67 files changed, 2118 insertions, 504 deletions

diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index f2989c525e48..5a824e355d04 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -174,7 +174,7 @@ static int cmdline_init(struct pevent *pevent)
         return 0;
 }
 
-static char *find_cmdline(struct pevent *pevent, int pid)
+static const char *find_cmdline(struct pevent *pevent, int pid)
 {
         const struct cmdline *comm;
         struct cmdline key;
@@ -2637,7 +2637,7 @@ process_func_handler(struct event_format *event, struct pevent_function_handler
         struct print_arg *farg;
         enum event_type type;
         char *token;
-        char *test;
+        const char *test;
         int i;
 
         arg->type = PRINT_FUNC;
@@ -3889,7 +3889,7 @@ static void print_mac_arg(struct trace_seq *s, int mac, void *data, int size,
                           struct event_format *event, struct print_arg *arg)
 {
         unsigned char *buf;
-        char *fmt = "%.2x:%.2x:%.2x:%.2x:%.2x:%.2x";
+        const char *fmt = "%.2x:%.2x:%.2x:%.2x:%.2x:%.2x";
 
         if (arg->type == PRINT_FUNC) {
                 process_defined_func(s, data, size, event, arg);
@@ -3931,7 +3931,8 @@ static int is_printable_array(char *p, unsigned int len)
         return 1;
 }
 
-static void print_event_fields(struct trace_seq *s, void *data, int size,
+static void print_event_fields(struct trace_seq *s, void *data,
+                               int size __maybe_unused,
                                struct event_format *event)
 {
         struct format_field *field;
@@ -4408,7 +4409,7 @@ void pevent_event_info(struct trace_seq *s, struct event_format *event,
 void pevent_print_event(struct pevent *pevent, struct trace_seq *s,
                         struct pevent_record *record)
 {
-        static char *spaces = "                    "; /* 20 spaces */
+        static const char *spaces = "                    "; /* 20 spaces */
         struct event_format *event;
         unsigned long secs;
         unsigned long usecs;
@@ -5070,8 +5071,8 @@ static const char * const pevent_error_str[] = {
 };
 #undef _PE
 
-int pevent_strerror(struct pevent *pevent, enum pevent_errno errnum,
-                    char *buf, size_t buflen)
+int pevent_strerror(struct pevent *pevent __maybe_unused,
+                    enum pevent_errno errnum, char *buf, size_t buflen)
 {
         int idx;
         const char *msg;
@@ -5100,6 +5101,7 @@ int pevent_strerror(struct pevent *pevent, enum pevent_errno errnum,
         case PEVENT_ERRNO__READ_FORMAT_FAILED:
         case PEVENT_ERRNO__READ_PRINT_FAILED:
         case PEVENT_ERRNO__OLD_FTRACE_ARG_FAILED:
+        case PEVENT_ERRNO__INVALID_ARG_TYPE:
                 snprintf(buf, buflen, "%s", msg);
                 break;
 
@@ -5362,7 +5364,7 @@ int pevent_register_print_function(struct pevent *pevent,
                 if (type == PEVENT_FUNC_ARG_VOID)
                         break;
 
-                if (type < 0 || type >= PEVENT_FUNC_ARG_MAX_TYPES) {
+                if (type >= PEVENT_FUNC_ARG_MAX_TYPES) {
                         do_warning("Invalid argument type %d", type);
                         ret = PEVENT_ERRNO__INVALID_ARG_TYPE;
                         goto out_free;
@@ -5560,7 +5562,7 @@ void pevent_free(struct pevent *pevent)
         }
 
         if (pevent->func_map) {
-                for (i = 0; i < pevent->func_count; i++) {
+                for (i = 0; i < (int)pevent->func_count; i++) {
                         free(pevent->func_map[i].func);
                         free(pevent->func_map[i].mod);
                 }
@@ -5582,7 +5584,7 @@ void pevent_free(struct pevent *pevent)
         }
 
         if (pevent->printk_map) {
-                for (i = 0; i < pevent->printk_count; i++)
+                for (i = 0; i < (int)pevent->printk_count; i++)
                         free(pevent->printk_map[i].printk);
                 free(pevent->printk_map);
         }
diff --git a/tools/perf/Documentation/android.txt b/tools/perf/Documentation/android.txt
index a39dbbb44c4c..8484c3a04a6a 100644
--- a/tools/perf/Documentation/android.txt
+++ b/tools/perf/Documentation/android.txt
@@ -48,7 +48,10 @@ For x86:
 II. Compile perf for Android
 ------------------------------------------------
 You need to run make with the NDK toolchain and sysroot defined above:
-  make CROSS_COMPILE=${NDK_TOOLCHAIN} CFLAGS="--sysroot=${NDK_SYSROOT}"
+For arm:
+  make ARCH=arm CROSS_COMPILE=${NDK_TOOLCHAIN} CFLAGS="--sysroot=${NDK_SYSROOT}"
+For x86:
+  make ARCH=x86 CROSS_COMPILE=${NDK_TOOLCHAIN} CFLAGS="--sysroot=${NDK_SYSROOT}"
 
 III. Install perf
 -----------------------------------------------
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 7e25f59e5e89..cca5bb8334ad 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -169,7 +169,7 @@ endif
 
 ### --- END CONFIGURATION SECTION ---
 
-BASIC_CFLAGS = -Iutil/include -Iarch/$(ARCH)/include -I$(OUTPUT)util -I$(TRACE_EVENT_DIR) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE
+BASIC_CFLAGS = -Iutil/include -Iarch/$(ARCH)/include -I$(OUTPUT)util -Iutil -I. -I$(TRACE_EVENT_DIR) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE
 BASIC_LDFLAGS =
 
 ifeq ($(call try-cc,$(SOURCE_BIONIC),$(CFLAGS),bionic),y)
@@ -371,7 +371,6 @@ LIB_OBJS += $(OUTPUT)util/help.o
 LIB_OBJS += $(OUTPUT)util/levenshtein.o
 LIB_OBJS += $(OUTPUT)util/parse-options.o
 LIB_OBJS += $(OUTPUT)util/parse-events.o
-LIB_OBJS += $(OUTPUT)util/parse-events-test.o
 LIB_OBJS += $(OUTPUT)util/path.o
 LIB_OBJS += $(OUTPUT)util/rbtree.o
 LIB_OBJS += $(OUTPUT)util/bitmap.o
@@ -389,7 +388,6 @@ LIB_OBJS += $(OUTPUT)util/sigchain.o
 LIB_OBJS += $(OUTPUT)util/dso.o
 LIB_OBJS += $(OUTPUT)util/symbol.o
 LIB_OBJS += $(OUTPUT)util/symbol-elf.o
-LIB_OBJS += $(OUTPUT)util/dso-test-data.o
 LIB_OBJS += $(OUTPUT)util/color.o
 LIB_OBJS += $(OUTPUT)util/pager.o
 LIB_OBJS += $(OUTPUT)util/header.o
@@ -430,6 +428,10 @@ LIB_OBJS += $(OUTPUT)ui/stdio/hist.o
 
 LIB_OBJS += $(OUTPUT)arch/common.o
 
+LIB_OBJS += $(OUTPUT)tests/parse-events.o
+LIB_OBJS += $(OUTPUT)tests/dso-data.o
+LIB_OBJS += $(OUTPUT)tests/attr.o
+
 BUILTIN_OBJS += $(OUTPUT)builtin-annotate.o
 BUILTIN_OBJS += $(OUTPUT)builtin-bench.o
 # Benchmark modules
@@ -459,8 +461,8 @@ BUILTIN_OBJS += $(OUTPUT)builtin-probe.o
 BUILTIN_OBJS += $(OUTPUT)builtin-kmem.o
 BUILTIN_OBJS += $(OUTPUT)builtin-lock.o
 BUILTIN_OBJS += $(OUTPUT)builtin-kvm.o
-BUILTIN_OBJS += $(OUTPUT)builtin-test.o
 BUILTIN_OBJS += $(OUTPUT)builtin-inject.o
+BUILTIN_OBJS += $(OUTPUT)tests/builtin-test.o
 
 PERFLIBS = $(LIB_FILE) $(LIBTRACEEVENT)
 
@@ -490,6 +492,8 @@ ifneq ($(call try-cc,$(SOURCE_LIBELF),$(FLAGS_LIBELF),libelf),y)
                 LIBC_SUPPORT := 1
         endif
         ifeq ($(LIBC_SUPPORT),1)
+                msg := $(warning No libelf found, disables 'probe' tool, please install elfutils-libelf-devel/libelf-dev);
+
                 NO_LIBELF := 1
                 NO_DWARF := 1
                 NO_DEMANGLE := 1
@@ -497,7 +501,14 @@ ifneq ($(call try-cc,$(SOURCE_LIBELF),$(FLAGS_LIBELF),libelf),y)
                 msg := $(error No gnu/libc-version.h found, please install glibc-dev[el]/glibc-static);
         endif
 else
-        FLAGS_DWARF=$(ALL_CFLAGS) -ldw -lelf $(ALL_LDFLAGS) $(EXTLIBS)
+        # for linking with debug library, run like:
+        # make DEBUG=1 LIBDW_DIR=/opt/libdw/
+        ifdef LIBDW_DIR
+                LIBDW_CFLAGS  := -I$(LIBDW_DIR)/include
+                LIBDW_LDFLAGS := -L$(LIBDW_DIR)/lib
+        endif
+
+        FLAGS_DWARF=$(ALL_CFLAGS) $(LIBDW_CFLAGS) -ldw -lelf $(LIBDW_LDFLAGS) $(ALL_LDFLAGS) $(EXTLIBS)
         ifneq ($(call try-cc,$(SOURCE_DWARF),$(FLAGS_DWARF),libdw),y)
                 msg := $(warning No libdw.h found or old libdw.h found or elfutils is older than 0.138, disables dwarf support. Please install new elfutils-devel/libdw-dev);
                 NO_DWARF := 1
@@ -552,7 +563,8 @@ ifndef NO_DWARF
 ifeq ($(origin PERF_HAVE_DWARF_REGS), undefined)
         msg := $(warning DWARF register mappings have not been defined for architecture $(ARCH), DWARF support disabled);
 else
-        BASIC_CFLAGS += -DDWARF_SUPPORT
+        BASIC_CFLAGS := -DDWARF_SUPPORT $(LIBDW_CFLAGS) $(BASIC_CFLAGS)
+        BASIC_LDFLAGS := $(LIBDW_LDFLAGS) $(BASIC_LDFLAGS)
         EXTLIBS += -lelf -ldw
         LIB_OBJS += $(OUTPUT)util/probe-finder.o
         LIB_OBJS += $(OUTPUT)util/dwarf-aux.o
@@ -891,10 +903,14 @@ $(OUTPUT)%.s: %.S
 $(OUTPUT)util/exec_cmd.o: util/exec_cmd.c $(OUTPUT)PERF-CFLAGS
         $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) \
                 '-DPERF_EXEC_PATH="$(perfexecdir_SQ)"' \
-                '-DBINDIR="$(bindir_relative_SQ)"' \
                 '-DPREFIX="$(prefix_SQ)"' \
                 $<
 
+$(OUTPUT)tests/attr.o: tests/attr.c $(OUTPUT)PERF-CFLAGS
+        $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) \
+                '-DBINDIR="$(bindir_SQ)"' \
+                $<
+
 $(OUTPUT)util/config.o: util/config.c $(OUTPUT)PERF-CFLAGS
         $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
 
@@ -1059,6 +1075,10 @@ install: all try-install-man
         $(INSTALL) scripts/python/bin/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/bin'
         $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d'
         $(INSTALL) bash_completion '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d/perf'
+        $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests'
+        $(INSTALL) tests/attr.py '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests'
+        $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'
+        $(INSTALL) tests/attr/* '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'
 
 install-python_ext:
         $(PYTHON_WORD) util/setup.py --quiet install --root='/$(DESTDIR_SQ)'
diff --git a/tools/perf/arch/common.c b/tools/perf/arch/common.c
index 2367b253f039..3e975cb6232e 100644
--- a/tools/perf/arch/common.c
+++ b/tools/perf/arch/common.c
@@ -93,16 +93,46 @@ static int lookup_triplets(const char *const *triplets, const char *name)
         return -1;
 }
 
+/*
+ * Return architecture name in a normalized form.
+ * The conversion logic comes from the Makefile.
+ */
+static const char *normalize_arch(char *arch)
+{
+        if (!strcmp(arch, "x86_64"))
+                return "x86";
+        if (arch[0] == 'i' && arch[2] == '8' && arch[3] == '6')
+                return "x86";
+        if (!strcmp(arch, "sun4u") || !strncmp(arch, "sparc", 5))
+                return "sparc";
+        if (!strncmp(arch, "arm", 3) || !strcmp(arch, "sa110"))
+                return "arm";
+        if (!strncmp(arch, "s390", 4))
+                return "s390";
+        if (!strncmp(arch, "parisc", 6))
+                return "parisc";
+        if (!strncmp(arch, "powerpc", 7) || !strncmp(arch, "ppc", 3))
+                return "powerpc";
+        if (!strncmp(arch, "mips", 4))
+                return "mips";
+        if (!strncmp(arch, "sh", 2) && isdigit(arch[2]))
+                return "sh";
+
+        return arch;
+}
+
 static int perf_session_env__lookup_binutils_path(struct perf_session_env *env,
                                                   const char *name,
                                                   const char **path)
 {
         int idx;
-        char *arch, *cross_env;
+        const char *arch, *cross_env;
         struct utsname uts;
         const char *const *path_list;
         char *buf = NULL;
 
+        arch = normalize_arch(env->arch);
+
         if (uname(&uts) < 0)
                 goto out;
 
@@ -110,7 +140,7 @@ static int perf_session_env__lookup_binutils_path(struct perf_session_env *env,
          * We don't need to try to find objdump path for native system.
          * Just use default binutils path (e.g.: "objdump").
          */
-        if (!strcmp(uts.machine, env->arch))
+        if (!strcmp(normalize_arch(uts.machine), arch))
                 goto out;
 
         cross_env = getenv("CROSS_COMPILE");
@@ -127,8 +157,6 @@ static int perf_session_env__lookup_binutils_path(struct perf_session_env *env,
                 free(buf);
         }
 
-        arch = env->arch;
-
         if (!strcmp(arch, "arm"))
                 path_list = arm_triplets;
         else if (!strcmp(arch, "powerpc"))
@@ -139,9 +167,7 @@ static int perf_session_env__lookup_binutils_path(struct perf_session_env *env,
                 path_list = s390_triplets;
         else if (!strcmp(arch, "sparc"))
                 path_list = sparc_triplets;
-        else if (!strcmp(arch, "x86") || !strcmp(arch, "i386") ||
-                 !strcmp(arch, "i486") || !strcmp(arch, "i586") ||
-                 !strcmp(arch, "i686"))
+        else if (!strcmp(arch, "x86"))
                 path_list = x86_triplets;
         else if (!strcmp(arch, "mips"))
                 path_list = mips_triplets;
@@ -173,6 +199,13 @@ out_error:
 
 int perf_session_env__lookup_objdump(struct perf_session_env *env)
 {
+        /*
+         * For live mode, env->arch will be NULL and we can use
+         * the native objdump tool.
+         */
+        if (env->arch == NULL)
+                return 0;
+
         return perf_session_env__lookup_binutils_path(env, "objdump",
                                                       &objdump_path);
 }
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index cb234765ce3d..dc870cf31b79 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -139,7 +139,7 @@ find_next:
                 }
 
                 if (use_browser > 0) {
-                        key = hist_entry__tui_annotate(he, evidx, NULL, NULL, 0);
+                        key = hist_entry__tui_annotate(he, evidx, NULL);
                         switch (key) {
                         case K_RIGHT:
                                 next = rb_next(nd);
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 380683de1df3..93b852f8a5d5 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -154,7 +154,7 @@ static double get_period_percent(struct hist_entry *he, u64 period)
 
 double perf_diff__compute_delta(struct hist_entry *he)
 {
-        struct hist_entry *pair = he->pair;
+        struct hist_entry *pair = hist_entry__next_pair(he);
         double new_percent = get_period_percent(he, he->stat.period);
         double old_percent = pair ? get_period_percent(pair, pair->stat.period) : 0.0;
 
