23 files changed, 190 insertions, 141 deletions

diff --git a/tools/perf/Documentation/intel-pt.txt b/tools/perf/Documentation/intel-pt.txt
index 4a0501d7a3b4..c94c9de3173e 100644
--- a/tools/perf/Documentation/intel-pt.txt
+++ b/tools/perf/Documentation/intel-pt.txt
@@ -364,21 +364,6 @@ cyc_thresh	Specifies how frequently CYC packets are produced - see cyc
 
                 CYC packets are not requested by default.
 
-no_force_psb    This is a driver option and is not in the IA32_RTIT_CTL MSR.
-
-                It stops the driver resetting the byte count to zero whenever
-                enabling the trace (for example on context switches) which in
-                turn results in no PSB being forced.  However some processors
-                will produce a PSB anyway.
-
-                In any case, there is still a PSB when the trace is enabled for
-                the first time.
-
-                no_force_psb can be used to slightly decrease the trace size but
-                may make it harder for the decoder to recover from errors.
-
-                no_force_psb is not selected by default.
-
 
 new snapshot option
 -------------------
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index eb51325e8ad9..284a76e04628 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -768,8 +768,8 @@ static int process_exit_event(struct perf_tool *tool,
         if (!evsel->attr.sample_id_all) {
                 sample->cpu = 0;
                 sample->time = 0;
-                sample->tid = event->comm.tid;
-                sample->pid = event->comm.pid;
+                sample->tid = event->fork.tid;
+                sample->pid = event->fork.pid;
         }
         print_sample_start(sample, thread, evsel);
         perf_event__fprintf(event, stdout);
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index 827557fc7511..38a08539f4bf 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -573,9 +573,14 @@ ifndef NO_LIBNUMA
     msg := $(warning No numa.h found, disables 'perf bench numa mem' benchmark, please install numactl-devel/libnuma-devel/libnuma-dev);
     NO_LIBNUMA := 1
   else
-    CFLAGS += -DHAVE_LIBNUMA_SUPPORT
-    EXTLIBS += -lnuma
-    $(call detected,CONFIG_NUMA)
+    ifeq ($(feature-numa_num_possible_cpus), 0)
+      msg := $(warning Old numa library found, disables 'perf bench numa mem' benchmark, please install numactl-devel/libnuma-devel/libnuma-dev >= 2.0.8);
+      NO_LIBNUMA := 1
+    else
+      CFLAGS += -DHAVE_LIBNUMA_SUPPORT
+      EXTLIBS += -lnuma
+      $(call detected,CONFIG_NUMA)
+    endif
   endif
 endif
 
@@ -621,8 +626,13 @@ ifdef LIBBABELTRACE
 endif
 
 ifndef NO_AUXTRACE
-  $(call detected,CONFIG_AUXTRACE)
-  CFLAGS += -DHAVE_AUXTRACE_SUPPORT
+  ifeq ($(feature-get_cpuid), 0)
+    msg := $(warning Your gcc lacks the __get_cpuid() builtin, disables support for auxtrace/Intel PT, please install a newer gcc);
+    NO_AUXTRACE := 1
+  else
+    $(call detected,CONFIG_AUXTRACE)
+    CFLAGS += -DHAVE_AUXTRACE_SUPPORT
+  endif
 endif
 
 # Among the variables below, these:
diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c
index 1aa21c90731b..5b83f56a3b6f 100644
--- a/tools/perf/tests/sw-clock.c
+++ b/tools/perf/tests/sw-clock.c
@@ -34,6 +34,8 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
                 .disabled = 1,
                 .freq = 1,
         };
+        struct cpu_map *cpus;
+        struct thread_map *threads;
 
         attr.sample_freq = 500;
 
@@ -50,14 +52,19 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
         }
         perf_evlist__add(evlist, evsel);
 
