55 files changed, 724 insertions, 436 deletions

diff --git a/tools/perf/util/include/asm/bug.h b/tools/include/asm/bug.h
index 7fcc6810adc2..9e5f4846967f 100644
--- a/tools/perf/util/include/asm/bug.h
+++ b/tools/include/asm/bug.h
@@ -1,5 +1,7 @@
-#ifndef _PERF_ASM_GENERIC_BUG_H
-#define _PERF_ASM_GENERIC_BUG_H
+#ifndef _TOOLS_ASM_BUG_H
+#define _TOOLS_ASM_BUG_H
+
+#include <linux/compiler.h>
 
 #define __WARN_printf(arg...)   do { fprintf(stderr, arg); } while (0)
 
@@ -19,4 +21,5 @@
                         __warned = 1;           \
         unlikely(__ret_warn_once);              \
 })
-#endif
+
+#endif /* _TOOLS_ASM_BUG_H */
diff --git a/tools/perf/util/include/linux/compiler.h b/tools/include/linux/compiler.h
index b003ad7200b2..fbc6665c6d53 100644
--- a/tools/perf/util/include/linux/compiler.h
+++ b/tools/include/linux/compiler.h
@@ -1,5 +1,5 @@
-#ifndef _PERF_LINUX_COMPILER_H_
-#define _PERF_LINUX_COMPILER_H_
+#ifndef _TOOLS_LINUX_COMPILER_H_
+#define _TOOLS_LINUX_COMPILER_H_
 
 #ifndef __always_inline
 # define __always_inline        inline __attribute__((always_inline))
@@ -27,4 +27,12 @@
 # define __weak                 __attribute__((weak))
 #endif
 
+#ifndef likely
+# define likely(x)              __builtin_expect(!!(x), 1)
 #endif
+
+#ifndef unlikely
+# define unlikely(x)            __builtin_expect(!!(x), 0)
+#endif
+
+#endif /* _TOOLS_LINUX_COMPILER_H */
diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile
index ca4ab78425d1..f778d48ac609 100644
--- a/tools/lib/traceevent/Makefile
+++ b/tools/lib/traceevent/Makefile
@@ -86,8 +86,8 @@ ifeq ($(BUILD_SRC),)
 ifneq ($(OUTPUT),)
 
 define build_output
-        $(if $(VERBOSE:1=),@)+$(MAKE) -C $(OUTPUT) \
-        BUILD_SRC=$(CURDIR)/ -f $(CURDIR)/Makefile $1
+  $(if $(VERBOSE:1=),@)+$(MAKE) -C $(OUTPUT) \
+  BUILD_SRC=$(CURDIR)/ -f $(CURDIR)/Makefile $1
 endef
 
 all: sub-make
@@ -221,23 +221,23 @@ $(PLUGINS): %.so: %.o
         $(QUIET_LINK)$(CC) $(CFLAGS) -shared -nostartfiles -o $@ $<
 
 define make_version.h
-        (echo '/* This file is automatically generated. Do not modify. */';             \
-        echo \#define VERSION_CODE $(shell                                              \
-        expr $(VERSION) \* 256 + $(PATCHLEVEL));                                        \
-        echo '#define EXTRAVERSION ' $(EXTRAVERSION);                                   \
-        echo '#define VERSION_STRING "'$(VERSION).$(PATCHLEVEL).$(EXTRAVERSION)'"';     \
-        echo '#define FILE_VERSION '$(FILE_VERSION);                                    \
-        ) > $1
+  (echo '/* This file is automatically generated. Do not modify. */';           \
+   echo \#define VERSION_CODE $(shell                                           \
+   expr $(VERSION) \* 256 + $(PATCHLEVEL));                                     \
+   echo '#define EXTRAVERSION ' $(EXTRAVERSION);                                \
+   echo '#define VERSION_STRING "'$(VERSION).$(PATCHLEVEL).$(EXTRAVERSION)'"';  \
+   echo '#define FILE_VERSION '$(FILE_VERSION);                                 \
+  ) > $1
 endef
 
 define update_version.h
-        ($(call make_version.h, $@.tmp);                \
-        if [ -r $@ ] && cmp -s $@ $@.tmp; then          \
-                rm -f $@.tmp;                           \
-        else                                            \
-                echo '  UPDATE                 $@';     \
-                mv -f $@.tmp $@;                        \
-        fi);
+  ($(call make_version.h, $@.tmp);              \
+    if [ -r $@ ] && cmp -s $@ $@.tmp; then      \
+      rm -f $@.tmp;                             \
+    else                                        \
+      echo '  UPDATE                 $@';       \
+      mv -f $@.tmp $@;                          \
+    fi);
 endef
 
 ep_version.h: force
@@ -246,13 +246,13 @@ ep_version.h: force
 VERSION_FILES = ep_version.h
 
 define update_dir
-        (echo $1 > $@.tmp;      \
-        if [ -r $@ ] && cmp -s $@ $@.tmp; then          \
-                rm -f $@.tmp;                           \
-        else                                            \
-                echo '  UPDATE                 $@';     \
-                mv -f $@.tmp $@;                        \
-        fi);
+  (echo $1 > $@.tmp;                            \
+   if [ -r $@ ] && cmp -s $@ $@.tmp; then       \
+     rm -f $@.tmp;                              \
+   else                                         \
+     echo '  UPDATE                 $@';        \
+     mv -f $@.tmp $@;                           \
+   fi);
 endef
 
 ## make deps
@@ -262,10 +262,10 @@ all_deps := $(all_objs:%.o=.%.d)
 
 # let .d file also depends on the source and header files
 define check_deps
-                @set -e; $(RM) $@; \
-                $(CC) -MM $(CFLAGS) $< > $@.$$$$; \
-                sed 's,\($*\)\.o[ :]*,\1.o $@ : ,g' < $@.$$$$ > $@; \
-                $(RM) $@.$$$$
+  @set -e; $(RM) $@; \
+  $(CC) -MM $(CFLAGS) $< > $@.$$$$; \
+  sed 's,\($*\)\.o[ :]*,\1.o $@ : ,g' < $@.$$$$ > $@; \
+  $(RM) $@.$$$$
 endef
 
 $(all_deps): .%.d: $(src)/%.c
@@ -329,9 +329,12 @@ clean:
 
 endif # skip-makefile
 
-PHONY += force
+PHONY += force plugins
 force:
 
+plugins:
+        @echo > /dev/null
+
 # Declare the contents of the .PHONY variable as phony.  We keep that
 # information in a variable so we can use it in if_changed and friends.
 .PHONY: $(PHONY)
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index c407897f0435..82bffac036e1 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -209,6 +209,10 @@ overrides that and uses per-thread mmaps.  A side-effect of that is that
 inheritance is automatically disabled.  --per-thread is ignored with a warning
 if combined with -a or -C options.
 
+--initial-delay msecs::
+After starting the program, wait msecs before measuring. This is useful to
+filter out the startup phase of the program, which is often very different.
+
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-list[1]
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 80c7da6732f2..29ee857c09c6 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -133,7 +133,7 @@ use --per-core in addition to -a. (system-wide).  The output includes the
 core number and the number of online logical processors on that physical processor.
 
 -D msecs::
---initial-delay msecs::
+--delay msecs::
 After starting the program, wait msecs before measuring. This is useful to
 filter out the startup phase of the program, which is often very different.
 
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index 3170a7ff5782..f41572d0dd76 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -1,9 +1,11 @@
 tools/perf
 tools/scripts
 tools/lib/traceevent
-tools/lib/lk
+tools/lib/api
 tools/lib/symbol/kallsyms.c
 tools/lib/symbol/kallsyms.h
+tools/include/asm/bug.h
+tools/include/linux/compiler.h
 include/linux/const.h
 include/linux/perf_event.h
 include/linux/rbtree.h
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 3638b0bd20dc..87d7726cee2d 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -211,7 +211,7 @@ LIB_H += ../../include/linux/hash.h
 LIB_H += ../../include/linux/stringify.h
 LIB_H += util/include/linux/bitmap.h
 LIB_H += util/include/linux/bitops.h
-LIB_H += util/include/linux/compiler.h
+LIB_H += ../include/linux/compiler.h
 LIB_H += util/include/linux/const.h
 LIB_H += util/include/linux/ctype.h
 LIB_H += util/include/linux/kernel.h
@@ -226,7 +226,7 @@ LIB_H += util/include/linux/string.h
 LIB_H += util/include/linux/types.h
 LIB_H += util/include/linux/linkage.h
 LIB_H += util/include/asm/asm-offsets.h
-LIB_H += util/include/asm/bug.h
+LIB_H += ../include/asm/bug.h
 LIB_H += util/include/asm/byteorder.h
 LIB_H += util/include/asm/hweight.h
 LIB_H += util/include/asm/swab.h
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index ab65057a0317..0da603b79b61 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -232,7 +232,7 @@ static int __cmd_annotate(struct perf_annotate *ann)
                 perf_session__fprintf_dsos(session, stdout);
 
         total_nr_samples = 0;
-        list_for_each_entry(pos, &session->evlist->entries, node) {
+        evlist__for_each(session->evlist, pos) {
                 struct hists *hists = &pos->hists;
                 u32 nr_samples = hists->stats.nr_events[PERF_RECORD_SAMPLE];
 
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index e6a0844bc2f0..a77e31246c00 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -356,9 +356,10 @@ static struct perf_evsel *evsel_match(struct perf_evsel *evsel,
 {
         struct perf_evsel *e;
 
-        list_for_each_entry(e, &evlist->entries, node)
+        evlist__for_each(evlist, e) {
                 if (perf_evsel__match2(evsel, e))
                         return e;
+        }
 
         return NULL;
 }
@@ -367,7 +368,7 @@ static void perf_evlist__collapse_resort(struct perf_evlist *evlist)
 {
         struct perf_evsel *evsel;
 
-        list_for_each_entry(evsel, &evlist->entries, node) {
+        evlist__for_each(evlist, evsel) {
                 struct hists *hists = &evsel->hists;
 
                 hists__collapse_resort(hists, NULL);
@@ -614,7 +615,7 @@ static void data_process(void)
         struct perf_evsel *evsel_base;
         bool first = true;
 
-        list_for_each_entry(evsel_base, &evlist_base->entries, node) {
+        evlist__for_each(evlist_base, evsel_base) {
                 struct data__file *d;
                 int i;
 
@@ -769,6 +770,81 @@ static int hpp__entry_baseline(struct hist_entry *he, char *buf, size_t size)
         return ret;
 }
 
+static int __hpp__color_compare(struct perf_hpp_fmt *fmt,
+                                struct perf_hpp *hpp, struct hist_entry *he,
+                                int comparison_method)
+{
+        struct diff_hpp_fmt *dfmt =
+                container_of(fmt, struct diff_hpp_fmt, fmt);
+        struct hist_entry *pair = get_pair_fmt(he, dfmt);
+        double diff;
+        s64 wdiff;
+        char pfmt[20] = " ";
+
+        if (!pair)
+                goto dummy_print;
+
+        switch (comparison_method) {
+        case COMPUTE_DELTA:
+                if (pair->diff.computed)
+                        diff = pair->diff.period_ratio_delta;
+                else
+                        diff = compute_delta(he, pair);
+
+                if (fabs(diff) < 0.01)
+                        goto dummy_print;
+                scnprintf(pfmt, 20, "%%%+d.2f%%%%", dfmt->header_width - 1);
+                return percent_color_snprintf(hpp->buf, hpp->size,
+                                        pfmt, diff);
+        case COMPUTE_RATIO:
+                if (he->dummy)
+                        goto dummy_print;
+                if (pair->diff.computed)
+                        diff = pair->diff.period_ratio;
+                else
+                        diff = compute_ratio(he, pair);
+
+                scnprintf(pfmt, 20, "%%%d.6f", dfmt->header_width);
+                return value_color_snprintf(hpp->buf, hpp->size,
+                                        pfmt, diff);
+        case COMPUTE_WEIGHTED_DIFF:
+                if (he->dummy)
+                        goto dummy_print;
+                if (pair->diff.computed)
+                        wdiff = pair->diff.wdiff;
+                else
+                        wdiff = compute_wdiff(he, pair);
+
+                scnprintf(pfmt, 20, "%%14ld", dfmt->header_width);
+                return color_snprintf(hpp->buf, hpp->size,
+                                get_percent_color(wdiff),
+                                pfmt, wdiff);
+        default:
+                BUG_ON(1);
+        }
+dummy_print:
+        return scnprintf(hpp->buf, hpp->size, "%*s",
+                        dfmt->header_width, pfmt);
+}
+
+static int hpp__color_delta(struct perf_hpp_fmt *fmt,
+                        struct perf_hpp *hpp, struct hist_entry *he)
+{
+        return __hpp__color_compare(fmt, hpp, he, COMPUTE_DELTA);
+}
+
+static int hpp__color_ratio(struct perf_hpp_fmt *fmt,
+                        struct perf_hpp *hpp, struct hist_entry *he)
+{
+        return __hpp__color_compare(fmt, hpp, he, COMPUTE_RATIO);
+}
+
+static int hpp__color_wdiff(struct perf_hpp_fmt *fmt,
+                        struct perf_hpp *hpp, struct hist_entry *he)
+{
+        return __hpp__color_compare(fmt, hpp, he, COMPUTE_WEIGHTED_DIFF);
+}
+
 static void
 hpp__entry_unpair(struct hist_entry *he, int idx, char *buf, size_t size)
 {
@@ -940,8 +1016,22 @@ static void data__hpp_register(struct data__file *d, int idx)
         fmt->entry  = hpp__entry_global;
 