@@ -165,7 +165,7 @@ double perf_diff__compute_delta(struct hist_entry *he)
 
 double perf_diff__compute_ratio(struct hist_entry *he)
 {
-        struct hist_entry *pair = he->pair;
+        struct hist_entry *pair = hist_entry__next_pair(he);
         double new_period = he->stat.period;
         double old_period = pair ? pair->stat.period : 0;
 
@@ -176,7 +176,7 @@ double perf_diff__compute_ratio(struct hist_entry *he)
 
 s64 perf_diff__compute_wdiff(struct hist_entry *he)
 {
-        struct hist_entry *pair = he->pair;
+        struct hist_entry *pair = hist_entry__next_pair(he);
         u64 new_period = he->stat.period;
         u64 old_period = pair ? pair->stat.period : 0;
 
@@ -193,7 +193,7 @@ s64 perf_diff__compute_wdiff(struct hist_entry *he)
 
 static int formula_delta(struct hist_entry *he, char *buf, size_t size)
 {
-        struct hist_entry *pair = he->pair;
+        struct hist_entry *pair = hist_entry__next_pair(he);
 
         if (!pair)
                 return -1;
@@ -207,7 +207,7 @@ static int formula_delta(struct hist_entry *he, char *buf, size_t size)
 
 static int formula_ratio(struct hist_entry *he, char *buf, size_t size)
 {
-        struct hist_entry *pair = he->pair;
+        struct hist_entry *pair = hist_entry__next_pair(he);
         double new_period = he->stat.period;
         double old_period = pair ? pair->stat.period : 0;
 
@@ -219,7 +219,7 @@ static int formula_ratio(struct hist_entry *he, char *buf, size_t size)
 
 static int formula_wdiff(struct hist_entry *he, char *buf, size_t size)
 {
-        struct hist_entry *pair = he->pair;
+        struct hist_entry *pair = hist_entry__next_pair(he);
         u64 new_period = he->stat.period;
         u64 old_period = pair ? pair->stat.period : 0;
 
@@ -334,36 +334,6 @@ static void hists__name_resort(struct hists *self, bool sort)
                 self->entries = tmp;
 }
 
-static struct hist_entry *hists__find_entry(struct hists *self,
-                                            struct hist_entry *he)
-{
-        struct rb_node *n = self->entries.rb_node;
-
-        while (n) {
-                struct hist_entry *iter = rb_entry(n, struct hist_entry, rb_node);
-                int64_t cmp = hist_entry__cmp(he, iter);
-
-                if (cmp < 0)
-                        n = n->rb_left;
-                else if (cmp > 0)
-                        n = n->rb_right;
-                else
-                        return iter;
-        }
-
-        return NULL;
-}
-
-static void hists__match(struct hists *older, struct hists *newer)
-{
-        struct rb_node *nd;
-
-        for (nd = rb_first(&newer->entries); nd; nd = rb_next(nd)) {
-                struct hist_entry *pos = rb_entry(nd, struct hist_entry, rb_node);
-                pos->pair = hists__find_entry(older, pos);
-        }
-}
-
 static struct perf_evsel *evsel_match(struct perf_evsel *evsel,
                                       struct perf_evlist *evlist)
 {
@@ -402,7 +372,7 @@ static void hists__baseline_only(struct hists *hists)
                 struct hist_entry *he = rb_entry(next, struct hist_entry, rb_node);
 
                 next = rb_next(&he->rb_node);
-                if (!he->pair) {
+                if (!hist_entry__next_pair(he)) {
                         rb_erase(&he->rb_node, &hists->entries);
                         hist_entry__free(he);
                 }
@@ -517,10 +487,12 @@ static void hists__compute_resort(struct hists *hists)
 
 static void hists__process(struct hists *old, struct hists *new)
 {
-        hists__match(old, new);
+        hists__match(new, old);
 
         if (show_baseline_only)
                 hists__baseline_only(new);
+        else
+                hists__link(new, old);
 
         if (sort_compute) {
                 hists__precompute(new);
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index f07eae73e692..fc251005dd3d 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -428,10 +428,11 @@ static int __cmd_report(struct perf_report *rep)
         if (use_browser > 0) {
                 if (use_browser == 1) {
                         perf_evlist__tui_browse_hists(session->evlist, help,
-                                                      NULL, NULL, 0);
+                                                      NULL,
+                                                      &session->header.env);
                 } else if (use_browser == 2) {
                         perf_evlist__gtk_browse_hists(session->evlist, help,
-                                                      NULL, NULL, 0);
+                                                      NULL);
                 }
         } else
                 perf_evlist__tty_browse_hists(session->evlist, rep, help);
@@ -672,12 +673,6 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
         has_br_stack = perf_header__has_feat(&session->header,
                                              HEADER_BRANCH_STACK);
 
-        if (!objdump_path) {
-                ret = perf_session_env__lookup_objdump(&session->header.env);
-                if (ret)
-                        goto error;
-        }
-
         if (sort__branch_mode == -1 && has_br_stack)
                 sort__branch_mode = 1;
 
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index f2ecd498c72d..c9ff3950cd4b 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -582,6 +582,11 @@ static void *display_thread_tui(void *arg)
         struct perf_evsel *pos;
         struct perf_top *top = arg;
         const char *help = "For a higher level overview, try: perf top --sort comm,dso";
+        struct hist_browser_timer hbt = {
+                .timer          = perf_top__sort_new_samples,
+                .arg            = top,
+                .refresh        = top->delay_secs,
+        };
 
         perf_top__sort_new_samples(top);
 
@@ -593,9 +598,8 @@ static void *display_thread_tui(void *arg)
         list_for_each_entry(pos, &top->evlist->entries, node)
                 pos->hists.uid_filter_str = top->target.uid_str;
 
-        perf_evlist__tui_browse_hists(top->evlist, help,
-                                      perf_top__sort_new_samples,
-                                      top, top->delay_secs);
+        perf_evlist__tui_browse_hists(top->evlist, help, &hbt,
+                                      &top->session->header.env);
 
         exit_browser(0);
         exit(0);
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index e9683738d89f..a0ae2902f9c9 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -484,6 +484,8 @@ int main(int argc, const char **argv)
         }
         cmd = argv[0];
 
+        test_attr__init();
+
         /*
          * We use PATH to find perf commands, but we prepend some higher
          * precedence paths: the "--exec-path" option, the PERF_EXEC_PATH
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 469fbf2daea4..054182e41dca 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -174,13 +174,26 @@ static inline unsigned long long rdclock(void)
         (void) (&_min1 == &_min2);              \
         _min1 < _min2 ? _min1 : _min2; })
 
+extern bool test_attr__enabled;
+void test_attr__init(void);
+void test_attr__open(struct perf_event_attr *attr, pid_t pid, int cpu,
+                     int fd, int group_fd, unsigned long flags);
+int  test_attr__run(void);
+
 static inline int
 sys_perf_event_open(struct perf_event_attr *attr,
                       pid_t pid, int cpu, int group_fd,
                       unsigned long flags)
 {
-        return syscall(__NR_perf_event_open, attr, pid, cpu,
-                       group_fd, flags);
+        int fd;
+
+        fd = syscall(__NR_perf_event_open, attr, pid, cpu,
+                     group_fd, flags);
+
+        if (unlikely(test_attr__enabled))
+                test_attr__open(attr, pid, cpu, fd, group_fd, flags);
+
+        return fd;
 }
 
