE_LIBCLANGLLVM_SUPPORT -I$(shell $(LLVM_CONFIG) --includedir)
@@ -816,6 +817,9 @@ ifdef LIBCLANGLLVM
         USE_CXX = 1
         USE_LLVM = 1
         USE_CLANG = 1
+        ifneq ($(feature-llvm-version),1)
+          msg := $(warning This version of LLVM is not tested. May cause build errors)
+        endif
       endif
     endif
   endif
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 10495c9dbe71..8f1c258b151a 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -128,10 +128,6 @@ endif
 # (this improves performance and avoids hard-to-debug behaviour);
 MAKEFLAGS += -r
 
-$(OUTPUT)PERF-VERSION-FILE: ../../.git/HEAD
-        $(Q)$(SHELL_PATH) util/PERF-VERSION-GEN $(OUTPUT)
-        $(Q)touch $(OUTPUT)PERF-VERSION-FILE
-
 # Makefiles suck: This macro sets a default value of $(2) for the
 # variable named by $(1), unless the variable has been set by
 # environment or command line. This is necessary for CC and AR
@@ -168,11 +164,6 @@ BISON   = bison
 STRIP   = strip
 AWK     = awk
 
-LIB_DIR         = $(srctree)/tools/lib/api/
-TRACE_EVENT_DIR = $(srctree)/tools/lib/traceevent/
-BPF_DIR         = $(srctree)/tools/lib/bpf/
-SUBCMD_DIR      = $(srctree)/tools/lib/subcmd/
-
 # include Makefile.config by default and rule out
 # non-config cases
 config := 1
@@ -185,6 +176,40 @@ ifeq ($(filter-out $(NON_CONFIG_TARGETS),$(MAKECMDGOALS)),)
 endif
 endif
 
+# The fixdep build - we force fixdep tool to be built as
+# the first target in the separate make session not to be
+# disturbed by any parallel make jobs. Once fixdep is done
+# we issue the requested build with FIXDEP=1 variable.
+#
+# The fixdep build is disabled for $(NON_CONFIG_TARGETS)
+# targets, because it's not necessary.
+
+ifdef FIXDEP
+  force_fixdep := 0
+else
+  force_fixdep := $(config)
+endif
+
+export srctree OUTPUT RM CC CXX LD AR CFLAGS CXXFLAGS V BISON FLEX AWK
+export HOSTCC HOSTLD HOSTAR
+
+include $(srctree)/tools/build/Makefile.include
+
+ifeq ($(force_fixdep),1)
+goals := $(filter-out all sub-make, $(MAKECMDGOALS))
+
+$(goals) all: sub-make
+
+sub-make: fixdep
+        $(Q)$(MAKE) FIXDEP=1 -f Makefile.perf $(goals)
+
+else # force_fixdep
+
+LIB_DIR         = $(srctree)/tools/lib/api/
+TRACE_EVENT_DIR = $(srctree)/tools/lib/traceevent/
+BPF_DIR         = $(srctree)/tools/lib/bpf/
+SUBCMD_DIR      = $(srctree)/tools/lib/subcmd/
+
 # Set FEATURE_TESTS to 'all' so all possible feature checkers are executed.
 # Without this setting the output feature dump file misses some features, for
 # example, liberty. Select all checkers so we won't get an incomplete feature
@@ -369,10 +394,6 @@ strip: $(PROGRAMS) $(OUTPUT)perf
 
 PERF_IN := $(OUTPUT)perf-in.o
 
-export srctree OUTPUT RM CC CXX LD AR CFLAGS CXXFLAGS V BISON FLEX AWK
-export HOSTCC HOSTLD HOSTAR
-include $(srctree)/tools/build/Makefile.include
-
 JEVENTS       := $(OUTPUT)pmu-events/jevents
 JEVENTS_IN    := $(OUTPUT)pmu-events/jevents-in.o
 
@@ -491,7 +512,7 @@ $(OUTPUT)perf: $(PERFLIBS) $(PERF_IN) $(PMU_EVENTS_IN) $(LIBTRACEEVENT_DYNAMIC_L
         $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $(LIBTRACEEVENT_DYNAMIC_LIST_LDFLAGS) \
                 $(PERF_IN) $(PMU_EVENTS_IN) $(LIBS) -o $@
 
-$(GTK_IN): fixdep FORCE
+$(GTK_IN): FORCE
         $(Q)$(MAKE) $(build)=gtk
 
 $(OUTPUT)libperf-gtk.so: $(GTK_IN) $(PERFLIBS)
@@ -505,6 +526,10 @@ $(OUTPUT)common-cmds.h: $(wildcard Documentation/perf-*.txt)
 $(SCRIPTS) : % : %.sh
         $(QUIET_GEN)$(INSTALL) '$@.sh' '$(OUTPUT)$@'
 
+$(OUTPUT)PERF-VERSION-FILE: ../../.git/HEAD
+        $(Q)$(SHELL_PATH) util/PERF-VERSION-GEN $(OUTPUT)
+        $(Q)touch $(OUTPUT)PERF-VERSION-FILE
+
 # These can record PERF_VERSION
 perf.spec $(SCRIPTS) \
         : $(OUTPUT)PERF-VERSION-FILE
@@ -536,7 +561,7 @@ endif
 __build-dir = $(subst $(OUTPUT),,$(dir $@))
 build-dir   = $(if $(__build-dir),$(__build-dir),.)
 
-prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h fixdep archheaders
+prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h archheaders
 
 $(OUTPUT)%.o: %.c prepare FORCE
         $(Q)$(MAKE) -f $(srctree)/tools/build/Makefile.build dir=$(build-dir) $@
@@ -586,7 +611,7 @@ $(patsubst perf-%,%.o,$(PROGRAMS)): $(wildcard */*.h)
 
 LIBPERF_IN := $(OUTPUT)libperf-in.o
 
-$(LIBPERF_IN): prepare fixdep FORCE
+$(LIBPERF_IN): prepare FORCE
         $(Q)$(MAKE) $(build)=libperf
 
 $(LIB_FILE): $(LIBPERF_IN)
@@ -594,10 +619,10 @@ $(LIB_FILE): $(LIBPERF_IN)
 
 LIBTRACEEVENT_FLAGS += plugin_dir=$(plugindir_SQ)
 
-$(LIBTRACEEVENT): fixdep FORCE
+$(LIBTRACEEVENT): FORCE
         $(Q)$(MAKE) -C $(TRACE_EVENT_DIR) $(LIBTRACEEVENT_FLAGS) O=$(OUTPUT) $(OUTPUT)libtraceevent.a
 
-libtraceevent_plugins: fixdep FORCE
+libtraceevent_plugins: FORCE
         $(Q)$(MAKE) -C $(TRACE_EVENT_DIR) $(LIBTRACEEVENT_FLAGS) O=$(OUTPUT) plugins
 
 $(LIBTRACEEVENT_DYNAMIC_LIST): libtraceevent_plugins
@@ -610,21 +635,21 @@ $(LIBTRACEEVENT)-clean:
 install-traceevent-plugins: libtraceevent_plugins
         $(Q)$(MAKE) -C $(TRACE_EVENT_DIR) $(LIBTRACEEVENT_FLAGS) O=$(OUTPUT) install_plugins
 
-$(LIBAPI): fixdep FORCE
+$(LIBAPI): FORCE
         $(Q)$(MAKE) -C $(LIB_DIR) O=$(OUTPUT) $(OUTPUT)libapi.a
 
 $(LIBAPI)-clean:
         $(call QUIET_CLEAN, libapi)
         $(Q)$(MAKE) -C $(LIB_DIR) O=$(OUTPUT) clean >/dev/null
 
-$(LIBBPF): fixdep FORCE
+$(LIBBPF): FORCE
         $(Q)$(MAKE) -C $(BPF_DIR) O=$(OUTPUT) $(OUTPUT)libbpf.a FEATURES_DUMP=$(FEATURE_DUMP_EXPORT)
 
 $(LIBBPF)-clean:
         $(call QUIET_CLEAN, libbpf)
         $(Q)$(MAKE) -C $(BPF_DIR) O=$(OUTPUT) clean >/dev/null
 
-$(LIBSUBCMD): fixdep FORCE
+$(LIBSUBCMD): FORCE
         $(Q)$(MAKE) -C $(SUBCMD_DIR) O=$(OUTPUT) $(OUTPUT)libsubcmd.a
 
 $(LIBSUBCMD)-clean:
@@ -832,3 +857,4 @@ FORCE:
 .PHONY: $(GIT-HEAD-PHONY) TAGS tags cscope FORCE prepare
 .PHONY: libtraceevent_plugins archheaders
 
+endif # force_fixdep
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 870d94cd20ba..1a3f1be93372 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -2010,7 +2010,7 @@ static int init_idle_threads(int ncpu)
         if (!idle_threads)
                 return -ENOMEM;
 
-        idle_max_cpu = ncpu - 1;
+        idle_max_cpu = ncpu;
 
         /* allocate the actual thread struct if needed */
         for (i = 0; i < ncpu; ++i) {
@@ -2031,7 +2031,7 @@ static void free_idle_threads(void)
         if (idle_threads == NULL)
                 return;
 