         /* TODO more colors */
-        if (idx == PERF_HPP_DIFF__BASELINE)
+        switch (idx) {
+        case PERF_HPP_DIFF__BASELINE:
                 fmt->color = hpp__color_baseline;
+                break;
+        case PERF_HPP_DIFF__DELTA:
+                fmt->color = hpp__color_delta;
+                break;
+        case PERF_HPP_DIFF__RATIO:
+                fmt->color = hpp__color_ratio;
+                break;
+        case PERF_HPP_DIFF__WEIGHTED_DIFF:
+                fmt->color = hpp__color_wdiff;
+                break;
+        default:
+                break;
+        }
 
         init_header(d, dfmt);
         perf_hpp__column_register(fmt);
diff --git a/tools/perf/builtin-evlist.c b/tools/perf/builtin-evlist.c
index 20b0f12763b0..c99e0de7e54a 100644
--- a/tools/perf/builtin-evlist.c
+++ b/tools/perf/builtin-evlist.c
@@ -29,7 +29,7 @@ static int __cmd_evlist(const char *file_name, struct perf_attr_details *details
         if (session == NULL)
                 return -ENOMEM;
 
-        list_for_each_entry(pos, &session->evlist->entries, node)
+        evlist__for_each(session->evlist, pos)
                 perf_evsel__fprintf(pos, details, stdout);
 
         perf_session__delete(session);
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index c9f6d74e1fd7..b3466018bbd7 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -369,7 +369,7 @@ static int __cmd_inject(struct perf_inject *inject)
 
                 inject->tool.ordered_samples = true;
 
-                list_for_each_entry(evsel, &session->evlist->entries, node) {
+                evlist__for_each(session->evlist, evsel) {
                         const char *name = perf_evsel__name(evsel);
 
                         if (!strcmp(name, "sched:sched_switch")) {
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index a6ec1052c291..a7350519c63f 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -1174,7 +1174,7 @@ static int kvm_live_open_events(struct perf_kvm_stat *kvm)
          * Note: exclude_{guest,host} do not apply here.
          *       This command processes KVM tracepoints from host only
          */
-        list_for_each_entry(pos, &evlist->entries, node) {
+        evlist__for_each(evlist, pos) {
                 struct perf_event_attr *attr = &pos->attr;
 
                 /* make sure these *are* set */
@@ -1556,10 +1556,8 @@ out:
         if (kvm->session)
                 perf_session__delete(kvm->session);
         kvm->session = NULL;
-        if (kvm->evlist) {
-                perf_evlist__delete_maps(kvm->evlist);
+        if (kvm->evlist)
                 perf_evlist__delete(kvm->evlist);
-        }
 
         return err;
 }
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 6ec0cbc2a5d5..07d4cf8d3fd3 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -183,7 +183,7 @@ static int record__open(struct record *rec)
 
         perf_evlist__config(evlist, opts);
 
-        list_for_each_entry(pos, &evlist->entries, node) {
+        evlist__for_each(evlist, pos) {
 try_again:
                 if (perf_evsel__open(pos, evlist->cpus, evlist->threads) < 0) {
                         if (perf_evsel__fallback(pos, errno, msg, sizeof(msg))) {
@@ -324,7 +324,6 @@ out:
 
 static void record__init_features(struct record *rec)
 {
-        struct perf_evlist *evsel_list = rec->evlist;
         struct perf_session *session = rec->session;
         int feat;
 
@@ -334,13 +333,29 @@ static void record__init_features(struct record *rec)
         if (rec->no_buildid)
                 perf_header__clear_feat(&session->header, HEADER_BUILD_ID);
 
-        if (!have_tracepoints(&evsel_list->entries))
+        if (!have_tracepoints(&rec->evlist->entries))
                 perf_header__clear_feat(&session->header, HEADER_TRACING_DATA);
 
         if (!rec->opts.branch_stack)
                 perf_header__clear_feat(&session->header, HEADER_BRANCH_STACK);
 }
 
+static volatile int workload_exec_errno;
+
+/*
+ * perf_evlist__prepare_workload will send a SIGUSR1
+ * if the fork fails, since we asked by setting its
+ * want_signal to true.
+ */
+static void workload_exec_failed_signal(int signo, siginfo_t *info,
+                                        void *ucontext __maybe_unused)
+{
+        workload_exec_errno = info->si_value.sival_int;
+        done = 1;
+        signr = signo;
+        child_finished = 1;
+}
+
 static int __cmd_record(struct record *rec, int argc, const char **argv)
 {
         int err;
@@ -349,7 +364,6 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
         struct machine *machine;
         struct perf_tool *tool = &rec->tool;
         struct record_opts *opts = &rec->opts;
-        struct perf_evlist *evsel_list = rec->evlist;
         struct perf_data_file *file = &rec->file;
         struct perf_session *session;
         bool disabled = false;
@@ -359,7 +373,6 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
         on_exit(record__sig_exit, rec);
         signal(SIGCHLD, sig_handler);
         signal(SIGINT, sig_handler);
-        signal(SIGUSR1, sig_handler);
         signal(SIGTERM, sig_handler);
 
         session = perf_session__new(file, false, NULL);
@@ -373,9 +386,9 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
         record__init_features(rec);
 
         if (forks) {
-                err = perf_evlist__prepare_workload(evsel_list, &opts->target,
+                err = perf_evlist__prepare_workload(rec->evlist, &opts->target,
                                                     argv, file->is_pipe,
-                                                    true);
+                                                    workload_exec_failed_signal);
                 if (err < 0) {
                         pr_err("Couldn't run the workload!\n");
                         goto out_delete_session;
@@ -387,7 +400,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
                 goto out_delete_session;
         }
 
-        if (!evsel_list->nr_groups)
+        if (!rec->evlist->nr_groups)
                 perf_header__clear_feat(&session->header, HEADER_GROUP_DESC);
 
         /*
@@ -400,7 +413,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
                 if (err < 0)
                         goto out_delete_session;
         } else {
-                err = perf_session__write_header(session, evsel_list,
+                err = perf_session__write_header(session, rec->evlist,
                                                  file->fd, false);
                 if (err < 0)
                         goto out_delete_session;
@@ -424,7 +437,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
                         goto out_delete_session;
                 }
 
-                if (have_tracepoints(&evsel_list->entries)) {
+                if (have_tracepoints(&rec->evlist->entries)) {
                         /*
                          * FIXME err <= 0 here actually means that
                          * there were no tracepoints so its not really
@@ -433,7 +446,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
                          * return this more properly and also
                          * propagate errors that now are calling die()
                          */
-                        err = perf_event__synthesize_tracing_data(tool, file->fd, evsel_list,
+                        err = perf_event__synthesize_tracing_data(tool, file->fd, rec->evlist,
                                                                   process_synthesized_event);
                         if (err <= 0) {
                                 pr_err("Couldn't record tracing data.\n");
@@ -465,7 +478,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
                                          perf_event__synthesize_guest_os, tool);
         }
 
-        err = __machine__synthesize_threads(machine, tool, &opts->target, evsel_list->threads,
+        err = __machine__synthesize_threads(machine, tool, &opts->target, rec->evlist->threads,
                                             process_synthesized_event, opts->sample_address);
         if (err != 0)
                 goto out_delete_session;
@@ -486,14 +499,19 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
          * (apart from group members) have enable_on_exec=1 set,
          * so don't spoil it by prematurely enabling them.
          */
-        if (!target__none(&opts->target))
-                perf_evlist__enable(evsel_list);
+        if (!target__none(&opts->target) && !opts->initial_delay)
+                perf_evlist__enable(rec->evlist);
 
         /*
          * Let the child rip
          */
         if (forks)
-                perf_evlist__start_workload(evsel_list);
+                perf_evlist__start_workload(rec->evlist);
+
+        if (opts->initial_delay) {
+                usleep(opts->initial_delay * 1000);
+                perf_evlist__enable(rec->evlist);
+        }
 
         for (;;) {
                 int hits = rec->samples;
@@ -506,7 +524,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
                 if (hits == rec->samples) {
                         if (done)
                                 break;
-                        err = poll(evsel_list->pollfd, evsel_list->nr_fds, -1);
+                        err = poll(rec->evlist->pollfd, rec->evlist->nr_fds, -1);
                         waking++;
                 }
 
@@ -516,11 +534,19 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
                  * disable events in this case.
                  */
                 if (done && !disabled && !target__none(&opts->target)) {
-                        perf_evlist__disable(evsel_list);
+                        perf_evlist__disable(rec->evlist);
                         disabled = true;
                 }
         }
 
+        if (forks && workload_exec_errno) {
+                char msg[512];
+                const char *emsg = strerror_r(workload_exec_errno, msg, sizeof(msg));
+                pr_err("Workload failed: %s\n", emsg);
+                err = -1;
+                goto out_delete_session;
+        }
+
         if (quiet || signr == SIGUSR1)
                 return 0;
 
@@ -856,6 +882,8 @@ const struct option record_options[] = {
         OPT_CALLBACK('G', "cgroup", &record.evlist, "name",
                      "monitor event in cgroup name only",
                      parse_cgroups),
+        OPT_UINTEGER(0, "initial-delay", &record.opts.initial_delay,
+                  "ms to wait before starting measurement after program start"),
         OPT_STRING('u', "uid", &record.opts.target.uid_str, "user",
                    "user to profile"),
 
@@ -878,16 +906,13 @@ const struct option record_options[] = {
 int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 {
         int err = -ENOMEM;
-        struct perf_evlist *evsel_list;
         struct record *rec = &record;
         char errbuf[BUFSIZ];
 
-        evsel_list = perf_evlist__new();
-        if (evsel_list == NULL)
+        rec->evlist = perf_evlist__new();
+        if (rec->evlist == NULL)
                 return -ENOMEM;
 
-        rec->evlist = evsel_list;
-
         argc = parse_options(argc, argv, record_options, record_usage,
                             PARSE_OPT_STOP_AT_NON_OPTION);
         if (!argc && target__none(&rec->opts.target))
@@ -914,8 +939,8 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
         if (rec->no_buildid_cache || rec->no_buildid)
                 disable_buildid_cache();
 
-        if (evsel_list->nr_entries == 0 &&
-            perf_evlist__add_default(evsel_list) < 0) {
+        if (rec->evlist->nr_entries == 0 &&
+            perf_evlist__add_default(rec->evlist) < 0) {
                 pr_err("Not enough memory for event selector list\n");
                 goto out_symbol_exit;
         }
@@ -941,20 +966,15 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
         }
 
         err = -ENOMEM;
-        if (perf_evlist__create_maps(evsel_list, &rec->opts.target) < 0)
+        if (perf_evlist__create_maps(rec->evlist, &rec->opts.target) < 0)
                 usage_with_options(record_usage, record_options);
 
         if (record_opts__config(&rec->opts)) {
                 err = -EINVAL;
-                goto out_free_fd;
+                goto out_symbol_exit;
         }
 
         err = __cmd_record(&record, argc, argv);
-
-        perf_evlist__munmap(evsel_list);
-        perf_evlist__close(evsel_list);
-out_free_fd:
-        perf_evlist__delete_maps(evsel_list);
 out_symbol_exit:
         symbol__exit();
         return err;
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index bf8dd2e893e4..46864dd7eb83 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -384,7 +384,7 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
 {
         struct perf_evsel *pos;
 
-        list_for_each_entry(pos, &evlist->entries, node) {
+        evlist__for_each(evlist, pos) {
                 struct hists *hists = &pos->hists;
                 const char *evname = perf_evsel__name(pos);
 
@@ -412,40 +412,11 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
         return 0;
 }
 
-static int __cmd_report(struct report *rep)
+static void report__warn_kptr_restrict(const struct report *rep)
 {
-        int ret = -EINVAL;
-        u64 nr_samples;
-        struct perf_session *session = rep->session;
-        struct perf_evsel *pos;
-        struct map *kernel_map;
-        struct kmap *kernel_kmap;
-        const char *help = "For a higher level overview, try: perf report --sort comm,dso";
-        struct ui_progress prog;
-        struct perf_data_file *file = session->file;
+        struct map *kernel_map = rep->session->machines.host.vmlinux_maps[MAP__FUNCTION];
+        struct kmap *kernel_kmap = map__kmap(kernel_map);
 
-        signal(SIGINT, sig_handler);
-
-        if (rep->cpu_list) {
-                ret = perf_session__cpu_bitmap(session, rep->cpu_list,
-                                               rep->cpu_bitmap);
-                if (ret)
-                        return ret;
-        }
-
-        if (rep->show_threads)
-                perf_read_values_init(&rep->show_threads_values);
-
-        ret = report__setup_sample_type(rep);
-        if (ret)
-                return ret;
-
-        ret = perf_session__process_events(session, &rep->tool);
-        if (ret)
-                return ret;
-
-        kernel_map = session->machines.host.vmlinux_maps[MAP__FUNCTION];
-        kernel_kmap = map__kmap(kernel_map);
         if (kernel_map == NULL ||
             (kernel_map->dso->hit &&
              (kernel_kmap->ref_reloc_sym == NULL ||
@@ -468,28 +439,73 @@ static int __cmd_report(struct report *rep)
 "Samples in kernel modules can't be resolved as well.\n\n",
                 desc);
         }
+}
 