 #define MAX_COUNTERS                    256
diff --git a/tools/perf/tests/attr.c b/tools/perf/tests/attr.c
new file mode 100644
index 000000000000..6e2feee8db2a
--- /dev/null
+++ b/tools/perf/tests/attr.c
@@ -0,0 +1,174 @@
+
+/*
+ * The struct perf_event_attr test support.
+ *
+ * This test is embedded inside into perf directly and is governed
+ * by the PERF_TEST_ATTR environment variable and hook inside
+ * sys_perf_event_open function.
+ *
+ * The general idea is to store 'struct perf_event_attr' details for
+ * each event created within single perf command. Each event details
+ * are stored into separate text file. Once perf command is finished
+ * these files can be checked for values we expect for command.
+ *
+ * Besides 'struct perf_event_attr' values we also store 'fd' and
+ * 'group_fd' values to allow checking for groups created.
+ *
+ * This all is triggered by setting PERF_TEST_ATTR environment variable.
+ * It must contain name of existing directory with access and write
+ * permissions. All the event text files are stored there.
+ */
+
+#include <stdlib.h>
+#include <stdio.h>
+#include <inttypes.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include "../perf.h"
+#include "util.h"
+#include "exec_cmd.h"
+
+#define ENV "PERF_TEST_ATTR"
+
+extern int verbose;
+
+bool test_attr__enabled;
+
+static char *dir;
+
+void test_attr__init(void)
+{
+        dir = getenv(ENV);
+        test_attr__enabled = (dir != NULL);
+}
+
+#define BUFSIZE 1024
+
+#define __WRITE_ASS(str, fmt, data)                                     \
+do {                                                                    \
+        char buf[BUFSIZE];                                              \
+        size_t size;                                                    \
+                                                                        \
+        size = snprintf(buf, BUFSIZE, #str "=%"fmt "\n", data);         \
+        if (1 != fwrite(buf, size, 1, file)) {                          \
+                perror("test attr - failed to write event file");       \
+                fclose(file);                                           \
+                return -1;                                              \
+        }                                                               \
+                                                                        \
+} while (0)
+
+#define WRITE_ASS(field, fmt) __WRITE_ASS(field, fmt, attr->field)
+
+static int store_event(struct perf_event_attr *attr, pid_t pid, int cpu,
+                       int fd, int group_fd, unsigned long flags)
+{
+        FILE *file;
+        char path[PATH_MAX];
+
+        snprintf(path, PATH_MAX, "%s/event-%d-%llu-%d", dir,
+                 attr->type, attr->config, fd);
+
+        file = fopen(path, "w+");
+        if (!file) {
+                perror("test attr - failed to open event file");
+                return -1;
+        }
+
+        if (fprintf(file, "[event-%d-%llu-%d]\n",
+                    attr->type, attr->config, fd) < 0) {
+                perror("test attr - failed to write event file");
+                fclose(file);
+                return -1;
+        }
+
+        /* syscall arguments */
+        __WRITE_ASS(fd,       "d", fd);
+        __WRITE_ASS(group_fd, "d", group_fd);
+        __WRITE_ASS(cpu,      "d", cpu);
+        __WRITE_ASS(pid,      "d", pid);
+        __WRITE_ASS(flags,   "lu", flags);
+
+        /* struct perf_event_attr */
+        WRITE_ASS(type,   PRIu32);
+        WRITE_ASS(size,   PRIu32);
+        WRITE_ASS(config,  "llu");
+        WRITE_ASS(sample_period, "llu");
+        WRITE_ASS(sample_type,   "llu");
+        WRITE_ASS(read_format,   "llu");
+        WRITE_ASS(disabled,       "d");
+        WRITE_ASS(inherit,        "d");
+        WRITE_ASS(pinned,         "d");
+        WRITE_ASS(exclusive,      "d");
+        WRITE_ASS(exclude_user,   "d");
+        WRITE_ASS(exclude_kernel, "d");
+        WRITE_ASS(exclude_hv,     "d");
+        WRITE_ASS(exclude_idle,   "d");
+        WRITE_ASS(mmap,           "d");
+        WRITE_ASS(comm,           "d");
+        WRITE_ASS(freq,           "d");
+        WRITE_ASS(inherit_stat,   "d");
+        WRITE_ASS(enable_on_exec, "d");
+        WRITE_ASS(task,           "d");
+        WRITE_ASS(watermark,      "d");
+        WRITE_ASS(precise_ip,     "d");
+        WRITE_ASS(mmap_data,      "d");
+        WRITE_ASS(sample_id_all,  "d");
+        WRITE_ASS(exclude_host,   "d");
+        WRITE_ASS(exclude_guest,  "d");
+        WRITE_ASS(exclude_callchain_kernel, "d");
+        WRITE_ASS(exclude_callchain_user, "d");
+        WRITE_ASS(wakeup_events, PRIu32);
+        WRITE_ASS(bp_type, PRIu32);
+        WRITE_ASS(config1, "llu");
+        WRITE_ASS(config2, "llu");
+        WRITE_ASS(branch_sample_type, "llu");
+        WRITE_ASS(sample_regs_user,   "llu");
+        WRITE_ASS(sample_stack_user,  PRIu32);
+
+        fclose(file);
+        return 0;
+}
+
+void test_attr__open(struct perf_event_attr *attr, pid_t pid, int cpu,
+                     int fd, int group_fd, unsigned long flags)
+{
+        int errno_saved = errno;
+
+        if (store_event(attr, pid, cpu, fd, group_fd, flags))
+                die("test attr FAILED");
+
+        errno = errno_saved;
+}
+
+static int run_dir(const char *d, const char *perf)
+{
+        char cmd[3*PATH_MAX];
+
+        snprintf(cmd, 3*PATH_MAX, "python %s/attr.py -d %s/attr/ -p %s %s",
+                 d, d, perf, verbose ? "-v" : "");
+
+        return system(cmd);
+}
+
+int test_attr__run(void)
+{
+        struct stat st;
+        char path_perf[PATH_MAX];
+        char path_dir[PATH_MAX];
+
+        /* First try developement tree tests. */
+        if (!lstat("./tests", &st))
+                return run_dir("./tests", "./perf");
+
+        /* Then installed path. */
+        snprintf(path_dir,  PATH_MAX, "%s/tests", perf_exec_path());
+        snprintf(path_perf, PATH_MAX, "%s/perf", BINDIR);
+
+        if (!lstat(path_dir, &st) &&
+            !lstat(path_perf, &st))
+                return run_dir(path_dir, path_perf);
+
+        fprintf(stderr, " (ommitted)");
+        return 0;
+}
diff --git a/tools/perf/tests/attr.py b/tools/perf/tests/attr.py
new file mode 100644
index 000000000000..e702b82dcb86
--- /dev/null
+++ b/tools/perf/tests/attr.py
@@ -0,0 +1,322 @@
+#! /usr/bin/python
+
+import os
+import sys
+import glob
+import optparse
+import tempfile
+import logging
+import shutil
+import ConfigParser
+
+class Fail(Exception):
+    def __init__(self, test, msg):
+        self.msg = msg
+        self.test = test
+    def getMsg(self):
+        return '\'%s\' - %s' % (self.test.path, self.msg)
+
+class Unsup(Exception):
+    def __init__(self, test):
+        self.test = test
+    def getMsg(self):
+        return '\'%s\'' % self.test.path
+
+class Event(dict):
+    terms = [
+        'flags',
+        'type',
+        'size',
+        'config',
+        'sample_period',
+        'sample_type',
+        'read_format',
+        'disabled',
+        'inherit',
+        'pinned',
+        'exclusive',
+        'exclude_user',
+        'exclude_kernel',
+        'exclude_hv',
+        'exclude_idle',
+        'mmap',
+        'comm',
+        'freq',
+        'inherit_stat',
+        'enable_on_exec',
+        'task',
+        'watermark',
+        'precise_ip',
+        'mmap_data',
+        'sample_id_all',
+        'exclude_host',
+        'exclude_guest',
+        'exclude_callchain_kernel',
+        'exclude_callchain_user',
+        'wakeup_events',
+        'bp_type',
+        'config1',
+        'config2',
+        'branch_sample_type',
+        'sample_regs_user',
+        'sample_stack_user',
+    ]
+
+    def add(self, data):
+        for key, val in data:
+            log.debug("      %s = %s" % (key, val))
+            self[key] = val
+
+    def __init__(self, name, data, base):
+        log.info("    Event %s" % name);
+        self.name  = name;
+        self.group = ''
+        self.add(base)
+        self.add(data)
+
+    def compare_data(self, a, b):
+        # Allow multiple values in assignment separated by '|'
+        a_list = a.split('|')
+        b_list = b.split('|')
+
+        for a_item in a_list:
+            for b_item in b_list:
+                if (a_item == b_item):
+                    return True
+                elif (a_item == '*') or (b_item == '*'):
+                    return True
+
+        return False
+
+    def equal(self, other):
+        for t in Event.terms:
+            log.debug("      [%s] %s %s" % (t, self[t], other[t]));
+            if not self.has_key(t) or not other.has_key(t):
+                return False
+            if not self.compare_data(self[t], other[t]):
+                return False
+        return True
+
+# Test file description needs to have following sections:
+# [config]
+#   - just single instance in file
+#   - needs to specify:
+#     'command' - perf command name
+#     'args'    - special command arguments
+#     'ret'     - expected command return value (0 by default)
+#
+# [eventX:base]
+#   - one or multiple instances in file
+#   - expected values assignments
+class Test(object):
+    def __init__(self, path, options):
+        parser = ConfigParser.SafeConfigParser()
+        parser.read(path)
+
+        log.warning("running '%s'" % path)
+
+        self.path     = path
+        self.test_dir = options.test_dir
+        self.perf     = options.perf
+        self.command  = parser.get('config', 'command')
+        self.args     = parser.get('config', 'args')
+
+        try:
+            self.ret  = parser.get('config', 'ret')
+        except:
+            self.ret  = 0
+
+        self.expect   = {}
+        self.result   = {}
+        log.info("  loading expected events");
+        self.load_events(path, self.expect)
+
+    def is_event(self, name):
+        if name.find("event") == -1:
+            return False
+        else:
+            return True
+
+    def load_events(self, path, events):
+        parser_event = ConfigParser.SafeConfigParser()
+        parser_event.read(path)
+
+        # The event record section header contains 'event' word,
+        # optionaly followed by ':' allowing to load 'parent
+        # event' first as a base
+        for section in filter(self.is_event, parser_event.sections()):
+
+            parser_items = parser_event.items(section);
+            base_items   = {}
+
+            # Read parent event if there's any
+            if (':' in section):
+                base = section[section.index(':') + 1:]
+                parser_base = ConfigParser.SafeConfigParser()
+                parser_base.read(self.test_dir + '/' + base)
+                base_items = parser_base.items('event')
+
+            e = Event(section, parser_items, base_items)
+            events[section] = e
+
+    def run_cmd(self, tempdir):
+        cmd = "PERF_TEST_ATTR=%s %s %s -o %s/perf.data %s" % (tempdir,
+              self.perf, self.command, tempdir, self.args)
+        ret = os.WEXITSTATUS(os.system(cmd))
+
+        log.info("  running '%s' ret %d " % (cmd, ret))
+
+        if ret != int(self.ret):
+            raise Unsup(self)
+
+    def compare(self, expect, result):
+        match = {}
+
+        log.info("  compare");
+
+        # For each expected event find all matching
+        # events in result. Fail if there's not any.
+        for exp_name, exp_event in expect.items():
+            exp_list = []
+            log.debug("    matching [%s]" % exp_name)
+            for res_name, res_event in result.items():
+                log.debug("      to [%s]" % res_name)
+                if (exp_event.equal(res_event)):
+                    exp_list.append(res_name)
+                    log.debug("    ->OK")
+                else:
+                    log.debug("    ->FAIL");
+
+            log.info("    match: [%s] matches %s" % (exp_name, str(exp_list)))
+
+            # we did not any matching event - fail
+            if (not exp_list):
+                raise Fail(self, 'match failure');
+
+            match[exp_name] = exp_list
+
+        # For each defined group in the expected events
+        # check we match the same group in the result.
+        for exp_name, exp_event in expect.items():
+            group = exp_event.group
+
+            if (group == ''):
+                continue
+
+            for res_name in match[exp_name]:
+                res_group = result[res_name].group
+                if res_group not in match[group]:
+                    raise Fail(self, 'group failure')
+
+                log.info("    group: [%s] matches group leader %s" %
+                         (exp_name, str(match[group])))
+
+        log.info("  matched")
+
+    def resolve_groups(self, events):
+        for name, event in events.items():
+            group_fd = event['group_fd'];
+            if group_fd == '-1':
+                continue;
+
+            for iname, ievent in events.items():
+                if (ievent['fd'] == group_fd):
+                    event.group = iname
+                    log.debug('[%s] has group leader [%s]' % (name, iname))
+                    break;
+
+    def run(self):
+        tempdir = tempfile.mkdtemp();
+
+        try:
+            # run the test script
+            self.run_cmd(tempdir);
+
+            # load events expectation for the test
+            log.info("  loading result events");
+            for f in glob.glob(tempdir + '/event*'):
+                self.load_events(f, self.result);
+
+            # resolve group_fd to event names
+            self.resolve_groups(self.expect);
+            self.resolve_groups(self.result);
+
+            # do the expectation - results matching - both ways
+            self.compare(self.expect, self.result)
+            self.compare(self.result, self.expect)
+
+        finally:
+            # cleanup
+            shutil.rmtree(tempdir)
+
+
+def run_tests(options):
+    for f in glob.glob(options.test_dir + '/' + options.test):
+        try:
+            Test(f, options).run()
+        except Unsup, obj:
+            log.warning("unsupp  %s" % obj.getMsg())
+
+def setup_log(verbose):
+    global log
+    level = logging.CRITICAL
+
+    if verbose == 1:
+        level = logging.WARNING
+    if verbose == 2:
+        level = logging.INFO
+    if verbose >= 3:
+        level = logging.DEBUG
+
+    log = logging.getLogger('test')
+    log.setLevel(level)
+    ch  = logging.StreamHandler()
+    ch.setLevel(level)
+    formatter = logging.Formatter('%(message)s')
+    ch.setFormatter(formatter)
+    log.addHandler(ch)
+
+USAGE = '''%s [OPTIONS]
+  -d dir  # tests dir
+  -p path # perf binary
+  -t test # single test
+  -v      # verbose level
+''' % sys.argv[0]
+
+def main():
+    parser = optparse.OptionParser(usage=USAGE)
+
+    parser.add_option("-t", "--test",
+                      action="store", type="string", dest="test")
+    parser.add_option("-d", "--test-dir",
+                      action="store", type="string", dest="test_dir")
+    parser.add_option("-p", "--perf",
+                      action="store", type="string", dest="perf")
+    parser.add_option("-v", "--verbose",
+                      action="count", dest="verbose")
+
+    options, args = parser.parse_args()
+    if args:
+        parser.error('FAILED wrong arguments %s' %  ' '.join(args))
+        return -1
+
+    setup_log(options.verbose)
+
+    if not options.test_dir:
+        print 'FAILED no -d option specified'
+        sys.exit(-1)
+
+    if not options.test:
+        options.test = 'test*'
+
+    try:
+        run_tests(options)
+
+    except Fail, obj:
+        print "FAILED %s" % obj.getMsg();
+        sys.exit(-1)
+
+    sys.exit(0)
+
+if __name__ == '__main__':
+    main()
diff --git a/tools/perf/tests/attr/README b/tools/perf/tests/attr/README
new file mode 100644
index 000000000000..d102957cd59a
--- /dev/null
+++ b/tools/perf/tests/attr/README
@@ -0,0 +1,64 @@
+The struct perf_event_attr test (attr tests) support
+====================================================
+This testing support is embedded into perf directly and is governed
+by the PERF_TEST_ATTR environment variable and hook inside the
+sys_perf_event_open function.
+
+The general idea is to store 'struct perf_event_attr' details for
+each event created within single perf command. Each event details
+are stored into separate text file. Once perf command is finished
+these files are checked for values we expect for command.
+
+The attr tests consist of following parts:
+
+tests/attr.c
+------------
+This is the sys_perf_event_open hook implementation. The hook
+is triggered when the PERF_TEST_ATTR environment variable is
+defined. It must contain name of existing directory with access
+and write permissions.
+
+For each sys_perf_event_open call event details are stored in
+separate file. Besides 'struct perf_event_attr' values we also
+store 'fd' and 'group_fd' values to allow checking for groups.
+
+tests/attr.py
+-------------
+This is the python script that does all the hard work. It reads
+the test definition, executes it and checks results.
+
+tests/attr/
+-----------
+Directory containing all attr test definitions.
+Following tests are defined (with perf commands):
+
+  perf record kill                              (test-record-basic)
+  perf record -b kill                           (test-record-branch-any)
+  perf record -j any kill                       (test-record-branch-filter-any)
+  perf record -j any_call kill                  (test-record-branch-filter-any_call)
+  perf record -j any_ret kill                   (test-record-branch-filter-any_ret)
+  perf record -j hv kill                        (test-record-branch-filter-hv)
+  perf record -j ind_call kill                  (test-record-branch-filter-ind_call)
+  perf record -j k kill                         (test-record-branch-filter-k)
+  perf record -j u kill                         (test-record-branch-filter-u)
+  perf record -c 123 kill                       (test-record-count)
+  perf record -d kill                           (test-record-data)
+  perf record -F 100 kill                       (test-record-freq)
+  perf record -g -- kill                        (test-record-graph-default)
+  perf record -g dwarf -- kill                  (test-record-graph-dwarf)
+  perf record -g fp kill                        (test-record-graph-fp)
+  perf record --group -e cycles,instructions kill (test-record-group)
+  perf record -e '{cycles,instructions}' kill   (test-record-group1)
+  perf record -D kill                           (test-record-no-delay)
+  perf record -i kill                           (test-record-no-inherit)
+  perf record -n kill                           (test-record-no-samples)
+  perf record -c 100 -P kill                    (test-record-period)
+  perf record -R kill                           (test-record-raw)
+  perf stat -e cycles kill                      (test-stat-basic)
+  perf stat kill                                (test-stat-default)
+  perf stat -d kill                             (test-stat-detailed-1)
+  perf stat -dd kill                            (test-stat-detailed-2)
+  perf stat -ddd kill                           (test-stat-detailed-3)
+  perf stat --group -e cycles,instructions kill (test-stat-group)
+  perf stat -e '{cycles,instructions}' kill     (test-stat-group1)
+  perf stat -i -e cycles kill                   (test-stat-no-inherit)
diff --git a/tools/perf/tests/attr/base-record b/tools/perf/tests/attr/base-record
new file mode 100644
index 000000000000..f1485d8e6a0b
--- /dev/null
+++ b/tools/perf/tests/attr/base-record
@@ -0,0 +1,39 @@
+[event]
+fd=1
+group_fd=-1
+flags=0
+type=0|1
+size=96
+config=0
+sample_period=4000
+sample_type=263
+read_format=7
+disabled=1
+inherit=1
+pinned=0
+exclusive=0
+exclude_user=0
+exclude_kernel=0
+exclude_hv=0
+exclude_idle=0
+mmap=1
+comm=1
+freq=1
+inherit_stat=0
+enable_on_exec=1
+task=0
+watermark=0
+precise_ip=0
+mmap_data=0
+sample_id_all=1
+exclude_host=0
+exclude_guest=1
+exclude_callchain_kernel=0
+exclude_callchain_user=0
+wakeup_events=0
+bp_type=0
+config1=0
+config2=0
+branch_sample_type=0
+sample_regs_user=0
+sample_stack_user=0
diff --git a/tools/perf/tests/attr/base-stat b/tools/perf/tests/attr/base-stat
new file mode 100644
index 000000000000..4bd79a82784f
--- /dev/null
+++ b/tools/perf/tests/attr/base-stat
@@ -0,0 +1,39 @@
+[event]
+fd=1
+group_fd=-1
+flags=0
+type=0
+size=96
+config=0
+sample_period=0
+sample_type=0
+read_format=3
+disabled=1
+inherit=1
+pinned=0
+exclusive=0
+exclude_user=0
+exclude_kernel=0
+exclude_hv=0
+exclude_idle=0
+mmap=0
+comm=0
+freq=0
+inherit_stat=0
+enable_on_exec=1
+task=0
+watermark=0
+precise_ip=0
+mmap_data=0
+sample_id_all=0
+exclude_host=0
+exclude_guest=1
+exclude_callchain_kernel=0
+exclude_callchain_user=0
+wakeup_events=0
+bp_type=0
+config1=0
+config2=0
+branch_sample_type=0
+sample_regs_user=0
+sample_stack_user=0
diff --git a/tools/perf/tests/attr/test-record-basic b/tools/perf/tests/attr/test-record-basic
new file mode 100644
index 000000000000..55c0428370ca
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-basic
@@ -0,0 +1,5 @@
+[config]
