29 files changed, 280 insertions, 107 deletions

diff --git a/tools/lib/subcmd/parse-options.c b/tools/lib/subcmd/parse-options.c
index 3284bb14ae78..8aad81151d50 100644
--- a/tools/lib/subcmd/parse-options.c
+++ b/tools/lib/subcmd/parse-options.c
@@ -213,6 +213,9 @@ static int get_value(struct parse_opt_ctx_t *p,
                 else
                         err = get_arg(p, opt, flags, (const char **)opt->value);
 
+                if (opt->set)
+                        *(bool *)opt->set = true;
+
                 /* PARSE_OPT_NOEMPTY: Allow NULL but disallow empty string. */
                 if (opt->flags & PARSE_OPT_NOEMPTY) {
                         const char *val = *(const char **)opt->value;
diff --git a/tools/lib/subcmd/parse-options.h b/tools/lib/subcmd/parse-options.h
index 8866ac438b34..11c3be3bcce7 100644
--- a/tools/lib/subcmd/parse-options.h
+++ b/tools/lib/subcmd/parse-options.h
@@ -137,6 +137,11 @@ struct option {
         { .type = OPTION_STRING,  .short_name = (s), .long_name = (l), \
           .value = check_vtype(v, const char **), (a), .help = (h), \
           .flags = PARSE_OPT_OPTARG, .defval = (intptr_t)(d) }
+#define OPT_STRING_OPTARG_SET(s, l, v, os, a, h, d) \
+        { .type = OPTION_STRING, .short_name = (s), .long_name = (l), \
+          .value = check_vtype(v, const char **), (a), .help = (h), \
+          .flags = PARSE_OPT_OPTARG, .defval = (intptr_t)(d), \
+          .set = check_vtype(os, bool *)}
 #define OPT_STRING_NOEMPTY(s, l, v, a, h)   { .type = OPTION_STRING,  .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), (a), .help = (h), .flags = PARSE_OPT_NOEMPTY}
 #define OPT_DATE(s, l, v, h) \
         { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), .argh = "time", .help = (h), .callback = parse_opt_approxidate_cb }
diff --git a/tools/lib/traceevent/plugin_sched_switch.c b/tools/lib/traceevent/plugin_sched_switch.c
index f1ce60065258..ec30c2fcbac0 100644
--- a/tools/lib/traceevent/plugin_sched_switch.c
+++ b/tools/lib/traceevent/plugin_sched_switch.c
@@ -111,7 +111,7 @@ static int sched_switch_handler(struct trace_seq *s,
         trace_seq_printf(s, "%lld ", val);
 
         if (pevent_get_field_val(s, event, "prev_prio", record, &val, 0) == 0)
-                trace_seq_printf(s, "[%lld] ", val);
+                trace_seq_printf(s, "[%d] ", (int) val);
 
         if (pevent_get_field_val(s,  event, "prev_state", record, &val, 0) == 0)
                 write_state(s, val);
@@ -129,7 +129,7 @@ static int sched_switch_handler(struct trace_seq *s,
         trace_seq_printf(s, "%lld", val);
 
         if (pevent_get_field_val(s, event, "next_prio", record, &val, 0) == 0)
-                trace_seq_printf(s, " [%lld]", val);
+                trace_seq_printf(s, " [%d]", (int) val);
 
         return 0;
 }
diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c
index 5e0dea2cdc01..039636ffb6c8 100644
--- a/tools/objtool/arch/x86/decode.c
+++ b/tools/objtool/arch/x86/decode.c
@@ -150,9 +150,9 @@ int arch_decode_instruction(struct elf *elf, struct section *sec,
                 *type = INSN_RETURN;
                 break;
 
-        case 0xc5: /* iret */
         case 0xca: /* retf */
         case 0xcb: /* retf */
+        case 0xcf: /* iret */
                 *type = INSN_CONTEXT_SWITCH;
                 break;
 
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 27fc3617c6a4..5054d9147f0f 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -430,6 +430,10 @@ that gets then processed, possibly via a perf script, to decide if that
 particular perf.data snapshot should be kept or not.
 
 Implies --timestamp-filename, --no-buildid and --no-buildid-cache.
+The reason for the latter two is to reduce the data file switching
+overhead. You can still switch them on with:
+
+  --switch-output --no-no-buildid  --no-no-buildid-cache
 
 --dry-run::
 Parse options then exit. --dry-run can be used to detect errors in cmdline
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 8fc24824705e..8bb16aa9d661 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -704,9 +704,9 @@ install-tests: all install-gtk
                 $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'; \
                 $(INSTALL) tests/attr/* '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'
 
-install-bin: install-tools install-tests
+install-bin: install-tools install-tests install-traceevent-plugins
 
-install: install-bin try-install-man install-traceevent-plugins
+install: install-bin try-install-man
 
 install-python_ext:
         $(PYTHON_WORD) util/setup.py --quiet install --root='/$(DESTDIR_SQ)'
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 9ff0db4e2d0c..933aeec46f4a 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -1199,7 +1199,7 @@ static int ui_init(void)
                 BUG_ON(1);
         }
 
-        perf_hpp__register_sort_field(fmt);
+        perf_hpp__prepend_sort_field(fmt);
         return 0;
 }
 
