Merge tag 'perf-core-for-mingo-4.14-20170829' of...

Merge tag 'perf-core-for-mingo-4.14-20170829' 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:

 - Fix remote HITM detection for Skylake in 'perf c2c' (Jiri Olsa)

 - Fixes for the handling of PERF_RECORD_READ records (Jiri Olsa)

 - Fix kprobes blackist symbol lookup in 'perf probe' (Li Bin)

 - The PLT header and entry sizes are not the same in !x86, fix it for ARM and
   AARCH64 (Li Bin)

 - Beautify pkey_{alloc,free,mprotect} arguments in 'perf trace' (Arnaldo Carvalho de Melo)

 - Fix CC, AR, LD external definition, allow flex and bison to be
   externally defined and other related Makefile fixes (David Carrillo-Cisneros)

 - Sync CPU features kernel ABI headers with tooling headers (Arnaldo Carvalho de Melo)

 - Fix path to PMU formats in 'perf stat' documentation (Jack Henschel)

 - Fix static build with newer toolchains (Jiri Olsa)
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

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

@@ -177,7 +177,7 @@
 #define X86_FEATURE_PERFCTR_NB  ( 6*32+24) /* NB performance counter extensions */
 #define X86_FEATURE_BPEXT	(6*32+26) /* data breakpoint extension */
 #define X86_FEATURE_PTSC	( 6*32+27) /* performance time-stamp counter */
-#define X86_FEATURE_PERFCTR_L2	( 6*32+28) /* L2 performance counter extensions */
+#define X86_FEATURE_PERFCTR_LLC	( 6*32+28) /* Last Level Cache performance counter extensions */
 #define X86_FEATURE_MWAITX	( 6*32+29) /* MWAIT extension (MONITORX/MWAITX) */
 
 /*
@@ -196,7 +196,6 @@
 
 #define X86_FEATURE_HW_PSTATE	( 7*32+ 8) /* AMD HW-PState */
 #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */
-#define X86_FEATURE_SME		( 7*32+10) /* AMD Secure Memory Encryption */
 
 #define X86_FEATURE_INTEL_PPIN	( 7*32+14) /* Intel Processor Inventory Number */
 #define X86_FEATURE_INTEL_PT	( 7*32+15) /* Intel Processor Trace */
@@ -287,7 +286,7 @@
 #define X86_FEATURE_PAUSEFILTER (15*32+10) /* filtered pause intercept */
 #define X86_FEATURE_PFTHRESHOLD (15*32+12) /* pause filter threshold */
 #define X86_FEATURE_AVIC	(15*32+13) /* Virtual Interrupt Controller */
-#define X86_FEATURE_VIRTUAL_VMLOAD_VMSAVE (15*32+15) /* Virtual VMLOAD VMSAVE */
+#define X86_FEATURE_V_VMSAVE_VMLOAD (15*32+15) /* Virtual VMSAVE VMLOAD */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (ecx), word 16 */
 #define X86_FEATURE_AVX512VBMI  (16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/

tools/arch/x86/include/asm/disabled-features.h

@@ -21,13 +21,11 @@
 # define DISABLE_K6_MTRR	(1<<(X86_FEATURE_K6_MTRR & 31))
 # define DISABLE_CYRIX_ARR	(1<<(X86_FEATURE_CYRIX_ARR & 31))
 # define DISABLE_CENTAUR_MCR	(1<<(X86_FEATURE_CENTAUR_MCR & 31))
-# define DISABLE_PCID		0
 #else
 # define DISABLE_VME		0
 # define DISABLE_K6_MTRR	0
 # define DISABLE_CYRIX_ARR	0
 # define DISABLE_CENTAUR_MCR	0
-# define DISABLE_PCID		(1<<(X86_FEATURE_PCID & 31))
 #endif /* CONFIG_X86_64 */
 