+command = record
+args    = kill >/dev/null 2>&1
+
+[event:base-record]
diff --git a/tools/perf/tests/attr/test-record-branch-any b/tools/perf/tests/attr/test-record-branch-any
new file mode 100644
index 000000000000..1421960ed4e9
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-branch-any
@@ -0,0 +1,8 @@
+[config]
+command = record
+args    = -b kill >/dev/null 2>&1
+
+[event:base-record]
+sample_period=4000
+sample_type=2311
+branch_sample_type=8
diff --git a/tools/perf/tests/attr/test-record-branch-filter-any b/tools/perf/tests/attr/test-record-branch-filter-any
new file mode 100644
index 000000000000..915c4df0e0c2
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-branch-filter-any
@@ -0,0 +1,8 @@
+[config]
+command = record
+args    = -j any kill >/dev/null 2>&1
+
+[event:base-record]
+sample_period=4000
+sample_type=2311
+branch_sample_type=8
diff --git a/tools/perf/tests/attr/test-record-branch-filter-any_call b/tools/perf/tests/attr/test-record-branch-filter-any_call
new file mode 100644
index 000000000000..8708dbd4f373
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-branch-filter-any_call
@@ -0,0 +1,8 @@
+[config]
+command = record
+args    = -j any_call kill >/dev/null 2>&1
+
+[event:base-record]
+sample_period=4000
+sample_type=2311
+branch_sample_type=16
diff --git a/tools/perf/tests/attr/test-record-branch-filter-any_ret b/tools/perf/tests/attr/test-record-branch-filter-any_ret
new file mode 100644
index 000000000000..0d3607a6dcbe
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-branch-filter-any_ret
@@ -0,0 +1,8 @@
+[config]
+command = record
+args    = -j any_ret kill >/dev/null 2>&1
+
+[event:base-record]
+sample_period=4000
+sample_type=2311
+branch_sample_type=32
diff --git a/tools/perf/tests/attr/test-record-branch-filter-hv b/tools/perf/tests/attr/test-record-branch-filter-hv
new file mode 100644
index 000000000000..f25526740cec
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-branch-filter-hv
@@ -0,0 +1,8 @@
+[config]
+command = record
+args    = -j hv kill >/dev/null 2>&1
+
+[event:base-record]
+sample_period=4000
+sample_type=2311
+branch_sample_type=8
diff --git a/tools/perf/tests/attr/test-record-branch-filter-ind_call b/tools/perf/tests/attr/test-record-branch-filter-ind_call
new file mode 100644
index 000000000000..e862dd179128
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-branch-filter-ind_call
@@ -0,0 +1,8 @@
+[config]
+command = record
+args    = -j ind_call kill >/dev/null 2>&1
+
+[event:base-record]
+sample_period=4000
+sample_type=2311
+branch_sample_type=64
diff --git a/tools/perf/tests/attr/test-record-branch-filter-k b/tools/perf/tests/attr/test-record-branch-filter-k
new file mode 100644
index 000000000000..182971e898f5
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-branch-filter-k
@@ -0,0 +1,8 @@
+[config]
+command = record
+args    = -j k kill >/dev/null 2>&1
+
+[event:base-record]
+sample_period=4000
+sample_type=2311
+branch_sample_type=8
diff --git a/tools/perf/tests/attr/test-record-branch-filter-u b/tools/perf/tests/attr/test-record-branch-filter-u
new file mode 100644
index 000000000000..83449ef9e687
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-branch-filter-u
@@ -0,0 +1,8 @@
+[config]
+command = record
+args    = -j u kill >/dev/null 2>&1
+
+[event:base-record]
+sample_period=4000
+sample_type=2311
+branch_sample_type=8
diff --git a/tools/perf/tests/attr/test-record-count b/tools/perf/tests/attr/test-record-count
new file mode 100644
index 000000000000..2f841de56f6b
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-count
@@ -0,0 +1,8 @@
+[config]
+command = record
+args    = -c 123 kill >/dev/null 2>&1
+
+[event:base-record]
+sample_period=123
+sample_type=7
+freq=0
diff --git a/tools/perf/tests/attr/test-record-data b/tools/perf/tests/attr/test-record-data
new file mode 100644
index 000000000000..6627c3e7534a
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-data
@@ -0,0 +1,8 @@
+[config]
+command = record
+args    = -d kill >/dev/null 2>&1
+
+[event:base-record]
+sample_period=4000
+sample_type=271
+mmap_data=1
diff --git a/tools/perf/tests/attr/test-record-freq b/tools/perf/tests/attr/test-record-freq
new file mode 100644
index 000000000000..600d0f8f2583
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-freq
@@ -0,0 +1,6 @@
+[config]
+command = record
+args    = -F 100 kill >/dev/null 2>&1
+
+[event:base-record]
+sample_period=100
diff --git a/tools/perf/tests/attr/test-record-graph-default b/tools/perf/tests/attr/test-record-graph-default
new file mode 100644
index 000000000000..833d1849d767
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-graph-default
@@ -0,0 +1,6 @@
+[config]
+command = record
+args    = -g -- kill >/dev/null 2>&1
+
+[event:base-record]
+sample_type=295
diff --git a/tools/perf/tests/attr/test-record-graph-dwarf b/tools/perf/tests/attr/test-record-graph-dwarf
new file mode 100644
index 000000000000..e93e082f5208
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-graph-dwarf
@@ -0,0 +1,10 @@
+[config]
+command = record
+args    = -g dwarf -- kill >/dev/null 2>&1
+
+[event:base-record]
+sample_type=12583
+exclude_callchain_user=1
+sample_stack_user=8192
+# TODO different for each arch, no support for that now
+sample_regs_user=*
diff --git a/tools/perf/tests/attr/test-record-graph-fp b/tools/perf/tests/attr/test-record-graph-fp
new file mode 100644
index 000000000000..7cef3743f03f
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-graph-fp
@@ -0,0 +1,6 @@
+[config]
+command = record
+args    = -g fp kill >/dev/null 2>&1
+
+[event:base-record]
+sample_type=295
diff --git a/tools/perf/tests/attr/test-record-group b/tools/perf/tests/attr/test-record-group
new file mode 100644
index 000000000000..b945f770dc9e
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-group
@@ -0,0 +1,17 @@
+[config]
+command = record
+args    = --group -e cycles,instructions kill >/dev/null 2>&1
+
+[event-1:base-record]
+fd=1
+group_fd=-1
+sample_type=327
+
+[event-2:base-record]
+fd=2
+group_fd=1
+config=1
+sample_type=327
+mmap=0
+comm=0
+enable_on_exec=0
diff --git a/tools/perf/tests/attr/test-record-group1 b/tools/perf/tests/attr/test-record-group1
new file mode 100644
index 000000000000..39bf8609538c
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-group1
@@ -0,0 +1,20 @@
+[config]
+command = record
+args    = -e '{cycles,instructions}' kill >/tmp/krava 2>&1
+
+[event-1:base-record]
+fd=1
+group_fd=-1
+sample_type=327
+
+[event-2:base-record]
+fd=2
+group_fd=1
+type=0
+config=1
+sample_type=327
+mmap=0
+comm=0
+# TODO this is disabled for --group option, enabled otherwise
+#      check why..
+enable_on_exec=1
diff --git a/tools/perf/tests/attr/test-record-no-delay b/tools/perf/tests/attr/test-record-no-delay
new file mode 100644
index 000000000000..f253b78cdbf2
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-no-delay
@@ -0,0 +1,9 @@
+[config]
+command = record
+args    = -D kill >/dev/null 2>&1
+
+[event:base-record]
+sample_period=4000
+sample_type=263
+watermark=0
+wakeup_events=1
diff --git a/tools/perf/tests/attr/test-record-no-inherit b/tools/perf/tests/attr/test-record-no-inherit
new file mode 100644
index 000000000000..9079a25cd643
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-no-inherit
@@ -0,0 +1,7 @@
+[config]
+command = record
+args    = -i kill >/dev/null 2>&1
+
+[event:base-record]
+sample_type=259
+inherit=0
diff --git a/tools/perf/tests/attr/test-record-no-samples b/tools/perf/tests/attr/test-record-no-samples
new file mode 100644
index 000000000000..d0141b2418b5
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-no-samples
@@ -0,0 +1,6 @@
+[config]
+command = record
+args    = -n kill >/dev/null 2>&1
+
+[event:base-record]
+sample_period=0
diff --git a/tools/perf/tests/attr/test-record-period b/tools/perf/tests/attr/test-record-period
new file mode 100644
index 000000000000..8abc5314fc52
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-period
@@ -0,0 +1,7 @@
+[config]
+command = record
+args    = -c 100 -P kill >/dev/null 2>&1
+
+[event:base-record]
+sample_period=100
+freq=0
diff --git a/tools/perf/tests/attr/test-record-raw b/tools/perf/tests/attr/test-record-raw
new file mode 100644
index 000000000000..4a8ef25b5f49
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-raw
@@ -0,0 +1,7 @@
+[config]
+command = record
+args    = -R kill >/dev/null 2>&1
+
+[event:base-record]
+sample_period=4000
+sample_type=1415
diff --git a/tools/perf/tests/attr/test-stat-basic b/tools/perf/tests/attr/test-stat-basic
new file mode 100644
index 000000000000..74e17881f2ba
--- /dev/null
+++ b/tools/perf/tests/attr/test-stat-basic
@@ -0,0 +1,6 @@
+[config]
+command = stat
+args    = -e cycles kill >/dev/null 2>&1
+ret     = 1
+
+[event:base-stat]
diff --git a/tools/perf/tests/attr/test-stat-default b/tools/perf/tests/attr/test-stat-default
new file mode 100644
index 000000000000..19270f54c96e
--- /dev/null
+++ b/tools/perf/tests/attr/test-stat-default
@@ -0,0 +1,64 @@
+[config]
+command = stat
+args    = kill >/dev/null 2>&1
+ret     = 1
+
+# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_TASK_CLOCK
+[event1:base-stat]
+fd=1
+type=1
+config=1
+
+# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_CONTEXT_SWITCHES
+[event2:base-stat]
+fd=2
+type=1
+config=3
+
+# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_CPU_MIGRATIONS
+[event3:base-stat]
+fd=3
+type=1
+config=4
+
+# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_PAGE_FAULTS
+[event4:base-stat]
+fd=4
+type=1
+config=2
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_CPU_CYCLES
+[event5:base-stat]
+fd=5
+type=0
+config=0
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_FRONTEND
+[event6:base-stat]
+fd=6
+type=0
+config=7
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_BACKEND
+[event7:base-stat]
+fd=7
+type=0
+config=8
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_INSTRUCTIONS
+[event8:base-stat]
+fd=8
+type=0
+config=1
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_BRANCH_INSTRUCTIONS
+[event9:base-stat]
+fd=9
+type=0
+config=4
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_BRANCH_MISSES
+[event10:base-stat]
+fd=10
+type=0
+config=5
diff --git a/tools/perf/tests/attr/test-stat-detailed-1 b/tools/perf/tests/attr/test-stat-detailed-1
new file mode 100644
index 000000000000..51426b87153b
--- /dev/null
+++ b/tools/perf/tests/attr/test-stat-detailed-1
@@ -0,0 +1,101 @@
+[config]
+command = stat
+args    = -d kill >/dev/null 2>&1
+ret     = 1
+
+
+# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_TASK_CLOCK
+[event1:base-stat]
+fd=1
+type=1
+config=1
+
+# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_CONTEXT_SWITCHES
+[event2:base-stat]
+fd=2
+type=1
+config=3
+
+# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_CPU_MIGRATIONS
+[event3:base-stat]
+fd=3
+type=1
+config=4
+
+# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_PAGE_FAULTS
+[event4:base-stat]
+fd=4
+type=1
+config=2
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_CPU_CYCLES
+[event5:base-stat]
+fd=5
+type=0
+config=0
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_FRONTEND
+[event6:base-stat]
+fd=6
+type=0
+config=7
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_BACKEND
+[event7:base-stat]
+fd=7
+type=0
+config=8
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_INSTRUCTIONS
+[event8:base-stat]
+fd=8
+type=0
+config=1
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_BRANCH_INSTRUCTIONS
+[event9:base-stat]
+fd=9
+type=0
+config=4
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_BRANCH_MISSES
+[event10:base-stat]
+fd=10
+type=0
+config=5
+
+# PERF_TYPE_HW_CACHE /
+#  PERF_COUNT_HW_CACHE_L1D                <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
+[event11:base-stat]
+fd=11
+type=3
+config=0
+
+# PERF_TYPE_HW_CACHE /
+#  PERF_COUNT_HW_CACHE_L1D                <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
+[event12:base-stat]
+fd=12
+type=3
+config=65536
+
+# PERF_TYPE_HW_CACHE /
+#  PERF_COUNT_HW_CACHE_LL                 <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
+[event13:base-stat]
+fd=13
+type=3
+config=2
+
+# PERF_TYPE_HW_CACHE,
+#  PERF_COUNT_HW_CACHE_LL                 <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
+[event14:base-stat]
+fd=14
+type=3
+config=65538
diff --git a/tools/perf/tests/attr/test-stat-detailed-2 b/tools/perf/tests/attr/test-stat-detailed-2
new file mode 100644
index 000000000000..8de5acc31c27
--- /dev/null
+++ b/tools/perf/tests/attr/test-stat-detailed-2
@@ -0,0 +1,155 @@
+[config]
+command = stat
+args    = -dd kill >/dev/null 2>&1
+ret     = 1
+
+
+# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_TASK_CLOCK
+[event1:base-stat]
+fd=1
+type=1
+config=1
+
+# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_CONTEXT_SWITCHES
+[event2:base-stat]
+fd=2
+type=1
+config=3
+
+# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_CPU_MIGRATIONS
+[event3:base-stat]
+fd=3
+type=1
+config=4
+
+# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_PAGE_FAULTS
+[event4:base-stat]
+fd=4
+type=1
+config=2
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_CPU_CYCLES
+[event5:base-stat]
+fd=5
+type=0
+config=0
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_FRONTEND
+[event6:base-stat]
+fd=6
+type=0
+config=7
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_BACKEND
+[event7:base-stat]
+fd=7
+type=0
+config=8
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_INSTRUCTIONS
+[event8:base-stat]
+fd=8
+type=0
+config=1
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_BRANCH_INSTRUCTIONS
+[event9:base-stat]
+fd=9
+type=0
+config=4
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_BRANCH_MISSES
+[event10:base-stat]
+fd=10
+type=0
+config=5
+
+# PERF_TYPE_HW_CACHE /
+#  PERF_COUNT_HW_CACHE_L1D                <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
+[event11:base-stat]
+fd=11
+type=3
+config=0
+
+# PERF_TYPE_HW_CACHE /
+#  PERF_COUNT_HW_CACHE_L1D                <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
+[event12:base-stat]
+fd=12
+type=3
+config=65536
+
+# PERF_TYPE_HW_CACHE /
+#  PERF_COUNT_HW_CACHE_LL                 <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
+[event13:base-stat]
+fd=13
+type=3
+config=2
+
+# PERF_TYPE_HW_CACHE,
+#  PERF_COUNT_HW_CACHE_LL                 <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
+[event14:base-stat]
+fd=14
+type=3
+config=65538
+
+# PERF_TYPE_HW_CACHE,
+#  PERF_COUNT_HW_CACHE_L1I                <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
+[event15:base-stat]
+fd=15
+type=3
+config=1
+
+# PERF_TYPE_HW_CACHE,
+#  PERF_COUNT_HW_CACHE_L1I                <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
+[event16:base-stat]
+fd=16
+type=3
+config=65537
+
+# PERF_TYPE_HW_CACHE,
+#  PERF_COUNT_HW_CACHE_DTLB               <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
+[event17:base-stat]
+fd=17
+type=3
+config=3
+
+# PERF_TYPE_HW_CACHE,
+#  PERF_COUNT_HW_CACHE_DTLB               <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
+[event18:base-stat]
+fd=18
+type=3
+config=65539
+
+# PERF_TYPE_HW_CACHE,
+#  PERF_COUNT_HW_CACHE_ITLB               <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
+[event19:base-stat]
+fd=19
+type=3
+config=4
+
+# PERF_TYPE_HW_CACHE,
+#  PERF_COUNT_HW_CACHE_ITLB               <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
+[event20:base-stat]
+fd=20
+type=3
+config=65540
diff --git a/tools/perf/tests/attr/test-stat-detailed-3 b/tools/perf/tests/attr/test-stat-detailed-3
new file mode 100644
index 000000000000..0a1f45bf7d79
--- /dev/null
+++ b/tools/perf/tests/attr/test-stat-detailed-3
@@ -0,0 +1,173 @@
+[config]
+command = stat
+args    = -ddd kill >/dev/null 2>&1
+ret     = 1
+
+
+# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_TASK_CLOCK
+[event1:base-stat]
+fd=1
+type=1
+config=1
+
+# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_CONTEXT_SWITCHES
+[event2:base-stat]
+fd=2
+type=1
+config=3
+
+# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_CPU_MIGRATIONS
+[event3:base-stat]
+fd=3
+type=1
+config=4
+
+# PERF_TYPE_SOFTWARE / PERF_COUNT_SW_PAGE_FAULTS
+[event4:base-stat]
+fd=4
+type=1
+config=2
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_CPU_CYCLES
+[event5:base-stat]
+fd=5
+type=0
+config=0
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_FRONTEND
+[event6:base-stat]
+fd=6
+type=0
+config=7
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_BACKEND
+[event7:base-stat]
+fd=7
+type=0
+config=8
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_INSTRUCTIONS
+[event8:base-stat]
+fd=8
+type=0
+config=1
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_BRANCH_INSTRUCTIONS
+[event9:base-stat]
+fd=9
+type=0
+config=4
+
+# PERF_TYPE_HARDWARE / PERF_COUNT_HW_BRANCH_MISSES
+[event10:base-stat]
+fd=10
+type=0
+config=5
+
+# PERF_TYPE_HW_CACHE /
+#  PERF_COUNT_HW_CACHE_L1D                <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
+[event11:base-stat]
+fd=11
+type=3
+config=0
+
+# PERF_TYPE_HW_CACHE /
+#  PERF_COUNT_HW_CACHE_L1D                <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
+[event12:base-stat]
+fd=12
+type=3
+config=65536
+
+# PERF_TYPE_HW_CACHE /
+#  PERF_COUNT_HW_CACHE_LL                 <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
+[event13:base-stat]
+fd=13
+type=3
+config=2
+
+# PERF_TYPE_HW_CACHE,
+#  PERF_COUNT_HW_CACHE_LL                 <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
+[event14:base-stat]
+fd=14
+type=3
+config=65538
+
+# PERF_TYPE_HW_CACHE,
+#  PERF_COUNT_HW_CACHE_L1I                <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
+[event15:base-stat]
+fd=15
+type=3
+config=1
+
+# PERF_TYPE_HW_CACHE,
+#  PERF_COUNT_HW_CACHE_L1I                <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
+[event16:base-stat]
+fd=16
+type=3
+config=65537
+
+# PERF_TYPE_HW_CACHE,
+#  PERF_COUNT_HW_CACHE_DTLB               <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
+[event17:base-stat]
+fd=17
+type=3
+config=3
+
+# PERF_TYPE_HW_CACHE,
+#  PERF_COUNT_HW_CACHE_DTLB               <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
+[event18:base-stat]
+fd=18
+type=3
+config=65539
+
+# PERF_TYPE_HW_CACHE,
+#  PERF_COUNT_HW_CACHE_ITLB               <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
+[event19:base-stat]
+fd=19
+type=3
+config=4
+
+# PERF_TYPE_HW_CACHE,
+#  PERF_COUNT_HW_CACHE_ITLB               <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_READ            <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
+[event20:base-stat]
+fd=20
+type=3
+config=65540
+
+# PERF_TYPE_HW_CACHE,
+#  PERF_COUNT_HW_CACHE_L1D                <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_PREFETCH        <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_ACCESS      << 16)
+[event21:base-stat]
+fd=21
+type=3
+config=512
+
+# PERF_TYPE_HW_CACHE,
+#  PERF_COUNT_HW_CACHE_L1D                <<  0  |
+# (PERF_COUNT_HW_CACHE_OP_PREFETCH        <<  8) |
+# (PERF_COUNT_HW_CACHE_RESULT_MISS        << 16)
+[event22:base-stat]
+fd=22
+type=3
+config=66048
diff --git a/tools/perf/tests/attr/test-stat-group b/tools/perf/tests/attr/test-stat-group
new file mode 100644
index 000000000000..fdc1596a8862
--- /dev/null
+++ b/tools/perf/tests/attr/test-stat-group
@@ -0,0 +1,15 @@
+[config]
+command = stat
+args    = --group -e cycles,instructions kill >/dev/null 2>&1
+ret     = 1
+
+[event-1:base-stat]
+fd=1
+group_fd=-1
+
+[event-2:base-stat]
+fd=2
+group_fd=1
+config=1
+disabled=0
+enable_on_exec=0
diff --git a/tools/perf/tests/attr/test-stat-group1 b/tools/perf/tests/attr/test-stat-group1
new file mode 100644
index 000000000000..5ae2718de864
--- /dev/null
+++ b/tools/perf/tests/attr/test-stat-group1
@@ -0,0 +1,17 @@
+[config]
+command = stat
+args    = -e '{cycles,instructions}' kill >/dev/null 2>&1
+ret     = 1
+
+[event-1:base-stat]
+fd=1
+group_fd=-1
+
+[event-2:base-stat]
+fd=2
+group_fd=1
+config=1
+# TODO both disabled and enable_on_exec are disabled for --group option,
+#      enabled otherwise, check why..
+disabled=1
+enable_on_exec=1
diff --git a/tools/perf/tests/attr/test-stat-no-inherit b/tools/perf/tests/attr/test-stat-no-inherit
new file mode 100644
index 000000000000..d54b2a1e3e28
--- /dev/null
+++ b/tools/perf/tests/attr/test-stat-no-inherit
@@ -0,0 +1,7 @@
+[config]
+command = stat
+args    = -i -e cycles kill >/dev/null 2>&1
+ret     = 1
+
+[event:base-stat]
+inherit=0
diff --git a/tools/perf/builtin-test.c b/tools/perf/tests/builtin-test.c
index a04276e81f40..5d4354e24457 100644
--- a/tools/perf/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -10,6 +10,7 @@
 #include "util/debug.h"
 #include "util/debugfs.h"
 #include "util/evlist.h"
+#include "util/machine.h"
 #include "util/parse-options.h"
 #include "util/parse-events.h"
 #include "util/symbol.h"
@@ -318,7 +319,7 @@ static int test__open_syscall_event(void)
                          nr_open_calls, evsel->counts->cpu[0].val);
                 goto out_close_fd;
         }
-        
+
         err = 0;
 out_close_fd:
         perf_evsel__close_fd(evsel, 1, threads->nr);
@@ -604,19 +605,13 @@ out_free_threads:
 #undef nsyscalls
 }
 
