Merge pull request #21 from falstaff84/4.9-1.0.x-imx-fixes-stable-merge

4.9-1.0.x-imx stable 4.9.67 merge

21 files changed, 239 insertions, 97 deletions

diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 982d6439bb07..ef52d1e3d431 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -729,9 +729,9 @@ 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/bench/numa.c b/tools/perf/bench/numa.c
index 8efe904e486b..9e5a02d6b9a9 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -1573,13 +1573,13 @@ static int __bench_numa(const char *name)
 		"GB/sec,", "total-speed",	"GB/sec total speed");
 
 	if (g->p.show_details >= 2) {
-		char tname[32];
+		char tname[14 + 2 * 10 + 1];
 		struct thread_data *td;
 		for (p = 0; p < g->p.nr_proc; p++) {
 			for (t = 0; t < g->p.nr_threads; t++) {
-				memset(tname, 0, 32);
+				memset(tname, 0, sizeof(tname));
 				td = g->threads + p*g->p.nr_threads + t;
-				snprintf(tname, 32, "process%d:thread%d", p, t);
+				snprintf(tname, sizeof(tname), "process%d:thread%d", p, t);
 				print_res(tname, td->speed_gbs,
 					"GB/sec",	"thread-speed", "GB/sec/thread speed");
 				print_res(tname, td->system_time_ns / NSEC_PER_SEC,
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index fe3af9535e85..0b613e701736 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -643,7 +643,7 @@ repeat:
 		case -1:
 			if (errno == EINTR)
 				continue;
-			/* Fall trhu */
+			__fallthrough;
 		default:
 			c = getc(stdin);
 			tcsetattr(0, TCSAFLUSH, &save);
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 20c2e641c422..aa9276bfe3e9 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -1779,15 +1779,14 @@ static int test_pmu_events(void)
 	}
 
 	while (!ret && (ent = readdir(dir))) {
-#define MAX_NAME 100
 		struct evlist_test e;
-		char name[MAX_NAME];
+		char name[2 * NAME_MAX + 1 + 12 + 3];
 
 		/* Names containing . are special and cannot be used directly */
 		if (strchr(ent->d_name, '.'))
 			continue;
 
-		snprintf(name, MAX_NAME, "cpu/event=%s/u", ent->d_name);
+		snprintf(name, sizeof(name), "cpu/event=%s/u", ent->d_name);
 
 		e.name  = name;
 		e.check = test__checkevent_pmu_events;
@@ -1795,11 +1794,10 @@ static int test_pmu_events(void)
 		ret = test_event(&e);
 		if (ret)
 			break;
-		snprintf(name, MAX_NAME, "%s:u,cpu/event=%s/u", ent->d_name, ent->d_name);
+		snprintf(name, sizeof(name), "%s:u,cpu/event=%s/u", ent->d_name, ent->d_name);
 		e.name  = name;
 		e.check = test__checkevent_pmu_events_mix;
 		ret = test_event(&e);
-#undef MAX_NAME
 	}
 
 	closedir(dir);
diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c
index 3eb3edb307a4..a1309010d109 100644
--- a/tools/perf/ui/browser.c
+++ b/tools/perf/ui/browser.c
@@ -702,7 +702,7 @@ static void __ui_browser__line_arrow_down(struct ui_browser *browser,
 		ui_browser__gotorc(browser, row, column + 1);
 		SLsmg_draw_hline(2);
 
-		if (row++ == 0)
+		if (++row == 0)
 			goto out;
 	} else
 		row = 0;
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index c5a6e0b12452..78bd632f144d 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -1826,7 +1826,7 @@ static int addr_filter__resolve_kernel_syms(struct addr_filter *filt)
 		filt->addr = start;
 		if (filt->range && !filt->size && !filt->sym_to) {
 			filt->size = size;
-			no_size = !!size;
+			no_size = !size;
 		}
 	}
 
