Merge branch 'locking/urgent' into locking/core, to pick up fixes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

69 files changed, 535 insertions, 150 deletions

diff --git a/tools/bootconfig/test-bootconfig.sh b/tools/bootconfig/test-bootconfig.sh
index 56284b98d8f0..d295e406a756 100755
--- a/tools/bootconfig/test-bootconfig.sh
+++ b/tools/bootconfig/test-bootconfig.sh
@@ -137,6 +137,31 @@ $BOOTCONF $INITRD > $TEMPCONF
 cat $TEMPCONF
 xpass grep \'\"string\"\' $TEMPCONF
 
+echo "Repeat same-key tree"
+cat > $TEMPCONF << EOF
+foo
+bar
+foo { buz }
+EOF
+echo > $INITRD
+
+xpass $BOOTCONF -a $TEMPCONF $INITRD
+$BOOTCONF $INITRD > $OUTFILE
+xpass grep -q "bar" $OUTFILE
+
+
+echo "Remove/keep tailing spaces"
+cat > $TEMPCONF << EOF
+foo = val     # comment
+bar = "val2 " # comment
+EOF
+echo > $INITRD
+
+xpass $BOOTCONF -a $TEMPCONF $INITRD
+$BOOTCONF $INITRD > $OUTFILE
+xfail grep -q val[[:space:]] $OUTFILE
+xpass grep -q val2[[:space:]] $OUTFILE
+
 echo "=== expected failure cases ==="
 for i in samples/bad-* ; do
   xfail $BOOTCONF -a $i $INITRD
diff --git a/tools/bpf/Makefile b/tools/bpf/Makefile
index 0a6d09a3e91f..39bb322707b4 100644
--- a/tools/bpf/Makefile
+++ b/tools/bpf/Makefile
@@ -38,7 +38,7 @@ FEATURE_TESTS = libbfd disassembler-four-args
 FEATURE_DISPLAY = libbfd disassembler-four-args
 
 check_feat := 1
-NON_CHECK_FEAT_TARGETS := clean bpftool_clean runqslower_clean
+NON_CHECK_FEAT_TARGETS := clean bpftool_clean runqslower_clean resolve_btfids_clean
 ifdef MAKECMDGOALS
 ifeq ($(filter-out $(NON_CHECK_FEAT_TARGETS),$(MAKECMDGOALS)),)
   check_feat := 0
@@ -89,7 +89,7 @@ $(OUTPUT)bpf_exp.lex.c: $(OUTPUT)bpf_exp.yacc.c
 $(OUTPUT)bpf_exp.yacc.o: $(OUTPUT)bpf_exp.yacc.c
 $(OUTPUT)bpf_exp.lex.o: $(OUTPUT)bpf_exp.lex.c
 
-clean: bpftool_clean runqslower_clean
+clean: bpftool_clean runqslower_clean resolve_btfids_clean
 	$(call QUIET_CLEAN, bpf-progs)
 	$(Q)$(RM) -r -- $(OUTPUT)*.o $(OUTPUT)bpf_jit_disasm $(OUTPUT)bpf_dbg \
 	       $(OUTPUT)bpf_asm $(OUTPUT)bpf_exp.yacc.* $(OUTPUT)bpf_exp.lex.*
diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile
index 8462690a039b..4828913703b6 100644
--- a/tools/bpf/bpftool/Makefile
+++ b/tools/bpf/bpftool/Makefile
@@ -25,7 +25,7 @@ endif
 
 LIBBPF = $(LIBBPF_PATH)libbpf.a
 
-BPFTOOL_VERSION := $(shell make -rR --no-print-directory -sC ../../.. kernelversion)
+BPFTOOL_VERSION ?= $(shell make -rR --no-print-directory -sC ../../.. kernelversion)
 
 $(LIBBPF): FORCE
 	$(if $(LIBBPF_OUTPUT),@mkdir -p $(LIBBPF_OUTPUT))
diff --git a/tools/bpf/resolve_btfids/Makefile b/tools/bpf/resolve_btfids/Makefile
index a88cd4426398..fe8eb537688b 100644
--- a/tools/bpf/resolve_btfids/Makefile
+++ b/tools/bpf/resolve_btfids/Makefile
@@ -80,6 +80,7 @@ libbpf-clean:
 clean: libsubcmd-clean libbpf-clean fixdep-clean
 	$(call msg,CLEAN,$(BINARY))
 	$(Q)$(RM) -f $(BINARY); \
+	$(RM) -rf $(if $(OUTPUT),$(OUTPUT),.)/feature; \
 	find $(if $(OUTPUT),$(OUTPUT),.) -name \*.o -or -name \*.o.cmd -or -name \*.o.d | xargs $(RM)
 
 tags:
diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h
index 3d0d8231dc19..7d6687618d80 100644
--- a/tools/include/uapi/linux/in.h
+++ b/tools/include/uapi/linux/in.h
@@ -135,7 +135,7 @@ struct in_addr {
  * this socket to prevent accepting spoofed ones.
  */
 #define IP_PMTUDISC_INTERFACE		4
-/* weaker version of IP_PMTUDISC_INTERFACE, which allos packets to get
+/* weaker version of IP_PMTUDISC_INTERFACE, which allows packets to get
  * fragmented if they exeed the interface mtu
  */
 #define IP_PMTUDISC_OMIT		5
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index f6d86033c4fa..7d8eced6f459 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -790,9 +790,10 @@ struct kvm_ppc_resize_hpt {
 #define KVM_VM_PPC_HV 1
 #define KVM_VM_PPC_PR 2
 
