diff --git a/tools/perf/Documentation/Makefile b/tools/perf/Documentation/Makefile
index 6d148a40551ceda23b590184e92cf632dc705f01..adc5a7e44b98223e6350908a417862541ef57513 100644
--- a/tools/perf/Documentation/Makefile
+++ b/tools/perf/Documentation/Makefile
@@ -242,7 +242,7 @@ $(OUTPUT)doc.dep : $(wildcard *.txt) build-docdep.perl
 	$(PERL_PATH) ./build-docdep.perl >$@+ $(QUIET_STDERR) && \
 	mv $@+ $@
 
--include $(OUPTUT)doc.dep
+-include $(OUTPUT)doc.dep
 
 _cmds_txt = cmds-ancillaryinterrogators.txt \
 	cmds-ancillarymanipulators.txt \
diff --git a/tools/perf/arch/s390/util/machine.c b/tools/perf/arch/s390/util/machine.c
index a19690a17291ebb52a9f0bccf97a356f4af6ade0..c8c86a0c9b793d6f5173d9bc2fa7bb60f7d23f6e 100644
--- a/tools/perf/arch/s390/util/machine.c
+++ b/tools/perf/arch/s390/util/machine.c
@@ -6,8 +6,9 @@
 #include "machine.h"
 #include "api/fs/fs.h"
 #include "debug.h"
+#include "symbol.h"
 
-int arch__fix_module_text_start(u64 *start, const char *name)
+int arch__fix_module_text_start(u64 *start, u64 *size, const char *name)
 {
 	u64 m_start = *start;
 	char path[PATH_MAX];
@@ -17,7 +18,35 @@ int arch__fix_module_text_start(u64 *start, const char *name)
 	if (sysfs__read_ull(path, (unsigned long long *)start) < 0) {
 		pr_debug2("Using module %s start:%#lx\n", path, m_start);
 		*start = m_start;
+	} else {
+		/* Successful read of the modules segment text start address.
+		 * Calculate difference between module start address
+		 * in memory and module text segment start address.
+		 * For example module load address is 0x3ff8011b000
+		 * (from /proc/modules) and module text segment start
+		 * address is 0x3ff8011b870 (from file above).
+		 *
+		 * Adjust the module size and subtract the GOT table
+		 * size located at the beginning of the module.
+		 */
+		*size -= (*start - m_start);
 	}
 
 	return 0;
 }
+
+/* On s390 kernel text segment start is located at very low memory addresses,
+ * for example 0x10000. Modules are located at very high memory addresses,
+ * for example 0x3ff xxxx xxxx. The gap between end of kernel text segment
+ * and beginning of first module's text segment is very big.
+ * Therefore do not fill this gap and do not assign it to the kernel dso map.
+ */
+void arch__symbols__fixup_end(struct symbol *p, struct symbol *c)
+{
+	if (strchr(p->name, '[') == NULL && strchr(c->name, '['))
+		/* Last kernel symbol mapped to end of page */
+		p->end = roundup(p->end, page_size);
+	else
+		p->end = c->start;
+	pr_debug4("%s sym:%s end:%#lx\n", __func__, p->name, p->end);
+}
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index a640ca7aaadaf5c170703a711d91a3fc072e01e5..513cb2f2fa32e08e3d4b531b4709d53b28c4b07a 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -379,8 +379,10 @@ static u8 *alloc_data(ssize_t bytes0, int map_flags,
 
 	/* Allocate and initialize all memory on CPU#0: */
 	if (init_cpu0) {
-		orig_mask = bind_to_node(0);
-		bind_to_memnode(0);
+		int node = numa_node_of_cpu(0);
+
+		orig_mask = bind_to_node(node);
+		bind_to_memnode(node);
 	}
 
 	bytes = bytes0 + HPSIZE;
diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c
index 66d5a6658daf542489d5eed878b9ed0e1035498a..01931281040563358793d74151233c8989df1082 100644
--- a/tools/perf/builtin-ftrace.c
+++ b/tools/perf/builtin-ftrace.c
@@ -173,7 +173,7 @@ static int set_tracing_cpumask(struct cpu_map *cpumap)
 	int last_cpu;
 
 	last_cpu = cpu_map__cpu(cpumap, cpumap->nr - 1);
-	mask_size = (last_cpu + 3) / 4 + 1;
+	mask_size = last_cpu / 4 + 2; /* one more byte for EOS */
 	mask_size += last_cpu / 32; /* ',' is needed for every 32th cpus */
 
 	cpumask = malloc(mask_size);
diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c
index 1a91a197cafb02124b9ca20cda355b7195c51fcd..d413761621b09673e5063a308e544e07c799da67 100644
--- a/tools/perf/pmu-events/jevents.c
+++ b/tools/perf/pmu-events/jevents.c
@@ -453,6 +453,7 @@ static struct fixed {
 	{ "inst_retired.any_p", "event=0xc0" },
 	{ "cpu_clk_unhalted.ref", "event=0x0,umask=0x03" },
 	{ "cpu_clk_unhalted.thread", "event=0x3c" },
+	{ "cpu_clk_unhalted.core", "event=0x3c" },
 	{ "cpu_clk_unhalted.thread_any", "event=0x3c,any=1" },
 	{ NULL, NULL},
 };
diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c
index f80c51d5356555a7789f952a1d99985a9f552ac3..d227d74b28f812040159fa6b99148abf9d821480 100644
--- a/tools/perf/ui/browser.c
+++ b/tools/perf/ui/browser.c
@@ -1,7 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
-#include "../string2.h"
-#include "../config.h"
-#include "../../perf.h"
+#include "../util/util.h"
+#include "../util/string2.h"
+#include "../util/config.h"
+#include "../perf.h"
 #include "libslang.h"
 #include "ui.h"
 #include "util.h"
@@ -14,7 +15,7 @@
 #include "browser.h"
 #include "helpline.h"
 #include "keysyms.h"
-#include "../color.h"
+#include "../util/color.h"
 #include <linux/ctype.h>
 #include <linux/zalloc.h>
 