-        evlist->cpus = cpu_map__dummy_new();
-        evlist->threads = thread_map__new_by_tid(getpid());
-        if (!evlist->cpus || !evlist->threads) {
+        cpus = cpu_map__dummy_new();
+        threads = thread_map__new_by_tid(getpid());
+        if (!cpus || !threads) {
                 err = -ENOMEM;
                 pr_debug("Not enough memory to create thread/cpu maps\n");
-                goto out_delete_evlist;
+                goto out_free_maps;
         }
 
+        perf_evlist__set_maps(evlist, cpus, threads);
+
+        cpus    = NULL;
+        threads = NULL;
+
         if (perf_evlist__open(evlist)) {
                 const char *knob = "/proc/sys/kernel/perf_event_max_sample_rate";
 
@@ -107,6 +114,9 @@ next_event:
                 err = -1;
         }
 
+out_free_maps:
+        cpu_map__put(cpus);
+        thread_map__put(threads);
 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 3a8fedef83bc..add16385f13e 100644
--- a/tools/perf/tests/task-exit.c
+++ b/tools/perf/tests/task-exit.c
@@ -43,6 +43,8 @@ int test__task_exit(void)
         };
         const char *argv[] = { "true", NULL };
         char sbuf[STRERR_BUFSIZE];
+        struct cpu_map *cpus;
+        struct thread_map *threads;
 
         signal(SIGCHLD, sig_handler);
 
@@ -58,14 +60,19 @@ int test__task_exit(void)
          * perf_evlist__prepare_workload we'll fill in the only thread
          * we're monitoring, the one forked there.
          */
-        evlist->cpus = cpu_map__dummy_new();
-        evlist->threads = thread_map__new_by_tid(-1);
-        if (!evlist->cpus || !evlist->threads) {
+        cpus = cpu_map__dummy_new();
+        threads = thread_map__new_by_tid(-1);
+        if (!cpus || !threads) {
                 err = -ENOMEM;
                 pr_debug("Not enough memory to create thread/cpu maps\n");
-                goto out_delete_evlist;
+                goto out_free_maps;
         }
 
+        perf_evlist__set_maps(evlist, cpus, threads);
+
+        cpus    = NULL;
+        threads = NULL;
+
         err = perf_evlist__prepare_workload(evlist, &target, argv, false,
                                             workload_exec_failed_signal);
         if (err < 0) {
@@ -114,6 +121,9 @@ retry:
                 err = -1;
         }
 
+out_free_maps:
+        cpu_map__put(cpus);
+        thread_map__put(threads);
 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 cf86f2d3a5e7..c04c60d4863c 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -1968,7 +1968,8 @@ skip_annotation:
                                           &options[nr_options], dso);
                 nr_options += add_map_opt(browser, &actions[nr_options],
                                           &options[nr_options],
-                                          browser->selection->map);
+                                          browser->selection ?
+                                                browser->selection->map : NULL);
 
                 /* perf script support */
                 if (browser->he_selection) {
@@ -1976,6 +1977,15 @@ skip_annotation:
                                                      &actions[nr_options],
                                                      &options[nr_options],
                                                      thread, NULL);
+                        /*
+                         * Note that browser->selection != NULL
+                         * when browser->he_selection is not NULL,
+                         * so we don't need to check browser->selection
+                         * before fetching browser->selection->sym like what
+                         * we do before fetching browser->selection->map.
+                         *
+                         * See hist_browser__show_entry.
+                         */
                         nr_options += add_script_opt(browser,
                                                      &actions[nr_options],
                                                      &options[nr_options],
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 349bc96ca1fe..e5f18a288b74 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -17,6 +17,7 @@ libperf-y += levenshtein.o
 libperf-y += llvm-utils.o
 libperf-y += parse-options.o
 libperf-y += parse-events.o
+libperf-y += perf_regs.o
 libperf-y += path.o
 libperf-y += rbtree.o
 libperf-y += bitmap.o
@@ -103,7 +104,6 @@ libperf-$(CONFIG_LIBBABELTRACE) += data-convert-bt.o
 
 libperf-y += scripting-engines/
 
-libperf-$(CONFIG_PERF_REGS) += perf_regs.o
 libperf-$(CONFIG_ZLIB) += zlib.o
 libperf-$(CONFIG_LZMA) += lzma.o
 