 #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
@@ -51,7 +49,7 @@
 #define DISABLED_MASK1	0
 #define DISABLED_MASK2	0
 #define DISABLED_MASK3	(DISABLE_CYRIX_ARR|DISABLE_CENTAUR_MCR|DISABLE_K6_MTRR)
-#define DISABLED_MASK4	(DISABLE_PCID)
+#define DISABLED_MASK4	0
 #define DISABLED_MASK5	0
 #define DISABLED_MASK6	0
 #define DISABLED_MASK7	0

tools/build/tests/ex/Makefile

@@ -8,7 +8,7 @@ ex:
 include $(srctree)/tools/build/Makefile.include
 
 ex: ex-in.o libex-in.o
-	gcc -o $@ $^
+	$(CC) -o $@ $^
 
 ex.%: fixdep FORCE
 	make -f $(srctree)/tools/build/Makefile.build dir=. $@

tools/lib/api/Makefile

@@ -8,9 +8,9 @@ srctree := $(patsubst %/,%,$(dir $(srctree)))
 #$(info Determined 'srctree' to be $(srctree))
 endif
 
-CC = $(CROSS_COMPILE)gcc
-AR = $(CROSS_COMPILE)ar
-LD = $(CROSS_COMPILE)ld
+CC ?= $(CROSS_COMPILE)gcc
+AR ?= $(CROSS_COMPILE)ar
+LD ?= $(CROSS_COMPILE)ld
 
 MAKEFLAGS += --no-print-directory
 
@@ -19,7 +19,7 @@ LIBFILE = $(OUTPUT)libapi.a
 CFLAGS := $(EXTRA_WARNINGS) $(EXTRA_CFLAGS)
 CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -fPIC
 
-ifeq ($(CC), clang)
+ifeq ($(CC_NO_CLANG), 0)
   CFLAGS += -O3
 else
   CFLAGS += -O6

tools/lib/subcmd/Makefile

@@ -21,7 +21,7 @@ LIBFILE = $(OUTPUT)libsubcmd.a
 CFLAGS := $(EXTRA_WARNINGS) $(EXTRA_CFLAGS)
 CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -fPIC
 
-ifeq ($(CC), clang)
+ifeq ($(CC_NO_CLANG), 0)
   CFLAGS += -O3
 else
   CFLAGS += -O6

tools/perf/Documentation/perf-stat.txt

@@ -41,13 +41,13 @@ report::
 
 	- a symbolically formed event like 'pmu/param1=0x3,param2/' where
 	  param1 and param2 are defined as formats for the PMU in
-	  /sys/bus/event_sources/devices/<pmu>/format/*
+	  /sys/bus/event_source/devices/<pmu>/format/*
 
 	- a symbolically formed event like 'pmu/config=M,config1=N,config2=K/'
 	  where M, N, K are numbers (in decimal, hex, octal format).
 	  Acceptable values for each of 'config', 'config1' and 'config2'
 	  parameters are defined by corresponding entries in
-	  /sys/bus/event_sources/devices/<pmu>/format/*
+	  /sys/bus/event_source/devices/<pmu>/format/*
 
 -i::
 --no-inherit::

tools/perf/Makefile.config

@@ -148,7 +148,7 @@ ifndef DEBUG
 endif
 
 ifeq ($(DEBUG),0)
-ifeq ($(CC), clang)
+ifeq ($(CC_NO_CLANG), 0)
   CFLAGS += -O3
 else
   CFLAGS += -O6
@@ -184,7 +184,7 @@ ifdef PYTHON_CONFIG
   PYTHON_EMBED_LDFLAGS := $(call strip-libs,$(PYTHON_EMBED_LDOPTS))
   PYTHON_EMBED_LIBADD := $(call grep-libs,$(PYTHON_EMBED_LDOPTS)) -lutil
   PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null)
-  ifeq ($(CC), clang)
+  ifeq ($(CC_NO_CLANG), 1)
     PYTHON_EMBED_CCOPTS := $(filter-out -specs=%,$(PYTHON_EMBED_CCOPTS))
   endif
   FLAGS_PYTHON_EMBED := $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS)

tools/perf/Makefile.perf

@@ -164,8 +164,8 @@ LN      = ln -f
 MKDIR   = mkdir
 FIND    = find
 INSTALL = install
-FLEX    = flex
-BISON   = bison
+FLEX    ?= flex
+BISON   ?= bison
 STRIP   = strip
 AWK     = awk
 
