Merge branch 'perf/urgent' into perf/core

Pick up v3.7-rc2 and fixes before applying more patches.

Signed-off-by: Ingo Molnar <mingo@kernel.org>

21 files changed, 76 insertions, 41 deletions

diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 318bec8e14e4..f530502630a4 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -74,7 +74,7 @@ ifeq ($(ARCH),x86_64)
 	override ARCH := x86
 	IS_X86_64 := 0
 	ifeq (, $(findstring m32,$(EXTRA_CFLAGS)))
-		IS_X86_64 := $(shell echo __x86_64__ | ${CC} -E -xc - | tail -n 1)
+		IS_X86_64 := $(shell echo __x86_64__ | ${CC} -E -x c - | tail -n 1)
 	endif
 	ifeq (${IS_X86_64}, 1)
 		RAW_ARCH := x86_64
@@ -191,9 +191,22 @@ SCRIPT_SH += perf-archive.sh
 grep-libs = $(filter -l%,$(1))
 strip-libs = $(filter-out -l%,$(1))
 
+TRACE_EVENT_DIR = ../lib/traceevent/
+
+ifneq ($(OUTPUT),)
+	TE_PATH=$(OUTPUT)
+else
+	TE_PATH=$(TRACE_EVENT_DIR)
+endif
+
+LIBTRACEEVENT = $(TE_PATH)libtraceevent.a
+TE_LIB := -L$(TE_PATH) -ltraceevent
+
 PYTHON_EXT_SRCS := $(shell grep -v ^\# util/python-ext-sources)
 PYTHON_EXT_DEPS := util/python-ext-sources util/setup.py
 
+export LIBTRACEEVENT
+
 $(OUTPUT)python/perf.so: $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS)
 	$(QUIET_GEN)CFLAGS='$(BASIC_CFLAGS)' $(PYTHON_WORD) util/setup.py \
 	  --quiet build_ext; \
@@ -205,17 +218,6 @@ $(OUTPUT)python/perf.so: $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS)
 
 SCRIPTS = $(patsubst %.sh,%,$(SCRIPT_SH))
 
-TRACE_EVENT_DIR = ../lib/traceevent/
-
-ifneq ($(OUTPUT),)
-	TE_PATH=$(OUTPUT)
-else
-	TE_PATH=$(TRACE_EVENT_DIR)
-endif
-
-LIBTRACEEVENT = $(TE_PATH)libtraceevent.a
-TE_LIB := -L$(TE_PATH) -ltraceevent
-
 #
 # Single 'perf' binary right now:
 #
@@ -259,10 +261,10 @@ $(OUTPUT)util/pmu.o: $(OUTPUT)util/pmu-flex.c $(OUTPUT)util/pmu-bison.c
 
 LIB_FILE=$(OUTPUT)libperf.a
 
-LIB_H += ../../include/linux/perf_event.h
+LIB_H += ../../include/uapi/linux/perf_event.h
 LIB_H += ../../include/linux/rbtree.h
 LIB_H += ../../include/linux/list.h
-LIB_H += ../../include/linux/const.h
+LIB_H += ../../include/uapi/linux/const.h
 LIB_H += ../../include/linux/hash.h
 LIB_H += ../../include/linux/stringify.h
 LIB_H += util/include/linux/bitmap.h
@@ -277,6 +279,7 @@ LIB_H += util/include/linux/magic.h
 LIB_H += util/include/linux/poison.h
 LIB_H += util/include/linux/prefetch.h
 LIB_H += util/include/linux/rbtree.h
+LIB_H += util/include/linux/rbtree_augmented.h
 LIB_H += util/include/linux/string.h
 LIB_H += util/include/linux/types.h
 LIB_H += util/include/linux/linkage.h
@@ -902,7 +905,7 @@ $(OUTPUT)ui/browsers/map.o: ui/browsers/map.c $(OUTPUT)PERF-CFLAGS
 	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DENABLE_SLFUTURE_CONST $<
 
 $(OUTPUT)util/rbtree.o: ../../lib/rbtree.c $(OUTPUT)PERF-CFLAGS
-	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
+	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -Wno-unused-parameter -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
 