-        if (use_browser == 0) {
-                if (verbose > 3)
-                        perf_session__fprintf(session, stdout);
+static int report__gtk_browse_hists(struct report *rep, const char *help)
+{
+        int (*hist_browser)(struct perf_evlist *evlist, const char *help,
+                            struct hist_browser_timer *timer, float min_pcnt);
 
-                if (verbose > 2)
-                        perf_session__fprintf_dsos(session, stdout);
+        hist_browser = dlsym(perf_gtk_handle, "perf_evlist__gtk_browse_hists");
 
-                if (dump_trace) {
-                        perf_session__fprintf_nr_events(session, stdout);
-                        return 0;
-                }
+        if (hist_browser == NULL) {
+                ui__error("GTK browser not found!\n");
+                return -1;
         }
 
-        nr_samples = 0;
-        list_for_each_entry(pos, &session->evlist->entries, node)
+        return hist_browser(rep->session->evlist, help, NULL, rep->min_percent);
+}
+
+static int report__browse_hists(struct report *rep)
+{
+        int ret;
+        struct perf_session *session = rep->session;
+        struct perf_evlist *evlist = session->evlist;
+        const char *help = "For a higher level overview, try: perf report --sort comm,dso";
+
+        switch (use_browser) {
+        case 1:
+                ret = perf_evlist__tui_browse_hists(evlist, help, NULL,
+                                                    rep->min_percent,
+                                                    &session->header.env);
+                /*
+                 * Usually "ret" is the last pressed key, and we only
+                 * care if the key notifies us to switch data file.
+                 */
+                if (ret != K_SWITCH_INPUT_DATA)
+                        ret = 0;
+                break;
+        case 2:
+                ret = report__gtk_browse_hists(rep, help);
+                break;
+        default:
+                ret = perf_evlist__tty_browse_hists(evlist, rep, help);
+                break;
+        }
+
+        return ret;
+}
+
+static u64 report__collapse_hists(struct report *rep)
+{
+        struct ui_progress prog;
+        struct perf_evsel *pos;
+        u64 nr_samples = 0;
+        /*
+         * Count number of histogram entries to use when showing progress,
+         * reusing nr_samples variable.
+         */
+        evlist__for_each(rep->session->evlist, pos)
                 nr_samples += pos->hists.nr_entries;
 
         ui_progress__init(&prog, nr_samples, "Merging related events...");
-
+        /*
+         * Count total number of samples, will be used to check if this
+         * session had any.
+         */
         nr_samples = 0;
-        list_for_each_entry(pos, &session->evlist->entries, node) {
+
+        evlist__for_each(rep->session->evlist, pos) {
                 struct hists *hists = &pos->hists;
 
                 if (pos->idx == 0)
@@ -507,8 +523,57 @@ static int __cmd_report(struct report *rep)
                         hists__link(leader_hists, hists);
                 }
         }
+
         ui_progress__finish();
 
+        return nr_samples;
+}
+
+static int __cmd_report(struct report *rep)
+{
+        int ret;
+        u64 nr_samples;
+        struct perf_session *session = rep->session;
+        struct perf_evsel *pos;
+        struct perf_data_file *file = session->file;
+
+        signal(SIGINT, sig_handler);
+
+        if (rep->cpu_list) {
+                ret = perf_session__cpu_bitmap(session, rep->cpu_list,
+                                               rep->cpu_bitmap);
+                if (ret)
+                        return ret;
+        }
+
+        if (rep->show_threads)
+                perf_read_values_init(&rep->show_threads_values);
+
+        ret = report__setup_sample_type(rep);
+        if (ret)
+                return ret;
+
+        ret = perf_session__process_events(session, &rep->tool);
+        if (ret)
+                return ret;
+
+        report__warn_kptr_restrict(rep);
+
+        if (use_browser == 0) {
+                if (verbose > 3)
+                        perf_session__fprintf(session, stdout);
+
+                if (verbose > 2)
+                        perf_session__fprintf_dsos(session, stdout);
+
+                if (dump_trace) {
+                        perf_session__fprintf_nr_events(session, stdout);
+                        return 0;
+                }
+        }
+
+        nr_samples = report__collapse_hists(rep);
+
         if (session_done())
                 return 0;
 
@@ -517,41 +582,10 @@ static int __cmd_report(struct report *rep)
                 return 0;
         }
 
-        list_for_each_entry(pos, &session->evlist->entries, node)
+        evlist__for_each(session->evlist, pos)
                 hists__output_resort(&pos->hists);
 
-        if (use_browser > 0) {
-                if (use_browser == 1) {
-                        ret = perf_evlist__tui_browse_hists(session->evlist,
-                                                        help, NULL,
-                                                        rep->min_percent,
-                                                        &session->header.env);
-                        /*
-                         * Usually "ret" is the last pressed key, and we only
-                         * care if the key notifies us to switch data file.
-                         */
-                        if (ret != K_SWITCH_INPUT_DATA)
-                                ret = 0;
-
-                } else if (use_browser == 2) {
-                        int (*hist_browser)(struct perf_evlist *,
-                                            const char *,
-                                            struct hist_browser_timer *,
-                                            float min_pcnt);
-
-                        hist_browser = dlsym(perf_gtk_handle,
-                                             "perf_evlist__gtk_browse_hists");
-                        if (hist_browser == NULL) {
-                                ui__error("GTK browser not found!\n");
-                                return ret;
-                        }
-                        hist_browser(session->evlist, help, NULL,
-                                     rep->min_percent);
-                }
-        } else
-                perf_evlist__tty_browse_hists(session->evlist, rep, help);
-
-        return ret;
+        return report__browse_hists(rep);
 }
 
 static int
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 6040000bdfa6..9e9c91f5b7fa 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -603,7 +603,7 @@ static int process_attr(struct perf_tool *tool, union perf_event *event,
         if (evsel->attr.type >= PERF_TYPE_MAX)
                 return 0;
 
-        list_for_each_entry(pos, &evlist->entries, node) {
+        evlist__for_each(evlist, pos) {
                 if (pos->attr.type == evsel->attr.type && pos != evsel)
                         return 0;
         }
@@ -1309,8 +1309,7 @@ static int check_ev_match(char *dir_name, char *scriptname,
                         snprintf(evname, len + 1, "%s", p);
 
                         match = 0;
-                        list_for_each_entry(pos,
-                                        &session->evlist->entries, node) {
+                        evlist__for_each(session->evlist, pos) {
                                 if (!strcmp(perf_evsel__name(pos), evname)) {
                                         match = 1;
                                         break;
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 106a5e5b7842..8b0e1c9234d9 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -214,7 +214,7 @@ static void perf_evlist__free_stats(struct perf_evlist *evlist)
 {
         struct perf_evsel *evsel;
 
-        list_for_each_entry(evsel, &evlist->entries, node) {
+        evlist__for_each(evlist, evsel) {
                 perf_evsel__free_stat_priv(evsel);
                 perf_evsel__free_counts(evsel);
                 perf_evsel__free_prev_raw_counts(evsel);
@@ -225,7 +225,7 @@ static int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw)
 {
         struct perf_evsel *evsel;
 
-        list_for_each_entry(evsel, &evlist->entries, node) {
+        evlist__for_each(evlist, evsel) {
                 if (perf_evsel__alloc_stat_priv(evsel) < 0 ||
                     perf_evsel__alloc_counts(evsel, perf_evsel__nr_cpus(evsel)) < 0 ||
                     (alloc_raw && perf_evsel__alloc_prev_raw_counts(evsel) < 0))
@@ -259,7 +259,7 @@ static void perf_stat__reset_stats(struct perf_evlist *evlist)
 {
         struct perf_evsel *evsel;
 
-        list_for_each_entry(evsel, &evlist->entries, node) {
+        evlist__for_each(evlist, evsel) {
                 perf_evsel__reset_stat_priv(evsel);
                 perf_evsel__reset_counts(evsel, perf_evsel__nr_cpus(evsel));
         }
@@ -326,13 +326,13 @@ static struct perf_evsel *nth_evsel(int n)
 
         /* Assumes this only called when evsel_list does not change anymore. */
         if (!array) {
-                list_for_each_entry(ev, &evsel_list->entries, node)
+                evlist__for_each(evsel_list, ev)
                         array_len++;
                 array = malloc(array_len * sizeof(void *));
                 if (!array)
                         exit(ENOMEM);
                 j = 0;
-                list_for_each_entry(ev, &evsel_list->entries, node)
+                evlist__for_each(evsel_list, ev)
                         array[j++] = ev;
         }
         if (n < array_len)
@@ -440,13 +440,13 @@ static void print_interval(void)
         char prefix[64];
 
         if (aggr_mode == AGGR_GLOBAL) {
-                list_for_each_entry(counter, &evsel_list->entries, node) {
+                evlist__for_each(evsel_list, counter) {
                         ps = counter->priv;
                         memset(ps->res_stats, 0, sizeof(ps->res_stats));
                         read_counter_aggr(counter);
                 }
         } else  {
-                list_for_each_entry(counter, &evsel_list->entries, node) {
+                evlist__for_each(evsel_list, counter) {
                         ps = counter->priv;
                         memset(ps->res_stats, 0, sizeof(ps->res_stats));
                         read_counter(counter);
@@ -483,12 +483,12 @@ static void print_interval(void)
                 print_aggr(prefix);
                 break;
         case AGGR_NONE:
-                list_for_each_entry(counter, &evsel_list->entries, node)
+                evlist__for_each(evsel_list, counter)
                         print_counter(counter, prefix);
                 break;
         case AGGR_GLOBAL:
         default:
-                list_for_each_entry(counter, &evsel_list->entries, node)
+                evlist__for_each(evsel_list, counter)
                         print_counter_aggr(counter, prefix);
         }
 
@@ -504,11 +504,24 @@ static void handle_initial_delay(void)
                         nthreads = thread_map__nr(evsel_list->threads);
 
                 usleep(initial_delay * 1000);
-                list_for_each_entry(counter, &evsel_list->entries, node)
+                evlist__for_each(evsel_list, counter)
                         perf_evsel__enable(counter, ncpus, nthreads);
         }
 }
 
+static volatile int workload_exec_errno;
+
+/*
+ * perf_evlist__prepare_workload will send a SIGUSR1
+ * if the fork fails, since we asked by setting its
+ * want_signal to true.
+ */
+static void workload_exec_failed_signal(int signo __maybe_unused, siginfo_t *info,
+                                        void *ucontext __maybe_unused)
+{
+        workload_exec_errno = info->si_value.sival_int;
+}
+
 static int __run_perf_stat(int argc, const char **argv)
 {
         char msg[512];
@@ -528,8 +541,8 @@ static int __run_perf_stat(int argc, const char **argv)
         }
 
         if (forks) {
-                if (perf_evlist__prepare_workload(evsel_list, &target, argv,
-                                                  false, false) < 0) {
+                if (perf_evlist__prepare_workload(evsel_list, &target, argv, false,
+                                                  workload_exec_failed_signal) < 0) {
                         perror("failed to prepare workload");
                         return -1;
                 }
@@ -539,7 +552,7 @@ static int __run_perf_stat(int argc, const char **argv)
         if (group)
                 perf_evlist__set_leader(evsel_list);
 
-        list_for_each_entry(counter, &evsel_list->entries, node) {
+        evlist__for_each(evsel_list, counter) {
                 if (create_perf_stat_counter(counter) < 0) {
                         /*
                          * PPC returns ENXIO for HW counters until 2.6.37
@@ -594,6 +607,13 @@ static int __run_perf_stat(int argc, const char **argv)
                         }
                 }
                 wait(&status);
+
+                if (workload_exec_errno) {
+                        const char *emsg = strerror_r(workload_exec_errno, msg, sizeof(msg));
+                        pr_err("Workload failed: %s\n", emsg);
+                        return -1;
+                }
+
                 if (WIFSIGNALED(status))
                         psignal(WTERMSIG(status), argv[0]);
         } else {
@@ -610,13 +630,13 @@ static int __run_perf_stat(int argc, const char **argv)
         update_stats(&walltime_nsecs_stats, t1 - t0);
 
         if (aggr_mode == AGGR_GLOBAL) {
-                list_for_each_entry(counter, &evsel_list->entries, node) {
+                evlist__for_each(evsel_list, counter) {
                         read_counter_aggr(counter);
                         perf_evsel__close_fd(counter, perf_evsel__nr_cpus(counter),
                                              thread_map__nr(evsel_list->threads));
                 }
         } else {
-                list_for_each_entry(counter, &evsel_list->entries, node) {
+                evlist__for_each(evsel_list, counter) {
                         read_counter(counter);
                         perf_evsel__close_fd(counter, perf_evsel__nr_cpus(counter), 1);
                 }
@@ -625,7 +645,7 @@ static int __run_perf_stat(int argc, const char **argv)
         return WEXITSTATUS(status);
 }
 
-static int run_perf_stat(int argc __maybe_unused, const char **argv)
+static int run_perf_stat(int argc, const char **argv)
 {
         int ret;
 