@@ -1840,7 +1840,7 @@ static int addr_filter__resolve_kernel_syms(struct addr_filter *filt)
 		if (err)
 			return err;
 		filt->size = start + size - filt->addr;
-		no_size = !!size;
+		no_size = !size;
 	}
 
 	/* The very last symbol in kallsyms does not imply a particular size */
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index ae58b493af45..ecf6236f3b5f 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);
 		list_add_tail(&call->list, &node->val);
 
 		callchain_cursor_advance(cursor);
@@ -462,6 +462,7 @@ 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);
@@ -730,6 +731,7 @@ merge_chain_branch(struct callchain_cursor *cursor,
 		callchain_cursor_append(cursor, list->ip,
 					list->ms.map, list->ms.sym);
 		list_del(&list->list);
+		map__zput(list->ms.map);
 		free(list);
 	}
 
@@ -778,7 +780,8 @@ 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;
 
 	cursor->nr++;
@@ -945,11 +948,13 @@ 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);
 	}
 
@@ -1013,6 +1018,7 @@ 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;
@@ -1033,6 +1039,7 @@ 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 47cfd1080975..b7cbabb3931f 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"
@@ -174,8 +175,13 @@ 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/header.c b/tools/perf/util/header.c
index 2f3eded54b0c..5337f49db361 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -3184,6 +3184,7 @@ int perf_event__process_event_update(struct perf_tool *tool __maybe_unused,
 	case PERF_EVENT_UPDATE__SCALE:
 		ev_scale = (struct event_update_event_scale *) ev->data;
 		evsel->scale = ev_scale->scale;
+		break;
 	case PERF_EVENT_UPDATE__CPUS:
 		ev_cpus = (struct event_update_event_cpus *) ev->data;
 
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index a69f027368ef..10849a079026 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/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
index 16c06d3ae577..7e27207d0f45 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -22,6 +22,7 @@
 #include <errno.h>
 #include <stdint.h>
 #include <inttypes.h>
+#include <linux/compiler.h>
 
 #include "../cache.h"
 #include "../util.h"
@@ -63,6 +64,25 @@ enum intel_pt_pkt_state {
 	INTEL_PT_STATE_FUP_NO_TIP,
 };
 
+static inline bool intel_pt_sample_time(enum intel_pt_pkt_state pkt_state)
+{
+	switch (pkt_state) {
+	case INTEL_PT_STATE_NO_PSB:
+	case INTEL_PT_STATE_NO_IP:
+	case INTEL_PT_STATE_ERR_RESYNC:
+	case INTEL_PT_STATE_IN_SYNC:
+	case INTEL_PT_STATE_TNT:
+		return true;
+	case INTEL_PT_STATE_TIP:
+	case INTEL_PT_STATE_TIP_PGD:
+	case INTEL_PT_STATE_FUP:
+	case INTEL_PT_STATE_FUP_NO_TIP:
+		return false;
+	default:
+		return true;
+	};
+}
+
 #ifdef INTEL_PT_STRICT
 #define INTEL_PT_STATE_ERR1	INTEL_PT_STATE_NO_PSB
 #define INTEL_PT_STATE_ERR2	INTEL_PT_STATE_NO_PSB
@@ -91,6 +111,7 @@ struct intel_pt_decoder {
 	bool have_tma;
 	bool have_cyc;
 	bool fixup_last_mtc;
+	bool have_last_ip;
 	uint64_t pos;
 	uint64_t last_ip;
 	uint64_t ip;
@@ -98,6 +119,7 @@ struct intel_pt_decoder {
 	uint64_t timestamp;
 	uint64_t tsc_timestamp;
 	uint64_t ref_timestamp;
+	uint64_t sample_timestamp;
 	uint64_t ret_addr;
 	uint64_t ctc_timestamp;
 	uint64_t ctc_delta;
@@ -138,6 +160,7 @@ struct intel_pt_decoder {
 	unsigned int fup_tx_flags;
 	unsigned int tx_flags;
 	uint64_t timestamp_insn_cnt;
+	uint64_t sample_insn_cnt;
 	uint64_t stuck_ip;
 	int no_progress;
 	int stuck_ip_prd;
@@ -397,6 +420,7 @@ static uint64_t intel_pt_calc_ip(const struct intel_pt_pkt *packet,
 static inline void intel_pt_set_last_ip(struct intel_pt_decoder *decoder)
 {
 	decoder->last_ip = intel_pt_calc_ip(&decoder->packet, decoder->last_ip);
+	decoder->have_last_ip = true;
 }
 