@@ -240,7 +240,7 @@ endif
 ifeq ($(FEATURES_DUMP),)
 FEATURE_DUMP_EXPORT := $(realpath $(OUTPUT)FEATURE-DUMP)
 else
-FEATURE_DUMP_EXPORT := $(FEATURES_DUMP)
+FEATURE_DUMP_EXPORT := $(realpath $(FEATURES_DUMP))
 endif
 
 export prefix bindir sharedir sysconfdir DESTDIR
@@ -279,7 +279,13 @@ LIBTRACEEVENT = $(TE_PATH)libtraceevent.a
 export LIBTRACEEVENT
 
 LIBTRACEEVENT_DYNAMIC_LIST = $(TE_PATH)libtraceevent-dynamic-list
-LIBTRACEEVENT_DYNAMIC_LIST_LDFLAGS = -Xlinker --dynamic-list=$(LIBTRACEEVENT_DYNAMIC_LIST)
+
+#
+# The static build has no dynsym table, so this does not work for
+# static build. Looks like linker starts to scream about that now
+# (in Fedora 26) so we need to switch it off for static build.
+DYNAMIC_LIST_LDFLAGS               = -Xlinker --dynamic-list=$(LIBTRACEEVENT_DYNAMIC_LIST)
+LIBTRACEEVENT_DYNAMIC_LIST_LDFLAGS = $(if $(findstring -static,$(LDFLAGS)),,$(DYNAMIC_LIST_LDFLAGS))
 
 LIBAPI = $(API_PATH)libapi.a
 export LIBAPI
@@ -381,7 +387,8 @@ export INSTALL SHELL_PATH
 
 SHELL = $(SHELL_PATH)
 
-beauty_ioctl_outdir := $(OUTPUT)trace/beauty/generated/ioctl
+beauty_outdir := $(OUTPUT)trace/beauty/generated
+beauty_ioctl_outdir := $(beauty_outdir)/ioctl
 drm_ioctl_array := $(beauty_ioctl_outdir)/drm_ioctl_array.c
 drm_hdr_dir := $(srctree)/tools/include/uapi/drm
 drm_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/drm_ioctl.sh
@@ -392,6 +399,13 @@ _dummy := $(shell [ -d '$(beauty_ioctl_outdir)' ] || mkdir -p '$(beauty_ioctl_ou
 $(drm_ioctl_array): $(drm_hdr_dir)/drm.h $(drm_hdr_dir)/i915_drm.h $(drm_ioctl_tbl)
 	$(Q)$(SHELL) '$(drm_ioctl_tbl)' $(drm_hdr_dir) > $@
 
+pkey_alloc_access_rights_array := $(beauty_outdir)/pkey_alloc_access_rights_array.c
+asm_generic_hdr_dir := $(srctree)/tools/include/uapi/asm-generic/
+pkey_alloc_access_rights_tbl := $(srctree)/tools/perf/trace/beauty/pkey_alloc_access_rights.sh
+
+$(pkey_alloc_access_rights_array): $(asm_generic_hdr_dir)/mman-common.h $(pkey_alloc_access_rights_tbl)
+	$(Q)$(SHELL) '$(pkey_alloc_access_rights_tbl)' $(asm_generic_hdr_dir) > $@
+
 sndrv_ctl_ioctl_array := $(beauty_ioctl_outdir)/sndrv_ctl_ioctl_array.c
 sndrv_ctl_hdr_dir := $(srctree)/tools/include/uapi/sound
 sndrv_ctl_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh
@@ -522,6 +536,7 @@ __build-dir = $(subst $(OUTPUT),,$(dir $@))
 build-dir   = $(if $(__build-dir),$(__build-dir),.)
 
 prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h archheaders $(drm_ioctl_array) \
+	$(pkey_alloc_access_rights_array) \
 	$(sndrv_pcm_ioctl_array) \
 	$(sndrv_ctl_ioctl_array) \
 	$(kvm_ioctl_array) \
@@ -797,6 +812,7 @@ clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clea
 		$(OUTPUT)tests/llvm-src-{base,kbuild,prologue,relocation}.c \
 		$(OUTPUT)pmu-events/pmu-events.c \
 		$(OUTPUT)$(drm_ioctl_array) \
+		$(OUTPUT)$(pkey_alloc_access_rights_array) \
 		$(OUTPUT)$(sndrv_ctl_ioctl_array) \
 		$(OUTPUT)$(sndrv_pcm_ioctl_array) \
 		$(OUTPUT)$(kvm_ioctl_array) \

tools/perf/builtin-report.c

@@ -241,7 +241,7 @@ static int process_read_event(struct perf_tool *tool,
 		const char *name = evsel ? perf_evsel__name(evsel) : "unknown";
 		int err = perf_read_values_add_value(&rep->show_threads_values,
 					   event->read.pid, event->read.tid,
-					   event->read.id,
+					   evsel->idx,
 					   name,
 					   event->read.value);
 
@@ -249,10 +249,6 @@ static int process_read_event(struct perf_tool *tool,
 			return err;
 	}
 
-	dump_printf(": %d %d %s %" PRIu64 "\n", event->read.pid, event->read.tid,
-		    evsel ? perf_evsel__name(evsel) : "FAIL",
-		    event->read.value);
-
 	return 0;
 }
 

tools/perf/builtin-trace.c

@@ -693,6 +693,14 @@ static struct syscall_fmt {
 		   [4] = { .scnprintf = SCA_PERF_FLAGS, /* flags */ }, }, },
 	{ .name	    = "pipe2",
 	  .arg = { [1] = { .scnprintf = SCA_PIPE_FLAGS, /* flags */ }, }, },
+	{ .name	    = "pkey_alloc",
+	  .arg = { [1] = { .scnprintf = SCA_PKEY_ALLOC_ACCESS_RIGHTS,	/* access_rights */ }, }, },
+	{ .name	    = "pkey_free",
+	  .arg = { [0] = { .scnprintf = SCA_INT,	/* key */ }, }, },
+	{ .name	    = "pkey_mprotect",
+	  .arg = { [0] = { .scnprintf = SCA_HEX,	/* start */ },
+		   [2] = { .scnprintf = SCA_MMAP_PROT,	/* prot */ },
+		   [3] = { .scnprintf = SCA_INT,	/* pkey */ }, }, },
 	{ .name	    = "poll", .timeout = true, },
 	{ .name	    = "ppoll", .timeout = true, },
 	{ .name	    = "pread", .alias = "pread64", },

tools/perf/trace/beauty/Build

@@ -3,4 +3,5 @@ libperf-y += fcntl.o
 ifeq ($(SRCARCH),$(filter $(SRCARCH),x86))
 libperf-y += ioctl.o
 endif
+libperf-y += pkey_alloc.o
 libperf-y += statx.o

tools/perf/trace/beauty/beauty.h

@@ -78,6 +78,9 @@ size_t syscall_arg__scnprintf_fcntl_arg(char *bf, size_t size, struct syscall_ar
 size_t syscall_arg__scnprintf_ioctl_cmd(char *bf, size_t size, struct syscall_arg *arg);
 #define SCA_IOCTL_CMD syscall_arg__scnprintf_ioctl_cmd
 
+size_t syscall_arg__scnprintf_pkey_alloc_access_rights(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_PKEY_ALLOC_ACCESS_RIGHTS syscall_arg__scnprintf_pkey_alloc_access_rights
+
 size_t syscall_arg__scnprintf_open_flags(char *bf, size_t size, struct syscall_arg *arg);
 #define SCA_OPEN_FLAGS syscall_arg__scnprintf_open_flags
 

