Merge branch 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf tooling updates from Thomas Gleixner:

 - handle uretprobe placement proper on little endian PPC64

 - fix buffer handling in libtraceevent

 - add a missing pointer derefence in perf probe

 - fix the build of host tools in cross builds

 - fix Intel PT timestamp handling

 - synchronize memcpy, cpufeatures and bpf headers with the kernel headers

 - support for vendor supplied JSON files describing PMU events

 - a new set of tool tips

 - initial work for clang/llvm support

 - address some style issues found by cppcheck

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (35 commits)
  tools build: Add feature detection for g++
  tools build: Support compiling C++ source file
  perf top/report: Add tips about a list option
  perf report/top: Add a tip about system-wide collection from all CPUs
  perf report/top: Add a tip about source line numbers with overhead
  tools: Synchronize tools/include/uapi/linux/bpf.h
  tools: Synchronize tools/arch/x86/include/asm/cpufeatures.h
  perf bench mem: Sync memcpy assembly sources with the kernel
  perf jevents: Fix Intel JSON fixed counter conversions
  tools lib traceevent: Fix kbuffer_read_at_offset()
  perf intel-pt: Fix MTC timestamp calculation for large MTC periods
  perf intel-pt: Fix estimated timestamps for cycle-accurate mode
  perf uretprobe ppc64le: Fix probe location
  perf pmu-events: Add Skylake frontend MSR support
  perf pmu-events: Fix fixed counters on Intel
  perf tools: Make alias matching case-insensitive
  perf tools: Allow period= in perf stat CPU event descriptions.
  perf tools: Add README for info on parsing JSON/map files
  perf list jevents: Add support for event list topics
  perf list: Support long jevents descriptions
  ...

tools/arch/x86/include/asm/cpufeatures.h

@@ -106,7 +106,6 @@
 #define X86_FEATURE_APERFMPERF	( 3*32+28) /* APERFMPERF */
 #define X86_FEATURE_EAGER_FPU	( 3*32+29) /* "eagerfpu" Non lazy FPU restore */
 #define X86_FEATURE_NONSTOP_TSC_S3 ( 3*32+30) /* TSC doesn't stop in S3 state */
-#define X86_FEATURE_MCE_RECOVERY ( 3*32+31) /* cpu has recoverable machine checks */
 
 /* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
 #define X86_FEATURE_XMM3	( 4*32+ 0) /* "pni" SSE-3 */

tools/arch/x86/lib/memcpy_64.S

@@ -181,11 +181,11 @@ ENDPROC(memcpy_orig)
 
 #ifndef CONFIG_UML
 /*
- * memcpy_mcsafe - memory copy with machine check exception handling
+ * memcpy_mcsafe_unrolled - memory copy with machine check exception handling
  * Note that we only catch machine checks when reading the source addresses.
  * Writes to target are posted and don't generate machine checks.
  */
-ENTRY(memcpy_mcsafe)
+ENTRY(memcpy_mcsafe_unrolled)
 	cmpl $8, %edx
 	/* Less than 8 bytes? Go to byte copy loop */
 	jb .L_no_whole_words
@@ -273,7 +273,7 @@ ENTRY(memcpy_mcsafe)
 .L_done_memcpy_trap:
 	xorq %rax, %rax
 	ret
-ENDPROC(memcpy_mcsafe)
+ENDPROC(memcpy_mcsafe_unrolled)
 
 	.section .fixup, "ax"
 	/* Return -EFAULT for any failure */

tools/build/Build

+hostprogs := fixdep
+
 fixdep-y := fixdep.o

tools/build/Build.include

@@ -90,3 +90,9 @@ if_changed = $(if $(strip $(any-prereq) $(arg-check)),             \
 # - per object C flags
 # - BUILD_STR macro to allow '-D"$(variable)"' constructs
 c_flags = -Wp,-MD,$(depfile),-MT,$@ $(CFLAGS) -D"BUILD_STR(s)=\#s" $(CFLAGS_$(basetarget).o) $(CFLAGS_$(obj))
+cxx_flags = -Wp,-MD,$(depfile),-MT,$@ $(CXXFLAGS) -D"BUILD_STR(s)=\#s" $(CXXFLAGS_$(basetarget).o) $(CXXFLAGS_$(obj))
+
+###
+## HOSTCC C flags
+
+host_c_flags = -Wp,-MD,$(depfile),-MT,$@ $(CHOSTFLAGS) -D"BUILD_STR(s)=\#s" $(CHOSTFLAGS_$(basetarget).o) $(CHOSTFLAGS_$(obj))

tools/build/Makefile

@@ -14,6 +14,12 @@ endef
 $(call allow-override,CC,$(CROSS_COMPILE)gcc)
 $(call allow-override,LD,$(CROSS_COMPILE)ld)
 
+HOSTCC ?= gcc
+HOSTLD ?= ld
+HOSTAR ?= ar
+
+export HOSTCC HOSTLD HOSTAR
+
 ifeq ($(V),1)
   Q =
 else
@@ -36,7 +42,7 @@ $(OUTPUT)fixdep-in.o: FORCE
 	$(Q)$(MAKE) $(build)=fixdep
 
 $(OUTPUT)fixdep: $(OUTPUT)fixdep-in.o
-	$(QUIET_LINK)$(CC) $(LDFLAGS) -o $@ $<
+	$(QUIET_LINK)$(HOSTCC) $(LDFLAGS) -o $@ $<
 
 FORCE:
 

tools/build/Makefile.build

@@ -58,6 +58,12 @@ quiet_cmd_mkdir = MKDIR    $(dir $@)
 quiet_cmd_cc_o_c = CC       $@
       cmd_cc_o_c = $(CC) $(c_flags) -c -o $@ $<
 
+quiet_cmd_host_cc_o_c = HOSTCC   $@
+      cmd_host_cc_o_c = $(HOSTCC) $(host_c_flags) -c -o $@ $<
+
+quiet_cmd_cxx_o_c = CXX      $@
+      cmd_cxx_o_c = $(CXX) $(cxx_flags) -c -o $@ $<
+
 quiet_cmd_cpp_i_c = CPP      $@
       cmd_cpp_i_c = $(CC) $(c_flags) -E -o $@ $<
 
@@ -70,16 +76,28 @@ quiet_cmd_gen = GEN      $@
 # If there's nothing to link, create empty $@ object.
 quiet_cmd_ld_multi = LD       $@
       cmd_ld_multi = $(if $(strip $(obj-y)),\
-		       $(LD) -r -o $@  $(filter $(obj-y),$^),rm -f $@; $(AR) rcs $@)
+                     $(LD) -r -o $@  $(filter $(obj-y),$^),rm -f $@; $(AR) rcs $@)
+
+quiet_cmd_host_ld_multi = HOSTLD   $@
+      cmd_host_ld_multi = $(if $(strip $(obj-y)),\
+                          $(HOSTLD) -r -o $@  $(filter $(obj-y),$^),rm -f $@; $(HOSTAR) rcs $@)
+
+ifneq ($(filter $(obj),$(hostprogs)),)
+  host = host_
+endif
 
 # Build rules
 $(OUTPUT)%.o: %.c FORCE
 	$(call rule_mkdir)
-	$(call if_changed_dep,cc_o_c)
+	$(call if_changed_dep,$(host)cc_o_c)
+
+$(OUTPUT)%.o: %.cpp FORCE
+	$(call rule_mkdir)
+	$(call if_changed_dep,cxx_o_c)
 
 $(OUTPUT)%.o: %.S FORCE
 	$(call rule_mkdir)
-	$(call if_changed_dep,cc_o_c)
+	$(call if_changed_dep,$(host)cc_o_c)
 
 $(OUTPUT)%.i: %.c FORCE
 	$(call rule_mkdir)
@@ -119,7 +137,7 @@ $(sort $(subdir-obj-y)): $(subdir-y) ;
 
 $(in-target): $(obj-y) FORCE
 	$(call rule_mkdir)
-	$(call if_changed,ld_multi)
+	$(call if_changed,$(host)ld_multi)
 
 __build: $(in-target)
 	@:

tools/build/Makefile.feature

@@ -7,7 +7,7 @@ endif
 
 feature_check = $(eval $(feature_check_code))
 define feature_check_code
-  feature-$(1) := $(shell $(MAKE) OUTPUT=$(OUTPUT_FEATURES) CFLAGS="$(EXTRA_CFLAGS) $(FEATURE_CHECK_CFLAGS-$(1))" LDFLAGS="$(LDFLAGS) $(FEATURE_CHECK_LDFLAGS-$(1))" -C $(feature_dir) $(OUTPUT_FEATURES)test-$1.bin >/dev/null 2>/dev/null && echo 1 || echo 0)
+  feature-$(1) := $(shell $(MAKE) OUTPUT=$(OUTPUT_FEATURES) CFLAGS="$(EXTRA_CFLAGS) $(FEATURE_CHECK_CFLAGS-$(1))" CXXFLAGS="$(EXTRA_CXXFLAGS) $(FEATURE_CHECK_CXXFLAGS-$(1))" LDFLAGS="$(LDFLAGS) $(FEATURE_CHECK_LDFLAGS-$(1))" -C $(feature_dir) $(OUTPUT_FEATURES)test-$1.bin >/dev/null 2>/dev/null && echo 1 || echo 0)
 endef
 
 feature_set = $(eval $(feature_set_code))

tools/build/Makefile.include

 build := -f $(srctree)/tools/build/Makefile.build dir=. obj
 
-ifdef CROSS_COMPILE
-fixdep:
-else
 fixdep:
 	$(Q)$(MAKE) -C $(srctree)/tools/build CFLAGS= LDFLAGS= $(OUTPUT)fixdep
-endif
 