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 35a02f8e5a4a..915869e00d86 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -655,7 +655,6 @@ static const struct {
         { "__GFP_RECLAIM",              "R" },
         { "__GFP_DIRECT_RECLAIM",       "DR" },
         { "__GFP_KSWAPD_RECLAIM",       "KR" },
-        { "__GFP_OTHER_NODE",           "ON" },
 };
 
 static size_t max_gfp_len;
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 74d6a035133a..4ec10e9427d9 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -1405,7 +1405,7 @@ static bool dry_run;
  * perf_evlist__prepare_workload, etc instead of fork+exec'in 'perf record',
  * using pipes, etc.
  */
-struct option __record_options[] = {
+static struct option __record_options[] = {
         OPT_CALLBACK('e', "event", &record.evlist, "event",
                      "event selector. use 'perf list' to list available events",
                      parse_events_option),
@@ -1636,7 +1636,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
                  * overhead. Still generate buildid if they are required
                  * explicitly using
                  *
-                 *  perf record --signal-trigger --no-no-buildid \
+                 *  perf record --switch-output --no-no-buildid \
                  *              --no-no-buildid-cache
                  *
                  * Following code equals to:
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index d53e706a6f17..5b134b0d1ff3 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -209,6 +209,7 @@ struct perf_sched {
         u64             skipped_samples;
         const char      *time_str;
         struct perf_time_interval ptime;
+        struct perf_time_interval hist_time;
 };
 
 /* per thread run time data */
@@ -2460,6 +2461,11 @@ static int timehist_sched_change_event(struct perf_tool *tool,
                 timehist_print_sample(sched, sample, &al, thread, t);
 
 out:
+        if (sched->hist_time.start == 0 && t >= ptime->start)
+                sched->hist_time.start = t;
+        if (ptime->end == 0 || t <= ptime->end)
+                sched->hist_time.end = t;
+
         if (tr) {
                 /* time of this sched_switch event becomes last time task seen */
                 tr->last_time = sample->time;
@@ -2624,6 +2630,7 @@ static void timehist_print_summary(struct perf_sched *sched,
         struct thread *t;
         struct thread_runtime *r;
         int i;
+        u64 hist_time = sched->hist_time.end - sched->hist_time.start;
 
         memset(&totals, 0, sizeof(totals));
 
@@ -2665,7 +2672,7 @@ static void timehist_print_summary(struct perf_sched *sched,
                         totals.sched_count += r->run_stats.n;
                         printf("    CPU %2d idle for ", i);
                         print_sched_time(r->total_run_time, 6);
-                        printf(" msec\n");
+                        printf(" msec  (%6.2f%%)\n", 100.0 * r->total_run_time / hist_time);
                 } else
                         printf("    CPU %2d idle entire time window\n", i);
         }
@@ -2701,12 +2708,16 @@ static void timehist_print_summary(struct perf_sched *sched,
 
         printf("\n"
                "    Total number of unique tasks: %" PRIu64 "\n"
-               "Total number of context switches: %" PRIu64 "\n"
-               "           Total run time (msec): ",
+               "Total number of context switches: %" PRIu64 "\n",
                totals.task_count, totals.sched_count);
 
+        printf("           Total run time (msec): ");
         print_sched_time(totals.total_run_time, 2);
         printf("\n");
+
+        printf("    Total scheduling time (msec): ");
+        print_sched_time(hist_time, 2);
+        printf(" (x %d)\n", sched->max_cpu);
 }
 
 typedef int (*sched_handler)(struct perf_tool *tool,
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index 37388397b5bc..18cfcdc90356 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -521,6 +521,12 @@ void perf_hpp_list__register_sort_field(struct perf_hpp_list *list,
         list_add_tail(&format->sort_list, &list->sorts);
 }
 
+void perf_hpp_list__prepend_sort_field(struct perf_hpp_list *list,
+                                       struct perf_hpp_fmt *format)
+{
+        list_add(&format->sort_list, &list->sorts);
+}
+
 void perf_hpp__column_unregister(struct perf_hpp_fmt *format)
 {
         list_del(&format->list);
@@ -560,6 +566,10 @@ void perf_hpp__setup_output_field(struct perf_hpp_list *list)
         perf_hpp_list__for_each_sort_list(list, fmt) {
                 struct perf_hpp_fmt *pos;
 
+                /* skip sort-only fields ("sort_compute" in perf diff) */
+                if (!fmt->entry && !fmt->color)
+                        continue;
+
                 perf_hpp_list__for_each_format(list, pos) {
                         if (fmt_equal(fmt, pos))
                                 goto next;
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 42922512c1c6..8b610dd9e2f6 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -437,7 +437,7 @@ fill_node(struct callchain_node *node, struct callchain_cursor *cursor)
                 }
                 call->ip = cursor_node->ip;
                 call->ms.sym = cursor_node->sym;
-                call->ms.map = cursor_node->map;
+                call->ms.map = map__get(cursor_node->map);
 
                 if (cursor_node->branch) {
                         call->branch_count = 1;
@@ -477,6 +477,7 @@ add_child(struct callchain_node *parent,
 
                 list_for_each_entry_safe(call, tmp, &new->val, list) {
                         list_del(&call->list);
+                        map__zput(call->ms.map);
                         free(call);
                 }
                 free(new);
@@ -761,6 +762,7 @@ merge_chain_branch(struct callchain_cursor *cursor,
                                         list->ms.map, list->ms.sym,
                                         false, NULL, 0, 0);
                 list_del(&list->list);
+                map__zput(list->ms.map);
                 free(list);
         }
 