diff --git a/tools/perf/ui/tui/progress.c b/tools/perf/ui/tui/progress.c
index bc134b82829d64a55c61663bbfeadac09e14d6df..5a24dd3ce4db9bd13b5637481574cf0bd9b00f87 100644
--- a/tools/perf/ui/tui/progress.c
+++ b/tools/perf/ui/tui/progress.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/kernel.h>
-#include "../cache.h"
+#include "../../util/cache.h"
 #include "../progress.h"
 #include "../libslang.h"
 #include "../ui.h"
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index ac9ad2330f930d78fe499d38bdc80937d71bdd3c..163536720149baf525f8d1ce1a978868574f281b 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -1122,7 +1122,7 @@ static int disasm_line__parse(char *line, const char **namep, char **rawp)
 		goto out;
 
 	(*rawp)[0] = tmp;
-	*rawp = skip_spaces(*rawp);
+	*rawp = strim(*rawp);
 
 	return 0;
 
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index 3acfbe34ebafb53ea806a108e825a7c621164a7d..39cce66b4ebcca3aa071ba59ec43b2830ab83d79 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -751,7 +751,10 @@ size_t cpu_map__snprint_mask(struct cpu_map *map, char *buf, size_t size)
 	unsigned char *bitmap;
 	int last_cpu = cpu_map__cpu(map, map->nr - 1);
 
-	bitmap = zalloc((last_cpu + 7) / 8);
+	if (buf == NULL)
+		return 0;
+
+	bitmap = zalloc(last_cpu / 8 + 1);
 	if (bitmap == NULL) {
 		buf[0] = '\0';
 		return 0;
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index cf826eca3aafd7e65379c8caa001bf43e685881b..83b2fbbeeb900e713e733e054392a1eb45efac61 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1378,6 +1378,7 @@ static int machine__set_modules_path(struct machine *machine)
 	return map_groups__set_modules_path_dir(&machine->kmaps, modules_path, 0);
 }
 int __weak arch__fix_module_text_start(u64 *start __maybe_unused,
+				u64 *size __maybe_unused,
 				const char *name __maybe_unused)
 {
 	return 0;
@@ -1389,7 +1390,7 @@ static int machine__create_module(void *arg, const char *name, u64 start,
 	struct machine *machine = arg;
 	struct map *map;
 
-	if (arch__fix_module_text_start(&start, name) < 0)
+	if (arch__fix_module_text_start(&start, &size, name) < 0)
 		return -1;
 
 	map = machine__findnew_module_map(machine, start, name);
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index f70ab98a7bde5d3c4422db17ba082d54e7ffb556..7aa38da26427008eb7dc7a46c7ed16c9932c631c 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -222,7 +222,7 @@ struct symbol *machine__find_kernel_symbol_by_name(struct machine *machine,
 
 struct map *machine__findnew_module_map(struct machine *machine, u64 start,
 					const char *filename);
-int arch__fix_module_text_start(u64 *start, const char *name);
+int arch__fix_module_text_start(u64 *start, u64 *size, const char *name);
 
 int machine__load_kallsyms(struct machine *machine, const char *filename);
 
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 173f3378aaa0696a8497881a0b6b98928c1f10a2..4efde7879474cc63e32c4cbbd180495f7da72b5b 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -92,6 +92,11 @@ static int prefix_underscores_count(const char *str)
 	return tail - str;
 }
 
+void __weak arch__symbols__fixup_end(struct symbol *p, struct symbol *c)
+{
+	p->end = c->start;
+}
+
 const char * __weak arch__normalize_symbol_name(const char *name)
 {
 	return name;
@@ -218,7 +223,7 @@ void symbols__fixup_end(struct rb_root_cached *symbols)
 		curr = rb_entry(nd, struct symbol, rb_node);
 
 		if (prev->end == prev->start && prev->end != curr->start)
-			prev->end = curr->start;
+			arch__symbols__fixup_end(prev, curr);
 	}
 
 	/* Last entry */
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 12755b42ea93c86f6069ccfc93df581803d6ac60..183f630cb5f1b47b1fc7aaaf105814d6df0cb01c 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -288,6 +288,7 @@ const char *arch__normalize_symbol_name(const char *name);
 #define SYMBOL_A 0
 #define SYMBOL_B 1
 
+void arch__symbols__fixup_end(struct symbol *p, struct symbol *c);
 int arch__compare_symbol_names(const char *namea, const char *nameb);
 int arch__compare_symbol_names_n(const char *namea, const char *nameb,
 				 unsigned int n);
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 873ab505ca8071fdf38e2eb8b091e19553f165fc..590793cc51424c163b99e5e35f58b2609f206d70 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -214,14 +214,24 @@ struct comm *thread__comm(const struct thread *thread)
 
 struct comm *thread__exec_comm(const struct thread *thread)
 {
-	struct comm *comm, *last = NULL;
+	struct comm *comm, *last = NULL, *second_last = NULL;
 
 	list_for_each_entry(comm, &thread->comm_list, list) {
 		if (comm->exec)
 			return comm;
+		second_last = last;
 		last = comm;
 	}
 
+	/*
+	 * 'last' with no start time might be the parent's comm of a synthesized
+	 * thread (created by processing a synthesized fork event). For a main
+	 * thread, that is very probably wrong. Prefer a later comm to avoid
+	 * that case.
+	 */
+	if (second_last && !last->start && thread->pid_ == thread->tid)
+		return second_last;
+
 	return last;
 }