 .PHONY: fixdep

tools/build/feature/Makefile

@@ -46,11 +46,13 @@ FILES=					\
 	test-lzma.bin			\
 	test-bpf.bin			\
 	test-get_cpuid.bin		\
-	test-sdt.bin
+	test-sdt.bin			\
+	test-cxx.bin
 
 FILES := $(addprefix $(OUTPUT),$(FILES))
 
 CC := $(CROSS_COMPILE)gcc -MD
+CXX := $(CROSS_COMPILE)g++ -MD
 PKG_CONFIG := $(CROSS_COMPILE)pkg-config
 
 all: $(FILES)
@@ -58,6 +60,9 @@ all: $(FILES)
 __BUILD = $(CC) $(CFLAGS) -Wall -Werror -o $@ $(patsubst %.bin,%.c,$(@F)) $(LDFLAGS)
   BUILD = $(__BUILD) > $(@:.bin=.make.output) 2>&1
 
+__BUILDXX = $(CXX) $(CXXFLAGS) -Wall -Werror -o $@ $(patsubst %.bin,%.cpp,$(@F)) $(LDFLAGS)
+  BUILDXX = $(__BUILDXX) > $(@:.bin=.make.output) 2>&1
+
 ###############################
 
 $(OUTPUT)test-all.bin:
@@ -217,6 +222,9 @@ $(OUTPUT)test-bpf.bin:
 $(OUTPUT)test-sdt.bin:
 	$(BUILD)
 
+$(OUTPUT)test-cxx.bin:
+	$(BUILDXX) -std=gnu++11
+
 -include $(OUTPUT)*.d
 
 ###############################

tools/build/feature/test-cxx.cpp

+#include <iostream>
+#include <memory>
+
+static void print_str(std::string s)
+{
+	std::cout << s << std::endl;
+}
+
+int main()
+{
+	std::string s("Hello World!");
+	print_str(std::move(s));
+	std::cout << "|" << s << "|" << std::endl;
+	return 0;
+}

tools/include/uapi/linux/bpf.h

@@ -339,7 +339,7 @@ enum bpf_func_id {
 	BPF_FUNC_skb_change_type,
 
 	/**
-	 * bpf_skb_in_cgroup(skb, map, index) - Check cgroup2 membership of skb
+	 * bpf_skb_under_cgroup(skb, map, index) - Check cgroup2 membership of skb
 	 * @skb: pointer to skb
 	 * @map: pointer to bpf_map in BPF_MAP_TYPE_CGROUP_ARRAY type
 	 * @index: index of the cgroup in the bpf_map
@@ -348,7 +348,7 @@ enum bpf_func_id {
 	 *   == 1 skb succeeded the cgroup2 descendant test
 	 *    < 0 error
 	 */
-	BPF_FUNC_skb_in_cgroup,
+	BPF_FUNC_skb_under_cgroup,
 
 	/**
 	 * bpf_get_hash_recalc(skb)

tools/lib/subcmd/pager.c

@@ -3,6 +3,7 @@
 #include <stdio.h>
 #include <string.h>
 #include <signal.h>
+#include <sys/ioctl.h>
 #include "pager.h"
 #include "run-command.h"
 #include "sigchain.h"
@@ -14,6 +15,7 @@
  */
 
 static int spawned_pager;
+static int pager_columns;
 
 void pager_init(const char *pager_env)
 {
@@ -58,9 +60,12 @@ static void wait_for_pager_signal(int signo)
 void setup_pager(void)
 {
 	const char *pager = getenv(subcmd_config.pager_env);
+	struct winsize sz;
 
 	if (!isatty(1))
 		return;
+	if (ioctl(1, TIOCGWINSZ, &sz) == 0)
+		pager_columns = sz.ws_col;
 	if (!pager)
 		pager = getenv("PAGER");
 	if (!(pager || access("/usr/bin/pager", X_OK)))
@@ -98,3 +103,14 @@ int pager_in_use(void)
 {
 	return spawned_pager;
 }
+
+int pager_get_columns(void)
+{
+	char *s;
+
+	s = getenv("COLUMNS");
+	if (s)
+		return atoi(s);
+
+	return (pager_columns ? pager_columns : 80) - 2;
+}

tools/lib/subcmd/pager.h

@@ -5,5 +5,6 @@ extern void pager_init(const char *pager_env);
 
 extern void setup_pager(void);
 extern int pager_in_use(void);
+extern int pager_get_columns(void);
 
 #endif /* __SUBCMD_PAGER_H */

tools/lib/traceevent/kbuffer-parse.c

@@ -622,6 +622,7 @@ void *kbuffer_read_at_offset(struct kbuffer *kbuf, int offset,
 
 	/* Reset the buffer */
 	kbuffer_load_subbuffer(kbuf, kbuf->subbuffer);
+	data = kbuffer_read_event(kbuf, ts);
 
 	while (kbuf->curr < offset) {
 		data = kbuffer_next_event(kbuf, ts);

tools/perf/Documentation/perf-list.txt

@@ -8,13 +8,23 @@ perf-list - List all symbolic event types
 SYNOPSIS
 --------
 [verse]
-'perf list' [hw|sw|cache|tracepoint|pmu|event_glob]
+'perf list' [--no-desc] [--long-desc] [hw|sw|cache|tracepoint|pmu|event_glob]
 
 DESCRIPTION
 -----------
 This command displays the symbolic event types which can be selected in the
 various perf commands with the -e option.
 
+OPTIONS
+-------
+--no-desc::
+Don't print descriptions.
+
+-v::
+--long-desc::
+Print longer event descriptions.
+
+
 [[EVENT_MODIFIERS]]
 EVENT MODIFIERS
 ---------------

tools/perf/Documentation/tips.txt

@@ -28,3 +28,7 @@ To change sampling frequency to 100 Hz: perf record -F 100
 See assembly instructions with percentage: perf annotate <symbol>
 If you prefer Intel style assembly, try: perf annotate -M intel
 For hierarchical output, try: perf report --hierarchy
+Order by the overhead of source file name and line number: perf report -s srcline
+System-wide collection from all CPUs: perf record -a
+Show current config key-value pairs: perf config --list
+Show user configuration overrides: perf config --user --list

tools/perf/Makefile.perf

@@ -144,6 +144,10 @@ $(call allow-override,LD,$(CROSS_COMPILE)ld)
 
 LD += $(EXTRA_LDFLAGS)
 
+HOSTCC  ?= gcc
+HOSTLD  ?= ld
+HOSTAR  ?= ar
+
 PKG_CONFIG = $(CROSS_COMPILE)pkg-config
 
 RM      = rm -f
@@ -345,8 +349,18 @@ strip: $(PROGRAMS) $(OUTPUT)perf
 PERF_IN := $(OUTPUT)perf-in.o
 
 export srctree OUTPUT RM CC LD AR CFLAGS 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
+
+PMU_EVENTS_IN := $(OUTPUT)pmu-events/pmu-events-in.o
+
+export JEVENTS
+
+build := -f $(srctree)/tools/build/Makefile.build dir=. obj
+
 $(PERF_IN): prepare FORCE
 	@(test -f ../../include/uapi/linux/perf_event.h && ( \
         (diff -B ../include/uapi/linux/perf_event.h ../../include/uapi/linux/perf_event.h >/dev/null) \
@@ -443,9 +457,18 @@ $(PERF_IN): prepare FORCE
 	|| echo "Warning: tools/include/uapi/linux/mman.h differs from kernel" >&2 )) || true
 	$(Q)$(MAKE) $(build)=perf
 
