Merge tag 'perf-core-for-mingo-4.17-20180308' 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:

- Support to display the IPC/Cycle in 'annotate' TUI, for systems
  where this info can be obtained, like Intel's >= Skylake (Jin Yao)

- Support wildcards on PMU name in dynamic PMU events (Agustin Vega-Frias)

- Display pmu name when printing unmerged events in stat (Agustin Vega-Frias)

- Auto-merge PMU events created by prefix or glob match (Agustin Vega-Frias)

- Fix s390 'call' operations target function annotation (Thomas Richter)

- Handle s390 PC relative load and store instruction in the augmented
  'annotate', code, used so far in the TUI modes of 'perf report' and
  'perf annotate' (Thomas Richter)

- Provide libtraceevent with a kernel symbol resolver, so that
  symbols in tracepoint fields can be resolved when showing them in
  tools such as 'perf report' (Wang YanQing)

- Refactor the cgroups code to look more like other code in tools/perf,
  using cgroup__{put,get} for refcount operations instead of its
  open-coded equivalent, breaking larger functions, etc (Arnaldo Carvalho de Melo)

- Implement support for the -G/--cgroup target in 'perf trace', allowing
  strace like tracing (plus other events, backtraces, etc) for cgroups
  (Arnaldo Carvalho de Melo)

- Update thread shortname in 'perf sched map' when the thread's COMM
  changes (Changbin Du)

- refcount 'struct mem_info', for better sharing it over several
  users, avoid duplicating structs and fixing crashes related to
  use after free (Jiri Olsa)

- Display perf.data version, offsets in 'perf report --header' (Jiri Olsa)

- Record the machine's memory topology information in a perf.data
  feature section, to be used by tools such as 'perf c2c' (Jiri Olsa)

- Fix output of forced groups in the header for 'perf report' --stdio
  and --tui (Jiri Olsa)

- Better support llvm, clang, cxx make tests in the build process (Jiri Olsa)

- Streamline the 'struct perf_mmap' methods, storing some info in the
  struct instead of passing it via various methods, shortening its
  signatures (Kan Liang)

- Update the quipper perf.data parser library site information (Stephane Eranian)

- Correct perf's man pages title markers for asciidoctor (Takashi Iwai)

- Intel PT fixes and refactorings paving the way for implementing
  support for AUX area sampling (Adrian Hunter)

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

tools/build/Makefile.feature

@@ -82,7 +82,11 @@ FEATURE_TESTS_EXTRA :=                  \
          liberty-z                      \
          libunwind-debug-frame          \
          libunwind-debug-frame-arm      \
-         libunwind-debug-frame-aarch64
+         libunwind-debug-frame-aarch64  \
+         cxx                            \
+         llvm                           \
+         llvm-version                   \
+         clang
 
 FEATURE_TESTS ?= $(FEATURE_TESTS_BASIC)
 

tools/build/feature/Makefile

@@ -54,7 +54,10 @@ FILES=                                          \
          test-jvmti.bin				\
          test-sched_getcpu.bin			\
          test-setns.bin				\
-         test-libopencsd.bin
+         test-libopencsd.bin			\
+         test-clang.bin				\
+         test-llvm.bin				\
+         test-llvm-version.bin
 
 FILES := $(addprefix $(OUTPUT),$(FILES))
 
@@ -257,11 +260,13 @@ $(OUTPUT)test-llvm.bin:
 		-I$(shell $(LLVM_CONFIG) --includedir) 		\
 		-L$(shell $(LLVM_CONFIG) --libdir)		\
 		$(shell $(LLVM_CONFIG) --libs Core BPF)		\
-		$(shell $(LLVM_CONFIG) --system-libs)
+		$(shell $(LLVM_CONFIG) --system-libs)		\
+		> $(@:.bin=.make.output) 2>&1
 
 $(OUTPUT)test-llvm-version.bin:
 	$(BUILDXX) -std=gnu++11 				\
-		-I$(shell $(LLVM_CONFIG) --includedir)
+		-I$(shell $(LLVM_CONFIG) --includedir)		\
+		> $(@:.bin=.make.output) 2>&1
 
 $(OUTPUT)test-clang.bin:
 	$(BUILDXX) -std=gnu++11 				\
@@ -271,7 +276,8 @@ $(OUTPUT)test-clang.bin:
 		  -lclangFrontend -lclangEdit -lclangLex	\
 		  -lclangAST -Wl,--end-group 			\
 		$(shell $(LLVM_CONFIG) --libs Core option)	\
-		$(shell $(LLVM_CONFIG) --system-libs)
+		$(shell $(LLVM_CONFIG) --system-libs)		\
+		> $(@:.bin=.make.output) 2>&1
 