@@ -811,7 +813,8 @@ int callchain_cursor_append(struct callchain_cursor *cursor,
         }
 
         node->ip = ip;
-        node->map = map;
+        map__zput(node->map);
+        node->map = map__get(map);
         node->sym = sym;
         node->branch = branch;
         node->nr_loop_iter = nr_loop_iter;
@@ -1142,11 +1145,13 @@ static void free_callchain_node(struct callchain_node *node)
 
         list_for_each_entry_safe(list, tmp, &node->parent_val, list) {
                 list_del(&list->list);
+                map__zput(list->ms.map);
                 free(list);
         }
 
         list_for_each_entry_safe(list, tmp, &node->val, list) {
                 list_del(&list->list);
+                map__zput(list->ms.map);
                 free(list);
         }
 
@@ -1210,6 +1215,7 @@ int callchain_node__make_parent_list(struct callchain_node *node)
                                 goto out;
                         *new = *chain;
                         new->has_children = false;
+                        map__get(new->ms.map);
                         list_add_tail(&new->list, &head);
                 }
                 parent = parent->parent;
@@ -1230,6 +1236,7 @@ int callchain_node__make_parent_list(struct callchain_node *node)
 out:
         list_for_each_entry_safe(chain, new, &head, list) {
                 list_del(&chain->list);
+                map__zput(chain->ms.map);
                 free(chain);
         }
         return -ENOMEM;
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 35c8e379530f..4f4b60f1558a 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -5,6 +5,7 @@
 #include <linux/list.h>
 #include <linux/rbtree.h>
 #include "event.h"
+#include "map.h"
 #include "symbol.h"
 
 #define HELP_PAD "\t\t\t\t"
@@ -184,8 +185,13 @@ int callchain_merge(struct callchain_cursor *cursor,
  */
 static inline void callchain_cursor_reset(struct callchain_cursor *cursor)
 {
+        struct callchain_cursor_node *node;
+
         cursor->nr = 0;
         cursor->last = &cursor->first;
+
+        for (node = cursor->first; node != NULL; node = node->next)
+                map__zput(node->map);
 }
 
 int callchain_cursor_append(struct callchain_cursor *cursor, u64 ip,
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 6770a9645609..7d1b7d33e644 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -1,6 +1,7 @@
 #include "util.h"
 #include "build-id.h"
 #include "hist.h"
+#include "map.h"
 #include "session.h"
 #include "sort.h"
 #include "evlist.h"
@@ -1019,6 +1020,10 @@ int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
                          int max_stack_depth, void *arg)
 {
         int err, err2;
+        struct map *alm = NULL;
+
+        if (al && al->map)
+                alm = map__get(al->map);
 
         err = sample__resolve_callchain(iter->sample, &callchain_cursor, &iter->parent,
                                         iter->evsel, al, max_stack_depth);
@@ -1058,6 +1063,8 @@ out:
         if (!err)
                 err = err2;
 
+        map__put(alm);
+
         return err;
 }
 
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index d4b6514eeef5..28c216e3d5b7 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -283,6 +283,8 @@ void perf_hpp_list__column_register(struct perf_hpp_list *list,
                                     struct perf_hpp_fmt *format);
 void perf_hpp_list__register_sort_field(struct perf_hpp_list *list,
                                         struct perf_hpp_fmt *format);
+void perf_hpp_list__prepend_sort_field(struct perf_hpp_list *list,
+                                       struct perf_hpp_fmt *format);
 
 static inline void perf_hpp__column_register(struct perf_hpp_fmt *format)
 {
@@ -294,6 +296,11 @@ static inline void perf_hpp__register_sort_field(struct perf_hpp_fmt *format)
         perf_hpp_list__register_sort_field(&perf_hpp_list, format);
 }
 
+static inline void perf_hpp__prepend_sort_field(struct perf_hpp_fmt *format)
+{
+        perf_hpp_list__prepend_sort_field(&perf_hpp_list, format);
+}
+
 #define perf_hpp_list__for_each_format(_list, format) \
         list_for_each_entry(format, &(_list)->fields, list)
 
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index d281ae2b54e8..6a6f44dd594b 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -163,7 +163,7 @@ static struct map *kernel_get_module_map(const char *module)
 
         /* A file path -- this is an offline module */
         if (module && strchr(module, '/'))
-                return machine__findnew_module_map(host_machine, 0, module);
+                return dso__new_map(module);
 
         if (!module)
                 module = "kernel";
@@ -173,6 +173,7 @@ static struct map *kernel_get_module_map(const char *module)
                 if (strncmp(pos->dso->short_name + 1, module,
                             pos->dso->short_name_len - 2) == 0 &&
                     module[pos->dso->short_name_len - 2] == '\0') {
+                        map__get(pos);
                         return pos;
                 }
         }
@@ -188,15 +189,6 @@ struct map *get_target_map(const char *target, bool user)
                 return kernel_get_module_map(target);
 }
 