@@ -1097,7 +1117,7 @@ static void print_aggr(char *prefix)
 
         for (s = 0; s < aggr_map->nr; s++) {
                 id = aggr_map->map[s];
-                list_for_each_entry(counter, &evsel_list->entries, node) {
+                evlist__for_each(evsel_list, counter) {
                         val = ena = run = 0;
                         nr = 0;
                         for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
@@ -1308,11 +1328,11 @@ static void print_stat(int argc, const char **argv)
                 print_aggr(NULL);
                 break;
         case AGGR_GLOBAL:
-                list_for_each_entry(counter, &evsel_list->entries, node)
+                evlist__for_each(evsel_list, counter)
                         print_counter_aggr(counter, NULL);
                 break;
         case AGGR_NONE:
-                list_for_each_entry(counter, &evsel_list->entries, node)
+                evlist__for_each(evsel_list, counter)
                         print_counter(counter, NULL);
                 break;
         default:
@@ -1762,14 +1782,14 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
         if (interval && interval < 100) {
                 pr_err("print interval must be >= 100ms\n");
                 parse_options_usage(stat_usage, options, "I", 1);
-                goto out_free_maps;
+                goto out;
         }
 
         if (perf_evlist__alloc_stats(evsel_list, interval))
-                goto out_free_maps;
+                goto out;
 
         if (perf_stat_init_aggr_mode())
-                goto out_free_maps;
+                goto out;
 
         /*
          * We dont want to block the signals - that would cause
@@ -1801,8 +1821,6 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
                 print_stat(argc, argv);
 
         perf_evlist__free_stats(evsel_list);
-out_free_maps:
-        perf_evlist__delete_maps(evsel_list);
 out:
         perf_evlist__delete(evsel_list);
         return status;
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 172e91a9ce62..569dd87690ef 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -482,7 +482,7 @@ static bool perf_top__handle_keypress(struct perf_top *top, int c)
 
                                 fprintf(stderr, "\nAvailable events:");
 
-                                list_for_each_entry(top->sym_evsel, &top->evlist->entries, node)
+                                evlist__for_each(top->evlist, top->sym_evsel)
                                         fprintf(stderr, "\n\t%d %s", top->sym_evsel->idx, perf_evsel__name(top->sym_evsel));
 
                                 prompt_integer(&counter, "Enter details event counter");
@@ -493,7 +493,7 @@ static bool perf_top__handle_keypress(struct perf_top *top, int c)
                                         sleep(1);
                                         break;
                                 }
-                                list_for_each_entry(top->sym_evsel, &top->evlist->entries, node)
+                                evlist__for_each(top->evlist, top->sym_evsel)
                                         if (top->sym_evsel->idx == counter)
                                                 break;
                         } else
@@ -575,7 +575,7 @@ static void *display_thread_tui(void *arg)
          * Zooming in/out UIDs. For now juse use whatever the user passed
          * via --uid.
          */
-        list_for_each_entry(pos, &top->evlist->entries, node)
+        evlist__for_each(top->evlist, pos)
                 pos->hists.uid_filter_str = top->record_opts.target.uid_str;
 
         perf_evlist__tui_browse_hists(top->evlist, help, &hbt, top->min_percent,
@@ -858,7 +858,7 @@ static int perf_top__start_counters(struct perf_top *top)
 
         perf_evlist__config(evlist, opts);
 
-        list_for_each_entry(counter, &evlist->entries, node) {
+        evlist__for_each(evlist, counter) {
 try_again:
                 if (perf_evsel__open(counter, top->evlist->cpus,
                                      top->evlist->threads) < 0) {
@@ -1171,7 +1171,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
         if (!top.evlist->nr_entries &&
             perf_evlist__add_default(top.evlist) < 0) {
                 ui__error("Not enough memory for event selector list\n");
-                goto out_delete_maps;
+                goto out_delete_evlist;
         }
 
         symbol_conf.nr_events = top.evlist->nr_entries;
@@ -1181,7 +1181,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 
         if (record_opts__config(opts)) {
                 status = -EINVAL;
-                goto out_delete_maps;
+                goto out_delete_evlist;
         }
 
         top.sym_evsel = perf_evlist__first(top.evlist);
@@ -1206,8 +1206,6 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 
         status = __cmd_top(&top);
 
-out_delete_maps:
-        perf_evlist__delete_maps(top.evlist);
 out_delete_evlist:
         perf_evlist__delete(top.evlist);
 
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index c5b4bc51175c..4bd44aba343e 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1160,26 +1160,27 @@ struct trace {
         struct record_opts      opts;
         struct machine          *host;
         u64                     base_time;
-        bool                    full_time;
         FILE                    *output;
         unsigned long           nr_events;
         struct strlist          *ev_qualifier;
-        bool                    not_ev_qualifier;
-        bool                    live;
         const char              *last_vfs_getname;
         struct intlist          *tid_list;
         struct intlist          *pid_list;
+        double                  duration_filter;
+        double                  runtime_ms;
+        struct {
+                u64             vfs_getname,
+                                proc_getname;
+        } stats;
+        bool                    not_ev_qualifier;
+        bool                    live;
+        bool                    full_time;
         bool                    sched;
         bool                    multiple_threads;
         bool                    summary;
         bool                    summary_only;
         bool                    show_comm;
         bool                    show_tool_stats;
-        double                  duration_filter;
-        double                  runtime_ms;
-        struct {
-                u64             vfs_getname, proc_getname;
-        } stats;
 };
 
 static int trace__set_fd_pathname(struct thread *thread, int fd, const char *pathname)
@@ -1885,7 +1886,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
         err = trace__symbols_init(trace, evlist);
         if (err < 0) {
                 fprintf(trace->output, "Problems initializing symbol libraries!\n");
-                goto out_delete_maps;
+                goto out_delete_evlist;
         }
 
         perf_evlist__config(evlist, &trace->opts);
@@ -1895,10 +1896,10 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 
         if (forks) {
                 err = perf_evlist__prepare_workload(evlist, &trace->opts.target,
-                                                    argv, false, false);
+                                                    argv, false, NULL);
                 if (err < 0) {
                         fprintf(trace->output, "Couldn't run the workload!\n");
-                        goto out_delete_maps;
+                        goto out_delete_evlist;
                 }
         }
 
@@ -1909,7 +1910,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
         err = perf_evlist__mmap(evlist, trace->opts.mmap_pages, false);
         if (err < 0) {
                 fprintf(trace->output, "Couldn't mmap the events: %s\n", strerror(errno));
-                goto out_close_evlist;
+                goto out_delete_evlist;
         }
 
         perf_evlist__enable(evlist);
@@ -1993,11 +1994,6 @@ out_disable:
                 }
         }
 
-        perf_evlist__munmap(evlist);
-out_close_evlist:
-        perf_evlist__close(evlist);
-out_delete_maps:
-        perf_evlist__delete_maps(evlist);
 out_delete_evlist:
         perf_evlist__delete(evlist);
 out:
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index 14faeeb0d752..01dd43df0d04 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -1,28 +1,26 @@
-uname_M := $(shell uname -m 2>/dev/null || echo not)
 
-ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/i386/ -e s/sun4u/sparc64/ \
-                                  -e s/arm.*/arm/ -e s/sa110/arm/ \
-                                  -e s/s390x/s390/ -e s/parisc64/parisc/ \
-                                  -e s/ppc.*/powerpc/ -e s/mips.*/mips/ \
-                                  -e s/sh[234].*/sh/ -e s/aarch64.*/arm64/ )
-NO_PERF_REGS := 1
-CFLAGS := $(EXTRA_CFLAGS) $(EXTRA_WARNINGS)
+ifeq ($(src-perf),)
+src-perf := $(srctree)/tools/perf
+endif
 
-# Additional ARCH settings for x86
-ifeq ($(ARCH),i386)
-  override ARCH := x86
-  NO_PERF_REGS := 0
-  LIBUNWIND_LIBS = -lunwind -lunwind-x86
+ifeq ($(obj-perf),)
+obj-perf := $(OUTPUT)
 endif
 
-ifeq ($(ARCH),x86_64)
-  override ARCH := x86
-  IS_X86_64 := 0
-  ifeq (, $(findstring m32,$(CFLAGS)))
-    IS_X86_64 := $(shell echo __x86_64__ | ${CC} -E -x c - | tail -n 1)
-  endif
+ifneq ($(obj-perf),)
+obj-perf := $(abspath $(obj-perf))/
+endif
+
+LIB_INCLUDE := $(srctree)/tools/lib/
+CFLAGS := $(EXTRA_CFLAGS) $(EXTRA_WARNINGS)
+
+include $(src-perf)/config/Makefile.arch
+
+NO_PERF_REGS := 1
+
+# Additional ARCH settings for x86
+ifeq ($(ARCH),x86)
   ifeq (${IS_X86_64}, 1)
-    RAW_ARCH := x86_64
     CFLAGS += -DHAVE_ARCH_X86_64_SUPPORT
     ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S ../../arch/x86/lib/memset_64.S
     LIBUNWIND_LIBS = -lunwind -lunwind-x86_64
@@ -55,29 +53,12 @@ else
   FEATURE_CHECK_LDFLAGS-libunwind = $(LIBUNWIND_LDFLAGS)
   FEATURE_CHECK_CFLAGS-libunwind-debug-frame = $(LIBUNWIND_CFLAGS)
   FEATURE_CHECK_LDFLAGS-libunwind-debug-frame = $(LIBUNWIND_LDFLAGS)
-  #  and the flags for the test-all case
-  FEATURE_CHECK_CFLAGS-all += $(LIBUNWIND_CFLAGS)
-  FEATURE_CHECK_LDFLAGS-all += $(LIBUNWIND_LDFLAGS)
 endif
 
 ifeq ($(NO_PERF_REGS),0)
   CFLAGS += -DHAVE_PERF_REGS_SUPPORT
 endif
 
-ifeq ($(src-perf),)
-src-perf := $(srctree)/tools/perf
-endif
-
-ifeq ($(obj-perf),)
-obj-perf := $(OUTPUT)
-endif
-
-ifneq ($(obj-perf),)
-obj-perf := $(abspath $(obj-perf))/
-endif
-
-LIB_INCLUDE := $(srctree)/tools/lib/
-
 # include ARCH specific config
 -include $(src-perf)/arch/$(ARCH)/Makefile
 
@@ -168,6 +149,17 @@ CORE_FEATURE_TESTS =			\
         stackprotector-all              \
         timerfd
 
+# Set FEATURE_CHECK_(C|LD)FLAGS-all for all CORE_FEATURE_TESTS features.
+# If in the future we need per-feature checks/flags for features not
+# mentioned in this list we need to refactor this ;-).
+set_test_all_flags = $(eval $(set_test_all_flags_code))
+define set_test_all_flags_code
+  FEATURE_CHECK_CFLAGS-all  += $(FEATURE_CHECK_CFLAGS-$(1))
+  FEATURE_CHECK_LDFLAGS-all += $(FEATURE_CHECK_LDFLAGS-$(1))
+endef
+
+$(foreach feat,$(CORE_FEATURE_TESTS),$(call set_test_all_flags,$(feat)))
+
 #
 # So here we detect whether test-all was rebuilt, to be able
 # to skip the print-out of the long features list if the file
@@ -240,6 +232,7 @@ endif
 
 CFLAGS += -I$(src-perf)/util/include
 CFLAGS += -I$(src-perf)/arch/$(ARCH)/include
+CFLAGS += -I$(srctree)/tools/include/
 CFLAGS += -I$(srctree)/arch/$(ARCH)/include/uapi
 CFLAGS += -I$(srctree)/arch/$(ARCH)/include
 CFLAGS += -I$(srctree)/include/uapi
diff --git a/tools/perf/config/Makefile.arch b/tools/perf/config/Makefile.arch
new file mode 100644
index 000000000000..fef8ae922800
--- /dev/null
+++ b/tools/perf/config/Makefile.arch
@@ -0,0 +1,22 @@
+
+uname_M := $(shell uname -m 2>/dev/null || echo not)
+
+ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/i386/ -e s/sun4u/sparc64/ \
+                                  -e s/arm.*/arm/ -e s/sa110/arm/ \
+                                  -e s/s390x/s390/ -e s/parisc64/parisc/ \
+                                  -e s/ppc.*/powerpc/ -e s/mips.*/mips/ \
+                                  -e s/sh[234].*/sh/ -e s/aarch64.*/arm64/ )
+
+# Additional ARCH settings for x86
+ifeq ($(ARCH),i386)
+  override ARCH := x86
+endif
+
+ifeq ($(ARCH),x86_64)
+  override ARCH := x86
+  IS_X86_64 := 0
+  ifeq (, $(findstring m32,$(CFLAGS)))
+    IS_X86_64 := $(shell echo __x86_64__ | ${CC} -E -x c - | tail -n 1)
+    RAW_ARCH := x86_64
+  endif
+endif
diff --git a/tools/perf/config/feature-checks/test-volatile-register-var.c b/tools/perf/config/feature-checks/test-volatile-register-var.c
deleted file mode 100644
index c9f398d87868..000000000000
--- a/tools/perf/config/feature-checks/test-volatile-register-var.c
+++ /dev/null
@@ -1,6 +0,0 @@
-#include <stdio.h>
-
-int main(void)
-{
-        return puts("hi");
-}
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index b1cc84b01d5b..af1ce6e14a93 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -269,6 +269,7 @@ struct record_opts {
         u64          user_interval;
         u16          stack_dump_size;
         bool         sample_transaction;
+        unsigned     initial_delay;
 };
 