 -include $(OUTPUT)*.d
 

tools/include/linux/bitmap.h

@@ -98,7 +98,7 @@ static inline int test_and_set_bit(int nr, unsigned long *addr)
 
 /**
  * bitmap_alloc - Allocate bitmap
- * @nr: Bit to set
+ * @nbits: Number of bits
  */
 static inline unsigned long *bitmap_alloc(int nbits)
 {

tools/perf/Documentation/perf-data.txt

@@ -1,5 +1,5 @@
 perf-data(1)
-==============
+============
 
 NAME
 ----

tools/perf/Documentation/perf-ftrace.txt

@@ -1,5 +1,5 @@
 perf-ftrace(1)
-=============
+==============
 
 NAME
 ----

tools/perf/Documentation/perf-kallsyms.txt

@@ -1,5 +1,5 @@
 perf-kallsyms(1)
-==============
+================
 
 NAME
 ----

tools/perf/Documentation/perf-list.txt

@@ -141,7 +141,13 @@ on the first memory controller on socket 0 of a Intel Xeon system
 
 Each memory controller has its own PMU.  Measuring the complete system
 bandwidth would require specifying all imc PMUs (see perf list output),
-and adding the values together.
+and adding the values together. To simplify creation of multiple events,
+prefix and glob matching is supported in the PMU name, and the prefix
+'uncore_' is also ignored when performing the match. So the command above
+can be expanded to all memory controllers by using the syntaxes:
+
+  perf stat -C 0 -a imc/cas_count_read/,imc/cas_count_write/ -I 1000 ...
+  perf stat -C 0 -a *imc*/cas_count_read/,*imc*/cas_count_write/ -I 1000 ...
 
 This example measures the combined core power every second
 

tools/perf/Documentation/perf-sched.txt

@@ -1,5 +1,5 @@
 perf-sched(1)
-==============
+=============
 
 NAME
 ----

tools/perf/Documentation/perf-script-perl.txt

@@ -1,5 +1,5 @@
 perf-script-perl(1)
-==================
+===================
 
 NAME
 ----

tools/perf/Documentation/perf-stat.txt

@@ -49,6 +49,13 @@ report::
 	  parameters are defined by corresponding entries in
 	  /sys/bus/event_source/devices/<pmu>/format/*
 
+	Note that the last two syntaxes support prefix and glob matching in
+	the PMU name to simplify creation of events accross multiple instances
+	of the same type of PMU in large systems (e.g. memory controller PMUs).
+	Multiple PMU instances are typical for uncore PMUs, so the prefix
+	'uncore_' is also ignored when performing this match.
+
+
 -i::
 --no-inherit::
         child tasks do not inherit counters
@@ -260,6 +267,16 @@ taskset.
 --no-merge::
 Do not merge results from same PMUs.
 
+When multiple events are created from a single event specification,
+stat will, by default, aggregate the event counts and show the result
+in a single row. This option disables that behavior and shows
+the individual events and counts.
+
+Multiple events are created from a single event specification when:
+1. Prefix or glob matching is used for the PMU name.
+2. Aliases, which are listed immediately after the Kernel PMU events
+   by perf list, are used.
+
 --smi-cost::
 Measure SMI cost if msr/aperf/ and msr/smi/ events are supported.
 

tools/perf/Documentation/perf-trace.txt

@@ -63,6 +63,31 @@ filter out the startup phase of the program, which is often very different.
 --uid=::
         Record events in threads owned by uid. Name or number.
 