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index d51a5200c8af..c8fc8a258f42 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -124,6 +124,33 @@ void perf_evlist__delete(struct perf_evlist *evlist)
         free(evlist);
 }
 
+static void __perf_evlist__propagate_maps(struct perf_evlist *evlist,
+                                          struct perf_evsel *evsel)
+{
+        /*
+         * We already have cpus for evsel (via PMU sysfs) so
+         * keep it, if there's no target cpu list defined.
+         */
+        if (!evsel->own_cpus || evlist->has_user_cpus) {
+                cpu_map__put(evsel->cpus);
+                evsel->cpus = cpu_map__get(evlist->cpus);
+        } else if (evsel->cpus != evsel->own_cpus) {
+                cpu_map__put(evsel->cpus);
+                evsel->cpus = cpu_map__get(evsel->own_cpus);
+        }
+
+        thread_map__put(evsel->threads);
+        evsel->threads = thread_map__get(evlist->threads);
+}
+
+static void perf_evlist__propagate_maps(struct perf_evlist *evlist)
+{
+        struct perf_evsel *evsel;
+
+        evlist__for_each(evlist, evsel)
+                __perf_evlist__propagate_maps(evlist, evsel);
+}
+
 void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry)
 {
         entry->evlist = evlist;
@@ -133,18 +160,19 @@ void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry)
 
         if (!evlist->nr_entries++)
                 perf_evlist__set_id_pos(evlist);
+
+        __perf_evlist__propagate_maps(evlist, entry);
 }
 
 void perf_evlist__splice_list_tail(struct perf_evlist *evlist,
-                                   struct list_head *list,
-                                   int nr_entries)
+                                   struct list_head *list)
 {
-        bool set_id_pos = !evlist->nr_entries;
+        struct perf_evsel *evsel, *temp;
 
-        list_splice_tail(list, &evlist->entries);
-        evlist->nr_entries += nr_entries;
-        if (set_id_pos)
-                perf_evlist__set_id_pos(evlist);
+        __evlist__for_each_safe(list, temp, evsel) {
+                list_del_init(&evsel->node);
+                perf_evlist__add(evlist, evsel);
+        }
 }
 
 void __perf_evlist__set_leader(struct list_head *list)
@@ -210,7 +238,7 @@ static int perf_evlist__add_attrs(struct perf_evlist *evlist,
                 list_add_tail(&evsel->node, &head);
         }
 
-        perf_evlist__splice_list_tail(evlist, &head, nr_attrs);
+        perf_evlist__splice_list_tail(evlist, &head);
 
         return 0;
 
@@ -1103,71 +1131,56 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
         return perf_evlist__mmap_ex(evlist, pages, overwrite, 0, false);
 }
 
-static int perf_evlist__propagate_maps(struct perf_evlist *evlist,
-                                       bool has_user_cpus)
-{
-        struct perf_evsel *evsel;
-
-        evlist__for_each(evlist, evsel) {
-                /*
-                 * We already have cpus for evsel (via PMU sysfs) so
-                 * keep it, if there's no target cpu list defined.
-                 */
-                if (evsel->cpus && has_user_cpus)
-                        cpu_map__put(evsel->cpus);
-
-                if (!evsel->cpus || has_user_cpus)
-                        evsel->cpus = cpu_map__get(evlist->cpus);
-
-                evsel->threads = thread_map__get(evlist->threads);
-
-                if ((evlist->cpus && !evsel->cpus) ||
-                    (evlist->threads && !evsel->threads))
-                        return -ENOMEM;
-        }
-
-        return 0;
-}
-
 int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
 {
-        evlist->threads = thread_map__new_str(target->pid, target->tid,
-                                              target->uid);
+        struct cpu_map *cpus;
+        struct thread_map *threads;
+
+        threads = thread_map__new_str(target->pid, target->tid, target->uid);
 