 $(OUTPUT)util/parse-events.o: util/parse-events.c $(OUTPUT)PERF-CFLAGS
 	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -Wno-redundant-decls $<
diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c
index 411ee5664e98..178b88ae3d2f 100644
--- a/tools/perf/builtin-help.c
+++ b/tools/perf/builtin-help.c
@@ -414,7 +414,7 @@ static int show_html_page(const char *perf_cmd)
 int cmd_help(int argc, const char **argv, const char *prefix __maybe_unused)
 {
 	bool show_all = false;
-	enum help_format help_format = HELP_FORMAT_NONE;
+	enum help_format help_format = HELP_FORMAT_MAN;
 	struct option builtin_help_options[] = {
 	OPT_BOOLEAN('a', "all", &show_all, "print all available commands"),
 	OPT_SET_UINT('m', "man", &help_format, "show man page", HELP_FORMAT_MAN),
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 4e9320bf11e1..14b322961807 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -63,6 +63,10 @@ static int trace__read_syscall_info(struct trace *trace, int id)
 {
 	char tp_name[128];
 	struct syscall *sc;
+	const char *name = audit_syscall_to_name(id, trace->audit_machine);
+
+	if (name == NULL)
+		return -1;
 
 	if (id > trace->syscalls.max) {
 		struct syscall *nsyscalls = realloc(trace->syscalls.table, (id + 1) * sizeof(*sc));
@@ -82,11 +86,8 @@ static int trace__read_syscall_info(struct trace *trace, int id)
 	}
 
 	sc = trace->syscalls.table + id;
-	sc->name = audit_syscall_to_name(id, trace->audit_machine);
-	if (sc->name == NULL)
-		return -1;
-
-	sc->fmt = syscall_fmt__find(sc->name);
+	sc->name = name;
+	sc->fmt  = syscall_fmt__find(sc->name);
 
 	snprintf(tp_name, sizeof(tp_name), "sys_enter_%s", sc->name);
 	sc->tp_format = event_format__new("syscalls", tp_name);
@@ -290,6 +291,13 @@ again:
 			if (evlist->threads->map[0] == -1 || evlist->threads->nr > 1)
 				printf("%d ", sample.tid);
 
+			if (sample.raw_data == NULL) {
+				printf("%s sample with no payload for tid: %d, cpu %d, raw_size=%d, skipping...\n",
+				       perf_evsel__name(evsel), sample.tid,
+				       sample.cpu, sample.raw_size);
+				continue;
+			}
+
 			handler = evsel->handler.func;
 			handler(trace, evsel, &sample);
 		}
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 87f4ec6d1f36..c50985eaec41 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -57,7 +57,7 @@ void get_term_dimensions(struct winsize *ws);
 #endif
 
 #ifdef __sparc__
-#include "../../arch/sparc/include/asm/unistd.h"
+#include "../../arch/sparc/include/uapi/asm/unistd.h"
 #define rmb()		asm volatile("":::"memory")
 #define cpu_relax()	asm volatile("":::"memory")
 #define CPUINFO_PROC	"cpu"
@@ -88,6 +88,12 @@ void get_term_dimensions(struct winsize *ws);
 #define CPUINFO_PROC	"Processor"
 #endif
 
+#ifdef __aarch64__
+#include "../../arch/arm64/include/asm/unistd.h"
+#define rmb()		asm volatile("dmb ld" ::: "memory")
+#define cpu_relax()	asm volatile("yield" ::: "memory")
+#endif
+
 #ifdef __mips__
 #include "../../arch/mips/include/asm/unistd.h"
 #define rmb()		asm volatile(					\
@@ -106,7 +112,7 @@ void get_term_dimensions(struct winsize *ws);
 #include <sys/types.h>
 #include <sys/syscall.h>
 
-#include "../../include/linux/perf_event.h"
+#include "../../include/uapi/linux/perf_event.h"
 #include "util/types.h"
 #include <stdbool.h>
 
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 0568536ecf67..ef2f93ca7496 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -610,6 +610,7 @@ static int hist_browser__show_entry(struct hist_browser *browser,
 	char folded_sign = ' ';
 	bool current_entry = ui_browser__is_current_entry(&browser->b, row);
 	off_t row_offset = entry->row_offset;
+	bool first = true;
 
 	if (current_entry) {
 		browser->he_selection = entry;
@@ -633,10 +634,11 @@ static int hist_browser__show_entry(struct hist_browser *browser,
 			if (!perf_hpp__format[i].cond)
 				continue;
 
