diff --git a/tools/perf/Documentation/jitdump-specification.txt b/tools/perf/Documentation/jitdump-specification.txt
index 52152d156ad907e22c430e7ac48ef64c42f6032f..79936355d819a66969b90adcbd6e427a4c26b0a5 100644
--- a/tools/perf/Documentation/jitdump-specification.txt
+++ b/tools/perf/Documentation/jitdump-specification.txt
@@ -164,7 +164,7 @@ const char unwinding_data[n]: an array of unwinding data, consisting of the EH F
 The EH Frame header follows the Linux Standard Base (LSB) specification as described in the document at https://refspecs.linuxfoundation.org/LSB_1.3.0/gLSB/gLSB/ehframehdr.html
 
 
-The EH Frame follows the LSB specicfication as described in the document at https://refspecs.linuxbase.org/LSB_3.0.0/LSB-PDA/LSB-PDA/ehframechpt.html
+The EH Frame follows the LSB specification as described in the document at https://refspecs.linuxbase.org/LSB_3.0.0/LSB-PDA/LSB-PDA/ehframechpt.html
 
 
 NOTE: The mapped_size is generally either the same as unwind_data_size (if the unwinding data was mapped in memory by the running process) or zero (if the unwinding data is not mapped by the process). If the unwinding data was not mapped, then only the EH Frame Header will be read, which can be used to specify FP based unwinding for a function which does not have unwinding information.
diff --git a/tools/perf/Documentation/perf-c2c.txt b/tools/perf/Documentation/perf-c2c.txt
index de6beedb72834b45e29175b674d6e49a2ab0a49d..3b6a2c84ea027e955ba6cb7e5ba290f0d876a5b6 100644
--- a/tools/perf/Documentation/perf-c2c.txt
+++ b/tools/perf/Documentation/perf-c2c.txt
@@ -261,7 +261,7 @@ COALESCE
 User can specify how to sort offsets for cacheline.
 
 Following fields are available and governs the final
-output fields set for caheline offsets output:
+output fields set for cacheline offsets output:
 
   tid   - coalesced by process TIDs
   pid   - coalesced by process PIDs
diff --git a/tools/perf/Documentation/perf-intel-pt.txt b/tools/perf/Documentation/perf-intel-pt.txt
index 184ba62420f099707370e7db674caf7900fe3254..db465fa7ee918a19f39c2fbd03b451f3f9adffa8 100644
--- a/tools/perf/Documentation/perf-intel-pt.txt
+++ b/tools/perf/Documentation/perf-intel-pt.txt
@@ -883,7 +883,7 @@ and "r" can be combined to get calls and returns.
 
 "Transactions" events correspond to the start or end of transactions. The
 'flags' field can be used in perf script to determine whether the event is a
-tranasaction start, commit or abort.
+transaction start, commit or abort.
 
 Note that "instructions", "branches" and "transactions" events depend on code
 flow packets which can be disabled by using the config term "branch=0".  Refer
diff --git a/tools/perf/Documentation/perf-lock.txt b/tools/perf/Documentation/perf-lock.txt
index 74d7745921968b3a7286311f740d3f5aab0315e2..1b4d452923d7e2327f378b2922cdc7ae4856a69d 100644
--- a/tools/perf/Documentation/perf-lock.txt
+++ b/tools/perf/Documentation/perf-lock.txt
@@ -44,7 +44,7 @@ COMMON OPTIONS
 
 -f::
 --force::
-	Don't complan, do it.
+	Don't complain, do it.
 
 REPORT OPTIONS
 --------------
diff --git a/tools/perf/Documentation/perf-script-perl.txt b/tools/perf/Documentation/perf-script-perl.txt
index 5a1f68122f50aaaa13baa1d8491a40dbdce92f47..fa4f39d305a7d576107bd49f38d1a6c91819f98c 100644
--- a/tools/perf/Documentation/perf-script-perl.txt
+++ b/tools/perf/Documentation/perf-script-perl.txt
@@ -54,7 +54,7 @@ all sched_wakeup events in the system:
 Traces meant to be processed using a script should be recorded with
 the above option: -a to enable system-wide collection.
 
-The format file for the sched_wakep event defines the following fields
+The format file for the sched_wakeup event defines the following fields
 (see /sys/kernel/debug/tracing/events/sched/sched_wakeup/format):
 
 ----
diff --git a/tools/perf/Documentation/perf-script-python.txt b/tools/perf/Documentation/perf-script-python.txt
index 0250dc61cf98266898b9444db332402608f93447..cf4b7f4b625adc7a3c1bc58076f395bbc308bf2f 100644
--- a/tools/perf/Documentation/perf-script-python.txt
+++ b/tools/perf/Documentation/perf-script-python.txt
@@ -448,7 +448,7 @@ all sched_wakeup events in the system:
 Traces meant to be processed using a script should be recorded with
 the above option: -a to enable system-wide collection.
 