 #endif
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index 4248d1e96848..653a8fe2db95 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -540,14 +540,11 @@ static int do_test_code_reading(bool try_kcore)
                 err = TEST_CODE_READING_OK;
 out_err:
         if (evlist) {
-                perf_evlist__munmap(evlist);
-                perf_evlist__close(evlist);
                 perf_evlist__delete(evlist);
-        }
-        if (cpus)
+        } else {
                 cpu_map__delete(cpus);
-        if (threads)
                 thread_map__delete(threads);
+        }
         machines__destroy_kernel_maps(&machines);
         machine__delete_threads(machine);
         machines__exit(&machines);
diff --git a/tools/perf/tests/evsel-roundtrip-name.c b/tools/perf/tests/evsel-roundtrip-name.c
index 0197bda9c461..465cdbc345cf 100644
--- a/tools/perf/tests/evsel-roundtrip-name.c
+++ b/tools/perf/tests/evsel-roundtrip-name.c
@@ -79,7 +79,7 @@ static int __perf_evsel__name_array_test(const char *names[], int nr_names)
         }
 
         err = 0;
-        list_for_each_entry(evsel, &evlist->entries, node) {
+        evlist__for_each(evlist, evsel) {
                 if (strcmp(perf_evsel__name(evsel), names[evsel->idx])) {
                         --err;
                         pr_debug("%s != %s\n", perf_evsel__name(evsel), names[evsel->idx]);
diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c
index 173bf42cc03e..2b6519e0e36f 100644
--- a/tools/perf/tests/hists_link.c
+++ b/tools/perf/tests/hists_link.c
@@ -208,7 +208,7 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
          * However the second evsel also has a collapsed entry for
          * "bash [libc] malloc" so total 9 entries will be in the tree.
          */
-        list_for_each_entry(evsel, &evlist->entries, node) {
+        evlist__for_each(evlist, evsel) {
                 for (k = 0; k < ARRAY_SIZE(fake_common_samples); k++) {
                         const union perf_event event = {
                                 .header = {
@@ -466,7 +466,7 @@ int test__hists_link(void)
         if (err < 0)
                 goto out;
 
-        list_for_each_entry(evsel, &evlist->entries, node) {
+        evlist__for_each(evlist, evsel) {
                 hists__collapse_resort(&evsel->hists, NULL);
 
                 if (verbose > 2)
diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c
index 27eb75142b88..497957f269d8 100644
--- a/tools/perf/tests/keep-tracking.c
+++ b/tools/perf/tests/keep-tracking.c
@@ -142,14 +142,11 @@ int test__keep_tracking(void)
 out_err:
         if (evlist) {
                 perf_evlist__disable(evlist);
-                perf_evlist__munmap(evlist);
-                perf_evlist__close(evlist);
                 perf_evlist__delete(evlist);
-        }
-        if (cpus)
+        } else {
                 cpu_map__delete(cpus);
-        if (threads)
                 thread_map__delete(threads);
+        }
 
         return err;
 }
diff --git a/tools/perf/tests/make b/tools/perf/tests/make
index f641c35f2321..00544b8b644b 100644
--- a/tools/perf/tests/make
+++ b/tools/perf/tests/make
@@ -1,6 +1,16 @@
 PERF := .
 MK   := Makefile
 
+include config/Makefile.arch
+
+# FIXME looks like x86 is the only arch running tests ;-)
+# we need some IS_(32/64) flag to make this generic
+ifeq ($(IS_X86_64),1)
+lib = lib64
+else
+lib = lib
+endif
+
 has = $(shell which $1 2>/dev/null)
 
 # standard single make variable specified
@@ -118,16 +128,16 @@ installed_files_bin := bin/perf
 installed_files_bin += etc/bash_completion.d/perf
 installed_files_bin += libexec/perf-core/perf-archive
 
-installed_files_plugins := lib64/traceevent/plugins/plugin_cfg80211.so
-installed_files_plugins += lib64/traceevent/plugins/plugin_scsi.so
-installed_files_plugins += lib64/traceevent/plugins/plugin_xen.so
-installed_files_plugins += lib64/traceevent/plugins/plugin_function.so
-installed_files_plugins += lib64/traceevent/plugins/plugin_sched_switch.so
-installed_files_plugins += lib64/traceevent/plugins/plugin_mac80211.so
-installed_files_plugins += lib64/traceevent/plugins/plugin_kvm.so
-installed_files_plugins += lib64/traceevent/plugins/plugin_kmem.so
-installed_files_plugins += lib64/traceevent/plugins/plugin_hrtimer.so
-installed_files_plugins += lib64/traceevent/plugins/plugin_jbd2.so
+installed_files_plugins := $(lib)/traceevent/plugins/plugin_cfg80211.so
+installed_files_plugins += $(lib)/traceevent/plugins/plugin_scsi.so
+installed_files_plugins += $(lib)/traceevent/plugins/plugin_xen.so
+installed_files_plugins += $(lib)/traceevent/plugins/plugin_function.so
+installed_files_plugins += $(lib)/traceevent/plugins/plugin_sched_switch.so
+installed_files_plugins += $(lib)/traceevent/plugins/plugin_mac80211.so
+installed_files_plugins += $(lib)/traceevent/plugins/plugin_kvm.so
+installed_files_plugins += $(lib)/traceevent/plugins/plugin_kmem.so
+installed_files_plugins += $(lib)/traceevent/plugins/plugin_hrtimer.so
+installed_files_plugins += $(lib)/traceevent/plugins/plugin_jbd2.so
 
 installed_files_all := $(installed_files_bin)
 installed_files_all += $(installed_files_plugins)
@@ -206,10 +216,16 @@ $(run_O):
         rm -rf $$TMP_O \
         rm -rf $$TMP_DEST
 
-all: $(run) $(run_O)
+tarpkg:
+        @cmd="$(PERF)/tests/perf-targz-src-pkg $(PERF)"; \
+        echo "- $@: $$cmd" && echo $$cmd > $@ && \
+        ( eval $$cmd ) >> $@ 2>&1
+        
+
+all: $(run) $(run_O) tarpkg
         @echo OK
 
 out: $(run_O)
         @echo OK
 
-.PHONY: all $(run) $(run_O) clean
+.PHONY: all $(run) $(run_O) tarpkg clean
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index d64ab79c6d35..142263492f6f 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -68,7 +68,7 @@ int test__basic_mmap(void)
                 evsels[i] = perf_evsel__newtp("syscalls", name);
                 if (evsels[i] == NULL) {
                         pr_debug("perf_evsel__new\n");
-                        goto out_free_evlist;
+                        goto out_delete_evlist;
                 }
 
                 evsels[i]->attr.wakeup_events = 1;
@@ -80,7 +80,7 @@ int test__basic_mmap(void)
                         pr_debug("failed to open counter: %s, "
                                  "tweak /proc/sys/kernel/perf_event_paranoid?\n",
                                  strerror(errno));
-                        goto out_close_fd;
+                        goto out_delete_evlist;
                 }
 
                 nr_events[i] = 0;
@@ -90,7 +90,7 @@ int test__basic_mmap(void)
         if (perf_evlist__mmap(evlist, 128, true) < 0) {
                 pr_debug("failed to mmap events: %d (%s)\n", errno,
                          strerror(errno));
-                goto out_close_fd;
+                goto out_delete_evlist;
         }
 
         for (i = 0; i < nsyscalls; ++i)
@@ -105,13 +105,13 @@ int test__basic_mmap(void)
                 if (event->header.type != PERF_RECORD_SAMPLE) {
                         pr_debug("unexpected %s event\n",
                                  perf_event__name(event->header.type));
-                        goto out_munmap;
+                        goto out_delete_evlist;
                 }
 
                 err = perf_evlist__parse_sample(evlist, event, &sample);
                 if (err) {
                         pr_err("Can't parse sample, err = %d\n", err);
-                        goto out_munmap;
+                        goto out_delete_evlist;
                 }
 
                 err = -1;
@@ -119,30 +119,27 @@ int test__basic_mmap(void)
                 if (evsel == NULL) {
                         pr_debug("event with id %" PRIu64
                                  " doesn't map to an evsel\n", sample.id);
-                        goto out_munmap;
+                        goto out_delete_evlist;
                 }
                 nr_events[evsel->idx]++;
                 perf_evlist__mmap_consume(evlist, 0);
         }
 
         err = 0;
-        list_for_each_entry(evsel, &evlist->entries, node) {
+        evlist__for_each(evlist, evsel) {
                 if (nr_events[evsel->idx] != expected_nr_events[evsel->idx]) {
                         pr_debug("expected %d %s events, got %d\n",
                                  expected_nr_events[evsel->idx],
                                  perf_evsel__name(evsel), nr_events[evsel->idx]);
                         err = -1;
-                        goto out_munmap;
+                        goto out_delete_evlist;
                 }
         }
 
-out_munmap:
-        perf_evlist__munmap(evlist);
-out_close_fd:
-        for (i = 0; i < nsyscalls; ++i)
-                perf_evsel__close_fd(evsels[i], 1, threads->nr);
-out_free_evlist:
+out_delete_evlist:
         perf_evlist__delete(evlist);
+        cpus    = NULL;
+        threads = NULL;
 out_free_cpus:
         cpu_map__delete(cpus);
 out_free_threads:
diff --git a/tools/perf/tests/open-syscall-tp-fields.c b/tools/perf/tests/open-syscall-tp-fields.c
index 774620a5aecb..5a016f66f5d2 100644
--- a/tools/perf/tests/open-syscall-tp-fields.c
+++ b/tools/perf/tests/open-syscall-tp-fields.c
@@ -48,13 +48,13 @@ int test__syscall_open_tp_fields(void)
         err = perf_evlist__open(evlist);
         if (err < 0) {
                 pr_debug("perf_evlist__open: %s\n", strerror(errno));
-                goto out_delete_maps;
+                goto out_delete_evlist;
         }
 
         err = perf_evlist__mmap(evlist, UINT_MAX, false);
         if (err < 0) {
                 pr_debug("perf_evlist__mmap: %s\n", strerror(errno));
-                goto out_close_evlist;
+                goto out_delete_evlist;
         }
 
         perf_evlist__enable(evlist);
@@ -85,7 +85,7 @@ int test__syscall_open_tp_fields(void)
                                 err = perf_evsel__parse_sample(evsel, event, &sample);
                                 if (err) {
                                         pr_err("Can't parse sample, err = %d\n", err);
-                                        goto out_munmap;
+                                        goto out_delete_evlist;
                                 }
 
                                 tp_flags = perf_evsel__intval(evsel, &sample, "flags");
@@ -93,7 +93,7 @@ int test__syscall_open_tp_fields(void)
                                 if (flags != tp_flags) {
                                         pr_debug("%s: Expected flags=%#x, got %#x\n",
                                                  __func__, flags, tp_flags);
-                                        goto out_munmap;
+                                        goto out_delete_evlist;
                                 }
 
                                 goto out_ok;
@@ -105,17 +105,11 @@ int test__syscall_open_tp_fields(void)
 
                 if (++nr_polls > 5) {
                         pr_debug("%s: no events!\n", __func__);
-                        goto out_munmap;
+                        goto out_delete_evlist;
                 }
         }
 out_ok:
         err = 0;
-out_munmap:
-        perf_evlist__munmap(evlist);
-out_close_evlist:
-        perf_evlist__close(evlist);
-out_delete_maps:
-        perf_evlist__delete_maps(evlist);
 out_delete_evlist:
         perf_evlist__delete(evlist);
 out:
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index e4ce8aed29d3..4db0ae617d70 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -30,7 +30,7 @@ static int test__checkevent_tracepoint_multi(struct perf_evlist *evlist)
         TEST_ASSERT_VAL("wrong number of entries", evlist->nr_entries > 1);
         TEST_ASSERT_VAL("wrong number of groups", 0 == evlist->nr_groups);
 
-        list_for_each_entry(evsel, &evlist->entries, node) {
+        evlist__for_each(evlist, evsel) {
                 TEST_ASSERT_VAL("wrong type",
                         PERF_TYPE_TRACEPOINT == evsel->attr.type);
                 TEST_ASSERT_VAL("wrong sample_type",
@@ -201,7 +201,7 @@ test__checkevent_tracepoint_multi_modifier(struct perf_evlist *evlist)
 
         TEST_ASSERT_VAL("wrong number of entries", evlist->nr_entries > 1);
 
-        list_for_each_entry(evsel, &evlist->entries, node) {
+        evlist__for_each(evlist, evsel) {
                 TEST_ASSERT_VAL("wrong exclude_user",
                                 !evsel->attr.exclude_user);
                 TEST_ASSERT_VAL("wrong exclude_kernel",
@@ -1385,10 +1385,10 @@ static int test_event(struct evlist_test *e)
         if (ret) {
                 pr_debug("failed to parse event '%s', err %d\n",
                          e->name, ret);
-                return ret;
+        } else {
+                ret = e->check(evlist);
         }
-
-        ret = e->check(evlist);
+        
         perf_evlist__delete(evlist);
 
         return ret;
diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
index eeba562920e9..39cc7c3c0d0c 100644
--- a/tools/perf/tests/perf-record.c
+++ b/tools/perf/tests/perf-record.c
@@ -83,11 +83,10 @@ int test__PERF_RECORD(void)
          * so that we have time to open the evlist (calling sys_perf_event_open
          * on all the fds) and then mmap them.
          */
-        err = perf_evlist__prepare_workload(evlist, &opts.target, argv,
-                                            false, false);
+        err = perf_evlist__prepare_workload(evlist, &opts.target, argv, false, NULL);
         if (err < 0) {
                 pr_debug("Couldn't run the workload!\n");
-                goto out_delete_maps;
+                goto out_delete_evlist;
         }
 