-			if (i) {
+			if (!first) {
 				slsmg_printf("  ");
 				width -= 2;
 			}
+			first = false;
 
 			if (perf_hpp__format[i].color) {
 				hpp.ptr = &percent;
@@ -645,7 +647,7 @@ static int hist_browser__show_entry(struct hist_browser *browser,
 
 				ui_browser__set_percent_color(&browser->b, percent, current_entry);
 
-				if (i == 0 && symbol_conf.use_callchain) {
+				if (i == PERF_HPP__OVERHEAD && symbol_conf.use_callchain) {
 					slsmg_printf("%c ", folded_sign);
 					width -= 2;
 				}
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 3bdb407f9cd9..eb340571e7d6 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -58,7 +58,7 @@ struct callchain_list {
 /*
  * A callchain cursor is a single linked list that
  * let one feed a callchain progressively.
- * It keeps persitent allocated entries to minimize
+ * It keeps persistent allocated entries to minimize
  * allocations.
  */
 struct callchain_cursor_node {
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index ffdd94e9c9c3..618d41140abd 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -19,7 +19,7 @@
 #include "thread_map.h"
 #include "target.h"
 #include "../../../include/linux/hw_breakpoint.h"
-#include "../../include/linux/perf_event.h"
+#include "../../../include/uapi/linux/perf_event.h"
 #include "perf_regs.h"
 
 #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 3ead0d59c03d..6f94d6dea00f 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -3,7 +3,7 @@
 
 #include <linux/list.h>
 #include <stdbool.h>
-#include "../../../include/linux/perf_event.h"
+#include "../../../include/uapi/linux/perf_event.h"
 #include "types.h"
 #include "xyarray.h"
 #include "cgroup.h"
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 99bdd3abce59..879d215cdac9 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -1,7 +1,7 @@
 #ifndef __PERF_HEADER_H
 #define __PERF_HEADER_H
 
-#include "../../../include/linux/perf_event.h"
+#include "../../../include/uapi/linux/perf_event.h"
 #include <sys/types.h>
 #include <stdbool.h>
 #include "types.h"
diff --git a/tools/perf/util/include/asm/byteorder.h b/tools/perf/util/include/asm/byteorder.h
index b722abe3a626..2a9bdc066307 100644
--- a/tools/perf/util/include/asm/byteorder.h
+++ b/tools/perf/util/include/asm/byteorder.h
@@ -1,2 +1,2 @@
 #include <asm/types.h>
-#include "../../../../include/linux/swab.h"
+#include "../../../../include/uapi/linux/swab.h"
diff --git a/tools/perf/util/include/linux/const.h b/tools/perf/util/include/linux/const.h
index 1b476c9ae649..c10a35e1afb8 100644
--- a/tools/perf/util/include/linux/const.h
+++ b/tools/perf/util/include/linux/const.h
@@ -1 +1 @@
-#include "../../../../include/linux/const.h"
+#include "../../../../include/uapi/linux/const.h"
diff --git a/tools/perf/util/include/linux/rbtree_augmented.h b/tools/perf/util/include/linux/rbtree_augmented.h
new file mode 100644
index 000000000000..9d6fcdf1788b
--- /dev/null
+++ b/tools/perf/util/include/linux/rbtree_augmented.h
@@ -0,0 +1,2 @@
+#include <stdbool.h>
+#include "../../../../include/linux/rbtree_augmented.h"
diff --git a/tools/perf/util/parse-events-test.c b/tools/perf/util/parse-events-test.c
index d7244e553670..516ecd9ddd6e 100644
--- a/tools/perf/util/parse-events-test.c
+++ b/tools/perf/util/parse-events-test.c
@@ -513,7 +513,8 @@ static int test__group1(struct perf_evlist *evlist)
 	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
 	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
 	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
-	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+	/* use of precise requires exclude_guest */
+	TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest);
 	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip == 2);
 	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
@@ -599,7 +600,8 @@ static int test__group3(struct perf_evlist *evlist __maybe_unused)
 	TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user);
 	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
 	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
-	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+	/* use of precise requires exclude_guest */
+	TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest);
 	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip == 3);
 	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
@@ -662,7 +664,8 @@ static int test__group4(struct perf_evlist *evlist __maybe_unused)
 	TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
 	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
 	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
-	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+	/* use of precise requires exclude_guest */
+	TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest);
 	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip == 1);
 	TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
@@ -676,7 +679,8 @@ static int test__group4(struct perf_evlist *evlist __maybe_unused)
 	TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user);
 	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
 	TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
-	TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+	/* use of precise requires exclude_guest */
+	TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest);
 	TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip == 2);
 	TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
@@ -1016,7 +1020,7 @@ static int test_pmu(void)
 