-static void put_target_map(struct map *map, bool user)
-{
-        if (map && user) {
-                /* Only the user map needs to be released */
-                map__put(map);
-        }
-}
-
-
 static int convert_exec_to_group(const char *exec, char **result)
 {
         char *ptr1, *ptr2, *exec_copy;
@@ -268,21 +260,6 @@ static bool kprobe_warn_out_range(const char *symbol, unsigned long address)
 }
 
 /*
- * NOTE:
- * '.gnu.linkonce.this_module' section of kernel module elf directly
- * maps to 'struct module' from linux/module.h. This section contains
- * actual module name which will be used by kernel after loading it.
- * But, we cannot use 'struct module' here since linux/module.h is not
- * exposed to user-space. Offset of 'name' has remained same from long
- * time, so hardcoding it here.
- */
-#ifdef __LP64__
-#define MOD_NAME_OFFSET 24
-#else
-#define MOD_NAME_OFFSET 12
-#endif
-
-/*
  * @module can be module name of module file path. In case of path,
  * inspect elf and find out what is actual module name.
  * Caller has to free mod_name after using it.
@@ -296,6 +273,7 @@ static char *find_module_name(const char *module)
         Elf_Data *data;
         Elf_Scn *sec;
         char *mod_name = NULL;
+        int name_offset;
 
         fd = open(module, O_RDONLY);
         if (fd < 0)
@@ -317,7 +295,21 @@ static char *find_module_name(const char *module)
         if (!data || !data->d_buf)
                 goto ret_err;
 
-        mod_name = strdup((char *)data->d_buf + MOD_NAME_OFFSET);
+        /*
+         * NOTE:
+         * '.gnu.linkonce.this_module' section of kernel module elf directly
+         * maps to 'struct module' from linux/module.h. This section contains
+         * actual module name which will be used by kernel after loading it.
+         * But, we cannot use 'struct module' here since linux/module.h is not
+         * exposed to user-space. Offset of 'name' has remained same from long
+         * time, so hardcoding it here.
+         */
+        if (ehdr.e_ident[EI_CLASS] == ELFCLASS32)
+                name_offset = 12;
+        else    /* expect ELFCLASS64 by default */
+                name_offset = 24;
+
+        mod_name = strdup((char *)data->d_buf + name_offset);
 
 ret_err:
         elf_end(elf);
@@ -412,7 +404,7 @@ static int find_alternative_probe_point(struct debuginfo *dinfo,
         }
 
 out:
-        put_target_map(map, uprobes);
+        map__put(map);
         return ret;
 
 }
@@ -618,6 +610,67 @@ error:
         return ret ? : -ENOENT;
 }
 
+/* Adjust symbol name and address */
+static int post_process_probe_trace_point(struct probe_trace_point *tp,
+                                           struct map *map, unsigned long offs)
+{
+        struct symbol *sym;
+        u64 addr = tp->address + tp->offset - offs;
+
+        sym = map__find_symbol(map, addr);
+        if (!sym)
+                return -ENOENT;
+
+        if (strcmp(sym->name, tp->symbol)) {
+                /* If we have no realname, use symbol for it */
+                if (!tp->realname)
+                        tp->realname = tp->symbol;
+                else
+                        free(tp->symbol);
+                tp->symbol = strdup(sym->name);
+                if (!tp->symbol)
+                        return -ENOMEM;
+        }
+        tp->offset = addr - sym->start;
+        tp->address -= offs;
+
+        return 0;
+}
+
+/*
+ * Rename DWARF symbols to ELF symbols -- gcc sometimes optimizes functions
+ * and generate new symbols with suffixes such as .constprop.N or .isra.N
+ * etc. Since those symbols are not recorded in DWARF, we have to find
+ * correct generated symbols from offline ELF binary.
+ * For online kernel or uprobes we don't need this because those are
+ * rebased on _text, or already a section relative address.
+ */
+static int
+post_process_offline_probe_trace_events(struct probe_trace_event *tevs,
+                                        int ntevs, const char *pathname)
+{
+        struct map *map;
+        unsigned long stext = 0;
+        int i, ret = 0;
+
+        /* Prepare a map for offline binary */
+        map = dso__new_map(pathname);
+        if (!map || get_text_start_address(pathname, &stext) < 0) {
+                pr_warning("Failed to get ELF symbols for %s\n", pathname);
+                return -EINVAL;
+        }
+
+        for (i = 0; i < ntevs; i++) {
+                ret = post_process_probe_trace_point(&tevs[i].point,
+                                                     map, stext);
+                if (ret < 0)
+                        break;
+        }
+        map__put(map);
+
+        return ret;
+}
+
 static int add_exec_to_probe_trace_events(struct probe_trace_event *tevs,
                                           int ntevs, const char *exec)
 {
@@ -645,18 +698,31 @@ static int add_exec_to_probe_trace_events(struct probe_trace_event *tevs,
         return ret;
 }
 
-static int add_module_to_probe_trace_events(struct probe_trace_event *tevs,
-                                            int ntevs, const char *module)
+static int
+post_process_module_probe_trace_events(struct probe_trace_event *tevs,
+                                       int ntevs, const char *module,
+                                       struct debuginfo *dinfo)
 {
+        Dwarf_Addr text_offs = 0;
         int i, ret = 0;
         char *mod_name = NULL;
+        struct map *map;
 
         if (!module)
                 return 0;
 