-        if (evlist->threads == NULL)
+        if (!threads)
                 return -1;
 
         if (target__uses_dummy_map(target))
-                evlist->cpus = cpu_map__dummy_new();
+                cpus = cpu_map__dummy_new();
         else
-                evlist->cpus = cpu_map__new(target->cpu_list);
+                cpus = cpu_map__new(target->cpu_list);
 
-        if (evlist->cpus == NULL)
+        if (!cpus)
                 goto out_delete_threads;
 
-        return perf_evlist__propagate_maps(evlist, !!target->cpu_list);
+        evlist->has_user_cpus = !!target->cpu_list;
+
+        perf_evlist__set_maps(evlist, cpus, threads);
+
+        return 0;
 
 out_delete_threads:
-        thread_map__put(evlist->threads);
-        evlist->threads = NULL;
+        thread_map__put(threads);
         return -1;
 }
 
-int perf_evlist__set_maps(struct perf_evlist *evlist,
-                          struct cpu_map *cpus,
-                          struct thread_map *threads)
+void perf_evlist__set_maps(struct perf_evlist *evlist, struct cpu_map *cpus,
+                           struct thread_map *threads)
 {
-        if (evlist->cpus)
+        /*
+         * Allow for the possibility that one or another of the maps isn't being
+         * changed i.e. don't put it.  Note we are assuming the maps that are
+         * being applied are brand new and evlist is taking ownership of the
+         * original reference count of 1.  If that is not the case it is up to
+         * the caller to increase the reference count.
+         */
+        if (cpus != evlist->cpus) {
                 cpu_map__put(evlist->cpus);
+                evlist->cpus = cpus;
+        }
 
-        evlist->cpus = cpus;
-
-        if (evlist->threads)
+        if (threads != evlist->threads) {
                 thread_map__put(evlist->threads);
+                evlist->threads = threads;
+        }
 
-        evlist->threads = threads;
-
-        return perf_evlist__propagate_maps(evlist, false);
+        perf_evlist__propagate_maps(evlist);
 }
 
 int perf_evlist__apply_filters(struct perf_evlist *evlist, struct perf_evsel **err_evsel)
@@ -1387,6 +1400,8 @@ void perf_evlist__close(struct perf_evlist *evlist)
 
 static int perf_evlist__create_syswide_maps(struct perf_evlist *evlist)
 {
+        struct cpu_map    *cpus;
+        struct thread_map *threads;
         int err = -ENOMEM;
 
         /*
@@ -1398,20 +1413,19 @@ static int perf_evlist__create_syswide_maps(struct perf_evlist *evlist)
          * error, and we may not want to do that fallback to a
          * default cpu identity map :-\
          */
-        evlist->cpus = cpu_map__new(NULL);
-        if (evlist->cpus == NULL)
+        cpus = cpu_map__new(NULL);
+        if (!cpus)
                 goto out;
 
-        evlist->threads = thread_map__new_dummy();
-        if (evlist->threads == NULL)
-                goto out_free_cpus;
+        threads = thread_map__new_dummy();
+        if (!threads)
+                goto out_put;
 
-        err = 0;
+        perf_evlist__set_maps(evlist, cpus, threads);
 out:
         return err;
-out_free_cpus:
-        cpu_map__put(evlist->cpus);
-        evlist->cpus = NULL;
+out_put:
+        cpu_map__put(cpus);
         goto out;
 }
 
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index b39a6198f4ac..115d8b53c601 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -42,6 +42,7 @@ struct perf_evlist {
         int              nr_mmaps;
         bool             overwrite;
         bool             enabled;
+        bool             has_user_cpus;
         size_t           mmap_len;
         int              id_pos;
         int              is_pos;
@@ -155,9 +156,8 @@ int perf_evlist__enable_event_idx(struct perf_evlist *evlist,
 void perf_evlist__set_selected(struct perf_evlist *evlist,
                                struct perf_evsel *evsel);
 