-        for (i = 0; i <= idle_max_cpu; ++i) {
+        for (i = 0; i < idle_max_cpu; ++i) {
                 if ((idle_threads[i]))
                         thread__delete(idle_threads[i]);
         }
@@ -2054,8 +2054,7 @@ static struct thread *get_idle_thread(int cpu)
                         return NULL;
 
                 idle_threads = (struct thread **) p;
-                i = idle_max_cpu ? idle_max_cpu + 1 : 0;
-                for (; i < j; ++i)
+                for (i = idle_max_cpu; i < j; ++i)
                         idle_threads[i] = NULL;
 
                 idle_max_cpu = j;
@@ -2118,7 +2117,9 @@ static struct thread *timehist_get_thread(struct perf_sched *sched,
                         pr_err("Failed to get idle thread for cpu %d.\n", sample->cpu);
 
         } else {
-                thread = machine__findnew_thread(machine, sample->pid, sample->tid);
+                /* there were samples with tid 0 but non-zero pid */
+                thread = machine__findnew_thread(machine, sample->pid,
+                                                 sample->tid ?: sample->pid);
                 if (thread == NULL) {
                         pr_debug("Failed to get thread for tid %d. skipping sample.\n",
                                  sample->tid);
@@ -2493,7 +2494,7 @@ static void timehist_print_summary(struct perf_sched *sched,
                 return;
 
         printf("\nIdle stats:\n");
-        for (i = 0; i <= idle_max_cpu; ++i) {
+        for (i = 0; i < idle_max_cpu; ++i) {
                 t = idle_threads[i];
                 if (!t)
                         continue;
@@ -2583,6 +2584,7 @@ static int perf_sched__timehist(struct perf_sched *sched)
         struct perf_data_file file = {
                 .path = input_name,
                 .mode = PERF_DATA_MODE_READ,
+                .force = sched->force,
         };
 
         struct perf_session *session;
@@ -2629,8 +2631,12 @@ static int perf_sched__timehist(struct perf_sched *sched)
         if (perf_session__set_tracepoints_handlers(session, handlers))
                 goto out;
 
-        if (!perf_session__has_traces(session, "record -R"))
+        /* sched_switch event at a minimum needs to exist */
+        if (!perf_evlist__find_tracepoint_by_name(session->evlist,
+                                                  "sched:sched_switch")) {
+                pr_err("No sched_switch events found. Have you run 'perf sched record'?\n");
                 goto out;
+        }
 
         if (sched->show_migrations &&
             perf_session__set_tracepoints_handlers(session, migrate_handlers))
@@ -2984,6 +2990,7 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
                     "be more verbose (show symbol address, etc)"),
         OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
                     "dump raw trace in ASCII"),
+        OPT_BOOLEAN('f', "force", &sched.force, "don't complain, do it"),
         OPT_END()
         };
         const struct option latency_options[] = {
@@ -2991,8 +2998,6 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
                    "sort by key(s): runtime, switch, avg, max"),
         OPT_INTEGER('C', "CPU", &sched.profile_cpu,
                     "CPU to profile on"),
-        OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
-                    "dump raw trace in ASCII"),
         OPT_BOOLEAN('p', "pids", &sched.skip_merge,
                     "latency stats per pid instead of per comm"),
         OPT_PARENT(sched_options)
@@ -3000,9 +3005,6 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
         const struct option replay_options[] = {
         OPT_UINTEGER('r', "repeat", &sched.replay_repeat,
                      "repeat the workload replay N times (-1: infinite)"),
-        OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
-                    "dump raw trace in ASCII"),
-        OPT_BOOLEAN('f', "force", &sched.force, "don't complain, do it"),
         OPT_PARENT(sched_options)
         };
         const struct option map_options[] = {
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 823befd8209a..42922512c1c6 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -1234,3 +1234,30 @@ out:
         }
         return -ENOMEM;
 }
+
+int callchain_cursor__copy(struct callchain_cursor *dst,
+                           struct callchain_cursor *src)
+{
+        int rc = 0;
+
+        callchain_cursor_reset(dst);
+        callchain_cursor_commit(src);
+
+        while (true) {
+                struct callchain_cursor_node *node;
+
+                node = callchain_cursor_current(src);
+                if (node == NULL)
+                        break;
+
+                rc = callchain_cursor_append(dst, node->ip, node->map, node->sym,
+                                             node->branch, &node->branch_flags,
+                                             node->nr_loop_iter, node->samples);
+                if (rc)
+                        break;
+
+                callchain_cursor_advance(src);
+        }
+
+        return rc;
+}
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index d9c70dccf06a..35c8e379530f 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -216,6 +216,9 @@ static inline void callchain_cursor_advance(struct callchain_cursor *cursor)
         cursor->pos++;
 }
 
+int callchain_cursor__copy(struct callchain_cursor *dst,
+                           struct callchain_cursor *src);
+
 struct option;
 struct hist_entry;