 static inline void intel_pt_set_ip(struct intel_pt_decoder *decoder)
@@ -897,6 +921,7 @@ static int intel_pt_walk_insn(struct intel_pt_decoder *decoder,
 
 	decoder->tot_insn_cnt += insn_cnt;
 	decoder->timestamp_insn_cnt += insn_cnt;
+	decoder->sample_insn_cnt += insn_cnt;
 	decoder->period_insn_cnt += insn_cnt;
 
 	if (err) {
@@ -1443,7 +1468,8 @@ static int intel_pt_walk_psbend(struct intel_pt_decoder *decoder)
 
 		case INTEL_PT_FUP:
 			decoder->pge = true;
-			intel_pt_set_last_ip(decoder);
+			if (decoder->packet.count)
+				intel_pt_set_last_ip(decoder);
 			break;
 
 		case INTEL_PT_MODE_TSX:
@@ -1647,6 +1673,8 @@ next:
 			break;
 
 		case INTEL_PT_PSB:
+			decoder->last_ip = 0;
+			decoder->have_last_ip = true;
 			intel_pt_clear_stack(&decoder->stack);
 			err = intel_pt_walk_psbend(decoder);
 			if (err == -EAGAIN)
@@ -1727,8 +1755,9 @@ next:
 
 static inline bool intel_pt_have_ip(struct intel_pt_decoder *decoder)
 {
-	return decoder->last_ip || decoder->packet.count == 0 ||
-	       decoder->packet.count == 3 || decoder->packet.count == 6;
+	return decoder->packet.count &&
+	       (decoder->have_last_ip || decoder->packet.count == 3 ||
+		decoder->packet.count == 6);
 }
 
 /* Walk PSB+ packets to get in sync. */
@@ -1744,6 +1773,7 @@ static int intel_pt_walk_psb(struct intel_pt_decoder *decoder)
 		switch (decoder->packet.type) {
 		case INTEL_PT_TIP_PGD:
 			decoder->continuous_period = false;
+			__fallthrough;
 		case INTEL_PT_TIP_PGE:
 		case INTEL_PT_TIP:
 			intel_pt_log("ERROR: Unexpected packet\n");
@@ -1797,6 +1827,8 @@ static int intel_pt_walk_psb(struct intel_pt_decoder *decoder)
 			decoder->pge = false;
 			decoder->continuous_period = false;
 			intel_pt_clear_tx_flags(decoder);
+			__fallthrough;
+
 		case INTEL_PT_TNT:
 			decoder->have_tma = false;
 			intel_pt_log("ERROR: Unexpected packet\n");
@@ -1837,6 +1869,7 @@ static int intel_pt_walk_to_ip(struct intel_pt_decoder *decoder)
 		switch (decoder->packet.type) {
 		case INTEL_PT_TIP_PGD:
 			decoder->continuous_period = false;
+			__fallthrough;
 		case INTEL_PT_TIP_PGE:
 		case INTEL_PT_TIP:
 			decoder->pge = decoder->packet.type != INTEL_PT_TIP_PGD;
@@ -1847,14 +1880,10 @@ static int intel_pt_walk_to_ip(struct intel_pt_decoder *decoder)
 			break;
 