-int perf_evlist__set_maps(struct perf_evlist *evlist,
-                          struct cpu_map *cpus,
-                          struct thread_map *threads);
+void perf_evlist__set_maps(struct perf_evlist *evlist, struct cpu_map *cpus,
+                           struct thread_map *threads);
 int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target);
 int perf_evlist__apply_filters(struct perf_evlist *evlist, struct perf_evsel **err_evsel);
 
@@ -179,8 +179,7 @@ bool perf_evlist__valid_sample_id_all(struct perf_evlist *evlist);
 bool perf_evlist__valid_read_format(struct perf_evlist *evlist);
 
 void perf_evlist__splice_list_tail(struct perf_evlist *evlist,
-                                   struct list_head *list,
-                                   int nr_entries);
+                                   struct list_head *list);
 
 static inline struct perf_evsel *perf_evlist__first(struct perf_evlist *evlist)
 {
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index c53f79123b37..5410483d5219 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1033,6 +1033,7 @@ void perf_evsel__exit(struct perf_evsel *evsel)
         perf_evsel__free_config_terms(evsel);
         close_cgroup(evsel->cgrp);
         cpu_map__put(evsel->cpus);
+        cpu_map__put(evsel->own_cpus);
         thread_map__put(evsel->threads);
         zfree(&evsel->group_name);
         zfree(&evsel->name);
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 298e6bbca200..ef8925f7211a 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -98,6 +98,7 @@ struct perf_evsel {
         struct cgroup_sel       *cgrp;
         void                    *handler;
         struct cpu_map          *cpus;
+        struct cpu_map          *own_cpus;
         struct thread_map       *threads;
         unsigned int            sample_size;
         int                     id_pos;
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 41814547da15..fce6634aebe2 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1438,7 +1438,7 @@ static int process_nrcpus(struct perf_file_section *section __maybe_unused,
         if (ph->needs_swap)
                 nr = bswap_32(nr);
 
-        ph->env.nr_cpus_online = nr;
+        ph->env.nr_cpus_avail = nr;
 
         ret = readn(fd, &nr, sizeof(nr));
         if (ret != sizeof(nr))
@@ -1447,7 +1447,7 @@ static int process_nrcpus(struct perf_file_section *section __maybe_unused,
         if (ph->needs_swap)
                 nr = bswap_32(nr);
 
-        ph->env.nr_cpus_avail = nr;
+        ph->env.nr_cpus_online = nr;
         return 0;
 }
 
diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c
index ea768625ab5b..eb0e7f8bf515 100644
--- a/tools/perf/util/intel-bts.c
+++ b/tools/perf/util/intel-bts.c
@@ -623,7 +623,7 @@ static int intel_bts_process_event(struct perf_session *session,
         if (err)
                 return err;
         if (event->header.type == PERF_RECORD_EXIT) {
-                err = intel_bts_process_tid_exit(bts, event->comm.tid);
+                err = intel_bts_process_tid_exit(bts, event->fork.tid);
                 if (err)
                         return err;
         }
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index bb41c20e6005..535d86f8e4d1 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -1494,7 +1494,7 @@ static int intel_pt_process_event(struct perf_session *session,
         if (pt->timeless_decoding) {
                 if (event->header.type == PERF_RECORD_EXIT) {
                         err = intel_pt_process_timeless_queues(pt,
-                                                               event->comm.tid,
+                                                               event->fork.tid,
                                                                sample->time);
                 }
         } else if (timestamp) {
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index d826e6f515db..21ed6ee63da9 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -287,8 +287,8 @@ __add_event(struct list_head *list, int *idx,
         if (!evsel)
                 return NULL;
 
-        if (cpus)
-                evsel->cpus = cpu_map__get(cpus);
+        evsel->cpus     = cpu_map__get(cpus);
+        evsel->own_cpus = cpu_map__get(cpus);
 
         if (name)
                 evsel->name = strdup(name);
@@ -1140,10 +1140,9 @@ int parse_events(struct perf_evlist *evlist, const char *str,
         ret = parse_events__scanner(str, &data, PE_START_EVENTS);
         perf_pmu__parse_cleanup();
         if (!ret) {
-                int entries = data.idx - evlist->nr_entries;
                 struct perf_evsel *last;
 