-$(OUTPUT)perf: $(PERFLIBS) $(PERF_IN) $(LIBTRACEEVENT_DYNAMIC_LIST)
+$(JEVENTS_IN): FORCE
+	$(Q)$(MAKE) -f $(srctree)/tools/build/Makefile.build dir=pmu-events obj=jevents
+
+$(JEVENTS): $(JEVENTS_IN)
+	$(QUIET_LINK)$(HOSTCC) $(JEVENTS_IN) -o $@
+
+$(PMU_EVENTS_IN): $(JEVENTS) FORCE
+	$(Q)$(MAKE) -f $(srctree)/tools/build/Makefile.build dir=pmu-events obj=pmu-events
+
+$(OUTPUT)perf: $(PERFLIBS) $(PERF_IN) $(PMU_EVENTS_IN) $(LIBTRACEEVENT_DYNAMIC_LIST)
 	$(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $(LIBTRACEEVENT_DYNAMIC_LIST_LDFLAGS) \
-		$(PERF_IN) $(LIBS) -o $@
+		$(PERF_IN) $(PMU_EVENTS_IN) $(LIBS) -o $@
 
 $(GTK_IN): fixdep FORCE
 	$(Q)$(MAKE) $(build)=gtk
@@ -474,6 +497,8 @@ perf.spec $(SCRIPTS) \
 ifneq ($(OUTPUT),)
 %.o: $(OUTPUT)%.o
 	@echo "    # Redirected target $@ => $(OUTPUT)$@"
+pmu-events/%.o: $(OUTPUT)pmu-events/%.o
+	@echo "    # Redirected target $@ => $(OUTPUT)$@"
 util/%.o: $(OUTPUT)util/%.o
 	@echo "    # Redirected target $@ => $(OUTPUT)$@"
 bench/%.o: $(OUTPUT)bench/%.o
@@ -729,10 +754,11 @@ 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
+	$(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf perf-read-vdso32 perf-read-vdsox32 $(OUTPUT)pmu-events/jevents
 	$(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
+		$(OUTPUT)tests/llvm-src-{base,kbuild,prologue,relocation}.c \
+		$(OUTPUT)pmu-events/pmu-events.c
 	$(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean
 	$(python-clean)
 

tools/perf/arch/powerpc/util/header.c

@@ -32,3 +32,14 @@ get_cpuid(char *buffer, size_t sz)
 	}
 	return -1;
 }
+
+char *
+get_cpuid_str(void)
+{
+	char *bufp;
+
+	if (asprintf(&bufp, "%.8lx", mfspr(SPRN_PVR)) < 0)
+		bufp = NULL;
+
+	return bufp;
+}

tools/perf/arch/powerpc/util/sym-handling.c

@@ -82,7 +82,8 @@ void arch__fix_tev_from_maps(struct perf_probe_event *pev,
 	 *
 	 * In addition, we shouldn't specify an offset for kretprobes.
 	 */
-	if (pev->point.offset || pev->point.retprobe || !map || !sym)
+	if (pev->point.offset || (!pev->uprobes && pev->point.retprobe) ||
+	    !map || !sym)
 		return;
 
 	lep_offset = PPC64_LOCAL_ENTRY_OFFSET(sym->arch_sym);

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

@@ -19,8 +19,8 @@ cpuid(unsigned int op, unsigned int *a, unsigned int *b, unsigned int *c,
 			: "a" (op));
 }
 
-int
-get_cpuid(char *buffer, size_t sz)
+static int
+__get_cpuid(char *buffer, size_t sz, const char *fmt)
 {
 	unsigned int a, b, c, d, lvl;
 	int family = -1, model = -1, step = -1;
@@ -48,7 +48,7 @@ get_cpuid(char *buffer, size_t sz)
 		if (family >= 0x6)
 			model += ((a >> 16) & 0xf) << 4;
 	}
-	nb = scnprintf(buffer, sz, "%s,%u,%u,%u$", vendor, family, model, step);
+	nb = scnprintf(buffer, sz, fmt, vendor, family, model, step);
 
 	/* look for end marker to ensure the entire data fit */
 	if (strchr(buffer, '$')) {
@@ -57,3 +57,21 @@ get_cpuid(char *buffer, size_t sz)
 	}
 	return -1;
 }
+
+int
+get_cpuid(char *buffer, size_t sz)
+{
+	return __get_cpuid(buffer, sz, "%s,%u,%u,%u$");
+}
+
+char *
+get_cpuid_str(void)
+{
+	char *buf = malloc(128);
+
+	if (__get_cpuid(buf, 128, "%s-%u-%X$") < 0) {
+		free(buf);
+		return NULL;
+	}
+	return buf;
+}

tools/perf/builtin-list.c

@@ -16,16 +16,23 @@
 #include "util/pmu.h"
 #include <subcmd/parse-options.h>
 
+static bool desc_flag = true;
+
 int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
 {
 	int i;
 	bool raw_dump = false;
+	bool long_desc_flag = false;
 	struct option list_options[] = {
 		OPT_BOOLEAN(0, "raw-dump", &raw_dump, "Dump raw events"),
+		OPT_BOOLEAN('d', "desc", &desc_flag,
+			    "Print extra event descriptions. --no-desc to not print."),
+		OPT_BOOLEAN('v', "long-desc", &long_desc_flag,
+			    "Print longer event descriptions."),
 		OPT_END()
 	};
 	const char * const list_usage[] = {
-		"perf list [hw|sw|cache|tracepoint|pmu|sdt|event_glob]",
+		"perf list [<options>] [hw|sw|cache|tracepoint|pmu|sdt|event_glob]",
 		NULL
 	};
 
@@ -40,7 +47,7 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
 		printf("\nList of pre-defined events (to be used in -e):\n\n");
 
 	if (argc == 0) {
-		print_events(NULL, raw_dump);
+		print_events(NULL, raw_dump, !desc_flag, long_desc_flag);
 		return 0;
 	}
 
@@ -61,14 +68,16 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
 			 strcmp(argv[i], "hwcache") == 0)
 			print_hwcache_events(NULL, raw_dump);
 		else if (strcmp(argv[i], "pmu") == 0)
-			print_pmu_events(NULL, raw_dump);
+			print_pmu_events(NULL, raw_dump, !desc_flag,
+						long_desc_flag);
 		else if (strcmp(argv[i], "sdt") == 0)
 			print_sdt_events(NULL, NULL, raw_dump);
 		else if ((sep = strchr(argv[i], ':')) != NULL) {
 			int sep_idx;
 
 			if (sep == NULL) {
-				print_events(argv[i], raw_dump);
+				print_events(argv[i], raw_dump, !desc_flag,
+							long_desc_flag);
 				continue;
 			}
 			sep_idx = sep - argv[i];
@@ -90,7 +99,8 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
 			print_symbol_events(s, PERF_TYPE_SOFTWARE,
 					    event_symbols_sw, PERF_COUNT_SW_MAX, raw_dump);
 			print_hwcache_events(s, raw_dump);
-			print_pmu_events(s, raw_dump);
+			print_pmu_events(s, raw_dump, !desc_flag,
+						long_desc_flag);
 			print_tracepoint_events(NULL, s, raw_dump);
 			print_sdt_events(NULL, s, raw_dump);
 			free(s);

tools/perf/pmu-events/Build

+hostprogs := jevents
+
+jevents-y	+= json.o jsmn.o jevents.o
+pmu-events-y	+= pmu-events.o
+JDIR		=  pmu-events/arch/$(ARCH)
+JSON		=  $(shell [ -d $(JDIR) ] &&				\
+			find $(JDIR) -name '*.json' -o -name 'mapfile.csv')
+#
+# Locate/process JSON files in pmu-events/arch/
+# directory and create tables in pmu-events.c.
+#
+$(OUTPUT)pmu-events/pmu-events.c: $(JSON) $(JEVENTS)
+	$(Q)$(call echo-cmd,gen)$(JEVENTS) $(ARCH) pmu-events/arch $(OUTPUT)pmu-events/pmu-events.c $(V)