tools/perf/trace/beauty/pkey_alloc.c

+/*
+ * trace/beauty/pkey_alloc.c
+ *
+ *  Copyright (C) 2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ *
+ * Released under the GPL v2. (and only v2, not any later version)
+ */
+
+#include "trace/beauty/beauty.h"
+#include <linux/kernel.h>
+#include <linux/log2.h>
+
+static size_t pkey_alloc__scnprintf_access_rights(int access_rights, char *bf, size_t size)
+{
+	int i, printed = 0;
+
+#include "trace/beauty/generated/pkey_alloc_access_rights_array.c"
+	static DEFINE_STRARRAY(pkey_alloc_access_rights);
+
+	if (access_rights == 0) {
+		const char *s = strarray__pkey_alloc_access_rights.entries[0];
+		if (s)
+			return scnprintf(bf, size, "%s", s);
+		return scnprintf(bf, size, "%d", 0);
+	}
+
+	for (i = 1; i < strarray__pkey_alloc_access_rights.nr_entries; ++i) {
+		int bit = 1 << (i - 1);
+
+		if (!(access_rights & bit))
+			continue;
+
+		if (printed != 0)
+			printed += scnprintf(bf + printed, size - printed, "|");
+
+		if (strarray__pkey_alloc_access_rights.entries[i] != NULL)
+			printed += scnprintf(bf + printed, size - printed, "%s", strarray__pkey_alloc_access_rights.entries[i]);
+		else
+			printed += scnprintf(bf + printed, size - printed, "0x%#", bit);
+	}
+
+	return printed;
+}
+
+size_t syscall_arg__scnprintf_pkey_alloc_access_rights(char *bf, size_t size, struct syscall_arg *arg)
+{
+	unsigned long cmd = arg->val;
+
+	return pkey_alloc__scnprintf_access_rights(cmd, bf, size);
+}

tools/perf/trace/beauty/pkey_alloc_access_rights.sh

+#!/bin/sh
+
+header_dir=$1
+
+printf "static const char *pkey_alloc_access_rights[] = {\n"
+regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+PKEY_([[:alnum:]_]+)[[:space:]]+(0x[[:xdigit:]]+)[[:space:]]*'
+egrep $regex ${header_dir}/mman-common.h	| \
+	sed -r "s/$regex/\2 \2 \1/g"	| \
+	sort | xargs printf "\t[%s ? (ilog2(%s) + 1) : 0] = \"%s\",\n"
+printf "};\n"

tools/perf/util/evsel.c

@@ -902,8 +902,13 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
 	if (opts->no_samples)
 		attr->sample_freq = 0;
 
-	if (opts->inherit_stat)
+	if (opts->inherit_stat) {
+		evsel->attr.read_format |=
+			PERF_FORMAT_TOTAL_TIME_ENABLED |
+			PERF_FORMAT_TOTAL_TIME_RUNNING |
+			PERF_FORMAT_ID;
 		attr->inherit_stat = 1;
+	}
 
 	if (opts->sample_address) {
 		perf_evsel__set_sample_bit(evsel, ADDR);

tools/perf/util/intel-pt-decoder/Build

@@ -25,6 +25,6 @@ $(OUTPUT)util/intel-pt-decoder/intel-pt-insn-decoder.o: util/intel-pt-decoder/in
 
 CFLAGS_intel-pt-insn-decoder.o += -I$(OUTPUT)util/intel-pt-decoder
 
-ifneq ($(CC), clang)
+ifeq ($(CC_NO_CLANG), 1)
   CFLAGS_intel-pt-insn-decoder.o += -Wno-override-init
 endif

tools/perf/util/mem-events.c

@@ -316,6 +316,11 @@ int c2c_decode_stats(struct c2c_stats *stats, struct mem_info *mi)
 	u64 lvl    = data_src->mem_lvl;
 	u64 snoop  = data_src->mem_snoop;
 	u64 lock   = data_src->mem_lock;
+	/*
+	 * Skylake might report unknown remote level via this
+	 * bit, consider it when evaluating remote HITMs.
+	 */
+	bool mrem  = data_src->mem_remote;
 	int err = 0;
 