-The format file for the sched_wakep event defines the following fields
+The format file for the sched_wakeup event defines the following fields
 (see /sys/kernel/debug/tracing/events/sched/sched_wakeup/format):
 
 ----
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 4c9310be6acc9089dae38c45f5f1ce42ed058b7e..7e6fb7cbc0f423b09bdb1fb3f5dd243bbe2cd973 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -385,7 +385,7 @@ Aggregate counts per physical processor for system-wide mode measurements.
 Print metrics or metricgroups specified in a comma separated list.
 For a group all metrics from the group are added.
 The events from the metrics are automatically measured.
-See perf list output for the possble metrics and metricgroups.
+See perf list output for the possible metrics and metricgroups.
 
 -A::
 --no-aggr::
diff --git a/tools/perf/Documentation/topdown.txt b/tools/perf/Documentation/topdown.txt
index c6302df4cf29b9afbad34cc6165a29d15b8aa51d..a15b93fdcf50f910d596ec00dac712837154859d 100644
--- a/tools/perf/Documentation/topdown.txt
+++ b/tools/perf/Documentation/topdown.txt
@@ -2,7 +2,7 @@ Using TopDown metrics in user space
 -----------------------------------
 
 Intel CPUs (since Sandy Bridge and Silvermont) support a TopDown
-methology to break down CPU pipeline execution into 4 bottlenecks:
+methodology to break down CPU pipeline execution into 4 bottlenecks:
 frontend bound, backend bound, bad speculation, retiring.
 
 For more details on Topdown see [1][5]
diff --git a/tools/perf/arch/arm/util/auxtrace.c b/tools/perf/arch/arm/util/auxtrace.c
index c7c7ec0812d5aef4c4399ca3e86ecdf69d0c9815..5fc6a2a3dbc5fd77215047d7d2c5e8df92f165c4 100644
--- a/tools/perf/arch/arm/util/auxtrace.c
+++ b/tools/perf/arch/arm/util/auxtrace.c
@@ -8,10 +8,10 @@
 #include <linux/coresight-pmu.h>
 #include <linux/zalloc.h>
 
-#include "../../util/auxtrace.h"
-#include "../../util/debug.h"
-#include "../../util/evlist.h"
-#include "../../util/pmu.h"
+#include "../../../util/auxtrace.h"
+#include "../../../util/debug.h"
+#include "../../../util/evlist.h"
+#include "../../../util/pmu.h"
 #include "cs-etm.h"
 #include "arm-spe.h"
 
diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c
index 515aae470e23b0cf601d0711ecb355adcbcda043..293a23bf8be39a25a6a3813f60e082e62062bbb3 100644
--- a/tools/perf/arch/arm/util/cs-etm.c
+++ b/tools/perf/arch/arm/util/cs-etm.c
@@ -16,19 +16,19 @@
 #include <linux/zalloc.h>
 
 #include "cs-etm.h"
-#include "../../util/debug.h"
-#include "../../util/record.h"
-#include "../../util/auxtrace.h"
-#include "../../util/cpumap.h"
-#include "../../util/event.h"
-#include "../../util/evlist.h"
-#include "../../util/evsel.h"
-#include "../../util/perf_api_probe.h"
-#include "../../util/evsel_config.h"
-#include "../../util/pmu.h"
-#include "../../util/cs-etm.h"
+#include "../../../util/debug.h"
+#include "../../../util/record.h"
+#include "../../../util/auxtrace.h"
+#include "../../../util/cpumap.h"
+#include "../../../util/event.h"
+#include "../../../util/evlist.h"
+#include "../../../util/evsel.h"
+#include "../../../util/perf_api_probe.h"
+#include "../../../util/evsel_config.h"
+#include "../../../util/pmu.h"
+#include "../../../util/cs-etm.h"
 #include <internal/lib.h> // page_size
-#include "../../util/session.h"
+#include "../../../util/session.h"
 
 #include <errno.h>
 #include <stdlib.h>
diff --git a/tools/perf/arch/arm/util/perf_regs.c b/tools/perf/arch/arm/util/perf_regs.c
index 2864e2e3776d5105d39f83f4de94d306df4a07ac..2833e101a7c6407263130e9948a06a2caa32bc4b 100644
--- a/tools/perf/arch/arm/util/perf_regs.c
+++ b/tools/perf/arch/arm/util/perf_regs.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-#include "../../util/perf_regs.h"
+#include "../../../util/perf_regs.h"
 
 const struct sample_reg sample_reg_masks[] = {
 	SMPL_REG_END
diff --git a/tools/perf/arch/arm/util/pmu.c b/tools/perf/arch/arm/util/pmu.c
index bbc297a7e2e3517059f9c3b33816deb69074ac20..b8b23b9dc5987a4dc118ee7bc45b162d08a57111 100644
--- a/tools/perf/arch/arm/util/pmu.c
+++ b/tools/perf/arch/arm/util/pmu.c
@@ -10,7 +10,7 @@
 #include <linux/string.h>
 