tools/perf/pmu-events/README

+
+The contents of this directory allow users to specify PMU events in their
+CPUs by their symbolic names rather than raw event codes (see example below).
+
+The main program in this directory, is the 'jevents', which is built and
+executed _BEFORE_ the perf binary itself is built.
+
+The 'jevents' program tries to locate and process JSON files in the directory
+tree tools/perf/pmu-events/arch/foo.
+
+	- Regular files with '.json' extension in the name are assumed to be
+	  JSON files, each of which describes a set of PMU events.
+
+	- Regular files with basename starting with 'mapfile.csv' are assumed
+	  to be a CSV file that maps a specific CPU to its set of PMU events.
+	  (see below for mapfile format)
+
+	- Directories are traversed, but all other files are ignored.
+
+The PMU events supported by a CPU model are expected to grouped into topics
+such as Pipelining, Cache, Memory, Floating-point etc. All events for a topic
+should be placed in a separate JSON file - where the file name identifies
+the topic. Eg: "Floating-point.json".
+
+All the topic JSON files for a CPU model/family should be in a separate
+sub directory. Thus for the Silvermont X86 CPU:
+
+	$ ls tools/perf/pmu-events/arch/x86/Silvermont_core
+	Cache.json 	Memory.json 	Virtual-Memory.json
+	Frontend.json 	Pipeline.json
+
+Using the JSON files and the mapfile, 'jevents' generates the C source file,
+'pmu-events.c', which encodes the two sets of tables:
+
+	- Set of 'PMU events tables' for all known CPUs in the architecture,
+	  (one table like the following, per JSON file; table name 'pme_power8'
+	  is derived from JSON file name, 'power8.json').
+
+		struct pmu_event pme_power8[] = {
+
+			...
+
+			{
+				.name = "pm_1plus_ppc_cmpl",
+				.event = "event=0x100f2",
+				.desc = "1 or more ppc insts finished,",
+			},
+
+			...
+		}
+
+	- A 'mapping table' that maps each CPU of the architecture, to its
+	  'PMU events table'
+
+		struct pmu_events_map pmu_events_map[] = {
+		{
+			.cpuid = "004b0000",
+			.version = "1",
+			.type = "core",
+			.table = pme_power8
+		},
+			...
+
+		};
+
+After the 'pmu-events.c' is generated, it is compiled and the resulting
+'pmu-events.o' is added to 'libperf.a' which is then used to build perf.
+
+NOTES:
+	1. Several CPUs can support same set of events and hence use a common
+	   JSON file. Hence several entries in the pmu_events_map[] could map
+	   to a single 'PMU events table'.
+
+	2. The 'pmu-events.h' has an extern declaration for the mapping table
+	   and the generated 'pmu-events.c' defines this table.
+
+	3. _All_ known CPU tables for architecture are included in the perf
+	   binary.
+
+At run time, perf determines the actual CPU it is running on, finds the
+matching events table and builds aliases for those events. This allows
+users to specify events by their name:
+
+	$ perf stat -e pm_1plus_ppc_cmpl sleep 1
+
+where 'pm_1plus_ppc_cmpl' is a Power8 PMU event.
+
+In case of errors when processing files in the tools/perf/pmu-events/arch
+directory, 'jevents' tries to create an empty mapping file to allow the perf
+build to succeed even if the PMU event aliases cannot be used.
+
+However some errors in processing may cause the perf build to fail.
+
+Mapfile format
+===============
+
+The mapfile enables multiple CPU models to share a single set of PMU events.
+It is required even if such mapping is 1:1.
+
+The mapfile.csv format is expected to be:
+
+	Header line
+	CPUID,Version,Dir/path/name,Type
+
+where:
+
+	Comma:
+		is the required field delimiter (i.e other fields cannot
+		have commas within them).
+
+	Comments:
+		Lines in which the first character is either '\n' or '#'
+		are ignored.
+
+	Header line
+		The header line is the first line in the file, which is
+		always _IGNORED_. It can empty.
+
+	CPUID:
+		CPUID is an arch-specific char string, that can be used
+		to identify CPU (and associate it with a set of PMU events
+		it supports). Multiple CPUIDS can point to the same
+		File/path/name.json.
+
+		Example:
+			CPUID == 'GenuineIntel-6-2E' (on x86).
+			CPUID == '004b0100' (PVR value in Powerpc)
+	Version:
+		is the Version of the mapfile.
+
+	Dir/path/name:
+		is the pathname to the directory containing the CPU's JSON
+		files, relative to the directory containing the mapfile.csv
+
+	Type:
+		indicates whether the events or "core" or "uncore" events.
+
+
+	Eg:
+
+	$ grep Silvermont tools/perf/pmu-events/arch/x86/mapfile.csv
+	GenuineIntel-6-37,V13,Silvermont_core,core
+	GenuineIntel-6-4D,V13,Silvermont_core,core
+	GenuineIntel-6-4C,V13,Silvermont_core,core
+
+	i.e the three CPU models use the JSON files (i.e PMU events) listed
+	in the directory 'tools/perf/pmu-events/arch/x86/Silvermont_core'.

tools/perf/pmu-events/jevents.h

+#ifndef JEVENTS_H
+#define JEVENTS_H 1
+
+int json_events(const char *fn,
+		int (*func)(void *data, char *name, char *event, char *desc,
+				char *long_desc),
+		void *data);
+char *get_cpu_str(void);
+
+#ifndef min
+#define min(x, y) ({                            \
+	typeof(x) _min1 = (x);                  \
+	typeof(y) _min2 = (y);                  \
+	(void) (&_min1 == &_min2);              \
+	_min1 < _min2 ? _min1 : _min2; })
+#endif
+
+#endif

tools/perf/pmu-events/jsmn.c

+/*
+ * Copyright (c) 2010 Serge A. Zaitsev
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ *
+ * Slightly modified by AK to not assume 0 terminated input.
+ */
+
+#include <stdlib.h>
+#include "jsmn.h"
+
+/*
+ * Allocates a fresh unused token from the token pool.
+ */
+static jsmntok_t *jsmn_alloc_token(jsmn_parser *parser,
+				   jsmntok_t *tokens, size_t num_tokens)
+{
+	jsmntok_t *tok;
+
+	if ((unsigned)parser->toknext >= num_tokens)
+		return NULL;
+	tok = &tokens[parser->toknext++];
+	tok->start = tok->end = -1;
+	tok->size = 0;
+	return tok;
+}
+
+/*
+ * Fills token type and boundaries.
+ */
+static void jsmn_fill_token(jsmntok_t *token, jsmntype_t type,
+			    int start, int end)
+{
+	token->type = type;
+	token->start = start;
+	token->end = end;
+	token->size = 0;
+}
+
+/*
+ * Fills next available token with JSON primitive.
+ */
+static jsmnerr_t jsmn_parse_primitive(jsmn_parser *parser, const char *js,
+				      size_t len,
+				      jsmntok_t *tokens, size_t num_tokens)
+{
+	jsmntok_t *token;
+	int start;
+
+	start = parser->pos;
+
+	for (; parser->pos < len; parser->pos++) {
+		switch (js[parser->pos]) {
+#ifndef JSMN_STRICT
+		/*
+		 * In strict mode primitive must be followed by ","
+		 * or "}" or "]"
+		 */
+		case ':':
+#endif
+		case '\t':
+		case '\r':
+		case '\n':
+		case ' ':
+		case ',':
+		case ']':
+		case '}':
+			goto found;
+		default:
+			break;
+		}
+		if (js[parser->pos] < 32 || js[parser->pos] >= 127) {
+			parser->pos = start;
+			return JSMN_ERROR_INVAL;
+		}
+	}
+#ifdef JSMN_STRICT
+	/*
+	 * In strict mode primitive must be followed by a
+	 * comma/object/array.
+	 */
+	parser->pos = start;
+	return JSMN_ERROR_PART;
+#endif
+
+found:
+	token = jsmn_alloc_token(parser, tokens, num_tokens);
+	if (token == NULL) {
+		parser->pos = start;
+		return JSMN_ERROR_NOMEM;
+	}
+	jsmn_fill_token(token, JSMN_PRIMITIVE, start, parser->pos);
+	parser->pos--; /* parent sees closing brackets */
+	return JSMN_SUCCESS;
+}
+
+/*
+ * Fills next token with JSON string.
+ */
+static jsmnerr_t jsmn_parse_string(jsmn_parser *parser, const char *js,
+				   size_t len,
+				   jsmntok_t *tokens, size_t num_tokens)
+{
+	jsmntok_t *token;
+	int start = parser->pos;
+
+	/* Skip starting quote */
+	parser->pos++;
+
+	for (; parser->pos < len; parser->pos++) {
+		char c = js[parser->pos];
+
+		/* Quote: end of string */
+		if (c == '\"') {
+			token = jsmn_alloc_token(parser, tokens, num_tokens);
+			if (token == NULL) {
+				parser->pos = start;
+				return JSMN_ERROR_NOMEM;
+			}
+			jsmn_fill_token(token, JSMN_STRING, start+1,
+					parser->pos);
+			return JSMN_SUCCESS;
+		}
+
+		/* Backslash: Quoted symbol expected */
+		if (c == '\\') {
+			parser->pos++;
+			switch (js[parser->pos]) {
+				/* Allowed escaped symbols */
+			case '\"':
+			case '/':
+			case '\\':
+			case 'b':
+			case 'f':
+			case 'r':
+			case 'n':
+			case 't':
+				break;
+				/* Allows escaped symbol \uXXXX */
+			case 'u':
+				/* TODO */
+				break;
+				/* Unexpected symbol */
+			default:
+				parser->pos = start;
+				return JSMN_ERROR_INVAL;
+			}
+		}
+	}
+	parser->pos = start;
+	return JSMN_ERROR_PART;
+}
+
+/*
+ * Parse JSON string and fill tokens.
+ */
+jsmnerr_t jsmn_parse(jsmn_parser *parser, const char *js, size_t len,
+		     jsmntok_t *tokens, unsigned int num_tokens)
+{
+	jsmnerr_t r;
+	int i;
+	jsmntok_t *token;
+
+	for (; parser->pos < len; parser->pos++) {
+		char c;
+		jsmntype_t type;
+
+		c = js[parser->pos];
+		switch (c) {
+		case '{':
+		case '[':
+			token = jsmn_alloc_token(parser, tokens, num_tokens);
+			if (token == NULL)
+				return JSMN_ERROR_NOMEM;
+			if (parser->toksuper != -1)
+				tokens[parser->toksuper].size++;
+			token->type = (c == '{' ? JSMN_OBJECT : JSMN_ARRAY);
+			token->start = parser->pos;
+			parser->toksuper = parser->toknext - 1;
+			break;
+		case '}':
+		case ']':
+			type = (c == '}' ? JSMN_OBJECT : JSMN_ARRAY);
+			for (i = parser->toknext - 1; i >= 0; i--) {
+				token = &tokens[i];
+				if (token->start != -1 && token->end == -1) {
+					if (token->type != type)
+						return JSMN_ERROR_INVAL;
+					parser->toksuper = -1;
+					token->end = parser->pos + 1;
+					break;
+				}
+			}
+			/* Error if unmatched closing bracket */
+			if (i == -1)
+				return JSMN_ERROR_INVAL;
+			for (; i >= 0; i--) {
+				token = &tokens[i];
+				if (token->start != -1 && token->end == -1) {
+					parser->toksuper = i;
+					break;
+				}
+			}
+			break;
+		case '\"':
+			r = jsmn_parse_string(parser, js, len, tokens,
+					      num_tokens);
+			if (r < 0)
+				return r;
+			if (parser->toksuper != -1)
+				tokens[parser->toksuper].size++;
+			break;
+		case '\t':
+		case '\r':
+		case '\n':
+		case ':':
+		case ',':
+		case ' ':
+			break;
+#ifdef JSMN_STRICT
+			/*
+			 * In strict mode primitives are:
+			 * numbers and booleans.
+			 */
+		case '-':
+		case '0':
+		case '1':
+		case '2':
+		case '3':
+		case '4':
+		case '5':
+		case '6':
+		case '7':
+		case '8':
+		case '9':
+		case 't':
+		case 'f':
+		case 'n':
+#else
+			/*
+			 * In non-strict mode every unquoted value
+			 * is a primitive.
+			 */
+			/*FALL THROUGH */
+		default:
+#endif
+			r = jsmn_parse_primitive(parser, js, len, tokens,
+						 num_tokens);
+			if (r < 0)
+				return r;
+			if (parser->toksuper != -1)
+				tokens[parser->toksuper].size++;
+			break;
+
+#ifdef JSMN_STRICT
+			/* Unexpected char in strict mode */
+		default:
+			return JSMN_ERROR_INVAL;
+#endif
+		}
+	}
+
+	for (i = parser->toknext - 1; i >= 0; i--) {
+		/* Unmatched opened object or array */
+		if (tokens[i].start != -1 && tokens[i].end == -1)
+			return JSMN_ERROR_PART;
+	}
+
+	return JSMN_SUCCESS;
+}
+
+/*
+ * Creates a new parser based over a given  buffer with an array of tokens
+ * available.
+ */
+void jsmn_init(jsmn_parser *parser)
+{
+	parser->pos = 0;
+	parser->toknext = 0;
+	parser->toksuper = -1;
+}
+
+const char *jsmn_strerror(jsmnerr_t err)
+{
+	switch (err) {
+	case JSMN_ERROR_NOMEM:
+		return "No enough tokens";
+	case JSMN_ERROR_INVAL:
+		return "Invalid character inside JSON string";
+	case JSMN_ERROR_PART:
+		return "The string is not a full JSON packet, more bytes expected";
+	case JSMN_SUCCESS:
+		return "Success";
+	default:
+		return "Unknown json error";
+	}
+}