 		case INTEL_PT_FUP:
-			if (decoder->overflow) {
-				if (intel_pt_have_ip(decoder))
-					intel_pt_set_ip(decoder);
-				if (decoder->ip)
-					return 0;
-			}
-			if (decoder->packet.count)
-				intel_pt_set_last_ip(decoder);
+			if (intel_pt_have_ip(decoder))
+				intel_pt_set_ip(decoder);
+			if (decoder->ip)
+				return 0;
 			break;
 
 		case INTEL_PT_MTC:
@@ -1903,6 +1932,9 @@ static int intel_pt_walk_to_ip(struct intel_pt_decoder *decoder)
 			break;
 
 		case INTEL_PT_PSB:
+			decoder->last_ip = 0;
+			decoder->have_last_ip = true;
+			intel_pt_clear_stack(&decoder->stack);
 			err = intel_pt_walk_psb(decoder);
 			if (err)
 				return err;
@@ -1928,6 +1960,8 @@ static int intel_pt_sync_ip(struct intel_pt_decoder *decoder)
 {
 	int err;
 
+	decoder->set_fup_tx_flags = false;
+
 	intel_pt_log("Scanning for full IP\n");
 	err = intel_pt_walk_to_ip(decoder);
 	if (err)
@@ -2036,6 +2070,7 @@ static int intel_pt_sync(struct intel_pt_decoder *decoder)
 
 	decoder->pge = false;
 	decoder->continuous_period = false;
+	decoder->have_last_ip = false;
 	decoder->last_ip = 0;
 	decoder->ip = 0;
 	intel_pt_clear_stack(&decoder->stack);
@@ -2044,6 +2079,7 @@ static int intel_pt_sync(struct intel_pt_decoder *decoder)
 	if (err)
 		return err;
 
+	decoder->have_last_ip = true;
 	decoder->pkt_state = INTEL_PT_STATE_NO_IP;
 
 	err = intel_pt_walk_psb(decoder);
@@ -2062,7 +2098,7 @@ static int intel_pt_sync(struct intel_pt_decoder *decoder)
 
 static uint64_t intel_pt_est_timestamp(struct intel_pt_decoder *decoder)
 {
-	uint64_t est = decoder->timestamp_insn_cnt << 1;
+	uint64_t est = decoder->sample_insn_cnt << 1;
 
 	if (!decoder->cbr || !decoder->max_non_turbo_ratio)
 		goto out;
@@ -2070,7 +2106,7 @@ static uint64_t intel_pt_est_timestamp(struct intel_pt_decoder *decoder)
 	est *= decoder->max_non_turbo_ratio;
 	est /= decoder->cbr;
 out:
-	return decoder->timestamp + est;
+	return decoder->sample_timestamp + est;
 }
 
 const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder)
@@ -2086,7 +2122,9 @@ const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder)
 			err = intel_pt_sync(decoder);
 			break;
 		case INTEL_PT_STATE_NO_IP:
+			decoder->have_last_ip = false;
 			decoder->last_ip = 0;
+			decoder->ip = 0;
 			/* Fall through */
 		case INTEL_PT_STATE_ERR_RESYNC:
 			err = intel_pt_sync_ip(decoder);
@@ -2123,15 +2161,24 @@ const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder)
 		}
 	} while (err == -ENOLINK);
 
-	decoder->state.err = err ? intel_pt_ext_err(err) : 0;
-	decoder->state.timestamp = decoder->timestamp;
+	if (err) {
+		decoder->state.err = intel_pt_ext_err(err);
+		decoder->state.from_ip = decoder->ip;
+		decoder->sample_timestamp = decoder->timestamp;
+		decoder->sample_insn_cnt = decoder->timestamp_insn_cnt;
+	} else {
+		decoder->state.err = 0;
+		if (intel_pt_sample_time(decoder->pkt_state)) {
+			decoder->sample_timestamp = decoder->timestamp;
+			decoder->sample_insn_cnt = decoder->timestamp_insn_cnt;
+		}
+	}
+
+	decoder->state.timestamp = decoder->sample_timestamp;
 	decoder->state.est_timestamp = intel_pt_est_timestamp(decoder);
 	decoder->state.cr3 = decoder->cr3;
 	decoder->state.tot_insn_cnt = decoder->tot_insn_cnt;
 