-        mod_name = find_module_name(module);
+        map = get_target_map(module, false);
+        if (!map || debuginfo__get_text_offset(dinfo, &text_offs, true) < 0) {
+                pr_warning("Failed to get ELF symbols for %s\n", module);
+                return -EINVAL;
+        }
 
+        mod_name = find_module_name(module);
         for (i = 0; i < ntevs; i++) {
+                ret = post_process_probe_trace_point(&tevs[i].point,
+                                                map, (unsigned long)text_offs);
+                if (ret < 0)
+                        break;
                 tevs[i].point.module =
                         strdup(mod_name ? mod_name : module);
                 if (!tevs[i].point.module) {
@@ -666,6 +732,8 @@ static int add_module_to_probe_trace_events(struct probe_trace_event *tevs,
         }
 
         free(mod_name);
+        map__put(map);
+
         return ret;
 }
 
@@ -679,7 +747,8 @@ post_process_kernel_probe_trace_events(struct probe_trace_event *tevs,
 
         /* Skip post process if the target is an offline kernel */
         if (symbol_conf.ignore_vmlinux_buildid)
-                return 0;
+                return post_process_offline_probe_trace_events(tevs, ntevs,
+                                                symbol_conf.vmlinux_name);
 
         reloc_sym = kernel_get_ref_reloc_sym();
         if (!reloc_sym) {
@@ -722,7 +791,7 @@ arch__post_process_probe_trace_events(struct perf_probe_event *pev __maybe_unuse
 static int post_process_probe_trace_events(struct perf_probe_event *pev,
                                            struct probe_trace_event *tevs,
                                            int ntevs, const char *module,
-                                           bool uprobe)
+                                           bool uprobe, struct debuginfo *dinfo)
 {
         int ret;
 
@@ -730,7 +799,8 @@ static int post_process_probe_trace_events(struct perf_probe_event *pev,
                 ret = add_exec_to_probe_trace_events(tevs, ntevs, module);
         else if (module)
                 /* Currently ref_reloc_sym based probe is not for drivers */
-                ret = add_module_to_probe_trace_events(tevs, ntevs, module);
+                ret = post_process_module_probe_trace_events(tevs, ntevs,
+                                                             module, dinfo);
         else
                 ret = post_process_kernel_probe_trace_events(tevs, ntevs);
 
@@ -774,30 +844,27 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
                 }
         }
 
-        debuginfo__delete(dinfo);
-
         if (ntevs > 0) {        /* Succeeded to find trace events */
                 pr_debug("Found %d probe_trace_events.\n", ntevs);
                 ret = post_process_probe_trace_events(pev, *tevs, ntevs,
-                                                pev->target, pev->uprobes);
+                                        pev->target, pev->uprobes, dinfo);
                 if (ret < 0 || ret == ntevs) {
+                        pr_debug("Post processing failed or all events are skipped. (%d)\n", ret);
                         clear_probe_trace_events(*tevs, ntevs);
                         zfree(tevs);
+                        ntevs = 0;
                 }
-                if (ret != ntevs)
-                        return ret < 0 ? ret : ntevs;
-                ntevs = 0;
-                /* Fall through */
         }
 
+        debuginfo__delete(dinfo);
+
         if (ntevs == 0) {       /* No error but failed to find probe point. */
                 pr_warning("Probe point '%s' not found.\n",
                            synthesize_perf_probe_point(&pev->point));
                 return -ENOENT;
-        }
-        /* Error path : ntevs < 0 */
-        pr_debug("An error occurred in debuginfo analysis (%d).\n", ntevs);
-        if (ntevs < 0) {
+        } else if (ntevs < 0) {
+                /* Error path : ntevs < 0 */
+                pr_debug("An error occurred in debuginfo analysis (%d).\n", ntevs);
                 if (ntevs == -EBADF)
                         pr_warning("Warning: No dwarf info found in the vmlinux - "
                                 "please rebuild kernel with CONFIG_DEBUG_INFO=y.\n");
@@ -2869,7 +2936,7 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev,
         }
 
 out:
-        put_target_map(map, pev->uprobes);
+        map__put(map);
         free(syms);
         return ret;
 
@@ -3362,10 +3429,7 @@ int show_available_funcs(const char *target, struct strfilter *_filter,
                 return ret;
 
         /* Get a symbol map */
-        if (user)
-                map = dso__new_map(target);
-        else
-                map = kernel_get_module_map(target);
+        map = get_target_map(target, user);
         if (!map) {
                 pr_err("Failed to get a map for %s\n", (target) ? : "kernel");
                 return -EINVAL;
@@ -3397,9 +3461,7 @@ int show_available_funcs(const char *target, struct strfilter *_filter,
         }
 
 end:
-        if (user) {
-                map__put(map);
-        }
+        map__put(map);
         exit_probe_symbol_maps();
 
         return ret;
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index df4debe564da..0d9d6e0803b8 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -1501,7 +1501,8 @@ int debuginfo__find_available_vars_at(struct debuginfo *dbg,
 }
 