         /*
@@ -102,7 +101,7 @@ int test__PERF_RECORD(void)
         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_maps;
+                goto out_delete_evlist;
         }
 
         cpu = err;
@@ -112,7 +111,7 @@ int test__PERF_RECORD(void)
          */
         if (sched_setaffinity(evlist->workload.pid, cpu_mask_size, &cpu_mask) < 0) {
                 pr_debug("sched_setaffinity: %s\n", strerror(errno));
-                goto out_delete_maps;
+                goto out_delete_evlist;
         }
 
         /*
@@ -122,7 +121,7 @@ int test__PERF_RECORD(void)
         err = perf_evlist__open(evlist);
         if (err < 0) {
                 pr_debug("perf_evlist__open: %s\n", strerror(errno));
-                goto out_delete_maps;
+                goto out_delete_evlist;
         }
 
         /*
@@ -133,7 +132,7 @@ int test__PERF_RECORD(void)
         err = perf_evlist__mmap(evlist, opts.mmap_pages, false);
         if (err < 0) {
                 pr_debug("perf_evlist__mmap: %s\n", strerror(errno));
-                goto out_close_evlist;
+                goto out_delete_evlist;
         }
 
         /*
@@ -166,7 +165,7 @@ int test__PERF_RECORD(void)
                                         if (verbose)
                                                 perf_event__fprintf(event, stderr);
                                         pr_debug("Couldn't parse sample\n");
-                                        goto out_err;
+                                        goto out_delete_evlist;
                                 }
 
                                 if (verbose) {
@@ -303,12 +302,6 @@ found_exit:
                 pr_debug("PERF_RECORD_MMAP for %s missing!\n", "[vdso]");
                 ++errs;
         }
-out_err:
-        perf_evlist__munmap(evlist);
-out_close_evlist:
-        perf_evlist__close(evlist);
-out_delete_maps:
-        perf_evlist__delete_maps(evlist);
 out_delete_evlist:
         perf_evlist__delete(evlist);
 out:
diff --git a/tools/perf/tests/perf-targz-src-pkg b/tools/perf/tests/perf-targz-src-pkg
new file mode 100755
index 000000000000..238aa3927c71
--- /dev/null
+++ b/tools/perf/tests/perf-targz-src-pkg
@@ -0,0 +1,21 @@
+#!/bin/sh
+# Test one of the main kernel Makefile targets to generate a perf sources tarball
+# suitable for build outside the full kernel sources.
+#
+# This is to test that the tools/perf/MANIFEST file lists all the files needed to
+# be in such tarball, which sometimes gets broken when we move files around,
+# like when we made some files that were in tools/perf/ available to other tools/
+# codebases by moving it to tools/include/, etc.
+
+PERF=$1
+cd ${PERF}/../..
+make perf-targz-src-pkg > /dev/null
+TARBALL=$(ls -rt perf-*.tar.gz)
+TMP_DEST=$(mktemp -d)
+tar xf ${TARBALL} -C $TMP_DEST
+rm -f ${TARBALL}
+cd - > /dev/null
+make -C $TMP_DEST/perf*/tools/perf > /dev/null 2>&1
+RC=$?
+rm -rf ${TMP_DEST}
+exit $RC
diff --git a/tools/perf/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c
index c6398b90e897..47146d388dbf 100644
--- a/tools/perf/tests/perf-time-to-tsc.c
+++ b/tools/perf/tests/perf-time-to-tsc.c
@@ -166,14 +166,8 @@ next_event:
 out_err:
         if (evlist) {
                 perf_evlist__disable(evlist);
-                perf_evlist__munmap(evlist);
-                perf_evlist__close(evlist);
                 perf_evlist__delete(evlist);
         }
-        if (cpus)
-                cpu_map__delete(cpus);
-        if (threads)
-                thread_map__delete(threads);
 
         return err;
 }
diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c
index 6664a7cd828c..983d6b8562a8 100644
--- a/tools/perf/tests/sw-clock.c
+++ b/tools/perf/tests/sw-clock.c
@@ -45,7 +45,7 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
         evsel = perf_evsel__new(&attr);
         if (evsel == NULL) {
                 pr_debug("perf_evsel__new\n");
-                goto out_free_evlist;
+                goto out_delete_evlist;
         }
         perf_evlist__add(evlist, evsel);
 
@@ -54,7 +54,7 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
         if (!evlist->cpus || !evlist->threads) {
                 err = -ENOMEM;
                 pr_debug("Not enough memory to create thread/cpu maps\n");
-                goto out_delete_maps;
+                goto out_delete_evlist;
         }
 
         if (perf_evlist__open(evlist)) {
@@ -63,14 +63,14 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
                 err = -errno;
                 pr_debug("Couldn't open evlist: %s\nHint: check %s, using %" PRIu64 " in this test.\n",
                          strerror(errno), knob, (u64)attr.sample_freq);
-                goto out_delete_maps;
+                goto out_delete_evlist;
         }
 
         err = perf_evlist__mmap(evlist, 128, true);
         if (err < 0) {
                 pr_debug("failed to mmap event: %d (%s)\n", errno,
                          strerror(errno));
-                goto out_close_evlist;
+                goto out_delete_evlist;
         }
 
         perf_evlist__enable(evlist);
@@ -90,7 +90,7 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
                 err = perf_evlist__parse_sample(evlist, event, &sample);
                 if (err < 0) {
                         pr_debug("Error during parse sample\n");
-                        goto out_unmap_evlist;
+                        goto out_delete_evlist;
                 }
 
                 total_periods += sample.period;
@@ -105,13 +105,7 @@ next_event:
                 err = -1;
         }
 
-out_unmap_evlist:
-        perf_evlist__munmap(evlist);
-out_close_evlist:
-        perf_evlist__close(evlist);
-out_delete_maps:
-        perf_evlist__delete_maps(evlist);
-out_free_evlist:
+out_delete_evlist:
         perf_evlist__delete(evlist);
         return err;
 }
diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c
index d09ab579119e..5ff3db318f12 100644
--- a/tools/perf/tests/task-exit.c
+++ b/tools/perf/tests/task-exit.c
@@ -9,12 +9,21 @@
 static int exited;
 static int nr_exit;
 
-static void sig_handler(int sig)
+static void sig_handler(int sig __maybe_unused)
 {
         exited = 1;
+}
 
-        if (sig == SIGUSR1)
-                nr_exit = -1;
+/*
+ * perf_evlist__prepare_workload will send a SIGUSR1 if the fork fails, since
+ * we asked by setting its exec_error to this handler.
+ */
+static void workload_exec_failed_signal(int signo __maybe_unused,
+                                        siginfo_t *info __maybe_unused,
+                                        void *ucontext __maybe_unused)
+{
+        exited  = 1;
+        nr_exit = -1;
 }
 
 /*
@@ -35,7 +44,6 @@ int test__task_exit(void)
         const char *argv[] = { "true", NULL };
 
         signal(SIGCHLD, sig_handler);
-        signal(SIGUSR1, sig_handler);
 
         evlist = perf_evlist__new_default();
         if (evlist == NULL) {
@@ -54,13 +62,14 @@ int test__task_exit(void)
         if (!evlist->cpus || !evlist->threads) {
                 err = -ENOMEM;
                 pr_debug("Not enough memory to create thread/cpu maps\n");
-                goto out_delete_maps;
+                goto out_delete_evlist;
         }
 
-        err = perf_evlist__prepare_workload(evlist, &target, argv, false, true);
+        err = perf_evlist__prepare_workload(evlist, &target, argv, false,
+                                            workload_exec_failed_signal);
         if (err < 0) {
                 pr_debug("Couldn't run the workload!\n");
-                goto out_delete_maps;
+                goto out_delete_evlist;
         }
 
         evsel = perf_evlist__first(evlist);
@@ -74,13 +83,13 @@ int test__task_exit(void)
         err = perf_evlist__open(evlist);
         if (err < 0) {
                 pr_debug("Couldn't open the evlist: %s\n", strerror(-err));
-                goto out_delete_maps;
+                goto out_delete_evlist;
         }
 
         if (perf_evlist__mmap(evlist, 128, true) < 0) {
                 pr_debug("failed to mmap events: %d (%s)\n", errno,
                          strerror(errno));
-                goto out_close_evlist;
+                goto out_delete_evlist;
         }
 
         perf_evlist__start_workload(evlist);
@@ -103,11 +112,7 @@ retry:
                 err = -1;
         }
 
-        perf_evlist__munmap(evlist);
-out_close_evlist:
-        perf_evlist__close(evlist);
-out_delete_maps:
-        perf_evlist__delete_maps(evlist);
+out_delete_evlist:
         perf_evlist__delete(evlist);
         return err;
 }
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index a7045ea6d1d5..b720b92eba6e 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -1938,7 +1938,7 @@ static int __perf_evlist__tui_browse_hists(struct perf_evlist *evlist,
 
         ui_helpline__push("Press ESC to exit");
 
-        list_for_each_entry(pos, &evlist->entries, node) {
+        evlist__for_each(evlist, pos) {
                 const char *ev_name = perf_evsel__name(pos);
                 size_t line_len = strlen(ev_name) + 7;
 
@@ -1970,9 +1970,10 @@ single_entry:
                 struct perf_evsel *pos;
 
                 nr_entries = 0;
-                list_for_each_entry(pos, &evlist->entries, node)
+                evlist__for_each(evlist, pos) {
                         if (perf_evsel__is_group_leader(pos))
                                 nr_entries++;
+                }
 
                 if (nr_entries == 1)
                         goto single_entry;
diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c
index 2ca66cc1160f..5b95c44f3435 100644
--- a/tools/perf/ui/gtk/hists.c
+++ b/tools/perf/ui/gtk/hists.c
@@ -375,7 +375,7 @@ int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist,
 
         gtk_container_add(GTK_CONTAINER(window), vbox);
 
-        list_for_each_entry(pos, &evlist->entries, node) {
+        evlist__for_each(evlist, pos) {
                 struct hists *hists = &pos->hists;
                 const char *evname = perf_evsel__name(pos);
                 GtkWidget *scrolled_window;
diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
index 0922aa4218c2..88f7be399432 100644
--- a/tools/perf/util/cgroup.c
+++ b/tools/perf/util/cgroup.c
@@ -81,7 +81,7 @@ static int add_cgroup(struct perf_evlist *evlist, char *str)
         /*
          * check if cgrp is already defined, if so we reuse it
          */
-        list_for_each_entry(counter, &evlist->entries, node) {
+        evlist__for_each(evlist, counter) {
                 cgrp = counter->cgrp;
                 if (!cgrp)
                         continue;
@@ -110,7 +110,7 @@ static int add_cgroup(struct perf_evlist *evlist, char *str)
          * if add cgroup N, then need to find event N
          */
         n = 0;
-        list_for_each_entry(counter, &evlist->entries, node) {
+        evlist__for_each(evlist, counter) {
                 if (n == nr_cgroups)
                         goto found;
                 n++;
diff --git a/tools/perf/util/color.c b/tools/perf/util/color.c
index 66e44a5019d5..87b8672eb413 100644
--- a/tools/perf/util/color.c
+++ b/tools/perf/util/color.c
@@ -1,6 +1,7 @@
 #include <linux/kernel.h>
 #include "cache.h"
 #include "color.h"
+#include <math.h>
 
 int perf_use_color_default = -1;
 
@@ -298,10 +299,10 @@ const char *get_percent_color(double percent)
          * entries in green - and keep the low overhead places
          * normal:
          */
-        if (percent >= MIN_RED)
+        if (fabs(percent) >= MIN_RED)
                 color = PERF_COLOR_RED;
         else {
-                if (percent > MIN_GREEN)
+                if (fabs(percent) > MIN_GREEN)
                         color = PERF_COLOR_GREEN;
         }
         return color;
@@ -318,15 +319,19 @@ int percent_color_fprintf(FILE *fp, const char *fmt, double percent)
         return r;
 }
 
+int value_color_snprintf(char *bf, size_t size, const char *fmt, double value)
+{
+        const char *color = get_percent_color(value);
+        return color_snprintf(bf, size, color, fmt, value);
+}
+
 int percent_color_snprintf(char *bf, size_t size, const char *fmt, ...)
 {
         va_list args;
         double percent;
-        const char *color;
 
         va_start(args, fmt);
         percent = va_arg(args, double);
         va_end(args);
-        color = get_percent_color(percent);
-        return color_snprintf(bf, size, color, fmt, percent);
+        return value_color_snprintf(bf, size, fmt, percent);
 }
diff --git a/tools/perf/util/color.h b/tools/perf/util/color.h
index fced3840e99c..7ff30a62a132 100644
--- a/tools/perf/util/color.h
+++ b/tools/perf/util/color.h
@@ -39,6 +39,7 @@ int color_fprintf(FILE *fp, const char *color, const char *fmt, ...);
 int color_snprintf(char *bf, size_t size, const char *color, const char *fmt, ...);
 int color_fprintf_ln(FILE *fp, const char *color, const char *fmt, ...);
 int color_fwrite_lines(FILE *fp, const char *color, size_t count, const char *buf);
+int value_color_snprintf(char *bf, size_t size, const char *fmt, double value);
 int percent_color_snprintf(char *bf, size_t size, const char *fmt, ...);
 int percent_color_fprintf(FILE *fp, const char *fmt, double percent);
 const char *get_percent_color(double percent);
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 45a76c69a9ed..1fc1c2f04772 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -175,12 +175,12 @@ out:
         return tgid;
 }
 