-                perf_evlist__splice_list_tail(evlist, &data.list, entries);
+                perf_evlist__splice_list_tail(evlist, &data.list);
                 evlist->nr_groups += data.nr_groups;
                 last = perf_evlist__last(evlist);
                 last->cmdline_group_boundary = true;
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 591905a02b92..9cd70819c795 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -255,7 +255,7 @@ PE_PMU_EVENT_PRE '-' PE_PMU_EVENT_SUF sep_dc
         list_add_tail(&term->list, head);
 
         ALLOC_LIST(list);
-        ABORT_ON(parse_events_add_pmu(list, &data->idx, "cpu", head));
+        ABORT_ON(parse_events_add_pmu(data, list, "cpu", head));
         parse_events__free_terms(head);
         $$ = list;
 }
diff --git a/tools/perf/util/perf_regs.c b/tools/perf/util/perf_regs.c
index 885e8ac83997..6b8eb13e14e4 100644
--- a/tools/perf/util/perf_regs.c
+++ b/tools/perf/util/perf_regs.c
@@ -6,6 +6,7 @@ const struct sample_reg __weak sample_reg_masks[] = {
         SMPL_REG_END
 };
 
+#ifdef HAVE_PERF_REGS_SUPPORT
 int perf_reg_value(u64 *valp, struct regs_dump *regs, int id)
 {
         int i, idx = 0;
@@ -29,3 +30,4 @@ out:
         *valp = regs->cache_regs[id];
         return 0;
 }
+#endif
diff --git a/tools/perf/util/perf_regs.h b/tools/perf/util/perf_regs.h
index 2984dcc54d67..679d6e493962 100644
--- a/tools/perf/util/perf_regs.h
+++ b/tools/perf/util/perf_regs.h
@@ -2,6 +2,7 @@
 #define __PERF_REGS_H
 
 #include <linux/types.h>
+#include <linux/compiler.h>
 
 struct regs_dump;
 
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index eb5f18b75402..c6f9af78f6f5 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -270,12 +270,13 @@ static int kernel_get_module_dso(const char *module, struct dso **pdso)
         int ret = 0;
 
         if (module) {
-                list_for_each_entry(dso, &host_machine->dsos.head, node) {
-                        if (!dso->kernel)
-                                continue;
-                        if (strncmp(dso->short_name + 1, module,
-                                    dso->short_name_len - 2) == 0)
-                                goto found;
+                char module_name[128];
+
+                snprintf(module_name, sizeof(module_name), "[%s]", module);
+                map = map_groups__find_by_name(&host_machine->kmaps, MAP__FUNCTION, module_name);
+                if (map) {
+                        dso = map->dso;
+                        goto found;
                 }
                 pr_debug("Failed to find module %s.\n", module);
                 return -ENOENT;
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 8a4537ee9bc3..fc3f7c922f99 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1580,7 +1580,10 @@ static int __perf_session__process_events(struct perf_session *session,
         file_offset = page_offset;
         head = data_offset - page_offset;
 
-        if (data_size && (data_offset + data_size < file_size))
+        if (data_size == 0)
+                goto out;
+
+        if (data_offset + data_size < file_size)
                 file_size = data_offset + data_size;
 
         ui_progress__init(&prog, file_size, "Processing events...");
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 415c359de465..2d065d065b67 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -196,7 +196,8 @@ static void zero_per_pkg(struct perf_evsel *counter)
                 memset(counter->per_pkg_mask, 0, MAX_NR_CPUS);
 }
 
-static int check_per_pkg(struct perf_evsel *counter, int cpu, bool *skip)
+static int check_per_pkg(struct perf_evsel *counter,
+                         struct perf_counts_values *vals, int cpu, bool *skip)
 {
         unsigned long *mask = counter->per_pkg_mask;
         struct cpu_map *cpus = perf_evsel__cpus(counter);
@@ -218,6 +219,17 @@ static int check_per_pkg(struct perf_evsel *counter, int cpu, bool *skip)
                 counter->per_pkg_mask = mask;
         }
 