 /* For the kernel module, we need a special code to get a DIE */
-static int debuginfo__get_text_offset(struct debuginfo *dbg, Dwarf_Addr *offs)
+int debuginfo__get_text_offset(struct debuginfo *dbg, Dwarf_Addr *offs,
+                                bool adjust_offset)
 {
         int n, i;
         Elf32_Word shndx;
@@ -1530,6 +1531,8 @@ static int debuginfo__get_text_offset(struct debuginfo *dbg, Dwarf_Addr *offs)
                         if (!shdr)
                                 return -ENOENT;
                         *offs = shdr->sh_addr;
+                        if (adjust_offset)
+                                *offs -= shdr->sh_offset;
                 }
         }
         return 0;
@@ -1543,16 +1546,12 @@ int debuginfo__find_probe_point(struct debuginfo *dbg, unsigned long addr,
         Dwarf_Addr _addr = 0, baseaddr = 0;
         const char *fname = NULL, *func = NULL, *basefunc = NULL, *tmp;
         int baseline = 0, lineno = 0, ret = 0;
-        bool reloc = false;
 
-retry:
+        /* We always need to relocate the address for aranges */
+        if (debuginfo__get_text_offset(dbg, &baseaddr, false) == 0)
+                addr += baseaddr;
         /* Find cu die */
         if (!dwarf_addrdie(dbg->dbg, (Dwarf_Addr)addr, &cudie)) {
-                if (!reloc && debuginfo__get_text_offset(dbg, &baseaddr) == 0) {
-                        addr += baseaddr;
-                        reloc = true;
-                        goto retry;
-                }
                 pr_warning("Failed to find debug information for address %lx\n",
                            addr);
                 ret = -EINVAL;
diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h
index f1d8558f498e..2956c5198652 100644
--- a/tools/perf/util/probe-finder.h
+++ b/tools/perf/util/probe-finder.h
@@ -46,6 +46,9 @@ int debuginfo__find_trace_events(struct debuginfo *dbg,
 int debuginfo__find_probe_point(struct debuginfo *dbg, unsigned long addr,
                                 struct perf_probe_point *ppt);
 
+int debuginfo__get_text_offset(struct debuginfo *dbg, Dwarf_Addr *offs,
+                               bool adjust_offset);
+
 /* Find a line range */
 int debuginfo__find_line_range(struct debuginfo *dbg, struct line_range *lr);
 
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 99400b0e8f2a..adbc6c02c3aa 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -537,6 +537,12 @@ int sysfs__read_build_id(const char *filename, void *build_id, size_t size)
                                 break;
                 } else {
                         int n = namesz + descsz;
+
+                        if (n > (int)sizeof(bf)) {
+                                n = sizeof(bf);
+                                pr_debug("%s: truncating reading of build id in sysfs file %s: n_namesz=%u, n_descsz=%u.\n",
+                                         __func__, filename, nhdr.n_namesz, nhdr.n_descsz);
+                        }
                         if (read(fd, bf, n) != n)
                                 break;
                 }
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index 71b05891a6a1..831022b12848 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -90,7 +90,7 @@ ifdef INSTALL_PATH
         done;
 
         @# Ask all targets to emit their test scripts
-        echo "#!/bin/bash" > $(ALL_SCRIPT)
+        echo "#!/bin/sh" > $(ALL_SCRIPT)
         echo "cd \$$(dirname \$$0)" >> $(ALL_SCRIPT)
         echo "ROOT=\$$PWD" >> $(ALL_SCRIPT)
 
diff --git a/tools/testing/selftests/bpf/test_kmod.sh b/tools/testing/selftests/bpf/test_kmod.sh
index 92e627adf354..6d58cca8e235 100755
--- a/tools/testing/selftests/bpf/test_kmod.sh
+++ b/tools/testing/selftests/bpf/test_kmod.sh
@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/bin/sh
 
 SRC_TREE=../../../../
 
diff --git a/tools/testing/selftests/bpf/test_lru_map.c b/tools/testing/selftests/bpf/test_lru_map.c
index b13fed534d76..9f7bd1915c21 100644
--- a/tools/testing/selftests/bpf/test_lru_map.c
+++ b/tools/testing/selftests/bpf/test_lru_map.c
@@ -67,21 +67,23 @@ static int map_equal(int lru_map, int expected)
         return map_subset(lru_map, expected) && map_subset(expected, lru_map);
 }
 
-static int sched_next_online(int pid, int next_to_try)
+static int sched_next_online(int pid, int *next_to_try)
 {
         cpu_set_t cpuset;
+        int next = *next_to_try;
+        int ret = -1;
 
-        if (next_to_try == nr_cpus)
-                return -1;
-
-        while (next_to_try < nr_cpus) {
+        while (next < nr_cpus) {
                 CPU_ZERO(&cpuset);
-                CPU_SET(next_to_try++, &cpuset);
-                if (!sched_setaffinity(pid, sizeof(cpuset), &cpuset))
+                CPU_SET(next++, &cpuset);
+                if (!sched_setaffinity(pid, sizeof(cpuset), &cpuset)) {
+                        ret = 0;
                         break;
+                }
         }
 
-        return next_to_try;
+        *next_to_try = next;
+        return ret;
 }
 