-static int perf_event__synthesize_mmap_events(struct perf_tool *tool,
-                                              union perf_event *event,
-                                              pid_t pid, pid_t tgid,
-                                              perf_event__handler_t process,
-                                              struct machine *machine,
-                                              bool mmap_data)
+int perf_event__synthesize_mmap_events(struct perf_tool *tool,
+                                       union perf_event *event,
+                                       pid_t pid, pid_t tgid,
+                                       perf_event__handler_t process,
+                                       struct machine *machine,
+                                       bool mmap_data)
 {
         char filename[PATH_MAX];
         FILE *fp;
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 30fec9901e44..faf6e219be21 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -266,6 +266,13 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type,
                                   const struct perf_sample *sample,
                                   bool swapped);
 
+int perf_event__synthesize_mmap_events(struct perf_tool *tool,
+                                       union perf_event *event,
+                                       pid_t pid, pid_t tgid,
+                                       perf_event__handler_t process,
+                                       struct machine *machine,
+                                       bool mmap_data);
+
 size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp);
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index b08a7ecdcea1..40bd2c04df8a 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -81,7 +81,7 @@ static void perf_evlist__update_id_pos(struct perf_evlist *evlist)
 {
         struct perf_evsel *evsel;
 
-        list_for_each_entry(evsel, &evlist->entries, node)
+        evlist__for_each(evlist, evsel)
                 perf_evsel__calc_id_pos(evsel);
 
         perf_evlist__set_id_pos(evlist);
@@ -91,7 +91,7 @@ static void perf_evlist__purge(struct perf_evlist *evlist)
 {
         struct perf_evsel *pos, *n;
 
-        list_for_each_entry_safe(pos, n, &evlist->entries, node) {
+        evlist__for_each_safe(evlist, n, pos) {
                 list_del_init(&pos->node);
                 perf_evsel__delete(pos);
         }
@@ -107,6 +107,12 @@ void perf_evlist__exit(struct perf_evlist *evlist)
 
 void perf_evlist__delete(struct perf_evlist *evlist)
 {
+        perf_evlist__munmap(evlist);
+        perf_evlist__close(evlist);
+        cpu_map__delete(evlist->cpus);
+        thread_map__delete(evlist->threads);
+        evlist->cpus = NULL;
+        evlist->threads = NULL;
         perf_evlist__purge(evlist);
         perf_evlist__exit(evlist);
         free(evlist);
@@ -142,7 +148,7 @@ void __perf_evlist__set_leader(struct list_head *list)
 
         leader->nr_members = evsel->idx - leader->idx + 1;
 
-        list_for_each_entry(evsel, list, node) {
+        __evlist__for_each(list, evsel) {
                 evsel->leader = leader;
         }
 }
@@ -201,7 +207,7 @@ static int perf_evlist__add_attrs(struct perf_evlist *evlist,
         return 0;
 
 out_delete_partial_list:
-        list_for_each_entry_safe(evsel, n, &head, node)
+        __evlist__for_each_safe(&head, n, evsel)
                 perf_evsel__delete(evsel);
         return -1;
 }
@@ -222,7 +228,7 @@ perf_evlist__find_tracepoint_by_id(struct perf_evlist *evlist, int id)
 {
         struct perf_evsel *evsel;
 
-        list_for_each_entry(evsel, &evlist->entries, node) {
+        evlist__for_each(evlist, evsel) {
                 if (evsel->attr.type   == PERF_TYPE_TRACEPOINT &&
                     (int)evsel->attr.config == id)
                         return evsel;
@@ -237,7 +243,7 @@ perf_evlist__find_tracepoint_by_name(struct perf_evlist *evlist,
 {
         struct perf_evsel *evsel;
 
-        list_for_each_entry(evsel, &evlist->entries, node) {
+        evlist__for_each(evlist, evsel) {
                 if ((evsel->attr.type == PERF_TYPE_TRACEPOINT) &&
                     (strcmp(evsel->name, name) == 0))
                         return evsel;
@@ -267,7 +273,7 @@ void perf_evlist__disable(struct perf_evlist *evlist)
         int nr_threads = thread_map__nr(evlist->threads);
 
         for (cpu = 0; cpu < nr_cpus; cpu++) {
-                list_for_each_entry(pos, &evlist->entries, node) {
+                evlist__for_each(evlist, pos) {
                         if (!perf_evsel__is_group_leader(pos) || !pos->fd)
                                 continue;
                         for (thread = 0; thread < nr_threads; thread++)
@@ -285,7 +291,7 @@ void perf_evlist__enable(struct perf_evlist *evlist)
         int nr_threads = thread_map__nr(evlist->threads);
 
         for (cpu = 0; cpu < nr_cpus; cpu++) {
-                list_for_each_entry(pos, &evlist->entries, node) {
+                evlist__for_each(evlist, pos) {
                         if (!perf_evsel__is_group_leader(pos) || !pos->fd)
                                 continue;
                         for (thread = 0; thread < nr_threads; thread++)
@@ -582,6 +588,9 @@ void perf_evlist__munmap(struct perf_evlist *evlist)
 {
         int i;
 
+        if (evlist->mmap == NULL)
+                return;
+
         for (i = 0; i < evlist->nr_mmaps; i++)
                 __perf_evlist__munmap(evlist, i);
 
@@ -621,7 +630,7 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
 {
         struct perf_evsel *evsel;
 
-        list_for_each_entry(evsel, &evlist->entries, node) {
+        evlist__for_each(evlist, evsel) {
                 int fd = FD(evsel, cpu, thread);
 
                 if (*output == -1) {
@@ -797,7 +806,7 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
         pr_debug("mmap size %zuB\n", evlist->mmap_len);
         mask = evlist->mmap_len - page_size - 1;
 
-        list_for_each_entry(evsel, &evlist->entries, node) {
+        evlist__for_each(evlist, evsel) {
                 if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
                     evsel->sample_id == NULL &&
                     perf_evsel__alloc_id(evsel, cpu_map__nr(cpus), threads->nr) < 0)
@@ -833,14 +842,6 @@ out_delete_threads:
         return -1;
 }
 
-void perf_evlist__delete_maps(struct perf_evlist *evlist)
-{
-        cpu_map__delete(evlist->cpus);
-        thread_map__delete(evlist->threads);
-        evlist->cpus    = NULL;
-        evlist->threads = NULL;
-}
-
 int perf_evlist__apply_filters(struct perf_evlist *evlist)
 {
         struct perf_evsel *evsel;
@@ -848,7 +849,7 @@ int perf_evlist__apply_filters(struct perf_evlist *evlist)
         const int ncpus = cpu_map__nr(evlist->cpus),
                   nthreads = thread_map__nr(evlist->threads);
 
-        list_for_each_entry(evsel, &evlist->entries, node) {
+        evlist__for_each(evlist, evsel) {
                 if (evsel->filter == NULL)
                         continue;
 
@@ -867,7 +868,7 @@ int perf_evlist__set_filter(struct perf_evlist *evlist, const char *filter)
         const int ncpus = cpu_map__nr(evlist->cpus),
                   nthreads = thread_map__nr(evlist->threads);
 
-        list_for_each_entry(evsel, &evlist->entries, node) {
+        evlist__for_each(evlist, evsel) {
                 err = perf_evsel__set_filter(evsel, ncpus, nthreads, filter);
                 if (err)
                         break;
@@ -886,7 +887,7 @@ bool perf_evlist__valid_sample_type(struct perf_evlist *evlist)
         if (evlist->id_pos < 0 || evlist->is_pos < 0)
                 return false;
 
-        list_for_each_entry(pos, &evlist->entries, node) {
+        evlist__for_each(evlist, pos) {
                 if (pos->id_pos != evlist->id_pos ||
                     pos->is_pos != evlist->is_pos)
                         return false;
@@ -902,7 +903,7 @@ u64 __perf_evlist__combined_sample_type(struct perf_evlist *evlist)
         if (evlist->combined_sample_type)
                 return evlist->combined_sample_type;
 
-        list_for_each_entry(evsel, &evlist->entries, node)
+        evlist__for_each(evlist, evsel)
                 evlist->combined_sample_type |= evsel->attr.sample_type;
 
         return evlist->combined_sample_type;
@@ -920,7 +921,7 @@ bool perf_evlist__valid_read_format(struct perf_evlist *evlist)
         u64 read_format = first->attr.read_format;
         u64 sample_type = first->attr.sample_type;
 
-        list_for_each_entry_continue(pos, &evlist->entries, node) {
+        evlist__for_each(evlist, pos) {
                 if (read_format != pos->attr.read_format)
                         return false;
         }
@@ -977,7 +978,7 @@ bool perf_evlist__valid_sample_id_all(struct perf_evlist *evlist)
 {
         struct perf_evsel *first = perf_evlist__first(evlist), *pos = first;
 
-        list_for_each_entry_continue(pos, &evlist->entries, node) {
+        evlist__for_each_continue(evlist, pos) {
                 if (first->attr.sample_id_all != pos->attr.sample_id_all)
                         return false;
         }
@@ -1003,7 +1004,7 @@ void perf_evlist__close(struct perf_evlist *evlist)
         int ncpus = cpu_map__nr(evlist->cpus);
         int nthreads = thread_map__nr(evlist->threads);
 
-        list_for_each_entry_reverse(evsel, &evlist->entries, node)
+        evlist__for_each_reverse(evlist, evsel)
                 perf_evsel__close(evsel, ncpus, nthreads);
 }
 
@@ -1014,7 +1015,7 @@ int perf_evlist__open(struct perf_evlist *evlist)
 
         perf_evlist__update_id_pos(evlist);
 
-        list_for_each_entry(evsel, &evlist->entries, node) {
+        evlist__for_each(evlist, evsel) {
                 err = perf_evsel__open(evsel, evlist->cpus, evlist->threads);
                 if (err < 0)
                         goto out_err;
@@ -1029,7 +1030,7 @@ out_err:
 
 int perf_evlist__prepare_workload(struct perf_evlist *evlist, struct target *target,
                                   const char *argv[], bool pipe_output,
-                                  bool want_signal)
+                                  void (*exec_error)(int signo, siginfo_t *info, void *ucontext))
 {
         int child_ready_pipe[2], go_pipe[2];
         char bf;
@@ -1073,12 +1074,25 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist, struct target *tar
 
                 execvp(argv[0], (char **)argv);
 
-                perror(argv[0]);
-                if (want_signal)
-                        kill(getppid(), SIGUSR1);
+                if (exec_error) {
+                        union sigval val;
+
+                        val.sival_int = errno;
+                        if (sigqueue(getppid(), SIGUSR1, val))
+                                perror(argv[0]);
+                } else
+                        perror(argv[0]);
                 exit(-1);
         }
 
+        if (exec_error) {
+                struct sigaction act = {
+                        .sa_flags     = SA_SIGINFO,
+                        .sa_sigaction = exec_error,
+                };
+                sigaction(SIGUSR1, &act, NULL);
+        }
+
         if (target__none(target))
                 evlist->threads->map[0] = evlist->workload.pid;
 
@@ -1140,7 +1154,7 @@ size_t perf_evlist__fprintf(struct perf_evlist *evlist, FILE *fp)
         struct perf_evsel *evsel;
         size_t printed = 0;
 
-        list_for_each_entry(evsel, &evlist->entries, node) {
+        evlist__for_each(evlist, evsel) {
                 printed += fprintf(fp, "%s%s", evsel->idx ? ", " : "",
                                    perf_evsel__name(evsel));
         }
@@ -1219,7 +1233,7 @@ void perf_evlist__to_front(struct perf_evlist *evlist,
         if (move_evsel == perf_evlist__first(evlist))
                 return;
 
-        list_for_each_entry_safe(evsel, n, &evlist->entries, node) {
+        evlist__for_each_safe(evlist, n, evsel) {
                 if (evsel->leader == move_evsel->leader)
                         list_move_tail(&evsel->node, &move);
         }
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 2fe51958ed85..f5173cd63693 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -103,7 +103,8 @@ int record_opts__config(struct record_opts *opts);
 int perf_evlist__prepare_workload(struct perf_evlist *evlist,
                                   struct target *target,
                                   const char *argv[], bool pipe_output,
-                                  bool want_signal);
+                                  void (*exec_error)(int signo, siginfo_t *info,
+                                                     void *ucontext));
 int perf_evlist__start_workload(struct perf_evlist *evlist);
 
 int perf_evlist__parse_mmap_pages(const struct option *opt,
@@ -134,7 +135,6 @@ static inline void perf_evlist__set_maps(struct perf_evlist *evlist,
 }
 
 int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target);
-void perf_evlist__delete_maps(struct perf_evlist *evlist);
 int perf_evlist__apply_filters(struct perf_evlist *evlist);
 
 void __perf_evlist__set_leader(struct list_head *list);
@@ -196,5 +196,70 @@ bool perf_evlist__can_select_event(struct perf_evlist *evlist, const char *str);
 void perf_evlist__to_front(struct perf_evlist *evlist,
                            struct perf_evsel *move_evsel);
 