 #define HITM_INC(__f)		\
@@ -361,7 +366,8 @@ do {				\
 			}
 
 			if ((lvl & P(LVL, REM_RAM1)) ||
-			    (lvl & P(LVL, REM_RAM2))) {
+			    (lvl & P(LVL, REM_RAM2)) ||
+			     mrem) {
 				stats->rmt_dram++;
 				if (snoop & P(SNOOP, HIT))
 					stats->ld_shared++;
@@ -371,7 +377,8 @@ do {				\
 		}
 
 		if ((lvl & P(LVL, REM_CCE1)) ||
-		    (lvl & P(LVL, REM_CCE2))) {
+		    (lvl & P(LVL, REM_CCE2)) ||
+		     mrem) {
 			if (snoop & P(SNOOP, HIT))
 				stats->rmt_hit++;
 			else if (snoop & P(SNOOP, HITM))

tools/perf/util/probe-event.c

@@ -2395,7 +2395,7 @@ kprobe_blacklist__find_by_address(struct list_head *blacklist,
 	struct kprobe_blacklist_node *node;
 
 	list_for_each_entry(node, blacklist, list) {
-		if (node->start <= address && address <= node->end)
+		if (node->start <= address && address < node->end)
 			return node;
 	}
 

tools/perf/util/session.c

@@ -1127,6 +1127,30 @@ static void dump_sample(struct perf_evsel *evsel, union perf_event *event,
 		sample_read__printf(sample, evsel->attr.read_format);
 }
 
+static void dump_read(struct perf_evsel *evsel, union perf_event *event)
+{
+	struct read_event *read_event = &event->read;
+	u64 read_format;
+
+	if (!dump_trace)
+		return;
+
+	printf(": %d %d %s %" PRIu64 "\n", event->read.pid, event->read.tid,
+	       evsel ? perf_evsel__name(evsel) : "FAIL",
+	       event->read.value);
+
+	read_format = evsel->attr.read_format;
+
+	if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
+		printf("... time enabled : %" PRIu64 "\n", read_event->time_enabled);
+
+	if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
+		printf("... time running : %" PRIu64 "\n", read_event->time_running);
+
+	if (read_format & PERF_FORMAT_ID)
+		printf("... id           : %" PRIu64 "\n", read_event->id);
+}
+
 static struct machine *machines__find_for_cpumode(struct machines *machines,
 					       union perf_event *event,
 					       struct perf_sample *sample)
@@ -1271,6 +1295,7 @@ static int machines__deliver_event(struct machines *machines,
 			evlist->stats.total_lost_samples += event->lost_samples.lost;
 		return tool->lost_samples(tool, event, sample, machine);
 	case PERF_RECORD_READ:
+		dump_read(evsel, event);
 		return tool->read(tool, event, sample, evsel, machine);
 	case PERF_RECORD_THROTTLE:
 		return tool->throttle(tool, event, sample, machine);

tools/perf/util/symbol-elf.c

@@ -259,7 +259,7 @@ int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map *
 {
 	uint32_t nr_rel_entries, idx;
 	GElf_Sym sym;
-	u64 plt_offset;
+	u64 plt_offset, plt_header_size, plt_entry_size;
 	GElf_Shdr shdr_plt;
 	struct symbol *f;
 	GElf_Shdr shdr_rel_plt, shdr_dynsym;
@@ -326,6 +326,23 @@ int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map *
 
 	nr_rel_entries = shdr_rel_plt.sh_size / shdr_rel_plt.sh_entsize;
 	plt_offset = shdr_plt.sh_offset;
+	switch (ehdr.e_machine) {
+		case EM_ARM:
+			plt_header_size = 20;
+			plt_entry_size = 12;
+			break;
+
+		case EM_AARCH64:
+			plt_header_size = 32;
+			plt_entry_size = 16;
+			break;
+
+		default: /* FIXME: s390/alpha/mips/parisc/poperpc/sh/sparc/xtensa need to be checked */
+			plt_header_size = shdr_plt.sh_entsize;
+			plt_entry_size = shdr_plt.sh_entsize;
+			break;
+	}
+	plt_offset += plt_header_size;
 
 	if (shdr_rel_plt.sh_type == SHT_RELA) {
 		GElf_Rela pos_mem, *pos;
@@ -335,7 +352,6 @@ int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map *
 			const char *elf_name = NULL;
 			char *demangled = NULL;
 			symidx = GELF_R_SYM(pos->r_info);
-			plt_offset += shdr_plt.sh_entsize;
 			gelf_getsym(syms, symidx, &sym);
 
 			elf_name = elf_sym__name(&sym, symstrs);
@@ -346,11 +362,12 @@ int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map *
 				 "%s@plt", elf_name);
 			free(demangled);
 