 /* Size of the LRU amp is 2
@@ -96,11 +98,12 @@ static void test_lru_sanity0(int map_type, int map_flags)
 {
         unsigned long long key, value[nr_cpus];
         int lru_map_fd, expected_map_fd;
+        int next_cpu = 0;
 
         printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type,
                map_flags);
 
-        assert(sched_next_online(0, 0) != -1);
+        assert(sched_next_online(0, &next_cpu) != -1);
 
         if (map_flags & BPF_F_NO_COMMON_LRU)
                 lru_map_fd = create_map(map_type, map_flags, 2 * nr_cpus);
@@ -183,6 +186,7 @@ static void test_lru_sanity1(int map_type, int map_flags, unsigned int tgt_free)
         int lru_map_fd, expected_map_fd;
         unsigned int batch_size;
         unsigned int map_size;
+        int next_cpu = 0;
 
         if (map_flags & BPF_F_NO_COMMON_LRU)
                 /* Ther percpu lru list (i.e each cpu has its own LRU
@@ -196,7 +200,7 @@ static void test_lru_sanity1(int map_type, int map_flags, unsigned int tgt_free)
         printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type,
                map_flags);
 
-        assert(sched_next_online(0, 0) != -1);
+        assert(sched_next_online(0, &next_cpu) != -1);
 
         batch_size = tgt_free / 2;
         assert(batch_size * 2 == tgt_free);
@@ -262,6 +266,7 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free)
         int lru_map_fd, expected_map_fd;
         unsigned int batch_size;
         unsigned int map_size;
+        int next_cpu = 0;
 
         if (map_flags & BPF_F_NO_COMMON_LRU)
                 /* Ther percpu lru list (i.e each cpu has its own LRU
@@ -275,7 +280,7 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free)
         printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type,
                map_flags);
 
-        assert(sched_next_online(0, 0) != -1);
+        assert(sched_next_online(0, &next_cpu) != -1);
 
         batch_size = tgt_free / 2;
         assert(batch_size * 2 == tgt_free);
@@ -370,11 +375,12 @@ static void test_lru_sanity3(int map_type, int map_flags, unsigned int tgt_free)
         int lru_map_fd, expected_map_fd;
         unsigned int batch_size;
         unsigned int map_size;
+        int next_cpu = 0;
 
         printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type,
                map_flags);
 
-        assert(sched_next_online(0, 0) != -1);
+        assert(sched_next_online(0, &next_cpu) != -1);
 
         batch_size = tgt_free / 2;
         assert(batch_size * 2 == tgt_free);
@@ -430,11 +436,12 @@ static void test_lru_sanity4(int map_type, int map_flags, unsigned int tgt_free)
         int lru_map_fd, expected_map_fd;
         unsigned long long key, value[nr_cpus];
         unsigned long long end_key;
+        int next_cpu = 0;
 
         printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type,
                map_flags);
 
-        assert(sched_next_online(0, 0) != -1);
+        assert(sched_next_online(0, &next_cpu) != -1);
 
         if (map_flags & BPF_F_NO_COMMON_LRU)
                 lru_map_fd = create_map(map_type, map_flags,
@@ -502,9 +509,8 @@ static void do_test_lru_sanity5(unsigned long long last_key, int map_fd)
 static void test_lru_sanity5(int map_type, int map_flags)
 {
         unsigned long long key, value[nr_cpus];
-        int next_sched_cpu = 0;
+        int next_cpu = 0;
         int map_fd;
-        int i;
 
         if (map_flags & BPF_F_NO_COMMON_LRU)
                 return;
@@ -519,27 +525,20 @@ static void test_lru_sanity5(int map_type, int map_flags)
         key = 0;
         assert(!bpf_map_update(map_fd, &key, value, BPF_NOEXIST));
 
-        for (i = 0; i < nr_cpus; i++) {
+        while (sched_next_online(0, &next_cpu) != -1) {
                 pid_t pid;
 
                 pid = fork();
                 if (pid == 0) {
-                        next_sched_cpu = sched_next_online(0, next_sched_cpu);
-                        if (next_sched_cpu != -1)
-                                do_test_lru_sanity5(key, map_fd);
+                        do_test_lru_sanity5(key, map_fd);
                         exit(0);
                 } else if (pid == -1) {
-                        printf("couldn't spawn #%d process\n", i);
+                        printf("couldn't spawn process to test key:%llu\n",
+                               key);
                         exit(1);
                 } else {
                         int status;
 