+-G::
+--cgroup::
+	Record events in threads in a cgroup.
+
+	Look for cgroups to set at the /sys/fs/cgroup/perf_event directory, then
+	remove the /sys/fs/cgroup/perf_event/ part and try:
+
+		perf trace -G A -e sched:*switch
+
+	Will set all raw_syscalls:sys_{enter,exit}, pgfault, vfs_getname, etc
+	_and_ sched:sched_switch to the 'A' cgroup, while:
+
+		perf trace -e sched:*switch -G A
+
+	will only set the sched:sched_switch event to the 'A' cgroup, all the
+	other events (raw_syscalls:sys_{enter,exit}, etc are left "without"
+	a cgroup (on the root cgroup, sys wide, etc).
+
+	Multiple cgroups:
+
+		perf trace -G A -e sched:*switch -G B
+
+	the syscall ones go to the 'A' cgroup, the sched:sched_switch goes
+	to the 'B' cgroup.
+
 --filter-pids=::
 	Filter out events for these pids and for 'trace' itself (comma separated list).
 

tools/perf/Documentation/perf.data-file-format.txt

@@ -485,10 +485,5 @@ in pmu-tools parser. This allows to read perf.data from python and dump it.
 quipper
 
 The quipper C++ parser is available at
-https://chromium.googlesource.com/chromiumos/platform2
+http://github.com/google/perf_data_converter/tree/master/src/quipper
 
-It is under the chromiumos-wide-profiling/ subdirectory. This library can
-convert a perf data file to a protobuf and vice versa.
-
-Unfortunately this parser tends to be many versions behind and may not be able
-to parse data files generated by recent perf.

tools/perf/Makefile.perf

@@ -708,15 +708,15 @@ TAG_FILES= ../../include/uapi/linux/perf_event.h
 
 TAGS:
 	$(QUIET_GEN)$(RM) TAGS; \
-	$(FIND) $(TAG_FOLDERS) -name '*.[hcS]' -print | xargs etags -a $(TAG_FILES)
+	$(FIND) $(TAG_FOLDERS) -name '*.[hcS]' -print -o -name '*.cpp' -print | xargs etags -a $(TAG_FILES)
 
 tags:
 	$(QUIET_GEN)$(RM) tags; \
-	$(FIND) $(TAG_FOLDERS) -name '*.[hcS]' -print | xargs ctags -a $(TAG_FILES)
+	$(FIND) $(TAG_FOLDERS) -name '*.[hcS]' -print -o -name '*.cpp' -print | xargs ctags -a $(TAG_FILES)
 
 cscope:
 	$(QUIET_GEN)$(RM) cscope*; \
-	$(FIND) $(TAG_FOLDERS) -name '*.[hcS]' -print | xargs cscope -b $(TAG_FILES)
+	$(FIND) $(TAG_FOLDERS) -name '*.[hcS]' -print -o -name '*.cpp' -print | xargs cscope -b $(TAG_FILES)
 