tools/perf/pmu-events/jsmn.h

+#ifndef __JSMN_H_
+#define __JSMN_H_
+
+/*
+ * JSON type identifier. Basic types are:
+ *	o Object
+ *	o Array
+ *	o String
+ *	o Other primitive: number, boolean (true/false) or null
+ */
+typedef enum {
+	JSMN_PRIMITIVE = 0,
+	JSMN_OBJECT = 1,
+	JSMN_ARRAY = 2,
+	JSMN_STRING = 3
+} jsmntype_t;
+
+typedef enum {
+	/* Not enough tokens were provided */
+	JSMN_ERROR_NOMEM = -1,
+	/* Invalid character inside JSON string */
+	JSMN_ERROR_INVAL = -2,
+	/* The string is not a full JSON packet, more bytes expected */
+	JSMN_ERROR_PART = -3,
+	/* Everything was fine */
+	JSMN_SUCCESS = 0
+} jsmnerr_t;
+
+/*
+ * JSON token description.
+ * @param		type	type (object, array, string etc.)
+ * @param		start	start position in JSON data string
+ * @param		end		end position in JSON data string
+ */
+typedef struct {
+	jsmntype_t type;
+	int start;
+	int end;
+	int size;
+} jsmntok_t;
+
+/*
+ * JSON parser. Contains an array of token blocks available. Also stores
+ * the string being parsed now and current position in that string
+ */
+typedef struct {
+	unsigned int pos; /* offset in the JSON string */
+	int toknext; /* next token to allocate */
+	int toksuper; /* superior token node, e.g parent object or array */
+} jsmn_parser;
+
+/*
+ * Create JSON parser over an array of tokens
+ */
+void jsmn_init(jsmn_parser *parser);
+
+/*
+ * Run JSON parser. It parses a JSON data string into and array of tokens,
+ * each describing a single JSON object.
+ */
+jsmnerr_t jsmn_parse(jsmn_parser *parser, const char *js,
+		     size_t len,
+		     jsmntok_t *tokens, unsigned int num_tokens);
+
+const char *jsmn_strerror(jsmnerr_t err);
+
+#endif /* __JSMN_H_ */

tools/perf/pmu-events/json.c

+/* Parse JSON files using the JSMN parser. */
+
+/*
+ * Copyright (c) 2014, Intel Corporation
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright notice,
+ * this list of conditions and the following disclaimer.
+ *
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+ * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE
+ * COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT,
+ * INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+ * SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,
+ * STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED
+ * OF THE POSSIBILITY OF SUCH DAMAGE.
+*/
+
+#include <stdlib.h>
+#include <string.h>
+#include <sys/mman.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <stdio.h>
+#include <errno.h>
+#include <unistd.h>
+#include "jsmn.h"
+#include "json.h"
+#include <linux/kernel.h>
+
+
+static char *mapfile(const char *fn, size_t *size)
+{
+	unsigned ps = sysconf(_SC_PAGESIZE);
+	struct stat st;
+	char *map = NULL;
+	int err;
+	int fd = open(fn, O_RDONLY);
+
+	if (fd < 0 && verbose && fn) {
+		pr_err("Error opening events file '%s': %s\n", fn,
+				strerror(errno));
+	}
+
+	if (fd < 0)
+		return NULL;
+	err = fstat(fd, &st);
+	if (err < 0)
+		goto out;
+	*size = st.st_size;
+	map = mmap(NULL,
+		   (st.st_size + ps - 1) & ~(ps - 1),
+		   PROT_READ|PROT_WRITE, MAP_PRIVATE, fd, 0);
+	if (map == MAP_FAILED)
+		map = NULL;
+out:
+	close(fd);
+	return map;
+}
+
+static void unmapfile(char *map, size_t size)
+{
+	unsigned ps = sysconf(_SC_PAGESIZE);
+	munmap(map, roundup(size, ps));
+}
+
+/*
+ * Parse json file using jsmn. Return array of tokens,
+ * and mapped file. Caller needs to free array.
+ */
+jsmntok_t *parse_json(const char *fn, char **map, size_t *size, int *len)
+{
+	jsmn_parser parser;
+	jsmntok_t *tokens;
+	jsmnerr_t res;
+	unsigned sz;
+
+	*map = mapfile(fn, size);
+	if (!*map)
+		return NULL;
+	/* Heuristic */
+	sz = *size * 16;
+	tokens = malloc(sz);
+	if (!tokens)
+		goto error;
+	jsmn_init(&parser);
+	res = jsmn_parse(&parser, *map, *size, tokens,
+			 sz / sizeof(jsmntok_t));
+	if (res != JSMN_SUCCESS) {
+		pr_err("%s: json error %s\n", fn, jsmn_strerror(res));
+		goto error_free;
+	}
+	if (len)
+		*len = parser.toknext;
+	return tokens;
+error_free:
+	free(tokens);
+error:
+	unmapfile(*map, *size);
+	return NULL;
+}
+
+void free_json(char *map, size_t size, jsmntok_t *tokens)
+{
+	free(tokens);
+	unmapfile(map, size);
+}
+
+static int countchar(char *map, char c, int end)
+{
+	int i;
+	int count = 0;
+	for (i = 0; i < end; i++)
+		if (map[i] == c)
+			count++;
+	return count;
+}
+
+/* Return line number of a jsmn token */
+int json_line(char *map, jsmntok_t *t)
+{
+	return countchar(map, '\n', t->start) + 1;
+}
+
+static const char * const jsmn_types[] = {
+	[JSMN_PRIMITIVE] = "primitive",
+	[JSMN_ARRAY] = "array",
+	[JSMN_OBJECT] = "object",
+	[JSMN_STRING] = "string"
+};
+
+#define LOOKUP(a, i) ((i) < (sizeof(a)/sizeof(*(a))) ? ((a)[i]) : "?")
+
+/* Return type name of a jsmn token */
+const char *json_name(jsmntok_t *t)
+{
+	return LOOKUP(jsmn_types, t->type);
+}
+
+int json_len(jsmntok_t *t)
+{
+	return t->end - t->start;
+}
+
+/* Is string t equal to s? */
+int json_streq(char *map, jsmntok_t *t, const char *s)
+{
+	unsigned len = json_len(t);
+	return len == strlen(s) && !strncasecmp(map + t->start, s, len);
+}