+/**
+ * __evlist__for_each - iterate thru all the evsels
+ * @list: list_head instance to iterate
+ * @evsel: struct evsel iterator
+ */
+#define __evlist__for_each(list, evsel) \
+        list_for_each_entry(evsel, list, node)
+
+/**
+ * evlist__for_each - iterate thru all the evsels
+ * @evlist: evlist instance to iterate
+ * @evsel: struct evsel iterator
+ */
+#define evlist__for_each(evlist, evsel) \
+        __evlist__for_each(&(evlist)->entries, evsel)
+
+/**
+ * __evlist__for_each_continue - continue iteration thru all the evsels
+ * @list: list_head instance to iterate
+ * @evsel: struct evsel iterator
+ */
+#define __evlist__for_each_continue(list, evsel) \
+        list_for_each_entry_continue(evsel, list, node)
+
+/**
+ * evlist__for_each_continue - continue iteration thru all the evsels
+ * @evlist: evlist instance to iterate
+ * @evsel: struct evsel iterator
+ */
+#define evlist__for_each_continue(evlist, evsel) \
+        __evlist__for_each_continue(&(evlist)->entries, evsel)
+
+/**
+ * __evlist__for_each_reverse - iterate thru all the evsels in reverse order
+ * @list: list_head instance to iterate
+ * @evsel: struct evsel iterator
+ */
+#define __evlist__for_each_reverse(list, evsel) \
+        list_for_each_entry_reverse(evsel, list, node)
+
+/**
+ * evlist__for_each_reverse - iterate thru all the evsels in reverse order
+ * @evlist: evlist instance to iterate
+ * @evsel: struct evsel iterator
+ */
+#define evlist__for_each_reverse(evlist, evsel) \
+        __evlist__for_each_reverse(&(evlist)->entries, evsel)
+
+/**
+ * __evlist__for_each_safe - safely iterate thru all the evsels
+ * @list: list_head instance to iterate
+ * @tmp: struct evsel temp iterator
+ * @evsel: struct evsel iterator
+ */
+#define __evlist__for_each_safe(list, tmp, evsel) \
+        list_for_each_entry_safe(evsel, tmp, list, node)
+
+/**
+ * evlist__for_each_safe - safely iterate thru all the evsels
+ * @evlist: evlist instance to iterate
+ * @evsel: struct evsel iterator
+ * @tmp: struct evsel temp iterator
+ */
+#define evlist__for_each_safe(evlist, tmp, evsel) \
+        __evlist__for_each_safe(&(evlist)->entries, tmp, evsel)
 
 #endif /* __PERF_EVLIST_H */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index ade8d9c1c431..cd4630abfa43 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -658,7 +658,8 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
          * Setting enable_on_exec for independent events and
          * group leaders for traced executed by perf.
          */
-        if (target__none(&opts->target) && perf_evsel__is_group_leader(evsel))
+        if (target__none(&opts->target) && perf_evsel__is_group_leader(evsel) &&
+                !opts->initial_delay)
                 attr->enable_on_exec = 1;
 }
 
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index a4a60b7887ee..bb3e0ede6183 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -643,8 +643,7 @@ static int write_event_desc(int fd, struct perf_header *h __maybe_unused,
         if (ret < 0)
                 return ret;
 
-        list_for_each_entry(evsel, &evlist->entries, node) {
-
+        evlist__for_each(evlist, evsel) {
                 ret = do_write(fd, &evsel->attr, sz);
                 if (ret < 0)
                         return ret;
@@ -1092,7 +1091,7 @@ static int write_group_desc(int fd, struct perf_header *h __maybe_unused,
         if (ret < 0)
                 return ret;
 
-        list_for_each_entry(evsel, &evlist->entries, node) {
+        evlist__for_each(evlist, evsel) {
                 if (perf_evsel__is_group_leader(evsel) &&
                     evsel->nr_members > 1) {
                         const char *name = evsel->group_name ?: "{anon_group}";
@@ -1487,7 +1486,7 @@ static void print_group_desc(struct perf_header *ph, int fd __maybe_unused,
 
         session = container_of(ph, struct perf_session, header);
 
-        list_for_each_entry(evsel, &session->evlist->entries, node) {
+        evlist__for_each(session->evlist, evsel) {
                 if (perf_evsel__is_group_leader(evsel) &&
                     evsel->nr_members > 1) {
                         fprintf(fp, "# group: %s{%s", evsel->group_name ?: "",
@@ -1768,7 +1767,7 @@ perf_evlist__find_by_index(struct perf_evlist *evlist, int idx)
 {
         struct perf_evsel *evsel;
 
-        list_for_each_entry(evsel, &evlist->entries, node) {
+        evlist__for_each(evlist, evsel) {
                 if (evsel->idx == idx)
                         return evsel;
         }
@@ -2071,7 +2070,7 @@ static int process_group_desc(struct perf_file_section *section __maybe_unused,
         session->evlist->nr_groups = nr_groups;
 
         i = nr = 0;
-        list_for_each_entry(evsel, &session->evlist->entries, node) {
+        evlist__for_each(session->evlist, evsel) {
                 if (evsel->idx == (int) desc[i].leader_idx) {
                         evsel->leader = evsel;
                         /* {anon_group} is a dummy name */
@@ -2298,7 +2297,7 @@ int perf_session__write_header(struct perf_session *session,
 
         lseek(fd, sizeof(f_header), SEEK_SET);
 
-        list_for_each_entry(evsel, &evlist->entries, node) {
+        evlist__for_each(session->evlist, evsel) {
                 evsel->id_offset = lseek(fd, 0, SEEK_CUR);
                 err = do_write(fd, evsel->id, evsel->ids * sizeof(u64));
                 if (err < 0) {
@@ -2309,7 +2308,7 @@ int perf_session__write_header(struct perf_session *session,
 
         attr_offset = lseek(fd, 0, SEEK_CUR);
 
-        list_for_each_entry(evsel, &evlist->entries, node) {
+        evlist__for_each(evlist, evsel) {
                 f_attr = (struct perf_file_attr){
                         .attr = evsel->attr,
                         .ids  = {
@@ -2742,7 +2741,7 @@ static int perf_evlist__prepare_tracepoint_events(struct perf_evlist *evlist,
 {
         struct perf_evsel *pos;
 
-        list_for_each_entry(pos, &evlist->entries, node) {
+        evlist__for_each(evlist, pos) {
                 if (pos->attr.type == PERF_TYPE_TRACEPOINT &&
                     perf_evsel__prepare_tracepoint_event(pos, pevent))
                         return -1;
@@ -2890,7 +2889,7 @@ int perf_event__synthesize_attrs(struct perf_tool *tool,
         struct perf_evsel *evsel;
         int err = 0;
 
-        list_for_each_entry(evsel, &session->evlist->entries, node) {
+        evlist__for_each(session->evlist, evsel) {
                 err = perf_event__synthesize_attr(tool, &evsel->attr, evsel->ids,
                                                   evsel->id, process);
                 if (err) {
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 307c9aed972e..a2d047bdf4ef 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -77,16 +77,16 @@ struct perf_session_env {
         unsigned long long      total_mem;
 
         int                     nr_cmdline;
-        char                    *cmdline;
         int                     nr_sibling_cores;
-        char                    *sibling_cores;
         int                     nr_sibling_threads;
-        char                    *sibling_threads;
         int                     nr_numa_nodes;
-        char                    *numa_nodes;
         int                     nr_pmu_mappings;
-        char                    *pmu_mappings;
         int                     nr_groups;
+        char                    *cmdline;
+        char                    *sibling_cores;
+        char                    *sibling_threads;
+        char                    *numa_nodes;
+        char                    *pmu_mappings;
 };
 
 struct perf_header {
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index a98538dc465a..0130279aac51 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -27,6 +27,7 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
         machine->pid = pid;
 
         machine->symbol_filter = NULL;
+        machine->id_hdr_size = 0;
 
         machine->root_dir = strdup(root_dir);
         if (machine->root_dir == NULL)
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 0153435b8427..a7f1b6a91fdd 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -820,8 +820,7 @@ int parse_events__modifier_event(struct list_head *list, char *str, bool add)
         if (!add && get_event_modifier(&mod, str, NULL))
                 return -EINVAL;
 
-        list_for_each_entry(evsel, list, node) {
-
+        __evlist__for_each(list, evsel) {
                 if (add && get_event_modifier(&mod, str, evsel))
                         return -EINVAL;
 
@@ -845,7 +844,7 @@ int parse_events_name(struct list_head *list, char *name)
 {
         struct perf_evsel *evsel;
 
-        list_for_each_entry(evsel, list, node) {
+        __evlist__for_each(list, evsel) {
                 if (!evsel->name)
                         evsel->name = strdup(name);
         }
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 0934d645ebdc..d9cab4d27192 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -505,7 +505,7 @@ static __u64 pmu_format_value(unsigned long *format, __u64 value)
 
 /*
  * Setup one of config[12] attr members based on the
- * user input data - temr parameter.
+ * user input data - term parameter.
  */
 static int pmu_config_term(struct list_head *formats,
                            struct perf_event_attr *attr,
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 86ed8580c3cb..a4ee6b4a840f 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -172,6 +172,7 @@ const char *kernel_get_module_path(const char *module)
         return (dso) ? dso->long_name : NULL;
 }
 
+#ifdef HAVE_DWARF_SUPPORT
 /* Copied from unwind.c */
 static Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep,
                                     GElf_Shdr *shp, const char *name)
@@ -217,6 +218,7 @@ out:
         elf_end(elf);
         return ret;
 }
+#endif
 
 static int init_user_exec(void)
 {
@@ -750,7 +752,8 @@ static int kprobe_convert_to_perf_probe(struct probe_trace_point *tp,
 
 static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
                                 struct probe_trace_event **tevs __maybe_unused,
-                                int max_tevs __maybe_unused, const char *target)
+                                int max_tevs __maybe_unused,
+                                const char *target __maybe_unused)
 {
         if (perf_probe_event_need_dwarf(pev)) {
                 pr_warning("Debuginfo-analysis is not supported.\n");
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 4bf8ace7f511..122669c18ff4 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -908,9 +908,10 @@ static PyObject *pyrf_evlist__item(PyObject *obj, Py_ssize_t i)
         if (i >= pevlist->evlist.nr_entries)
                 return NULL;
 
-        list_for_each_entry(pos, &pevlist->evlist.entries, node)
+        evlist__for_each(&pevlist->evlist, pos) {
                 if (i-- == 0)
                         break;
+        }
 
         return Py_BuildValue("O", container_of(pos, struct pyrf_evsel, evsel));
 }
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index 104a47563d39..373762501dad 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -89,19 +89,19 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts)
         if (evlist->cpus->map[0] < 0)
                 opts->no_inherit = true;
 
-        list_for_each_entry(evsel, &evlist->entries, node)
+        evlist__for_each(evlist, evsel)
                 perf_evsel__config(evsel, opts);
 
         if (evlist->nr_entries > 1) {
                 struct perf_evsel *first = perf_evlist__first(evlist);
 
-                list_for_each_entry(evsel, &evlist->entries, node) {
+                evlist__for_each(evlist, evsel) {
                         if (evsel->attr.sample_type == first->attr.sample_type)
                                 continue;
                         use_sample_identifier = perf_can_sample_identifier();
                         break;
                 }
-                list_for_each_entry(evsel, &evlist->entries, node)
+                evlist__for_each(evlist, evsel)
                         perf_evsel__set_sample_id(evsel, use_sample_identifier);
         }
 
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 8ffe29c55d0f..7acc03e8f3b2 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1384,7 +1384,7 @@ bool perf_session__has_traces(struct perf_session *session, const char *msg)
 {
         struct perf_evsel *evsel;
 
-        list_for_each_entry(evsel, &session->evlist->entries, node) {
+        evlist__for_each(session->evlist, evsel) {
                 if (evsel->attr.type == PERF_TYPE_TRACEPOINT)
                         return true;
         }
@@ -1442,7 +1442,7 @@ size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp)
 
         ret += events_stats__fprintf(&session->stats, fp);
 
-        list_for_each_entry(pos, &session->evlist->entries, node) {
+        evlist__for_each(session->evlist, pos) {
                 ret += fprintf(fp, "%s stats:\n", perf_evsel__name(pos));
                 ret += events_stats__fprintf(&pos->hists.stats, fp);
         }
@@ -1464,7 +1464,7 @@ struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,
 {
         struct perf_evsel *pos;
 
-        list_for_each_entry(pos, &session->evlist->entries, node) {
+        evlist__for_each(session->evlist, pos) {
                 if (pos->attr.type == type)
                         return pos;
         }
diff --git a/tools/perf/util/unwind.c b/tools/perf/util/unwind.c
index 0efd5393de85..416f22bf3693 100644
--- a/tools/perf/util/unwind.c
+++ b/tools/perf/util/unwind.c
@@ -340,10 +340,10 @@ find_proc_info(unw_addr_space_t as, unw_word_t ip, unw_proc_info_t *pi,
         /* Check the .debug_frame section for unwinding info */
         if (!read_unwind_spec_debug_frame(map->dso, ui->machine, &segbase)) {
                 memset(&di, 0, sizeof(di));
-                dwarf_find_debug_frame(0, &di, ip, 0, map->dso->name,
-                                       map->start, map->end);
-                return dwarf_search_unwind_table(as, ip, &di, pi,
-                                                 need_unwind_info, arg);
+                if (dwarf_find_debug_frame(0, &di, ip, 0, map->dso->name,
+                                           map->start, map->end))
+                        return dwarf_search_unwind_table(as, ip, &di, pi,
+                                                         need_unwind_info, arg);
         }
 #endif