 	ret = stat(path, &st);
 	if (ret)
-		pr_debug("ommiting PMU cpu tests\n");
+		pr_debug("omitting PMU cpu tests\n");
 	return !ret;
 }
 
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index aed38e4b9dfa..75c7b0fca6d9 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -690,6 +690,9 @@ static int get_event_modifier(struct event_modifier *mod, char *str,
 			eH = 0;
 		} else if (*str == 'p') {
 			precise++;
+			/* use of precise requires exclude_guest */
+			if (!exclude_GH)
+				eG = 1;
 		} else
 			break;
 
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index c356e443448d..839230ceb18b 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -7,7 +7,7 @@
 #include <linux/list.h>
 #include <stdbool.h>
 #include "types.h"
-#include "../../../include/linux/perf_event.h"
+#include "../../../include/uapi/linux/perf_event.h"
 #include "types.h"
 
 struct list_head;
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 53c7794fc4be..39f3abac7744 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -2,7 +2,7 @@
 #define __PMU_H
 
 #include <linux/bitops.h>
-#include "../../../include/linux/perf_event.h"
+#include "../../../include/uapi/linux/perf_event.h"
 
 enum {
 	PERF_PMU_FORMAT_VALUE_CONFIG,
diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources
index 213362850abd..c40c2d33199e 100644
--- a/tools/perf/util/python-ext-sources
+++ b/tools/perf/util/python-ext-sources
@@ -1,5 +1,5 @@
 #
-# List of files needed by perf python extention
+# List of files needed by perf python extension
 #
 # Each source file must be placed on its own line so that it can be
 # processed by Makefile and util/setup.py accordingly.
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index aab414fbb64b..dd6426163ba6 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -7,7 +7,7 @@
 #include "symbol.h"
 #include "thread.h"
 #include <linux/rbtree.h>
-#include "../../../include/linux/perf_event.h"
+#include "../../../include/uapi/linux/perf_event.h"
 
 struct sample_queue;
 struct ip_callchain;
diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
index d0f9f29cf181..73d510269784 100644
--- a/tools/perf/util/setup.py
+++ b/tools/perf/util/setup.py
@@ -23,6 +23,7 @@ cflags += getenv('CFLAGS', '').split()
 
 build_lib = getenv('PYTHON_EXTBUILD_LIB')
 build_tmp = getenv('PYTHON_EXTBUILD_TMP')
+libtraceevent = getenv('LIBTRACEEVENT')
 
 ext_sources = [f.strip() for f in file('util/python-ext-sources')
 				if len(f.strip()) > 0 and f[0] != '#']
@@ -31,6 +32,7 @@ perf = Extension('perf',
 		  sources = ext_sources,
 		  include_dirs = ['util/include'],
 		  extra_compile_args = cflags,
+		  extra_objects = [libtraceevent],
                  )
 
 setup(name='perf',
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index b5b1b9211960..cfd1c0feb32d 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -260,6 +260,12 @@ static int hist_entry__srcline_snprintf(struct hist_entry *self, char *bf,
 	if (path != NULL)
 		goto out_path;
 
+	if (!self->ms.map)
+		goto out_ip;
+
+	if (!strncmp(self->ms.map->dso->long_name, "/tmp/perf-", 10))
+		goto out_ip;
+
 	snprintf(cmd, sizeof(cmd), "addr2line -e %s %016" PRIx64,
 		 self->ms.map->dso->long_name, self->ip);
 	fp = popen(cmd, "r");
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index fe3bb1ec1887..df59623ac763 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -39,7 +39,6 @@ int thread__set_comm(struct thread *self, const char *comm)
 	err = self->comm == NULL ? -ENOMEM : 0;
 	if (!err) {
 		self->comm_set = true;
-		map_groups__flush(&self->mg);
 	}
 	return err;
 }