tools/perf/pmu-events/json.h

+#ifndef JSON_H
+#define JSON_H 1
+
+#include "jsmn.h"
+
+jsmntok_t *parse_json(const char *fn, char **map, size_t *size, int *len);
+void free_json(char *map, size_t size, jsmntok_t *tokens);
+int json_line(char *map, jsmntok_t *t);
+const char *json_name(jsmntok_t *t);
+int json_streq(char *map, jsmntok_t *t, const char *s);
+int json_len(jsmntok_t *t);
+
+extern int verbose;
+
+#include <stdbool.h>
+
+extern int eprintf(int level, int var, const char *fmt, ...);
+#define pr_fmt(fmt)	fmt
+
+#define pr_err(fmt, ...) \
+	eprintf(0, verbose, pr_fmt(fmt), ##__VA_ARGS__)
+
+#define pr_info(fmt, ...) \
+	eprintf(1, verbose, pr_fmt(fmt), ##__VA_ARGS__)
+
+#define pr_debug(fmt, ...) \
+	eprintf(2, verbose, pr_fmt(fmt), ##__VA_ARGS__)
+
+#ifndef roundup
+#define roundup(x, y) (                                \
+{                                                      \
+        const typeof(y) __y = y;                       \
+        (((x) + (__y - 1)) / __y) * __y;               \
+}                                                      \
+)
+#endif
+
+#endif

tools/perf/pmu-events/pmu-events.h

+#ifndef PMU_EVENTS_H
+#define PMU_EVENTS_H
+
+/*
+ * Describe each PMU event. Each CPU has a table of PMU events.
+ */
+struct pmu_event {
+	const char *name;
+	const char *event;
+	const char *desc;
+	const char *topic;
+	const char *long_desc;
+};
+
+/*
+ *
+ * Map a CPU to its table of PMU events. The CPU is identified by the
+ * cpuid field, which is an arch-specific identifier for the CPU.
+ * The identifier specified in tools/perf/pmu-events/arch/xxx/mapfile
+ * must match the get_cpustr() in tools/perf/arch/xxx/util/header.c)
+ *
+ * The  cpuid can contain any character other than the comma.
+ */
+struct pmu_events_map {
+	const char *cpuid;
+	const char *version;
+	const char *type;		/* core, uncore etc */
+	struct pmu_event *table;
+};
+
+/*
+ * Global table mapping each known CPU for the architecture to its
+ * table of PMU events.
+ */
+extern struct pmu_events_map pmu_events_map[];
+
+#endif

tools/perf/util/evlist.c

@@ -384,15 +384,14 @@ void perf_evlist__toggle_enable(struct perf_evlist *evlist)
 static int perf_evlist__enable_event_cpu(struct perf_evlist *evlist,
 					 struct perf_evsel *evsel, int cpu)
 {
-	int thread, err;
+	int thread;
 	int nr_threads = perf_evlist__nr_threads(evlist, evsel);
 
 	if (!evsel->fd)
 		return -EINVAL;
 
 	for (thread = 0; thread < nr_threads; thread++) {
-		err = ioctl(FD(evsel, cpu, thread),
-			    PERF_EVENT_IOC_ENABLE, 0);
+		int err = ioctl(FD(evsel, cpu, thread), PERF_EVENT_IOC_ENABLE, 0);
 		if (err)
 			return err;
 	}
@@ -403,14 +402,14 @@ static int perf_evlist__enable_event_thread(struct perf_evlist *evlist,
 					    struct perf_evsel *evsel,
 					    int thread)
 {
-	int cpu, err;
+	int cpu;
 	int nr_cpus = cpu_map__nr(evlist->cpus);
 
 	if (!evsel->fd)
 		return -EINVAL;
 
 	for (cpu = 0; cpu < nr_cpus; cpu++) {
-		err = ioctl(FD(evsel, cpu, thread), PERF_EVENT_IOC_ENABLE, 0);
+		int err = ioctl(FD(evsel, cpu, thread), PERF_EVENT_IOC_ENABLE, 0);
 		if (err)
 			return err;
 	}
@@ -1606,10 +1605,9 @@ void perf_evlist__close(struct perf_evlist *evlist)
 	struct perf_evsel *evsel;
 	int ncpus = cpu_map__nr(evlist->cpus);
 	int nthreads = thread_map__nr(evlist->threads);
-	int n;
 
 	evlist__for_each_entry_reverse(evlist, evsel) {
-		n = evsel->cpus ? evsel->cpus->nr : ncpus;
+		int n = evsel->cpus ? evsel->cpus->nr : ncpus;
 		perf_evsel__close(evsel, n, nthreads);
 	}
 }

tools/perf/util/evsel.c

@@ -985,14 +985,13 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
 
 static int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
 {
-	int cpu, thread;
-
 	if (evsel->system_wide)
 		nthreads = 1;
 
 	evsel->fd = xyarray__new(ncpus, nthreads, sizeof(int));
 
 	if (evsel->fd) {
+		int cpu, thread;
 		for (cpu = 0; cpu < ncpus; cpu++) {
 			for (thread = 0; thread < nthreads; thread++) {
 				FD(evsel, cpu, thread) = -1;

tools/perf/util/header.h

@@ -151,4 +151,5 @@ int write_padded(int fd, const void *bf, size_t count, size_t count_aligned);
  */
 int get_cpuid(char *buffer, size_t sz);
 
+char *get_cpuid_str(void);
 #endif /* __PERF_HEADER_H */

tools/perf/util/intel-pt-decoder/intel-pt-decoder.c

@@ -90,6 +90,7 @@ struct intel_pt_decoder {
 	bool pge;
 	bool have_tma;
 	bool have_cyc;
+	bool fixup_last_mtc;
 	uint64_t pos;
 	uint64_t last_ip;
 	uint64_t ip;
@@ -586,10 +587,31 @@ struct intel_pt_calc_cyc_to_tsc_info {
 	uint64_t        tsc_timestamp;
 	uint64_t        timestamp;
 	bool            have_tma;
+	bool            fixup_last_mtc;
 	bool            from_mtc;
 	double          cbr_cyc_to_tsc;
 };
 
+/*
+ * MTC provides a 8-bit slice of CTC but the TMA packet only provides the lower
+ * 16 bits of CTC. If mtc_shift > 8 then some of the MTC bits are not in the CTC
+ * provided by the TMA packet. Fix-up the last_mtc calculated from the TMA
+ * packet by copying the missing bits from the current MTC assuming the least
+ * difference between the two, and that the current MTC comes after last_mtc.
+ */
+static void intel_pt_fixup_last_mtc(uint32_t mtc, int mtc_shift,
+				    uint32_t *last_mtc)
+{
+	uint32_t first_missing_bit = 1U << (16 - mtc_shift);
+	uint32_t mask = ~(first_missing_bit - 1);
+
+	*last_mtc |= mtc & mask;
+	if (*last_mtc >= mtc) {
+		*last_mtc -= first_missing_bit;
+		*last_mtc &= 0xff;
+	}
+}
+
 static int intel_pt_calc_cyc_cb(struct intel_pt_pkt_info *pkt_info)
 {
 	struct intel_pt_decoder *decoder = pkt_info->decoder;
@@ -619,6 +641,11 @@ static int intel_pt_calc_cyc_cb(struct intel_pt_pkt_info *pkt_info)
 			return 0;
 
 		mtc = pkt_info->packet.payload;
+		if (decoder->mtc_shift > 8 && data->fixup_last_mtc) {
+			data->fixup_last_mtc = false;
+			intel_pt_fixup_last_mtc(mtc, decoder->mtc_shift,
+						&data->last_mtc);
+		}
 		if (mtc > data->last_mtc)
 			mtc_delta = mtc - data->last_mtc;
 		else
@@ -687,6 +714,7 @@ static int intel_pt_calc_cyc_cb(struct intel_pt_pkt_info *pkt_info)
 
 		data->ctc_delta = 0;
 		data->have_tma = true;
+		data->fixup_last_mtc = true;
 
 		return 0;
 