-static int sched__get_first_possible_cpu(pid_t pid, cpu_set_t **maskp,
-                                         size_t *sizep)
+static int sched__get_first_possible_cpu(pid_t pid, cpu_set_t *maskp)
 {
-        cpu_set_t *mask;
-        size_t size;
         int i, cpu = -1, nrcpus = 1024;
 realloc:
-        mask = CPU_ALLOC(nrcpus);
-        size = CPU_ALLOC_SIZE(nrcpus);
-        CPU_ZERO_S(size, mask);
+        CPU_ZERO(maskp);
 
-        if (sched_getaffinity(pid, size, mask) == -1) {
-                CPU_FREE(mask);
+        if (sched_getaffinity(pid, sizeof(*maskp), maskp) == -1) {
                 if (errno == EINVAL && nrcpus < (1024 << 8)) {
                         nrcpus = nrcpus << 2;
                         goto realloc;
@@ -626,19 +621,14 @@ realloc:
         }
 
         for (i = 0; i < nrcpus; i++) {
-                if (CPU_ISSET_S(i, size, mask)) {
-                        if (cpu == -1) {
+                if (CPU_ISSET(i, maskp)) {
+                        if (cpu == -1)
                                 cpu = i;
-                                *maskp = mask;
-                                *sizep = size;
-                        } else
-                                CPU_CLR_S(i, size, mask);
+                        else
+                                CPU_CLR(i, maskp);
                 }
         }
 
-        if (cpu == -1)
-                CPU_FREE(mask);
-
         return cpu;
 }
 
@@ -653,8 +643,8 @@ static int test__PERF_RECORD(void)
                 .freq       = 10,
                 .mmap_pages = 256,
         };
-        cpu_set_t *cpu_mask = NULL;
-        size_t cpu_mask_size = 0;
+        cpu_set_t cpu_mask;
+        size_t cpu_mask_size = sizeof(cpu_mask);
         struct perf_evlist *evlist = perf_evlist__new(NULL, NULL);
         struct perf_evsel *evsel;
         struct perf_sample sample;
@@ -718,8 +708,7 @@ static int test__PERF_RECORD(void)
         evsel->attr.sample_type |= PERF_SAMPLE_TIME;
         perf_evlist__config_attrs(evlist, &opts);
 
-        err = sched__get_first_possible_cpu(evlist->workload.pid, &cpu_mask,
-                                            &cpu_mask_size);
+        err = sched__get_first_possible_cpu(evlist->workload.pid, &cpu_mask);
         if (err < 0) {
                 pr_debug("sched__get_first_possible_cpu: %s\n", strerror(errno));
                 goto out_delete_evlist;
@@ -730,9 +719,9 @@ static int test__PERF_RECORD(void)
         /*
          * So that we can check perf_sample.cpu on all the samples.
          */
-        if (sched_setaffinity(evlist->workload.pid, cpu_mask_size, cpu_mask) < 0) {
+        if (sched_setaffinity(evlist->workload.pid, cpu_mask_size, &cpu_mask) < 0) {
                 pr_debug("sched_setaffinity: %s\n", strerror(errno));
-                goto out_free_cpu_mask;
+                goto out_delete_evlist;
         }
 
         /*
@@ -916,8 +905,6 @@ found_exit:
         }
 out_err:
         perf_evlist__munmap(evlist);
-out_free_cpu_mask:
-        CPU_FREE(cpu_mask);
 out_delete_evlist:
         perf_evlist__delete(evlist);
 out:
@@ -1344,8 +1331,8 @@ static int test__syscall_open_tp_fields(void)
         perf_evlist__enable(evlist);
 
         /*
-         * Generate the event:
-         */
+         * Generate the event:
+         */
         open(filename, flags);
 
         while (1) {
@@ -1455,6 +1442,10 @@ static struct test {
                 .func = test__syscall_open_tp_fields,
         },
         {
+                .desc = "struct perf_event_attr setup",
+                .func = test_attr__run,
+        },
+        {
                 .func = NULL,
         },
 };
@@ -1495,7 +1486,7 @@ static int __cmd_test(int argc, const char *argv[])
                         width = len;
                 ++i;
         }
-                
+
         i = 0;
         while (tests[i].func) {
                 int curr = i++, err;
diff --git a/tools/perf/util/dso-test-data.c b/tools/perf/tests/dso-data.c
index c6caedeb1d6b..0cd42fc9bc13 100644
--- a/tools/perf/util/dso-test-data.c
+++ b/tools/perf/tests/dso-data.c
@@ -6,6 +6,7 @@
 #include <fcntl.h>
 #include <string.h>
 
+#include "machine.h"
 #include "symbol.h"
 
 #define TEST_ASSERT_VAL(text, cond) \
diff --git a/tools/perf/util/parse-events-test.c b/tools/perf/tests/parse-events.c
index b49c2eebff33..b49c2eebff33 100644
--- a/tools/perf/util/parse-events-test.c
+++ b/tools/perf/tests/parse-events.c
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index 28f8aab73aee..5dab3ca96980 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -188,6 +188,12 @@ static void annotate_browser__draw_current_jump(struct ui_browser *browser)
         struct disasm_line *cursor = ab->selection, *target;
         struct browser_disasm_line *btarget, *bcursor;
         unsigned int from, to;
+        struct map_symbol *ms = ab->b.priv;
+        struct symbol *sym = ms->sym;
+
+        /* PLT symbols contain external offsets */
+        if (strstr(sym->name, "@plt"))
+                return;
 
         if (!cursor || !cursor->ins || !ins__is_jump(cursor->ins) ||
             !disasm_line__has_offset(cursor))
@@ -386,9 +392,8 @@ static void annotate_browser__init_asm_mode(struct annotate_browser *browser)
         browser->b.nr_entries = browser->nr_asm_entries;
 }
 
-static bool annotate_browser__callq(struct annotate_browser *browser,
-                                    int evidx, void (*timer)(void *arg),
-                                    void *arg, int delay_secs)
+static bool annotate_browser__callq(struct annotate_browser *browser, int evidx,
+                                    struct hist_browser_timer *hbt)
 {
         struct map_symbol *ms = browser->b.priv;
         struct disasm_line *dl = browser->selection;
@@ -418,7 +423,7 @@ static bool annotate_browser__callq(struct annotate_browser *browser,
         }
 
         pthread_mutex_unlock(&notes->lock);
-        symbol__tui_annotate(target, ms->map, evidx, timer, arg, delay_secs);
+        symbol__tui_annotate(target, ms->map, evidx, hbt);
         ui_browser__show_title(&browser->b, sym->name);
         return true;
 }
@@ -602,13 +607,13 @@ static void annotate_browser__update_addr_width(struct annotate_browser *browser
 }
 
 static int annotate_browser__run(struct annotate_browser *browser, int evidx,
-                                 void(*timer)(void *arg),
-                                 void *arg, int delay_secs)
+                                 struct hist_browser_timer *hbt)
 {
         struct rb_node *nd = NULL;
         struct map_symbol *ms = browser->b.priv;
         struct symbol *sym = ms->sym;
         const char *help = "Press 'h' for help on key bindings";
+        int delay_secs = hbt ? hbt->refresh : 0;
         int key;
 
         if (ui_browser__show(&browser->b, sym->name, help) < 0)
@@ -639,8 +644,8 @@ static int annotate_browser__run(struct annotate_browser *browser, int evidx,
 
                 switch (key) {
                 case K_TIMER:
-                        if (timer != NULL)
-                                timer(arg);
+                        if (hbt)
+                                hbt->timer(hbt->arg);
 
                         if (delay_secs != 0)
                                 symbol__annotate_decay_histogram(sym, evidx);
@@ -740,7 +745,7 @@ show_help:
                                         goto show_sup_ins;
                                 goto out;
                         } else if (!(annotate_browser__jump(browser) ||
-                                     annotate_browser__callq(browser, evidx, timer, arg, delay_secs))) {
+                                     annotate_browser__callq(browser, evidx, hbt))) {
 show_sup_ins:
                                 ui_helpline__puts("Actions are only available for 'callq', 'retq' & jump instructions.");
                         }
@@ -763,16 +768,21 @@ out:
 }
 
 int hist_entry__tui_annotate(struct hist_entry *he, int evidx,
-                             void(*timer)(void *arg), void *arg, int delay_secs)
+                             struct hist_browser_timer *hbt)
 {
-        return symbol__tui_annotate(he->ms.sym, he->ms.map, evidx,
-                                    timer, arg, delay_secs);
+        return symbol__tui_annotate(he->ms.sym, he->ms.map, evidx, hbt);
 }
 
 static void annotate_browser__mark_jump_targets(struct annotate_browser *browser,
                                                 size_t size)
 {
         u64 offset;
+        struct map_symbol *ms = browser->b.priv;
+        struct symbol *sym = ms->sym;
+
+        /* PLT symbols contain external offsets */
+        if (strstr(sym->name, "@plt"))
+                return;
 
         for (offset = 0; offset < size; ++offset) {
                 struct disasm_line *dl = browser->offsets[offset], *dlt;
@@ -816,8 +826,7 @@ static inline int width_jumps(int n)
 }
 
 int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx,
-                         void(*timer)(void *arg), void *arg,
-                         int delay_secs)
+                         struct hist_browser_timer *hbt)
 {
         struct disasm_line *pos, *n;
         struct annotation *notes;
@@ -899,7 +908,7 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx,
 
         annotate_browser__update_addr_width(&browser);
 
-        ret = annotate_browser__run(&browser, evidx, timer, arg, delay_secs);
+        ret = annotate_browser__run(&browser, evidx, hbt);
         list_for_each_entry_safe(pos, n, &notes->src->source, node) {
                 list_del(&pos->node);
                 disasm_line__free(pos);
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index fe622845872e..ccc4bd161420 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -11,6 +11,7 @@
 #include "../../util/pstack.h"
 #include "../../util/sort.h"
 #include "../../util/util.h"
+#include "../../arch/common.h"
 
 #include "../browser.h"
 #include "../helpline.h"
@@ -310,10 +311,11 @@ static void ui_browser__warn_lost_events(struct ui_browser *browser)
 }
 
 static int hist_browser__run(struct hist_browser *browser, const char *ev_name,
-                             void(*timer)(void *arg), void *arg, int delay_secs)
+                             struct hist_browser_timer *hbt)
 {
         int key;
         char title[160];
+        int delay_secs = hbt ? hbt->refresh : 0;
 
         browser->b.entries = &browser->hists->entries;
         browser->b.nr_entries = browser->hists->nr_entries;
@@ -330,7 +332,7 @@ static int hist_browser__run(struct hist_browser *browser, const char *ev_name,
 
                 switch (key) {
                 case K_TIMER:
-                        timer(arg);
+                        hbt->timer(hbt->arg);
                         ui_browser__update_nr_entries(&browser->b, browser->hists->nr_entries);
 
                         if (browser->hists->stats.nr_lost_warned !=
@@ -1127,11 +1129,17 @@ static inline void free_popup_options(char **options, int n)
         }
 }
 
+/* Check whether the browser is for 'top' or 'report' */
+static inline bool is_report_browser(void *timer)
+{
+        return timer == NULL;
+}
+
 static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
                                     const char *helpline, const char *ev_name,
                                     bool left_exits,
-                                    void(*timer)(void *arg), void *arg,
-                                    int delay_secs)
+                                    struct hist_browser_timer *hbt,
+                                    struct perf_session_env *env)
 {
         struct hists *hists = &evsel->hists;
         struct hist_browser *browser = hist_browser__new(hists);
@@ -1142,6 +1150,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
         int key = -1;
         char buf[64];
         char script_opt[64];
+        int delay_secs = hbt ? hbt->refresh : 0;
 
         if (browser == NULL)
                 return -1;
@@ -1164,7 +1173,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 
                 nr_options = 0;
 
-                key = hist_browser__run(browser, ev_name, timer, arg, delay_secs);
+                key = hist_browser__run(browser, ev_name, hbt);
 
                 if (browser->he_selection != NULL) {
                         thread = hist_browser__selected_thread(browser);
@@ -1214,7 +1223,9 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
                         }
                         continue;
                 case 'r':
-                        goto do_scripts;
+                        if (is_report_browser(hbt))
+                                goto do_scripts;
+                        continue;
                 case K_F1:
                 case 'h':
                 case '?':
@@ -1233,7 +1244,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
                                         "E             Expand all callchains\n"
                                         "d             Zoom into current DSO\n"
                                         "t             Zoom into current Thread\n"
-                                        "r             Run available scripts\n"
+                                        "r             Run available scripts('perf report' only)\n"
                                         "P             Print histograms to perf.hist.N\n"
                                         "V             Verbose (DSO names in callchains, etc)\n"
                                         "/             Filter symbol by name");
@@ -1358,6 +1369,9 @@ retry_popup_menu:
                         struct hist_entry *he;
                         int err;
 do_annotate:
+                        if (!objdump_path && perf_session_env__lookup_objdump(env))
+                                continue;
+
                         he = hist_browser__selected_entry(browser);
                         if (he == NULL)
                                 continue;
@@ -1380,8 +1394,7 @@ do_annotate:
                          * Don't let this be freed, say, by hists__decay_entry.
                          */
                         he->used = true;
-                        err = hist_entry__tui_annotate(he, evsel->idx,
-                                                       timer, arg, delay_secs);
+                        err = hist_entry__tui_annotate(he, evsel->idx, hbt);
                         he->used = false;
                         /*
                          * offer option to annotate the other branch source or target
@@ -1462,6 +1475,7 @@ struct perf_evsel_menu {
         struct ui_browser b;
         struct perf_evsel *selection;
         bool lost_events, lost_events_warned;
+        struct perf_session_env *env;
 };
 
 static void perf_evsel_menu__write(struct ui_browser *browser,
@@ -1504,11 +1518,12 @@ static void perf_evsel_menu__write(struct ui_browser *browser,
 
 static int perf_evsel_menu__run(struct perf_evsel_menu *menu,
                                 int nr_events, const char *help,
-                                void(*timer)(void *arg), void *arg, int delay_secs)
+                                struct hist_browser_timer *hbt)
 {
         struct perf_evlist *evlist = menu->b.priv;
         struct perf_evsel *pos;
         const char *ev_name, *title = "Available samples";
+        int delay_secs = hbt ? hbt->refresh : 0;
         int key;
 
         if (ui_browser__show(&menu->b, title,
@@ -1520,7 +1535,7 @@ static int perf_evsel_menu__run(struct perf_evsel_menu *menu,
 
                 switch (key) {
                 case K_TIMER:
-                        timer(arg);
+                        hbt->timer(hbt->arg);
 