-			f = symbol__new(plt_offset, shdr_plt.sh_entsize,
+			f = symbol__new(plt_offset, plt_entry_size,
 					STB_GLOBAL, sympltname);
 			if (!f)
 				goto out_elf_end;
 
+			plt_offset += plt_entry_size;
 			symbols__insert(&dso->symbols[map->type], f);
 			++nr;
 		}
@@ -361,7 +378,6 @@ int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map *
 			const char *elf_name = NULL;
 			char *demangled = NULL;
 			symidx = GELF_R_SYM(pos->r_info);
-			plt_offset += shdr_plt.sh_entsize;
 			gelf_getsym(syms, symidx, &sym);
 
 			elf_name = elf_sym__name(&sym, symstrs);
@@ -372,11 +388,12 @@ int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map *
 				 "%s@plt", elf_name);
 			free(demangled);
 
-			f = symbol__new(plt_offset, shdr_plt.sh_entsize,
+			f = symbol__new(plt_offset, plt_entry_size,
 					STB_GLOBAL, sympltname);
 			if (!f)
 				goto out_elf_end;
 
+			plt_offset += plt_entry_size;
 			symbols__insert(&dso->symbols[map->type], f);
 			++nr;
 		}

tools/perf/util/values.c

@@ -12,7 +12,7 @@ int perf_read_values_init(struct perf_read_values *values)
 	values->threads_max = 16;
 	values->pid = malloc(values->threads_max * sizeof(*values->pid));
 	values->tid = malloc(values->threads_max * sizeof(*values->tid));
-	values->value = malloc(values->threads_max * sizeof(*values->value));
+	values->value = zalloc(values->threads_max * sizeof(*values->value));
 	if (!values->pid || !values->tid || !values->value) {
 		pr_debug("failed to allocate read_values threads arrays");
 		goto out_free_pid;
@@ -98,15 +98,16 @@ static int perf_read_values__findnew_thread(struct perf_read_values *values,
 			return i;
 	}
 
-	i = values->threads + 1;
-	values->value[i] = malloc(values->counters_max * sizeof(**values->value));
+	i = values->threads;
+
+	values->value[i] = zalloc(values->counters_max * sizeof(**values->value));
 	if (!values->value[i]) {
 		pr_debug("failed to allocate read_values counters array");
 		return -ENOMEM;
 	}
 	values->pid[i] = pid;
 	values->tid[i] = tid;
-	values->threads = i;
+	values->threads = i + 1;
 
 	return i;
 }
@@ -130,12 +131,16 @@ static int perf_read_values__enlarge_counters(struct perf_read_values *values)
 
 	for (i = 0; i < values->threads; i++) {
 		u64 *value = realloc(values->value[i], counters_max * sizeof(**values->value));
+		int j;
 
-		if (value) {
+		if (!value) {
 			pr_debug("failed to enlarge read_values ->values array");
 			goto out_free_name;
 		}
 
+		for (j = values->counters_max; j < counters_max; j++)
+			value[j] = 0;
+
 		values->value[i] = value;
 	}
 
@@ -187,7 +192,7 @@ int perf_read_values_add_value(struct perf_read_values *values,
 	if (cindex < 0)
 		return cindex;
 
-	values->value[tindex][cindex] = value;
+	values->value[tindex][cindex] += value;
 	return 0;
 }
 

tools/scripts/Makefile.include

@@ -39,7 +39,9 @@ EXTRA_WARNINGS += -Wundef
 EXTRA_WARNINGS += -Wwrite-strings
 EXTRA_WARNINGS += -Wformat
 
-ifneq ($(CC), clang)
+CC_NO_CLANG := $(shell $(CC) -dM -E -x c /dev/null | grep -Fq "__clang__"; echo $$?)
+
+ifeq ($(CC_NO_CLANG), 1)
 EXTRA_WARNINGS += -Wstrict-aliasing=3
 endif