-	if (err)
-		decoder->state.from_ip = decoder->ip;
-
 	return &decoder->state;
 }
 
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
index 4f7b32020487..7528ae4f7e28 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
@@ -17,6 +17,7 @@
 #include <string.h>
 #include <endian.h>
 #include <byteswap.h>
+#include <linux/compiler.h>
 
 #include "intel-pt-pkt-decoder.h"
 
@@ -498,6 +499,7 @@ int intel_pt_pkt_desc(const struct intel_pt_pkt *packet, char *buf,
 	case INTEL_PT_FUP:
 		if (!(packet->count))
 			return snprintf(buf, buf_len, "%s no ip", name);
+		__fallthrough;
 	case INTEL_PT_CYC:
 	case INTEL_PT_VMCS:
 	case INTEL_PT_MTC:
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 4e778eae1510..415a9c38d9f0 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -309,10 +309,11 @@ __add_event(struct list_head *list, int *idx,
 
 	event_attr_init(attr);
 
-	evsel = perf_evsel__new_idx(attr, (*idx)++);
+	evsel = perf_evsel__new_idx(attr, *idx);
 	if (!evsel)
 		return NULL;
 
+	(*idx)++;
 	evsel->cpus     = cpu_map__get(cpus);
 	evsel->own_cpus = cpu_map__get(cpus);
 
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/scripting-engines/Build b/tools/perf/util/scripting-engines/Build
index 6516e220c247..82d28c67e0f3 100644
--- a/tools/perf/util/scripting-engines/Build
+++ b/tools/perf/util/scripting-engines/Build
@@ -1,6 +1,6 @@
 libperf-$(CONFIG_LIBPERL)   += trace-event-perl.o
 libperf-$(CONFIG_LIBPYTHON) += trace-event-python.o
 
-CFLAGS_trace-event-perl.o += $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow -Wno-undef -Wno-switch-default
+CFLAGS_trace-event-perl.o += $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow -Wno-nested-externs -Wno-undef -Wno-switch-default
 
 CFLAGS_trace-event-python.o += $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow
diff --git a/tools/perf/util/strfilter.c b/tools/perf/util/strfilter.c
index bcae659b6546..efb53772e0ec 100644
--- a/tools/perf/util/strfilter.c
+++ b/tools/perf/util/strfilter.c
@@ -269,6 +269,7 @@ static int strfilter_node__sprint(struct strfilter_node *node, char *buf)
 		len = strfilter_node__sprint_pt(node->l, buf);
 		if (len < 0)
 			return len;
+		__fallthrough;
 	case '!':
 		if (buf) {
 			*(buf + len++) = *node->p;
diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c
index 7f7e072be746..f4e3444d90ab 100644
--- a/tools/perf/util/string.c
+++ b/tools/perf/util/string.c
@@ -21,6 +21,8 @@ s64 perf_atoll(const char *str)
 		case 'b': case 'B':
 			if (*p)
 				goto out_err;
+
+			__fallthrough;
 		case '\0':
 			return length;
 		default:
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/perf/util/thread_map.c b/tools/perf/util/thread_map.c
index 40585f5b7027..ddec5c583d2b 100644
--- a/tools/perf/util/thread_map.c
+++ b/tools/perf/util/thread_map.c
@@ -93,7 +93,7 @@ struct thread_map *thread_map__new_by_uid(uid_t uid)
 {
 	DIR *proc;
 	int max_threads = 32, items, i;
-	char path[256];
+	char path[NAME_MAX + 1 + 6];
 	struct dirent *dirent, **namelist = NULL;
 	struct thread_map *threads = thread_map__alloc(max_threads);