                         if (!menu->lost_events_warned && menu->lost_events) {
                                 ui_browser__warn_lost_events(&menu->b);
@@ -1538,12 +1553,12 @@ browse_hists:
                          * Give the calling tool a chance to populate the non
                          * default evsel resorted hists tree.
                          */
-                        if (timer)
-                                timer(arg);
+                        if (hbt)
+                                hbt->timer(hbt->arg);
                         ev_name = perf_evsel__name(pos);
                         key = perf_evsel__hists_browse(pos, nr_events, help,
-                                                       ev_name, true, timer,
-                                                       arg, delay_secs);
+                                                       ev_name, true, hbt,
+                                                       menu->env);
                         ui_browser__show_title(&menu->b, title);
                         switch (key) {
                         case K_TAB:
@@ -1591,8 +1606,8 @@ out:
 
 static int __perf_evlist__tui_browse_hists(struct perf_evlist *evlist,
                                            const char *help,
-                                           void(*timer)(void *arg), void *arg,
-                                           int delay_secs)
+                                           struct hist_browser_timer *hbt,
+                                           struct perf_session_env *env)
 {
         struct perf_evsel *pos;
         struct perf_evsel_menu menu = {
@@ -1604,6 +1619,7 @@ static int __perf_evlist__tui_browse_hists(struct perf_evlist *evlist,
                         .nr_entries = evlist->nr_entries,
                         .priv       = evlist,
                 },
+                .env = env,
         };
 
         ui_helpline__push("Press ESC to exit");
@@ -1616,23 +1632,20 @@ static int __perf_evlist__tui_browse_hists(struct perf_evlist *evlist,
                         menu.b.width = line_len;
         }
 
-        return perf_evsel_menu__run(&menu, evlist->nr_entries, help, timer,
-                                    arg, delay_secs);
+        return perf_evsel_menu__run(&menu, evlist->nr_entries, help, hbt);
 }
 
 int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help,
-                                  void(*timer)(void *arg), void *arg,
-                                  int delay_secs)
+                                  struct hist_browser_timer *hbt,
+                                  struct perf_session_env *env)
 {
         if (evlist->nr_entries == 1) {
                 struct perf_evsel *first = list_entry(evlist->entries.next,
                                                       struct perf_evsel, node);
                 const char *ev_name = perf_evsel__name(first);
                 return perf_evsel__hists_browse(first, evlist->nr_entries, help,
-                                                ev_name, false, timer, arg,
-                                                delay_secs);
+                                                ev_name, false, hbt, env);
         }
 
-        return __perf_evlist__tui_browse_hists(evlist, help,
-                                               timer, arg, delay_secs);
+        return __perf_evlist__tui_browse_hists(evlist, help, hbt, env);
 }
diff --git a/tools/perf/ui/gtk/browser.c b/tools/perf/ui/gtk/browser.c
index 4125c6284114..253b6219a39e 100644
--- a/tools/perf/ui/gtk/browser.c
+++ b/tools/perf/ui/gtk/browser.c
@@ -237,9 +237,7 @@ static GtkWidget *perf_gtk__setup_statusbar(void)
 
 int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist,
                                   const char *help,
-                                  void (*timer) (void *arg)__maybe_unused,
-                                  void *arg __maybe_unused,
-                                  int delay_secs __maybe_unused)
+                                  struct hist_browser_timer *hbt __maybe_unused)
 {
         struct perf_evsel *pos;
         GtkWidget *vbox;
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index 4f5f4756faac..aa84130024d5 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -161,7 +161,7 @@ static int hpp__width_baseline(struct perf_hpp *hpp __maybe_unused)
 
 static double baseline_percent(struct hist_entry *he)
 {
-        struct hist_entry *pair = he->pair;
+        struct hist_entry *pair = hist_entry__next_pair(he);
         struct hists *pair_hists = pair ? pair->hists : NULL;
         double percent = 0.0;
 
@@ -179,7 +179,7 @@ static int hpp__color_baseline(struct perf_hpp *hpp, struct hist_entry *he)
 {
         double percent = baseline_percent(he);
 
-        if (he->pair)
+        if (hist_entry__has_pairs(he))
                 return percent_color_snprintf(hpp->buf, hpp->size, " %6.2f%%", percent);
         else
                 return scnprintf(hpp->buf, hpp->size, "        ");
@@ -190,7 +190,7 @@ static int hpp__entry_baseline(struct perf_hpp *hpp, struct hist_entry *he)
         double percent = baseline_percent(he);
         const char *fmt = symbol_conf.field_sep ? "%.2f" : " %6.2f%%";
 
-        if (he->pair || symbol_conf.field_sep)
+        if (hist_entry__has_pairs(he) || symbol_conf.field_sep)
                 return scnprintf(hpp->buf, hpp->size, fmt, percent);
         else
                 return scnprintf(hpp->buf, hpp->size, "            ");
@@ -248,7 +248,7 @@ static int hpp__width_period_baseline(struct perf_hpp *hpp __maybe_unused)
 
 static int hpp__entry_period_baseline(struct perf_hpp *hpp, struct hist_entry *he)
 {
-        struct hist_entry *pair = he->pair;
+        struct hist_entry *pair = hist_entry__next_pair(he);
         u64 period = pair ? pair->stat.period : 0;
         const char *fmt = symbol_conf.field_sep ? "%" PRIu64 : "%12" PRIu64;
 
@@ -354,7 +354,7 @@ static int hpp__width_displ(struct perf_hpp *hpp __maybe_unused)
 static int hpp__entry_displ(struct perf_hpp *hpp,
                             struct hist_entry *he)
 {
-        struct hist_entry *pair = he->pair;
+        struct hist_entry *pair = hist_entry__next_pair(he);
         long displacement = pair ? pair->position - he->position : 0;
         const char *fmt = symbol_conf.field_sep ? "%s" : "%6.6s";
         char buf[32] = " ";
diff --git a/tools/perf/util/PERF-VERSION-GEN b/tools/perf/util/PERF-VERSION-GEN
index 95264f304179..6aa34e5afdcf 100755
--- a/tools/perf/util/PERF-VERSION-GEN
+++ b/tools/perf/util/PERF-VERSION-GEN
@@ -9,18 +9,14 @@ GVF=${OUTPUT}PERF-VERSION-FILE
 LF='
 '
 
+#
 # First check if there is a .git to get the version from git describe
-# otherwise try to get the version from the kernel makefile
+# otherwise try to get the version from the kernel Makefile
+#
 if test -d ../../.git -o -f ../../.git &&
-        VN=$(git describe --match 'v[0-9].[0-9]*' --abbrev=4 HEAD 2>/dev/null) &&
-        case "$VN" in
-        *$LF*) (exit 1) ;;
-        v[0-9]*)
-                git update-index -q --refresh
-                test -z "$(git diff-index --name-only HEAD --)" ||
-                VN="$VN-dirty" ;;
-        esac
+        VN=$(git tag 2>/dev/null | tail -1 | grep -E "v[0-9].[0-9]*")
 then
+        VN=$(echo $VN"-g"$(git log -1 --abbrev=4 --pretty=format:"%h" HEAD))
         VN=$(echo "$VN" | sed -e 's/-/./g');
 else
         VN=$(MAKEFLAGS= make -sC ../.. kernelversion)
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 7a34dd18b74c..07aaeea60000 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -171,15 +171,15 @@ static int lock__parse(struct ins_operands *ops)
         if (disasm_line__parse(ops->raw, &name, &ops->locked.ops->raw) < 0)
                 goto out_free_ops;
 
-        ops->locked.ins = ins__find(name);
-        if (ops->locked.ins == NULL)
-                goto out_free_ops;
+        ops->locked.ins = ins__find(name);
+        if (ops->locked.ins == NULL)
+                goto out_free_ops;
 
-        if (!ops->locked.ins->ops)
-                return 0;
+        if (!ops->locked.ins->ops)
+                return 0;
 
-        if (ops->locked.ins->ops->parse)
-                ops->locked.ins->ops->parse(ops->locked.ops);
+        if (ops->locked.ins->ops->parse)
+                ops->locked.ins->ops->parse(ops->locked.ops);
 
         return 0;
 
@@ -401,6 +401,8 @@ static struct ins instructions[] = {
         { .name = "testb", .ops  = &mov_ops, },
         { .name = "testl", .ops  = &mov_ops, },
         { .name = "xadd",  .ops  = &mov_ops, },
+        { .name = "xbeginl", .ops  = &jump_ops, },
+        { .name = "xbeginq", .ops  = &jump_ops, },
 };
 
 static int ins__cmp(const void *name, const void *insp)
@@ -856,21 +858,68 @@ static void insert_source_line(struct rb_root *root, struct source_line *src_lin
         struct source_line *iter;
         struct rb_node **p = &root->rb_node;
         struct rb_node *parent = NULL;
+        int ret;
 
         while (*p != NULL) {
                 parent = *p;
                 iter = rb_entry(parent, struct source_line, node);
 
-                if (src_line->percent > iter->percent)
+                ret = strcmp(iter->path, src_line->path);
+                if (ret == 0) {
+                        iter->percent_sum += src_line->percent;
+                        return;
+                }
+
+                if (ret < 0)
                         p = &(*p)->rb_left;
                 else
                         p = &(*p)->rb_right;
         }
 
+        src_line->percent_sum = src_line->percent;
+
         rb_link_node(&src_line->node, parent, p);
         rb_insert_color(&src_line->node, root);
 }
 
+static void __resort_source_line(struct rb_root *root, struct source_line *src_line)
+{
+        struct source_line *iter;
+        struct rb_node **p = &root->rb_node;
+        struct rb_node *parent = NULL;
+
+        while (*p != NULL) {
+                parent = *p;
+                iter = rb_entry(parent, struct source_line, node);
+
+                if (src_line->percent_sum > iter->percent_sum)
+                        p = &(*p)->rb_left;
+                else
+                        p = &(*p)->rb_right;
+        }
+
+        rb_link_node(&src_line->node, parent, p);
+        rb_insert_color(&src_line->node, root);
+}
+
+static void resort_source_line(struct rb_root *dest_root, struct rb_root *src_root)
+{
+        struct source_line *src_line;
+        struct rb_node *node;
+
+        node = rb_first(src_root);
+        while (node) {
+                struct rb_node *next;
+
+                src_line = rb_entry(node, struct source_line, node);
+                next = rb_next(node);
+                rb_erase(node, src_root);
+
+                __resort_source_line(dest_root, src_line);
+                node = next;
+        }
+}
+
 static void symbol__free_source_line(struct symbol *sym, int len)
 {
         struct annotation *notes = symbol__annotation(sym);
@@ -895,6 +944,7 @@ static int symbol__get_source_line(struct symbol *sym, struct map *map,
         struct source_line *src_line;
         struct annotation *notes = symbol__annotation(sym);
         struct sym_hist *h = annotation__histogram(notes, evidx);
+        struct rb_root tmp_root = RB_ROOT;
 
         if (!h->sum)
                 return 0;
@@ -929,12 +979,13 @@ static int symbol__get_source_line(struct symbol *sym, struct map *map,
                         goto next;
 
                 strcpy(src_line[i].path, path);
-                insert_source_line(root, &src_line[i]);
+                insert_source_line(&tmp_root, &src_line[i]);
 
         next:
                 pclose(fp);
         }
 
+        resort_source_line(root, &tmp_root);
         return 0;
 }
 
@@ -958,7 +1009,7 @@ static void print_summary(struct rb_root *root, const char *filename)
                 char *path;
 
                 src_line = rb_entry(node, struct source_line, node);
-                percent = src_line->percent;
+                percent = src_line->percent_sum;
                 color = get_percent_color(percent);
                 path = src_line->path;
 
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index a4dd25a61a07..8eec94358a4a 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -5,6 +5,7 @@
 #include <stdint.h>
 #include "types.h"
 #include "symbol.h"
+#include "hist.h"
 #include <linux/list.h>
 #include <linux/rbtree.h>
 #include <pthread.h>
@@ -75,6 +76,7 @@ struct sym_hist {
 struct source_line {
         struct rb_node  node;
         double          percent;
+        double          percent_sum;
         char            *path;
 };
 
@@ -140,14 +142,13 @@ int symbol__tty_annotate(struct symbol *sym, struct map *map, int evidx,
 
 #ifdef NEWT_SUPPORT
 int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx,
-                         void(*timer)(void *arg), void *arg, int delay_secs);
+                         struct hist_browser_timer *hbt);
 #else
 static inline int symbol__tui_annotate(struct symbol *sym __maybe_unused,
                                        struct map *map __maybe_unused,
                                        int evidx __maybe_unused,
-                                       void(*timer)(void *arg) __maybe_unused,
-                                       void *arg __maybe_unused,
-                                       int delay_secs __maybe_unused)
+                                       struct hist_browser_timer *hbt
+                                       __maybe_unused)
 {
         return 0;
 }
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index db24a3f0c820..d6d9a465acdb 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -1,5 +1,6 @@
 #include "symbol.h"
 #include "dso.h"
+#include "machine.h"
 #include "util.h"
 #include "debug.h"
 
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 277947a669b2..7c6e73b1b7ea 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -244,6 +244,8 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template)
                         he->ms.map->referenced = true;
                 if (symbol_conf.use_callchain)
                         callchain_init(he->callchain);
+
+                INIT_LIST_HEAD(&he->pairs.node);
         }
 
         return he;
@@ -410,6 +412,7 @@ hist_entry__collapse(struct hist_entry *left, struct hist_entry *right)
 
 void hist_entry__free(struct hist_entry *he)
 {
+        free(he->branch_info);
         free(he);
 }
 
@@ -713,3 +716,100 @@ void hists__inc_nr_events(struct hists *hists, u32 type)
         ++hists->stats.nr_events[0];
         ++hists->stats.nr_events[type];
 }
+
+static struct hist_entry *hists__add_dummy_entry(struct hists *hists,
+                                                 struct hist_entry *pair)
+{
+        struct rb_node **p = &hists->entries.rb_node;
+        struct rb_node *parent = NULL;
+        struct hist_entry *he;
+        int cmp;
+
+        while (*p != NULL) {
+                parent = *p;
+                he = rb_entry(parent, struct hist_entry, rb_node);
+
+                cmp = hist_entry__cmp(pair, he);
+
+                if (!cmp)
+                        goto out;
+
+                if (cmp < 0)
+                        p = &(*p)->rb_left;
+                else
+                        p = &(*p)->rb_right;
+        }
+
+        he = hist_entry__new(pair);
+        if (he) {
+                he->stat.nr_events = 0;
+                he->stat.period    = 0;
+                he->hists          = hists;
+                rb_link_node(&he->rb_node, parent, p);
+                rb_insert_color(&he->rb_node, &hists->entries);
+                hists__inc_nr_entries(hists, he);
+        }
+out:
+        return he;
+}
+
+static struct hist_entry *hists__find_entry(struct hists *hists,
+                                            struct hist_entry *he)
+{
+        struct rb_node *n = hists->entries.rb_node;
+
+        while (n) {
+                struct hist_entry *iter = rb_entry(n, struct hist_entry, rb_node);
+                int64_t cmp = hist_entry__cmp(he, iter);
+
+                if (cmp < 0)
+                        n = n->rb_left;
+                else if (cmp > 0)
+                        n = n->rb_right;
+                else
+                        return iter;
+        }
+
+        return NULL;
+}
+
+/*
+ * Look for pairs to link to the leader buckets (hist_entries):
+ */
+void hists__match(struct hists *leader, struct hists *other)
+{
+        struct rb_node *nd;
+        struct hist_entry *pos, *pair;
+
+        for (nd = rb_first(&leader->entries); nd; nd = rb_next(nd)) {
+                pos  = rb_entry(nd, struct hist_entry, rb_node);
+                pair = hists__find_entry(other, pos);
+
+                if (pair)
+                        hist__entry_add_pair(pos, pair);
+        }
+}
+
+/*
+ * Look for entries in the other hists that are not present in the leader, if
+ * we find them, just add a dummy entry on the leader hists, with period=0,
+ * nr_events=0, to serve as the list header.
+ */
+int hists__link(struct hists *leader, struct hists *other)
+{
+        struct rb_node *nd;
+        struct hist_entry *pos, *pair;
+
+        for (nd = rb_first(&other->entries); nd; nd = rb_next(nd)) {
+                pos = rb_entry(nd, struct hist_entry, rb_node);
+
+                if (!hist_entry__has_pairs(pos)) {
+                        pair = hists__add_dummy_entry(leader, pos);
+                        if (pair == NULL)
+                                return -1;
+                        hist__entry_add_pair(pair, pos);
+                }
+        }
+
+        return 0;
+}
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index b87460971736..1278c2c72a96 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -4,6 +4,7 @@
 #include <linux/types.h>
 #include <pthread.h>
 #include "callchain.h"
+#include "header.h"
 
 extern struct callchain_param callchain_param;
 