 #include "arm-spe.h"
-#include "../../util/pmu.h"
+#include "../../../util/pmu.h"
 
 struct perf_event_attr
 *perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused)
diff --git a/tools/perf/arch/arm/util/unwind-libdw.c b/tools/perf/arch/arm/util/unwind-libdw.c
index 36ba4c69c3c55cfec6c33a4b5cd52ee31d36f538..b7692cb0c73398e4f8c6bc6df4ebd7c83359fd3f 100644
--- a/tools/perf/arch/arm/util/unwind-libdw.c
+++ b/tools/perf/arch/arm/util/unwind-libdw.c
@@ -1,8 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <elfutils/libdwfl.h>
-#include "../../util/unwind-libdw.h"
-#include "../../util/perf_regs.h"
-#include "../../util/event.h"
+#include "../../../util/unwind-libdw.h"
+#include "../../../util/perf_regs.h"
+#include "../../../util/event.h"
 
 bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg)
 {
diff --git a/tools/perf/arch/arm/util/unwind-libunwind.c b/tools/perf/arch/arm/util/unwind-libunwind.c
index 3a550225dfafd37d579ba0a464e9ec067485660d..438906bf0014abb75d16db98ac304a20e7e5fb1b 100644
--- a/tools/perf/arch/arm/util/unwind-libunwind.c
+++ b/tools/perf/arch/arm/util/unwind-libunwind.c
@@ -3,8 +3,8 @@
 #include <errno.h>
 #include <libunwind.h>
 #include "perf_regs.h"
-#include "../../util/unwind.h"
-#include "../../util/debug.h"
+#include "../../../util/unwind.h"
+#include "../../../util/debug.h"
 
 int libunwind__arch_reg_id(int regnum)
 {
diff --git a/tools/perf/arch/x86/util/iostat.c b/tools/perf/arch/x86/util/iostat.c
index eeafe97b8105bbd0b1c36cf0b8393624d88eb48e..792cd75ade33d8707dd9dcab36962d5244c0977b 100644
--- a/tools/perf/arch/x86/util/iostat.c
+++ b/tools/perf/arch/x86/util/iostat.c
@@ -432,7 +432,7 @@ void iostat_print_metric(struct perf_stat_config *config, struct evsel *evsel,
 	u8 die = ((struct iio_root_port *)evsel->priv)->die;
 	struct perf_counts_values *count = perf_counts(evsel->counts, die, 0);
 
-	if (count->run && count->ena) {
+	if (count && count->run && count->ena) {
 		if (evsel->prev_raw_counts && !out->force_header) {
 			struct perf_counts_values *prev_count =
 				perf_counts(evsel->prev_raw_counts, die, 0);
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index f6e87b7be5fa22dd1c628b0c76df923bb981eb3b..f0ecfda34ecebaccf8e85e029f9fce50379bdf29 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -2408,6 +2408,8 @@ int cmd_stat(int argc, const char **argv)
 			goto out;
 		} else if (verbose)
 			iostat_list(evsel_list, &stat_config);
+		if (iostat_mode == IOSTAT_RUN && !target__has_cpu(&target))
+			target.system_wide = true;
 	}
 
 	if (add_default_attributes())
diff --git a/tools/perf/pmu-events/arch/powerpc/power8/other.json b/tools/perf/pmu-events/arch/powerpc/power8/other.json
index 84a0cedf1fd9bcfb7bf648a48640320a578fe18b..f1f2965f6775cad71bb0d47f3b15a9064d9c3b75 100644
--- a/tools/perf/pmu-events/arch/powerpc/power8/other.json
+++ b/tools/perf/pmu-events/arch/powerpc/power8/other.json
@@ -1046,7 +1046,7 @@
   {
     "EventCode": "0x4e010",
     "EventName": "PM_GCT_NOSLOT_IC_L3MISS",
-    "BriefDescription": "Gct empty for this thread due to icach l3 miss",
+    "BriefDescription": "Gct empty for this thread due to icache l3 miss",
     "PublicDescription": ""
   },
   {
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index 9866cddebf237c2fdf8b9c1d28501e9a4b277962..9b4a765e4b7340d8a58ef6a2afd26584a6759a8c 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -229,8 +229,8 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode,
 			    struct thread *thread, struct state *state)
 {
 	struct addr_location al;
-	unsigned char buf1[BUFSZ];
-	unsigned char buf2[BUFSZ];
+	unsigned char buf1[BUFSZ] = {0};
+	unsigned char buf2[BUFSZ] = {0};
 	size_t ret_len;
 	u64 objdump_addr;
 	const char *objdump_name;
diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c
index a288035eb36269bcb9d062df3e648faf7ed7bb2c..c756284b3b1353292b677d7f32b923877515c56e 100644
--- a/tools/perf/tests/dwarf-unwind.c
+++ b/tools/perf/tests/dwarf-unwind.c
@@ -20,6 +20,23 @@
 /* For bsearch. We try to unwind functions in shared object. */
 #include <stdlib.h>
 