-                        /* It is mostly redundant and just allow the parent
-                         * process to update next_shced_cpu for the next child
-                         * process
-                         */
-                        next_sched_cpu = sched_next_online(pid, next_sched_cpu);
-
                         assert(waitpid(pid, &status, 0) == pid);
                         assert(status == 0);
                         key++;
@@ -547,6 +546,8 @@ static void test_lru_sanity5(int map_type, int map_flags)
         }
 
         close(map_fd);
+        /* At least one key should be tested */
+        assert(key > 0);
 
         printf("Pass\n");
 }
diff --git a/tools/testing/selftests/drivers/gpu/drm_mm.sh b/tools/testing/selftests/drivers/gpu/drm_mm.sh
new file mode 100755
index 000000000000..96dd55c92799
--- /dev/null
+++ b/tools/testing/selftests/drivers/gpu/drm_mm.sh
@@ -0,0 +1,15 @@
+#!/bin/sh
+# Runs API tests for struct drm_mm (DRM range manager)
+
+if ! /sbin/modprobe -n -q test-drm_mm; then
+       echo "drivers/gpu/drm_mm: [skip]"
+       exit 77
+fi
+
+if /sbin/modprobe -q test-drm_mm; then
+       /sbin/modprobe -q -r test-drm_mm
+       echo "drivers/gpu/drm_mm: ok"
+else
+       echo "drivers/gpu/drm_mm: [FAIL]"
+       exit 1
+fi
diff --git a/tools/testing/selftests/lib/prime_numbers.sh b/tools/testing/selftests/lib/prime_numbers.sh
new file mode 100755
index 000000000000..da4cbcd766f5
--- /dev/null
+++ b/tools/testing/selftests/lib/prime_numbers.sh
@@ -0,0 +1,15 @@
+#!/bin/sh
+# Checks fast/slow prime_number generation for inconsistencies
+
+if ! /sbin/modprobe -q -r prime_numbers; then
+        echo "prime_numbers: [SKIP]"
+        exit 77
+fi
+
+if /sbin/modprobe -q prime_numbers selftest=65536; then
+        /sbin/modprobe -q -r prime_numbers
+        echo "prime_numbers: ok"
+else
+        echo "prime_numbers: [FAIL]"
+        exit 1
+fi
diff --git a/tools/testing/selftests/net/run_netsocktests b/tools/testing/selftests/net/run_netsocktests
index c09a682df56a..16058bbea7a8 100755
--- a/tools/testing/selftests/net/run_netsocktests
+++ b/tools/testing/selftests/net/run_netsocktests
@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/bin/sh
 
 echo "--------------------"
 echo "running socket test"
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c b/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c
index c22860ab9733..30e1ac62e8cb 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c
@@ -66,7 +66,7 @@ int pmc56_overflow(void)
 
         FAIL_IF(ebb_event_enable(&event));
 
-        mtspr(SPRN_PMC1, pmc_sample_period(sample_period));
+        mtspr(SPRN_PMC2, pmc_sample_period(sample_period));
         mtspr(SPRN_PMC5, 0);
         mtspr(SPRN_PMC6, 0);
 
diff --git a/tools/testing/selftests/x86/protection_keys.c b/tools/testing/selftests/x86/protection_keys.c
index bdd58c78902e..df9e0a0cdf29 100644
--- a/tools/testing/selftests/x86/protection_keys.c
+++ b/tools/testing/selftests/x86/protection_keys.c
@@ -1367,7 +1367,7 @@ void run_tests_once(void)
                 tracing_off();
                 close_test_fds();
 
-                printf("test %2d PASSED (itertation %d)\n", test_nr, iteration_nr);
+                printf("test %2d PASSED (iteration %d)\n", test_nr, iteration_nr);
                 dprintf1("======================\n\n");
         }
         iteration_nr++;
diff --git a/tools/virtio/ringtest/main.h b/tools/virtio/ringtest/main.h
index 34e63cc4c572..14142faf040b 100644
--- a/tools/virtio/ringtest/main.h
+++ b/tools/virtio/ringtest/main.h
@@ -26,6 +26,16 @@ static inline void wait_cycles(unsigned long long cycles)
 #define VMEXIT_CYCLES 500
 #define VMENTRY_CYCLES 500
 
+#elif defined(__s390x__)
+static inline void wait_cycles(unsigned long long cycles)
+{
+        asm volatile("0: brctg %0,0b" : : "d" (cycles));
+}
+
+/* tweak me */
+#define VMEXIT_CYCLES 200
+#define VMENTRY_CYCLES 200
+
 #else
 static inline void wait_cycles(unsigned long long cycles)
 {
@@ -81,6 +91,8 @@ extern unsigned ring_size;
 /* Is there a portable way to do this? */
 #if defined(__x86_64__) || defined(__i386__)
 #define cpu_relax() asm ("rep; nop" ::: "memory")
+#elif defined(__s390x__)
+#define cpu_relax() barrier()
 #else
 #define cpu_relax() assert(0)
 #endif
diff --git a/tools/virtio/ringtest/run-on-all.sh b/tools/virtio/ringtest/run-on-all.sh
index 2e69ca812b4c..29b0d3920bfc 100755
--- a/tools/virtio/ringtest/run-on-all.sh
+++ b/tools/virtio/ringtest/run-on-all.sh
@@ -1,12 +1,13 @@
 #!/bin/sh
 
+CPUS_ONLINE=$(lscpu --online -p=cpu|grep -v -e '#')
 #use last CPU for host. Why not the first?
 #many devices tend to use cpu0 by default so
 #it tends to be busier
-HOST_AFFINITY=$(lscpu -p=cpu | tail -1)
+HOST_AFFINITY=$(echo "${CPUS_ONLINE}"|tail -n 1)
 
 #run command on all cpus
-for cpu in $(seq 0 $HOST_AFFINITY)
+for cpu in $CPUS_ONLINE
 do
         #Don't run guest and host on same CPU
         #It actually works ok if using signalling