@@ -114,6 +115,9 @@ bool hists__new_col_len(struct hists *self, enum hist_column col, u16 len);
 void hists__reset_col_len(struct hists *hists);
 void hists__calc_col_len(struct hists *hists, struct hist_entry *he);
 
+void hists__match(struct hists *leader, struct hists *other);
+int hists__link(struct hists *leader, struct hists *other);
+
 struct perf_hpp {
         char *buf;
         size_t size;
@@ -157,22 +161,27 @@ int hist_entry__period_snprintf(struct perf_hpp *hpp, struct hist_entry *he,
 
 struct perf_evlist;
 
+struct hist_browser_timer {
+        void (*timer)(void *arg);
+        void *arg;
+        int refresh;
+};
+
 #ifdef NEWT_SUPPORT
 #include "../ui/keysyms.h"
 int hist_entry__tui_annotate(struct hist_entry *he, int evidx,
-                             void(*timer)(void *arg), void *arg, int delay_secs);
+                             struct hist_browser_timer *hbt);
 
 int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help,
-                                  void(*timer)(void *arg), void *arg,
-                                  int refresh);
+                                  struct hist_browser_timer *hbt,
+                                  struct perf_session_env *env);
 int script_browse(const char *script_opt);
 #else
 static inline
 int perf_evlist__tui_browse_hists(struct perf_evlist *evlist __maybe_unused,
                                   const char *help __maybe_unused,
-                                  void(*timer)(void *arg) __maybe_unused,
-                                  void *arg __maybe_unused,
-                                  int refresh __maybe_unused)
+                                  struct hist_browser_timer *hbt __maybe_unused,
+                                  struct perf_session_env *env __maybe_unused)
 {
         return 0;
 }
@@ -180,10 +189,8 @@ int perf_evlist__tui_browse_hists(struct perf_evlist *evlist __maybe_unused,
 static inline int hist_entry__tui_annotate(struct hist_entry *self
                                            __maybe_unused,
                                            int evidx __maybe_unused,
-                                           void(*timer)(void *arg)
-                                           __maybe_unused,
-                                           void *arg __maybe_unused,
-                                           int delay_secs __maybe_unused)
+                                           struct hist_browser_timer *hbt
+                                           __maybe_unused)
 {
         return 0;
 }
@@ -199,15 +206,12 @@ static inline int script_browse(const char *script_opt)
 
 #ifdef GTK2_SUPPORT
 int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist, const char *help,
-                                  void(*timer)(void *arg), void *arg,
-                                  int refresh);
+                                  struct hist_browser_timer *hbt __maybe_unused);
 #else
 static inline
 int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist __maybe_unused,
                                   const char *help __maybe_unused,
-                                  void(*timer)(void *arg) __maybe_unused,
-                                  void *arg __maybe_unused,
-                                  int refresh __maybe_unused)
+                                  struct hist_browser_timer *hbt __maybe_unused)
 {
         return 0;
 }
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 502eec0d4773..1f09d0581e6b 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -2,9 +2,192 @@
 #include "event.h"
 #include "machine.h"
 #include "map.h"
+#include "strlist.h"
 #include "thread.h"
 #include <stdbool.h>
 
+int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
+{
+        map_groups__init(&machine->kmaps);
+        RB_CLEAR_NODE(&machine->rb_node);
+        INIT_LIST_HEAD(&machine->user_dsos);
+        INIT_LIST_HEAD(&machine->kernel_dsos);
+
+        machine->threads = RB_ROOT;
+        INIT_LIST_HEAD(&machine->dead_threads);
+        machine->last_match = NULL;
+
+        machine->kmaps.machine = machine;
+        machine->pid = pid;
+
+        machine->root_dir = strdup(root_dir);
+        if (machine->root_dir == NULL)
+                return -ENOMEM;
+
+        if (pid != HOST_KERNEL_ID) {
+                struct thread *thread = machine__findnew_thread(machine, pid);
+                char comm[64];
+
+                if (thread == NULL)
+                        return -ENOMEM;
+
+                snprintf(comm, sizeof(comm), "[guest/%d]", pid);
+                thread__set_comm(thread, comm);
+        }
+
+        return 0;
+}
+
+static void dsos__delete(struct list_head *dsos)
+{
+        struct dso *pos, *n;
+
+        list_for_each_entry_safe(pos, n, dsos, node) {
+                list_del(&pos->node);
+                dso__delete(pos);
+        }
+}
+
+void machine__exit(struct machine *machine)
+{
+        map_groups__exit(&machine->kmaps);
+        dsos__delete(&machine->user_dsos);
+        dsos__delete(&machine->kernel_dsos);
+        free(machine->root_dir);
+        machine->root_dir = NULL;
+}
+
+void machine__delete(struct machine *machine)
+{
+        machine__exit(machine);
+        free(machine);
+}
+
+struct machine *machines__add(struct rb_root *machines, pid_t pid,
+                              const char *root_dir)
+{
+        struct rb_node **p = &machines->rb_node;
+        struct rb_node *parent = NULL;
+        struct machine *pos, *machine = malloc(sizeof(*machine));
+
+        if (machine == NULL)
+                return NULL;
+
+        if (machine__init(machine, root_dir, pid) != 0) {
+                free(machine);
+                return NULL;
+        }
+
+        while (*p != NULL) {
+                parent = *p;
+                pos = rb_entry(parent, struct machine, rb_node);
+                if (pid < pos->pid)
+                        p = &(*p)->rb_left;
+                else
+                        p = &(*p)->rb_right;
+        }
+
+        rb_link_node(&machine->rb_node, parent, p);
+        rb_insert_color(&machine->rb_node, machines);
+
+        return machine;
+}
+
+struct machine *machines__find(struct rb_root *machines, pid_t pid)
+{
+        struct rb_node **p = &machines->rb_node;
+        struct rb_node *parent = NULL;
+        struct machine *machine;
+        struct machine *default_machine = NULL;
+
+        while (*p != NULL) {
+                parent = *p;
+                machine = rb_entry(parent, struct machine, rb_node);
+                if (pid < machine->pid)
+                        p = &(*p)->rb_left;
+                else if (pid > machine->pid)
+                        p = &(*p)->rb_right;
+                else
+                        return machine;
+                if (!machine->pid)
+                        default_machine = machine;
+        }
+
+        return default_machine;
+}
+
+struct machine *machines__findnew(struct rb_root *machines, pid_t pid)
+{
+        char path[PATH_MAX];
+        const char *root_dir = "";
+        struct machine *machine = machines__find(machines, pid);
+
+        if (machine && (machine->pid == pid))
+                goto out;
+
+        if ((pid != HOST_KERNEL_ID) &&
+            (pid != DEFAULT_GUEST_KERNEL_ID) &&
+            (symbol_conf.guestmount)) {
+                sprintf(path, "%s/%d", symbol_conf.guestmount, pid);
+                if (access(path, R_OK)) {
+                        static struct strlist *seen;
+
+                        if (!seen)
+                                seen = strlist__new(true, NULL);
+
+                        if (!strlist__has_entry(seen, path)) {
+                                pr_err("Can't access file %s\n", path);
+                                strlist__add(seen, path);
+                        }
+                        machine = NULL;
+                        goto out;
+                }
+                root_dir = path;
+        }
+
+        machine = machines__add(machines, pid, root_dir);
+out:
+        return machine;
+}
+
+void machines__process(struct rb_root *machines,
+                       machine__process_t process, void *data)
+{
+        struct rb_node *nd;
+
+        for (nd = rb_first(machines); nd; nd = rb_next(nd)) {
+                struct machine *pos = rb_entry(nd, struct machine, rb_node);
+                process(pos, data);
+        }
+}
+
+char *machine__mmap_name(struct machine *machine, char *bf, size_t size)
+{
+        if (machine__is_host(machine))
+                snprintf(bf, size, "[%s]", "kernel.kallsyms");
+        else if (machine__is_default_guest(machine))
+                snprintf(bf, size, "[%s]", "guest.kernel.kallsyms");
+        else {
+                snprintf(bf, size, "[%s.%d]", "guest.kernel.kallsyms",
+                         machine->pid);
+        }
+
+        return bf;
+}
+
+void machines__set_id_hdr_size(struct rb_root *machines, u16 id_hdr_size)
+{
+        struct rb_node *node;
+        struct machine *machine;
+
+        for (node = rb_first(machines); node; node = rb_next(node)) {
+                machine = rb_entry(node, struct machine, rb_node);
+                machine->id_hdr_size = id_hdr_size;
+        }
+
+        return;
+}
+
 static struct thread *__machine__findnew_thread(struct machine *machine, pid_t pid,
                                                 bool create)
 {
@@ -84,15 +267,19 @@ int machine__process_lost_event(struct machine *machine __maybe_unused,
 static void machine__set_kernel_mmap_len(struct machine *machine,
                                          union perf_event *event)
 {
-        machine->vmlinux_maps[MAP__FUNCTION]->start = event->mmap.start;
-        machine->vmlinux_maps[MAP__FUNCTION]->end   = (event->mmap.start +
-                                                       event->mmap.len);
-        /*
-         * Be a bit paranoid here, some perf.data file came with
-         * a zero sized synthesized MMAP event for the kernel.
-         */
-        if (machine->vmlinux_maps[MAP__FUNCTION]->end == 0)
-                machine->vmlinux_maps[MAP__FUNCTION]->end = ~0ULL;
+        int i;
+
+        for (i = 0; i < MAP__NR_TYPES; i++) {
+                machine->vmlinux_maps[i]->start = event->mmap.start;
+                machine->vmlinux_maps[i]->end   = (event->mmap.start +
+                                                   event->mmap.len);
+                /*
+                 * Be a bit paranoid here, some perf.data file came with
+                 * a zero sized synthesized MMAP event for the kernel.
+                 */
+                if (machine->vmlinux_maps[i]->end == 0)
+                        machine->vmlinux_maps[i]->end = ~0ULL;
+        }
 }
 
 static int machine__process_kernel_mmap_event(struct machine *machine,
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index df152f1768be..b7cde7467d55 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -2,11 +2,40 @@
 #define __PERF_MACHINE_H
 
 #include <sys/types.h>
+#include <linux/rbtree.h>
+#include "map.h"
 
+struct branch_stack;
+struct perf_evsel;
+struct perf_sample;
+struct symbol;
 struct thread;
-struct machine;
 union perf_event;
 
+/* Native host kernel uses -1 as pid index in machine */
+#define HOST_KERNEL_ID                  (-1)
+#define DEFAULT_GUEST_KERNEL_ID         (0)
+
+struct machine {
+        struct rb_node    rb_node;
+        pid_t             pid;
+        u16               id_hdr_size;
+        char              *root_dir;
+        struct rb_root    threads;
+        struct list_head  dead_threads;
+        struct thread     *last_match;
+        struct list_head  user_dsos;
+        struct list_head  kernel_dsos;
+        struct map_groups kmaps;
+        struct map        *vmlinux_maps[MAP__NR_TYPES];
+};
+
+static inline
+struct map *machine__kernel_map(struct machine *machine, enum map_type type)
+{
+        return machine->vmlinux_maps[type];
+}
+
 struct thread *machine__find_thread(struct machine *machine, pid_t pid);
 
 int machine__process_comm_event(struct machine *machine, union perf_event *event);
@@ -16,4 +45,104 @@ int machine__process_lost_event(struct machine *machine, union perf_event *event
 int machine__process_mmap_event(struct machine *machine, union perf_event *event);
 int machine__process_event(struct machine *machine, union perf_event *event);
 
+typedef void (*machine__process_t)(struct machine *machine, void *data);
+
+void machines__process(struct rb_root *machines,
+                       machine__process_t process, void *data);
+
+struct machine *machines__add(struct rb_root *machines, pid_t pid,
+                              const char *root_dir);
+struct machine *machines__find_host(struct rb_root *machines);
+struct machine *machines__find(struct rb_root *machines, pid_t pid);
+struct machine *machines__findnew(struct rb_root *machines, pid_t pid);
+
+void machines__set_id_hdr_size(struct rb_root *machines, u16 id_hdr_size);
+char *machine__mmap_name(struct machine *machine, char *bf, size_t size);
+
+int machine__init(struct machine *machine, const char *root_dir, pid_t pid);
+void machine__exit(struct machine *machine);
+void machine__delete(struct machine *machine);
+
+
+struct branch_info *machine__resolve_bstack(struct machine *machine,
+                                            struct thread *thread,
+                                            struct branch_stack *bs);
+int machine__resolve_callchain(struct machine *machine,
+                               struct perf_evsel *evsel,
+                               struct thread *thread,
+                               struct perf_sample *sample,
+                               struct symbol **parent);
+
+/*
+ * Default guest kernel is defined by parameter --guestkallsyms
+ * and --guestmodules
+ */
+static inline bool machine__is_default_guest(struct machine *machine)
+{
+        return machine ? machine->pid == DEFAULT_GUEST_KERNEL_ID : false;
+}
+
+static inline bool machine__is_host(struct machine *machine)
+{
+        return machine ? machine->pid == HOST_KERNEL_ID : false;
+}
+
+struct thread *machine__findnew_thread(struct machine *machine, pid_t pid);
+void machine__remove_thread(struct machine *machine, struct thread *th);
+
+size_t machine__fprintf(struct machine *machine, FILE *fp);
+
+static inline
+struct symbol *machine__find_kernel_symbol(struct machine *machine,
+                                           enum map_type type, u64 addr,
+                                           struct map **mapp,
+                                           symbol_filter_t filter)
+{
+        return map_groups__find_symbol(&machine->kmaps, type, addr,
+                                       mapp, filter);
+}
+
+static inline
+struct symbol *machine__find_kernel_function(struct machine *machine, u64 addr,
+                                             struct map **mapp,
+                                             symbol_filter_t filter)
+{
+        return machine__find_kernel_symbol(machine, MAP__FUNCTION, addr,
+                                           mapp, filter);
+}
+
+static inline
+struct symbol *machine__find_kernel_function_by_name(struct machine *machine,
+                                                     const char *name,
+                                                     struct map **mapp,
+                                                     symbol_filter_t filter)
+{
+        return map_groups__find_function_by_name(&machine->kmaps, name, mapp,
+                                                 filter);
+}
+
+struct map *machine__new_module(struct machine *machine, u64 start,
+                                const char *filename);
+
+int machine__load_kallsyms(struct machine *machine, const char *filename,
+                           enum map_type type, symbol_filter_t filter);
+int machine__load_vmlinux_path(struct machine *machine, enum map_type type,
+                               symbol_filter_t filter);
+
+size_t machine__fprintf_dsos_buildid(struct machine *machine,
+                                     FILE *fp, bool with_hits);
+size_t machines__fprintf_dsos(struct rb_root *machines, FILE *fp);
+size_t machines__fprintf_dsos_buildid(struct rb_root *machines,
+                                      FILE *fp, bool with_hits);
+
+void machine__destroy_kernel_maps(struct machine *machine);
+int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel);
+int machine__create_kernel_maps(struct machine *machine);
+
+int machines__create_kernel_maps(struct rb_root *machines, pid_t pid);
+int machines__create_guest_kernel_maps(struct rb_root *machines);
+void machines__destroy_guest_kernel_maps(struct rb_root *machines);
+
+size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp);
+
 #endif /* __PERF_MACHINE_H */
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 9b40c444039c..0328d45c4f2a 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -24,7 +24,7 @@ static inline int is_anon_memory(const char *filename)
 
 static inline int is_no_dso_memory(const char *filename)
 {
-        return !strcmp(filename, "[stack]") ||
+        return !strncmp(filename, "[stack", 6) ||
                !strcmp(filename, "[heap]");
 }
 