@@ -753,6 +781,7 @@ static void intel_pt_calc_cyc_to_tsc(struct intel_pt_decoder *decoder,
 		.tsc_timestamp  = decoder->tsc_timestamp,
 		.timestamp      = decoder->timestamp,
 		.have_tma       = decoder->have_tma,
+		.fixup_last_mtc = decoder->fixup_last_mtc,
 		.from_mtc       = from_mtc,
 		.cbr_cyc_to_tsc = 0,
 	};
@@ -1271,6 +1300,7 @@ static void intel_pt_calc_tma(struct intel_pt_decoder *decoder)
 	}
 	decoder->ctc_delta = 0;
 	decoder->have_tma = true;
+	decoder->fixup_last_mtc = true;
 	intel_pt_log("CTC timestamp " x64_fmt " last MTC %#x  CTC rem %#x\n",
 		     decoder->ctc_timestamp, decoder->last_mtc, ctc_rem);
 }
@@ -1285,6 +1315,12 @@ static void intel_pt_calc_mtc_timestamp(struct intel_pt_decoder *decoder)
 
 	mtc = decoder->packet.payload;
 
+	if (decoder->mtc_shift > 8 && decoder->fixup_last_mtc) {
+		decoder->fixup_last_mtc = false;
+		intel_pt_fixup_last_mtc(mtc, decoder->mtc_shift,
+					&decoder->last_mtc);
+	}
+
 	if (mtc > decoder->last_mtc)
 		mtc_delta = mtc - decoder->last_mtc;
 	else
@@ -1353,6 +1389,8 @@ static void intel_pt_calc_cyc_timestamp(struct intel_pt_decoder *decoder)
 			     timestamp, decoder->timestamp);
 	else
 		decoder->timestamp = timestamp;
+
+	decoder->timestamp_insn_cnt = 0;
 }
 
 /* Walk PSB+ packets when already in sync. */

tools/perf/util/machine.c

@@ -1745,9 +1745,8 @@ static int resolve_lbr_callchain_sample(struct thread *thread,
 					int max_stack)
 {
 	struct ip_callchain *chain = sample->callchain;
-	int chain_nr = min(max_stack, (int)chain->nr);
+	int chain_nr = min(max_stack, (int)chain->nr), i;
 	u8 cpumode = PERF_RECORD_MISC_USER;
-	int i, j, err;
 	u64 ip;
 
 	for (i = 0; i < chain_nr; i++) {
@@ -1758,7 +1757,7 @@ static int resolve_lbr_callchain_sample(struct thread *thread,
 	/* LBR only affects the user callchain */
 	if (i != chain_nr) {
 		struct branch_stack *lbr_stack = sample->branch_stack;
-		int lbr_nr = lbr_stack->nr;
+		int lbr_nr = lbr_stack->nr, j;
 		/*
 		 * LBR callstack can only get user call chain.
 		 * The mix_chain_nr is kernel call chain
@@ -1772,6 +1771,7 @@ static int resolve_lbr_callchain_sample(struct thread *thread,
 		int mix_chain_nr = i + 1 + lbr_nr + 1;
 
 		for (j = 0; j < mix_chain_nr; j++) {
+			int err;
 			if (callchain_param.order == ORDER_CALLEE) {
 				if (j < i + 1)
 					ip = chain->ips[j];

tools/perf/util/parse-events.c

@@ -924,6 +924,7 @@ config_term_avail(int term_type, struct parse_events_error *err)
 	case PARSE_EVENTS__TERM_TYPE_CONFIG1:
 	case PARSE_EVENTS__TERM_TYPE_CONFIG2:
 	case PARSE_EVENTS__TERM_TYPE_NAME:
+	case PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD:
 		return true;
 	default:
 		if (!err)
@@ -1458,7 +1459,7 @@ comp_pmu(const void *p1, const void *p2)
 	struct perf_pmu_event_symbol *pmu1 = (struct perf_pmu_event_symbol *) p1;
 	struct perf_pmu_event_symbol *pmu2 = (struct perf_pmu_event_symbol *) p2;
 
-	return strcmp(pmu1->symbol, pmu2->symbol);
+	return strcasecmp(pmu1->symbol, pmu2->symbol);
 }
 
 static void perf_pmu__parse_cleanup(void)
@@ -2263,7 +2264,8 @@ void print_symbol_events(const char *event_glob, unsigned type,
 /*
  * Print the help text for the event symbols:
  */
-void print_events(const char *event_glob, bool name_only)
+void print_events(const char *event_glob, bool name_only, bool quiet_flag,
+			bool long_desc)
 {
 	print_symbol_events(event_glob, PERF_TYPE_HARDWARE,
 			    event_symbols_hw, PERF_COUNT_HW_MAX, name_only);
@@ -2273,7 +2275,7 @@ void print_events(const char *event_glob, bool name_only)
 
 	print_hwcache_events(event_glob, name_only);
 
-	print_pmu_events(event_glob, name_only);
+	print_pmu_events(event_glob, name_only, quiet_flag, long_desc);
 
 	if (event_glob != NULL)
 		return;

tools/perf/util/parse-events.h

@@ -172,7 +172,8 @@ void parse_events_update_lists(struct list_head *list_event,
 void parse_events_evlist_error(struct parse_events_evlist *data,
 			       int idx, const char *str);
 
-void print_events(const char *event_glob, bool name_only);
+void print_events(const char *event_glob, bool name_only, bool quiet,
+		  bool long_desc);
 
 struct event_symbol {
 	const char	*symbol;

tools/perf/util/pmu.c

@@ -12,6 +12,9 @@
 #include "pmu.h"
 #include "parse-events.h"
 #include "cpumap.h"
+#include "header.h"
+#include "pmu-events/pmu-events.h"
+#include "cache.h"
 
 struct perf_pmu_format {
 	char *name;
@@ -220,7 +223,8 @@ static int perf_pmu__parse_snapshot(struct perf_pmu_alias *alias,
 }
 
 static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name,
-				 char *desc __maybe_unused, char *val)
+				 char *desc, char *val, char *long_desc,
+				 char *topic)
 {
 	struct perf_pmu_alias *alias;
 	int ret;
@@ -253,6 +257,11 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name,
 		perf_pmu__parse_snapshot(alias, dir, name);
 	}
 
+	alias->desc = desc ? strdup(desc) : NULL;
+	alias->long_desc = long_desc ? strdup(long_desc) :
+				desc ? strdup(desc) : NULL;
+	alias->topic = topic ? strdup(topic) : NULL;
+
 	list_add_tail(&alias->list, list);
 
 	return 0;
@@ -269,7 +278,7 @@ static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FI
 
 	buf[ret] = 0;
 
-	return __perf_pmu__new_alias(list, dir, name, NULL, buf);
+	return __perf_pmu__new_alias(list, dir, name, NULL, buf, NULL, NULL);
 }
 
 static inline bool pmu_alias_info_file(char *name)
@@ -473,6 +482,68 @@ static struct cpu_map *pmu_cpumask(const char *name)
 	return cpus;
 }
 
+/*
+ * Return the CPU id as a raw string.
+ *
+ * Each architecture should provide a more precise id string that
+ * can be use to match the architecture's "mapfile".
+ */
+char * __weak get_cpuid_str(void)
+{
+	return NULL;
+}
+
+/*
+ * From the pmu_events_map, find the table of PMU events that corresponds
+ * to the current running CPU. Then, add all PMU events from that table
+ * as aliases.
+ */
+static void pmu_add_cpu_aliases(struct list_head *head)
+{
+	int i;
+	struct pmu_events_map *map;
+	struct pmu_event *pe;
+	char *cpuid;
+
+	cpuid = getenv("PERF_CPUID");
+	if (cpuid)
+		cpuid = strdup(cpuid);
+	if (!cpuid)
+		cpuid = get_cpuid_str();
+	if (!cpuid)
+		return;
+
+	pr_debug("Using CPUID %s\n", cpuid);
+
+	i = 0;
+	while (1) {
+		map = &pmu_events_map[i++];
+		if (!map->table)
+			goto out;
+
+		if (!strcmp(map->cpuid, cpuid))
+			break;
+	}
+
+	/*
+	 * Found a matching PMU events table. Create aliases
+	 */
+	i = 0;
+	while (1) {
+		pe = &map->table[i++];
+		if (!pe->name)
+			break;
+
+		/* need type casts to override 'const' */
+		__perf_pmu__new_alias(head, NULL, (char *)pe->name,
+				(char *)pe->desc, (char *)pe->event,
+				(char *)pe->long_desc, (char *)pe->topic);
+	}
+
+out:
+	free(cpuid);
+}
+
 struct perf_event_attr * __weak
 perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused)
 {
@@ -497,6 +568,9 @@ static struct perf_pmu *pmu_lookup(const char *name)
 	if (pmu_aliases(name, &aliases))
 		return NULL;
 
