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>

7 files changed, 75 insertions, 16 deletions

diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index a5888c7..d9bd632 100644
--- a/tools/perf/util/evsel.c
+++ b/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);
diff --git a/tools/perf/util/intel-pt-decoder/Build b/tools/perf/util/intel-pt-decoder/Build
index 7aca5d6..10e0814 100644
--- a/tools/perf/util/intel-pt-decoder/Build
+++ b/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
diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
index ced4f3f..28afe5f 100644
--- a/tools/perf/util/mem-events.c
+++ b/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))
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index d7cd114..b7aaf9b 100644
--- a/tools/perf/util/probe-event.c
+++ b/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;
 	}
 
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index dc453f8..ac86369 100644
--- a/tools/perf/util/session.c
+++ b/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);
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index a704790..5c39f42 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/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;
 		}
diff --git a/tools/perf/util/values.c b/tools/perf/util/values.c
index 5de2e15..8a32bb0 100644
--- a/tools/perf/util/values.c
+++ b/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;
 }