+/*
+ * The test will assert frames are on the stack but tail call optimizations lose
+ * the frame of the caller. Clang can disable this optimization on a called
+ * function but GCC currently (11/2020) lacks this attribute. The barrier is
+ * used to inhibit tail calls in these cases.
+ */
+#ifdef __has_attribute
+#if __has_attribute(disable_tail_calls)
+#define NO_TAIL_CALL_ATTRIBUTE __attribute__((disable_tail_calls))
+#define NO_TAIL_CALL_BARRIER
+#endif
+#endif
+#ifndef NO_TAIL_CALL_ATTRIBUTE
+#define NO_TAIL_CALL_ATTRIBUTE
+#define NO_TAIL_CALL_BARRIER __asm__ __volatile__("" : : : "memory");
+#endif
+
 static int mmap_handler(struct perf_tool *tool __maybe_unused,
 			union perf_event *event,
 			struct perf_sample *sample,
@@ -91,7 +108,7 @@ static int unwind_entry(struct unwind_entry *entry, void *arg)
 	return strcmp((const char *) symbol, funcs[idx]);
 }
 
-noinline int test_dwarf_unwind__thread(struct thread *thread)
+NO_TAIL_CALL_ATTRIBUTE noinline int test_dwarf_unwind__thread(struct thread *thread)
 {
 	struct perf_sample sample;
 	unsigned long cnt = 0;
@@ -122,7 +139,7 @@ noinline int test_dwarf_unwind__thread(struct thread *thread)
 
 static int global_unwind_retval = -INT_MAX;
 
-noinline int test_dwarf_unwind__compare(void *p1, void *p2)
+NO_TAIL_CALL_ATTRIBUTE noinline int test_dwarf_unwind__compare(void *p1, void *p2)
 {
 	/* Any possible value should be 'thread' */
 	struct thread *thread = *(struct thread **)p1;
@@ -141,7 +158,7 @@ noinline int test_dwarf_unwind__compare(void *p1, void *p2)
 	return p1 - p2;
 }
 
-noinline int test_dwarf_unwind__krava_3(struct thread *thread)
+NO_TAIL_CALL_ATTRIBUTE noinline int test_dwarf_unwind__krava_3(struct thread *thread)
 {
 	struct thread *array[2] = {thread, thread};
 	void *fp = &bsearch;
@@ -160,14 +177,22 @@ noinline int test_dwarf_unwind__krava_3(struct thread *thread)
 	return global_unwind_retval;
 }
 
-noinline int test_dwarf_unwind__krava_2(struct thread *thread)
+NO_TAIL_CALL_ATTRIBUTE noinline int test_dwarf_unwind__krava_2(struct thread *thread)
 {
-	return test_dwarf_unwind__krava_3(thread);
+	int ret;
+
+	ret =  test_dwarf_unwind__krava_3(thread);
+	NO_TAIL_CALL_BARRIER;
+	return ret;
 }
 
-noinline int test_dwarf_unwind__krava_1(struct thread *thread)
+NO_TAIL_CALL_ATTRIBUTE noinline int test_dwarf_unwind__krava_1(struct thread *thread)
 {
-	return test_dwarf_unwind__krava_2(thread);
+	int ret;
+
+	ret =  test_dwarf_unwind__krava_2(thread);
+	NO_TAIL_CALL_BARRIER;
+	return ret;
 }
 
 int test__dwarf_unwind(struct test *test __maybe_unused, int subtest __maybe_unused)
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index 4fb5e90d7a57ae481873b2d632dc60a992ea165d..60ce5908c6640022c472acc6d0611195a4c93284 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -801,7 +801,7 @@ int perf_config_set(struct perf_config_set *set,
 				  section->name, item->name);
 			ret = fn(key, value, data);
 			if (ret < 0) {
-				pr_err("Error: wrong config key-value pair %s=%s\n",
+				pr_err("Error in the given config file: wrong config key-value pair %s=%s\n",
 				       key, value);
 				/*
 				 * Can't be just a 'break', as perf_config_set__for_each_entry()