+        /*
+         * we do not consider an event that has not run as a good
+         * instance to mark a package as used (skip=1). Otherwise
+         * we may run into a situation where the first CPU in a package
+         * is not running anything, yet the second is, and this function
+         * would mark the package as used after the first CPU and would
+         * not read the values from the second CPU.
+         */
+        if (!(vals->run && vals->ena))
+                return 0;
+
         s = cpu_map__get_socket(cpus, cpu);
         if (s < 0)
                 return -1;
@@ -235,7 +247,7 @@ process_counter_values(struct perf_stat_config *config, struct perf_evsel *evsel
         static struct perf_counts_values zero;
         bool skip = false;
 
-        if (check_per_pkg(evsel, cpu, &skip)) {
+        if (check_per_pkg(evsel, count, cpu, &skip)) {
                 pr_err("failed to read per-pkg counter\n");
                 return -1;
         }
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 53bb5f59ec58..475d88d0a1c9 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -38,7 +38,7 @@ static inline char *bfd_demangle(void __maybe_unused *v,
 #endif
 
 #ifndef HAVE_ELF_GETPHDRNUM_SUPPORT
-int elf_getphdrnum(Elf *elf, size_t *dst)
+static int elf_getphdrnum(Elf *elf, size_t *dst)
 {
         GElf_Ehdr gehdr;
         GElf_Ehdr *ehdr;
@@ -1271,8 +1271,6 @@ out_close:
 static int kcore__init(struct kcore *kcore, char *filename, int elfclass,
                        bool temp)
 {
-        GElf_Ehdr *ehdr;
-
         kcore->elfclass = elfclass;
 
         if (temp)
@@ -1289,9 +1287,7 @@ static int kcore__init(struct kcore *kcore, char *filename, int elfclass,
         if (!gelf_newehdr(kcore->elf, elfclass))
                 goto out_end;
 
-        ehdr = gelf_getehdr(kcore->elf, &kcore->ehdr);
-        if (!ehdr)
-                goto out_end;
+        memset(&kcore->ehdr, 0, sizeof(GElf_Ehdr));
 
         return 0;
 
@@ -1348,23 +1344,18 @@ static int kcore__copy_hdr(struct kcore *from, struct kcore *to, size_t count)
 static int kcore__add_phdr(struct kcore *kcore, int idx, off_t offset,
                            u64 addr, u64 len)
 {
-        GElf_Phdr gphdr;
-        GElf_Phdr *phdr;
-
-        phdr = gelf_getphdr(kcore->elf, idx, &gphdr);
-        if (!phdr)
-                return -1;
-
-        phdr->p_type    = PT_LOAD;
-        phdr->p_flags   = PF_R | PF_W | PF_X;
-        phdr->p_offset  = offset;
-        phdr->p_vaddr   = addr;
-        phdr->p_paddr   = 0;
-        phdr->p_filesz  = len;
-        phdr->p_memsz   = len;
-        phdr->p_align   = page_size;
-
-        if (!gelf_update_phdr(kcore->elf, idx, phdr))
+        GElf_Phdr phdr = {
+                .p_type         = PT_LOAD,
+                .p_flags        = PF_R | PF_W | PF_X,
+                .p_offset       = offset,
+                .p_vaddr        = addr,
+                .p_paddr        = 0,
+                .p_filesz       = len,
+                .p_memsz        = len,
+                .p_align        = page_size,
+        };
+
+        if (!gelf_update_phdr(kcore->elf, idx, &phdr))
                 return -1;
 
         return 0;
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 7acafb3c5592..c2cd9bf2348b 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -709,7 +709,7 @@ bool find_process(const char *name)
 
         dir = opendir(procfs__mountpoint());
         if (!dir)
-                return -1;
+                return false;
 
         /* Walk through the directory. */
         while (ret && (d = readdir(dir)) != NULL) {