 ### Testing rules
 

tools/perf/arch/s390/annotate/instructions.c

@@ -1,6 +1,112 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/compiler.h>
 
+static int s390_call__parse(struct arch *arch, struct ins_operands *ops,
+			    struct map *map)
+{
+	char *endptr, *tok, *name;
+	struct addr_map_symbol target = {
+		.map = map,
+	};
+
+	tok = strchr(ops->raw, ',');
+	if (!tok)
+		return -1;
+
+	ops->target.addr = strtoull(tok + 1, &endptr, 16);
+
+	name = strchr(endptr, '<');
+	if (name == NULL)
+		return -1;
+
+	name++;
+
+	if (arch->objdump.skip_functions_char &&
+	    strchr(name, arch->objdump.skip_functions_char))
+		return -1;
+
+	tok = strchr(name, '>');
+	if (tok == NULL)
+		return -1;
+
+	*tok = '\0';
+	ops->target.name = strdup(name);
+	*tok = '>';
+
+	if (ops->target.name == NULL)
+		return -1;
+	target.addr = map__objdump_2mem(map, ops->target.addr);
+
+	if (map_groups__find_ams(&target) == 0 &&
+	    map__rip_2objdump(target.map, map->map_ip(target.map, target.addr)) == ops->target.addr)
+		ops->target.sym = target.sym;
+
+	return 0;
+}
+
+static int call__scnprintf(struct ins *ins, char *bf, size_t size,
+			   struct ins_operands *ops);
+
+static struct ins_ops s390_call_ops = {
+	.parse	   = s390_call__parse,
+	.scnprintf = call__scnprintf,
+};
+
+static int s390_mov__parse(struct arch *arch __maybe_unused,
+			   struct ins_operands *ops,
+			   struct map *map __maybe_unused)
+{
+	char *s = strchr(ops->raw, ','), *target, *endptr;
+
+	if (s == NULL)
+		return -1;
+
+	*s = '\0';
+	ops->source.raw = strdup(ops->raw);
+	*s = ',';
+
+	if (ops->source.raw == NULL)
+		return -1;
+
+	target = ++s;
+	ops->target.raw = strdup(target);
+	if (ops->target.raw == NULL)
+		goto out_free_source;
+
+	ops->target.addr = strtoull(target, &endptr, 16);
+	if (endptr == target)
+		goto out_free_target;
+
+	s = strchr(endptr, '<');
+	if (s == NULL)
+		goto out_free_target;
+	endptr = strchr(s + 1, '>');
+	if (endptr == NULL)
+		goto out_free_target;
+
+	*endptr = '\0';
+	ops->target.name = strdup(s + 1);
+	*endptr = '>';
+	if (ops->target.name == NULL)
+		goto out_free_target;
+
+	return 0;
+
+out_free_target:
+	zfree(&ops->target.raw);
+out_free_source:
+	zfree(&ops->source.raw);
+	return -1;
+}
+
+static int mov__scnprintf(struct ins *ins, char *bf, size_t size,
+			  struct ins_operands *ops);
+
+static struct ins_ops s390_mov_ops = {
+	.parse	   = s390_mov__parse,
+	.scnprintf = mov__scnprintf,
+};
+
 static struct ins_ops *s390__associate_ins_ops(struct arch *arch, const char *name)
 {
 	struct ins_ops *ops = NULL;
@@ -14,9 +120,17 @@ static struct ins_ops *s390__associate_ins_ops(struct arch *arch, const char *na
 	if (!strcmp(name, "bras") ||
 	    !strcmp(name, "brasl") ||
 	    !strcmp(name, "basr"))
-		ops = &call_ops;
+		ops = &s390_call_ops;
 	if (!strcmp(name, "br"))
 		ops = &ret_ops;
+	/* override load/store relative to PC */
+	if (!strcmp(name, "lrl") ||
+	    !strcmp(name, "lgrl") ||
+	    !strcmp(name, "lgfrl") ||
+	    !strcmp(name, "llgfrl") ||
+	    !strcmp(name, "strl") ||
+	    !strcmp(name, "stgrl"))
+		ops = &s390_mov_ops;
 
 	if (ops)
 		arch__associate_ins_ops(arch, name, ops);

tools/perf/arch/x86/tests/perf-time-to-tsc.c

@@ -61,7 +61,6 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe
 	u64 test_tsc, comm1_tsc, comm2_tsc;
 	u64 test_time, comm1_time = 0, comm2_time = 0;
 	struct perf_mmap *md;
-	u64 end, start;
 
 	threads = thread_map__new(-1, getpid(), UINT_MAX);
 	CHECK_NOT_NULL__(threads);
@@ -112,10 +111,10 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe
 
 	for (i = 0; i < evlist->nr_mmaps; i++) {
 		md = &evlist->mmap[i];
-		if (perf_mmap__read_init(md, false, &start, &end) < 0)
+		if (perf_mmap__read_init(md) < 0)
 			continue;
 
-		while ((event = perf_mmap__read_event(md, false, &start, end)) != NULL) {
+		while ((event = perf_mmap__read_event(md)) != NULL) {
 			struct perf_sample sample;
 
 			if (event->header.type != PERF_RECORD_COMM ||
@@ -134,7 +133,7 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe
 				comm2_time = sample.time;
 			}
 next_event:
-			perf_mmap__consume(md, false);
+			perf_mmap__consume(md);
 		}
 		perf_mmap__read_done(md);
 	}

tools/perf/arch/x86/util/auxtrace.c

@@ -37,15 +37,11 @@ struct auxtrace_record *auxtrace_record__init_intel(struct perf_evlist *evlist,
 	intel_pt_pmu = perf_pmu__find(INTEL_PT_PMU_NAME);
 	intel_bts_pmu = perf_pmu__find(INTEL_BTS_PMU_NAME);
 
-	if (evlist) {
-		evlist__for_each_entry(evlist, evsel) {
-			if (intel_pt_pmu &&
-			    evsel->attr.type == intel_pt_pmu->type)
-				found_pt = true;
-			if (intel_bts_pmu &&
-			    evsel->attr.type == intel_bts_pmu->type)
-				found_bts = true;
-		}
+	evlist__for_each_entry(evlist, evsel) {
+		if (intel_pt_pmu && evsel->attr.type == intel_pt_pmu->type)
+			found_pt = true;
+		if (intel_bts_pmu && evsel->attr.type == intel_bts_pmu->type)
+			found_bts = true;
 	}
 
 	if (found_pt && found_bts) {