+	if (!strcmp(name, "cpu"))
+		pmu_add_cpu_aliases(&aliases);
+
 	if (pmu_type(name, &type))
 		return NULL;
 
@@ -983,21 +1057,63 @@ static char *format_alias_or(char *buf, int len, struct perf_pmu *pmu,
 	return buf;
 }
 
-static int cmp_string(const void *a, const void *b)
+struct sevent {
+	char *name;
+	char *desc;
+	char *topic;
+};
+
+static int cmp_sevent(const void *a, const void *b)
 {
-	const char * const *as = a;
-	const char * const *bs = b;
-	return strcmp(*as, *bs);
+	const struct sevent *as = a;
+	const struct sevent *bs = b;
+
+	/* Put extra events last */
+	if (!!as->desc != !!bs->desc)
+		return !!as->desc - !!bs->desc;
+	if (as->topic && bs->topic) {
+		int n = strcmp(as->topic, bs->topic);
+
+		if (n)
+			return n;
+	}
+	return strcmp(as->name, bs->name);
 }
 
-void print_pmu_events(const char *event_glob, bool name_only)
+static void wordwrap(char *s, int start, int max, int corr)
+{
+	int column = start;
+	int n;
+
+	while (*s) {
+		int wlen = strcspn(s, " \t");
+
+		if (column + wlen >= max && column > start) {
+			printf("\n%*s", start, "");
+			column = start + corr;
+		}
+		n = printf("%s%.*s", column > start ? " " : "", wlen, s);
+		if (n <= 0)
+			break;
+		s += wlen;
+		column += n;
+		while (isspace(*s))
+			s++;
+	}
+}
+
+void print_pmu_events(const char *event_glob, bool name_only, bool quiet_flag,
+			bool long_desc)
 {
 	struct perf_pmu *pmu;
 	struct perf_pmu_alias *alias;
 	char buf[1024];
 	int printed = 0;
 	int len, j;
-	char **aliases;
+	struct sevent *aliases;
+	int numdesc = 0;
+	int columns = pager_get_columns();
+	char *topic = NULL;
 
 	pmu = NULL;
 	len = 0;
@@ -1007,14 +1123,15 @@ void print_pmu_events(const char *event_glob, bool name_only)
 		if (pmu->selectable)
 			len++;
 	}
-	aliases = zalloc(sizeof(char *) * len);
+	aliases = zalloc(sizeof(struct sevent) * len);
 	if (!aliases)
 		goto out_enomem;
 	pmu = NULL;
 	j = 0;
 	while ((pmu = perf_pmu__scan(pmu)) != NULL) {
 		list_for_each_entry(alias, &pmu->aliases, list) {
-			char *name = format_alias(buf, sizeof(buf), pmu, alias);
+			char *name = alias->desc ? alias->name :
+				format_alias(buf, sizeof(buf), pmu, alias);
 			bool is_cpu = !strcmp(pmu->name, "cpu");
 
 			if (event_glob != NULL &&
@@ -1023,12 +1140,21 @@ void print_pmu_events(const char *event_glob, bool name_only)
 						       event_glob))))
 				continue;
 
-			if (is_cpu && !name_only)
+			if (is_cpu && !name_only && !alias->desc)
 				name = format_alias_or(buf, sizeof(buf), pmu, alias);
 
-			aliases[j] = strdup(name);
-			if (aliases[j] == NULL)
+			aliases[j].name = name;
+			if (is_cpu && !name_only && !alias->desc)
+				aliases[j].name = format_alias_or(buf,
+								  sizeof(buf),
+								  pmu, alias);
+			aliases[j].name = strdup(aliases[j].name);
+			if (!aliases[j].name)
 				goto out_enomem;
+
+			aliases[j].desc = long_desc ? alias->long_desc :
+						alias->desc;
+			aliases[j].topic = alias->topic;
 			j++;
 		}
 		if (pmu->selectable &&
@@ -1036,25 +1162,39 @@ void print_pmu_events(const char *event_glob, bool name_only)
 			char *s;
 			if (asprintf(&s, "%s//", pmu->name) < 0)
 				goto out_enomem;
-			aliases[j] = s;
+			aliases[j].name = s;
 			j++;
 		}
 	}
 	len = j;
-	qsort(aliases, len, sizeof(char *), cmp_string);
+	qsort(aliases, len, sizeof(struct sevent), cmp_sevent);
 	for (j = 0; j < len; j++) {
 		if (name_only) {
-			printf("%s ", aliases[j]);
+			printf("%s ", aliases[j].name);
 			continue;
 		}
-		printf("  %-50s [Kernel PMU event]\n", aliases[j]);
+		if (aliases[j].desc && !quiet_flag) {
+			if (numdesc++ == 0)
+				printf("\n");
+			if (aliases[j].topic && (!topic ||
+					strcmp(topic, aliases[j].topic))) {
+				printf("%s%s:\n", topic ? "\n" : "",
+						aliases[j].topic);
+				topic = aliases[j].topic;
+			}
+			printf("  %-50s\n", aliases[j].name);
+			printf("%*s", 8, "[");
+			wordwrap(aliases[j].desc, 8, columns, 0);
+			printf("]\n");
+		} else
+			printf("  %-50s [Kernel PMU event]\n", aliases[j].name);
 		printed++;
 	}
 	if (printed && pager_in_use())
 		printf("\n");
 out_free:
 	for (j = 0; j < len; j++)
-		zfree(&aliases[j]);
+		zfree(&aliases[j].name);
 	zfree(&aliases);
 	return;
 

tools/perf/util/pmu.h

@@ -40,6 +40,9 @@ struct perf_pmu_info {
 
 struct perf_pmu_alias {
 	char *name;
+	char *desc;
+	char *long_desc;
+	char *topic;
 	struct list_head terms; /* HEAD struct parse_events_term -> list */
 	struct list_head list;  /* ELEM */
 	char unit[UNIT_MAX_LEN+1];
@@ -71,7 +74,8 @@ int perf_pmu__format_parse(char *dir, struct list_head *head);
 
 struct perf_pmu *perf_pmu__scan(struct perf_pmu *pmu);
 
-void print_pmu_events(const char *event_glob, bool name_only);
+void print_pmu_events(const char *event_glob, bool name_only, bool quiet,
+		      bool long_desc);
 bool pmu_have_event(const char *pname, const char *name);
 
 int perf_pmu__scan_file(struct perf_pmu *pmu, const char *name, const char *fmt,

tools/perf/util/probe-event.c

@@ -213,7 +213,7 @@ static int convert_exec_to_group(const char *exec, char **result)
 		goto out;
 	}
 
-	for (ptr2 = ptr1; ptr2 != '\0'; ptr2++) {
+	for (ptr2 = ptr1; *ptr2 != '\0'; ptr2++) {
 		if (!isalnum(*ptr2) && *ptr2 != '_') {
 			*ptr2 = '\0';
 			break;

tools/perf/util/strbuf.h

@@ -66,9 +66,8 @@ static inline ssize_t strbuf_avail(const struct strbuf *sb) {
 int strbuf_grow(struct strbuf *buf, size_t);
 
 static inline int strbuf_setlen(struct strbuf *sb, size_t len) {
-	int ret;
 	if (!sb->alloc) {
-		ret = strbuf_grow(sb, 0);
+		int ret = strbuf_grow(sb, 0);
 		if (ret)
 			return ret;
 	}

tools/perf/util/thread.c

@@ -14,13 +14,12 @@
 
 int thread__init_map_groups(struct thread *thread, struct machine *machine)
 {
-	struct thread *leader;
 	pid_t pid = thread->pid_;
 
 	if (pid == thread->tid || pid == -1) {
 		thread->mg = map_groups__new(machine);
 	} else {
-		leader = __machine__findnew_thread(machine, pid, pid);
+		struct thread *leader = __machine__findnew_thread(machine, pid, pid);
 		if (leader) {
 			thread->mg = map_groups__get(leader->mg);
 			thread__put(leader);
@@ -130,11 +129,10 @@ int __thread__set_comm(struct thread *thread, const char *str, u64 timestamp,
 		       bool exec)
 {
 	struct comm *new, *curr = thread__comm(thread);
-	int err;
 
 	/* Override the default :tid entry */
 	if (!thread->comm_set) {
-		err = comm__override(curr, str, timestamp, exec);
+		int err = comm__override(curr, str, timestamp, exec);
 		if (err)
 			return err;
 	} else {
@@ -270,10 +268,9 @@ static int thread__clone_map_groups(struct thread *thread,
 
 int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp)
 {
-	int err;
-
 	if (parent->comm_set) {
 		const char *comm = thread__comm_str(parent);
+		int err;
 		if (!comm)
 			return -ENOMEM;
 		err = thread__set_comm(thread, comm, timestamp);