@@ -590,182 +590,3 @@ struct map *maps__find(struct rb_root *maps, u64 ip)
 
         return NULL;
 }
-
-int machine__init(struct machine *self, const char *root_dir, pid_t pid)
-{
-        map_groups__init(&self->kmaps);
-        RB_CLEAR_NODE(&self->rb_node);
-        INIT_LIST_HEAD(&self->user_dsos);
-        INIT_LIST_HEAD(&self->kernel_dsos);
-
-        self->threads = RB_ROOT;
-        INIT_LIST_HEAD(&self->dead_threads);
-        self->last_match = NULL;
-
-        self->kmaps.machine = self;
-        self->pid           = pid;
-        self->root_dir      = strdup(root_dir);
-        if (self->root_dir == NULL)
-                return -ENOMEM;
-
-        if (pid != HOST_KERNEL_ID) {
-                struct thread *thread = machine__findnew_thread(self, pid);
-                char comm[64];
-
-                if (thread == NULL)
-                        return -ENOMEM;
-
-                snprintf(comm, sizeof(comm), "[guest/%d]", pid);
-                thread__set_comm(thread, comm);
-        }
-
-        return 0;
-}
-
-static void dsos__delete(struct list_head *self)
-{
-        struct dso *pos, *n;
-
-        list_for_each_entry_safe(pos, n, self, node) {
-                list_del(&pos->node);
-                dso__delete(pos);
-        }
-}
-
-void machine__exit(struct machine *self)
-{
-        map_groups__exit(&self->kmaps);
-        dsos__delete(&self->user_dsos);
-        dsos__delete(&self->kernel_dsos);
-        free(self->root_dir);
-        self->root_dir = NULL;
-}
-
-void machine__delete(struct machine *self)
-{
-        machine__exit(self);
-        free(self);
-}
-
-struct machine *machines__add(struct rb_root *self, pid_t pid,
-                              const char *root_dir)
-{
-        struct rb_node **p = &self->rb_node;
-        struct rb_node *parent = NULL;
-        struct machine *pos, *machine = malloc(sizeof(*machine));
-
-        if (!machine)
-                return NULL;
-
-        if (machine__init(machine, root_dir, pid) != 0) {
-                free(machine);
-                return NULL;
-        }
-
-        while (*p != NULL) {
-                parent = *p;
-                pos = rb_entry(parent, struct machine, rb_node);
-                if (pid < pos->pid)
-                        p = &(*p)->rb_left;
-                else
-                        p = &(*p)->rb_right;
-        }
-
-        rb_link_node(&machine->rb_node, parent, p);
-        rb_insert_color(&machine->rb_node, self);
-
-        return machine;
-}
-
-struct machine *machines__find(struct rb_root *self, pid_t pid)
-{
-        struct rb_node **p = &self->rb_node;
-        struct rb_node *parent = NULL;
-        struct machine *machine;
-        struct machine *default_machine = NULL;
-
-        while (*p != NULL) {
-                parent = *p;
-                machine = rb_entry(parent, struct machine, rb_node);
-                if (pid < machine->pid)
-                        p = &(*p)->rb_left;
-                else if (pid > machine->pid)
-                        p = &(*p)->rb_right;
-                else
-                        return machine;
-                if (!machine->pid)
-                        default_machine = machine;
-        }
-
-        return default_machine;
-}
-
-struct machine *machines__findnew(struct rb_root *self, pid_t pid)
-{
-        char path[PATH_MAX];
-        const char *root_dir = "";
-        struct machine *machine = machines__find(self, pid);
-
-        if (machine && (machine->pid == pid))
-                goto out;
-
-        if ((pid != HOST_KERNEL_ID) &&
-            (pid != DEFAULT_GUEST_KERNEL_ID) &&
-            (symbol_conf.guestmount)) {
-                sprintf(path, "%s/%d", symbol_conf.guestmount, pid);
-                if (access(path, R_OK)) {
-                        static struct strlist *seen;
-
-                        if (!seen)
-                                seen = strlist__new(true, NULL);
-
-                        if (!strlist__has_entry(seen, path)) {
-                                pr_err("Can't access file %s\n", path);
-                                strlist__add(seen, path);
-                        }
-                        machine = NULL;
-                        goto out;
-                }
-                root_dir = path;
-        }
-
-        machine = machines__add(self, pid, root_dir);
-
-out:
-        return machine;
-}
-
-void machines__process(struct rb_root *self, machine__process_t process, void *data)
-{
-        struct rb_node *nd;
-
-        for (nd = rb_first(self); nd; nd = rb_next(nd)) {
-                struct machine *pos = rb_entry(nd, struct machine, rb_node);
-                process(pos, data);
-        }
-}
-
-char *machine__mmap_name(struct machine *self, char *bf, size_t size)
-{
-        if (machine__is_host(self))
-                snprintf(bf, size, "[%s]", "kernel.kallsyms");
-        else if (machine__is_default_guest(self))
-                snprintf(bf, size, "[%s]", "guest.kernel.kallsyms");
-        else
-                snprintf(bf, size, "[%s.%d]", "guest.kernel.kallsyms", self->pid);
-
-        return bf;
-}
-
-void machines__set_id_hdr_size(struct rb_root *machines, u16 id_hdr_size)
-{
-        struct rb_node *node;
-        struct machine *machine;
-
-        for (node = rb_first(machines); node; node = rb_next(node)) {
-                machine = rb_entry(node, struct machine, rb_node);
-                machine->id_hdr_size = id_hdr_size;
-        }
-
-        return;
-}
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index d2250fc97e25..bcb39e2a6965 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -57,30 +57,6 @@ struct map_groups {
         struct machine   *machine;
 };
 
-/* Native host kernel uses -1 as pid index in machine */
-#define HOST_KERNEL_ID                  (-1)
-#define DEFAULT_GUEST_KERNEL_ID         (0)
-
-struct machine {
-        struct rb_node    rb_node;
-        pid_t             pid;
-        u16               id_hdr_size;
-        char              *root_dir;
-        struct rb_root    threads;
-        struct list_head  dead_threads;
-        struct thread     *last_match;
-        struct list_head  user_dsos;
-        struct list_head  kernel_dsos;
-        struct map_groups kmaps;
-        struct map        *vmlinux_maps[MAP__NR_TYPES];
-};
-
-static inline
-struct map *machine__kernel_map(struct machine *self, enum map_type type)
-{
-        return self->vmlinux_maps[type];
-}
-
 static inline struct kmap *map__kmap(struct map *self)
 {
         return (struct kmap *)(self + 1);
@@ -143,44 +119,9 @@ int map_groups__clone(struct map_groups *mg,
 size_t map_groups__fprintf(struct map_groups *mg, int verbose, FILE *fp);
 size_t map_groups__fprintf_maps(struct map_groups *mg, int verbose, FILE *fp);
 
-typedef void (*machine__process_t)(struct machine *self, void *data);
-
-void machines__process(struct rb_root *self, machine__process_t process, void *data);
-struct machine *machines__add(struct rb_root *self, pid_t pid,
-                              const char *root_dir);
-struct machine *machines__find_host(struct rb_root *self);
-struct machine *machines__find(struct rb_root *self, pid_t pid);
-struct machine *machines__findnew(struct rb_root *self, pid_t pid);
-void machines__set_id_hdr_size(struct rb_root *self, u16 id_hdr_size);
-char *machine__mmap_name(struct machine *self, char *bf, size_t size);
-int machine__init(struct machine *self, const char *root_dir, pid_t pid);
-void machine__exit(struct machine *self);
-void machine__delete(struct machine *self);
-
-struct perf_evsel;
-struct perf_sample;
-int machine__resolve_callchain(struct machine *machine,
-                               struct perf_evsel *evsel,
-                               struct thread *thread,
-                               struct perf_sample *sample,
-                               struct symbol **parent);
 int maps__set_kallsyms_ref_reloc_sym(struct map **maps, const char *symbol_name,
                                      u64 addr);
 
-/*
- * Default guest kernel is defined by parameter --guestkallsyms
- * and --guestmodules
- */
-static inline bool machine__is_default_guest(struct machine *self)
-{
-        return self ? self->pid == DEFAULT_GUEST_KERNEL_ID : false;
-}
-
-static inline bool machine__is_host(struct machine *self)
-{
-        return self ? self->pid == HOST_KERNEL_ID : false;
-}
-
 static inline void map_groups__insert(struct map_groups *mg, struct map *map)
 {
         maps__insert(&mg->maps[map->type], map);
@@ -209,29 +150,6 @@ struct symbol *map_groups__find_symbol_by_name(struct map_groups *mg,
                                                struct map **mapp,
                                                symbol_filter_t filter);
 
-
-struct thread *machine__findnew_thread(struct machine *machine, pid_t pid);
-void machine__remove_thread(struct machine *machine, struct thread *th);
-
-size_t machine__fprintf(struct machine *machine, FILE *fp);
-
-static inline
-struct symbol *machine__find_kernel_symbol(struct machine *self,
-                                           enum map_type type, u64 addr,
-                                           struct map **mapp,
-                                           symbol_filter_t filter)
-{
-        return map_groups__find_symbol(&self->kmaps, type, addr, mapp, filter);
-}
-
-static inline
-struct symbol *machine__find_kernel_function(struct machine *self, u64 addr,
-                                             struct map **mapp,
-                                             symbol_filter_t filter)
-{
-        return machine__find_kernel_symbol(self, MAP__FUNCTION, addr, mapp, filter);
-}
-
 static inline
 struct symbol *map_groups__find_function_by_name(struct map_groups *mg,
                                                  const char *name, struct map **mapp,
@@ -240,22 +158,11 @@ struct symbol *map_groups__find_function_by_name(struct map_groups *mg,
         return map_groups__find_symbol_by_name(mg, MAP__FUNCTION, name, mapp, filter);
 }
 
-static inline
-struct symbol *machine__find_kernel_function_by_name(struct machine *self,
-                                                     const char *name,
-                                                     struct map **mapp,
-                                                     symbol_filter_t filter)
-{
-        return map_groups__find_function_by_name(&self->kmaps, name, mapp,
-                                                 filter);
-}
-
 int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map,
                                    int verbose, FILE *fp);
 
 struct map *map_groups__find_by_name(struct map_groups *mg,
                                      enum map_type type, const char *name);
-struct map *machine__new_module(struct machine *self, u64 start, const char *filename);
 
 void map_groups__flush(struct map_groups *mg);
 
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index c87efc12579d..66959fab6634 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -81,6 +81,7 @@ num_dec		[0-9]+
 num_hex         0x[a-fA-F0-9]+
 num_raw_hex     [a-fA-F0-9]+
 name            [a-zA-Z_*?][a-zA-Z0-9_*?]*
+name_minus      [a-zA-Z_*?][a-zA-Z0-9\-_*?]*
 modifier_event  [ukhpGH]{1,8}
 modifier_bp     [rwx]{1,3}
 
@@ -168,6 +169,7 @@ period			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD); }
 branch_type             { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE); }
 ,                       { return ','; }
 "/"                     { BEGIN(INITIAL); return '/'; }
+{name_minus}            { return str(yyscanner, PE_NAME); }
 }
 
 mem:                    { BEGIN(mem); return PE_PREFIX_MEM; }
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index dd6426163ba6..18d1222b05a2 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -4,6 +4,7 @@
 #include "hist.h"
 #include "event.h"
 #include "header.h"
+#include "machine.h"
 #include "symbol.h"
 #include "thread.h"
 #include <linux/rbtree.h>
@@ -68,10 +69,6 @@ int perf_session__resolve_callchain(struct perf_session *self, struct perf_evsel
                                     struct ip_callchain *chain,
                                     struct symbol **parent);
 
-struct branch_info *machine__resolve_bstack(struct machine *self,
-                                            struct thread *thread,
-                                            struct branch_stack *bs);
-
 bool perf_session__has_traces(struct perf_session *self, const char *msg);
 
 void mem_bswap_64(void *src, int byte_size);
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 13761d83a5a0..b4e8c3ba559d 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -77,6 +77,10 @@ struct hist_entry_diff {
 struct hist_entry {
         struct rb_node          rb_node_in;
         struct rb_node          rb_node;
+        union {
+                struct list_head node;
+                struct list_head head;
+        } pairs;
         struct he_stat          stat;
         struct map_symbol       ms;
         struct thread           *thread;
@@ -96,15 +100,30 @@ struct hist_entry {
         char                    *srcline;
         struct symbol           *parent;
         unsigned long           position;
-        union {
-                struct hist_entry *pair;
-                struct rb_root    sorted_chain;
-        };
+        struct rb_root          sorted_chain;
         struct branch_info      *branch_info;
         struct hists            *hists;
         struct callchain_root   callchain[0];
 };
 
+static inline bool hist_entry__has_pairs(struct hist_entry *he)
+{
+        return !list_empty(&he->pairs.node);
+}
+
+static inline struct hist_entry *hist_entry__next_pair(struct hist_entry *he)
+{
+        if (hist_entry__has_pairs(he))
+                return list_entry(he->pairs.node.next, struct hist_entry, pairs.node);
+        return NULL;
+}
+
+static inline void hist__entry_add_pair(struct hist_entry *he,
+                                        struct hist_entry *pair)
+{
+        list_add_tail(&he->pairs.head, &pair->pairs.node);
+}
+
 enum sort_type {
         SORT_PID,
         SORT_COMM,
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 624c65e6ab98..295f8d4feedf 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -12,6 +12,7 @@
 #include "build-id.h"
 #include "util.h"
 #include "debug.h"
+#include "machine.h"
 #include "symbol.h"
 #include "strlist.h"
 
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 863b05bea5ff..04ccf2962080 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -200,16 +200,6 @@ int dso__load_vmlinux_path(struct dso *dso, struct map *map,
                            symbol_filter_t filter);
 int dso__load_kallsyms(struct dso *dso, const char *filename, struct map *map,
                        symbol_filter_t filter);
-int machine__load_kallsyms(struct machine *machine, const char *filename,
-                           enum map_type type, symbol_filter_t filter);
-int machine__load_vmlinux_path(struct machine *machine, enum map_type type,
-                               symbol_filter_t filter);
-
-size_t machine__fprintf_dsos_buildid(struct machine *machine,
-                                     FILE *fp, bool with_hits);
-size_t machines__fprintf_dsos(struct rb_root *machines, FILE *fp);
-size_t machines__fprintf_dsos_buildid(struct rb_root *machines,
-                                      FILE *fp, bool with_hits);
 
 struct symbol *dso__find_symbol(struct dso *dso, enum map_type type,
                                 u64 addr);
@@ -224,14 +214,6 @@ int kallsyms__parse(const char *filename, void *arg,
 int filename__read_debuglink(const char *filename, char *debuglink,
                              size_t size);
 
-void machine__destroy_kernel_maps(struct machine *machine);
-int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel);
-int machine__create_kernel_maps(struct machine *machine);
-
-int machines__create_kernel_maps(struct rb_root *machines, pid_t pid);
-int machines__create_guest_kernel_maps(struct rb_root *machines);
-void machines__destroy_guest_kernel_maps(struct rb_root *machines);
-
 int symbol__init(void);
 void symbol__exit(void);
 void symbol__elf_init(void);
@@ -242,8 +224,6 @@ size_t symbol__fprintf_symname(const struct symbol *sym, FILE *fp);
 size_t symbol__fprintf(struct symbol *sym, FILE *fp);
 bool symbol_type__is_a(char symbol_type, enum map_type map_type);
 
-size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp);
-
 int dso__test_data(void);
 int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
                   struct symsrc *runtime_ss, symbol_filter_t filter,