-/* on MIPS, 0 forces trap & emulate, 1 forces VZ ASE */
-#define KVM_VM_MIPS_TE		0
+/* on MIPS, 0 indicates auto, 1 forces VZ ASE, 2 forces trap & emulate */
+#define KVM_VM_MIPS_AUTO	0
 #define KVM_VM_MIPS_VZ		1
+#define KVM_VM_MIPS_TE		2
 
 #define KVM_S390_SIE_PAGE_OFFSET 1
 
@@ -1035,6 +1036,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_LAST_CPU 184
 #define KVM_CAP_SMALLER_MAXPHYADDR 185
 #define KVM_CAP_S390_DIAG318 186
+#define KVM_CAP_STEAL_TIME 187
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index 077e7ee69e3d..3e5dcdd48a49 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -1196,7 +1196,7 @@ union perf_mem_data_src {
 
 #define PERF_MEM_SNOOPX_FWD	0x01 /* forward */
 /* 1 free */
-#define PERF_MEM_SNOOPX_SHIFT	37
+#define PERF_MEM_SNOOPX_SHIFT	38
 
 /* locked instruction */
 #define PERF_MEM_LOCK_NA	0x01 /* not available */
diff --git a/tools/io_uring/io_uring-bench.c b/tools/io_uring/io_uring-bench.c
index 0f257139b003..7703f0118385 100644
--- a/tools/io_uring/io_uring-bench.c
+++ b/tools/io_uring/io_uring-bench.c
@@ -130,7 +130,7 @@ static int io_uring_register_files(struct submitter *s)
 					s->nr_files);
 }
 
-static int gettid(void)
+static int lk_gettid(void)
 {
 	return syscall(__NR_gettid);
 }
@@ -281,7 +281,7 @@ static void *submitter_fn(void *data)
 	struct io_sq_ring *ring = &s->sq_ring;
 	int ret, prepped;
 
-	printf("submitter=%d\n", gettid());
+	printf("submitter=%d\n", lk_gettid());
 
 	srand48_r(pthread_self(), &s->rand);
 
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index bf8ed134cb8a..9ae8f4ef0aac 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -59,7 +59,7 @@ FEATURE_USER = .libbpf
 FEATURE_TESTS = libelf libelf-mmap zlib bpf reallocarray
 FEATURE_DISPLAY = libelf zlib bpf
 
-INCLUDES = -I. -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(ARCH)/include/uapi -I$(srctree)/tools/include/uapi
+INCLUDES = -I. -I$(srctree)/tools/include -I$(srctree)/tools/include/uapi
 FEATURE_CHECK_CFLAGS-bpf = $(INCLUDES)
 
 check_feat := 1
@@ -152,6 +152,7 @@ GLOBAL_SYM_COUNT = $(shell readelf -s --wide $(BPF_IN_SHARED) | \
 			   awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}' | \
 			   sort -u | wc -l)
 VERSIONED_SYM_COUNT = $(shell readelf --dyn-syms --wide $(OUTPUT)libbpf.so | \
+			      awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}' | \
 			      grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 | sort -u | wc -l)
 
 CMD_TARGETS = $(LIB_TARGET) $(PC_FILE)
@@ -219,6 +220,7 @@ check_abi: $(OUTPUT)libbpf.so
 		    awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}'|  \
 		    sort -u > $(OUTPUT)libbpf_global_syms.tmp;		 \
 		readelf --dyn-syms --wide $(OUTPUT)libbpf.so |		 \
+		    awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}'|  \
 		    grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 |		 \
 		    sort -u > $(OUTPUT)libbpf_versioned_syms.tmp; 	 \
 		diff -u $(OUTPUT)libbpf_global_syms.tmp			 \
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 7dfca7016aaa..6bdbc389b493 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -659,6 +659,12 @@ struct btf *btf__parse_raw(const char *path)
 		err = -EIO;
 		goto err_out;
 	}
+	if (magic == __bswap_16(BTF_MAGIC)) {
+		/* non-native endian raw BTF */
+		pr_warn("non-native BTF endianness is not supported\n");
+		err = -LIBBPF_ERRNO__ENDIAN;
+		goto err_out;
+	}
 	if (magic != BTF_MAGIC) {
 		/* definitely not a raw BTF */
 		err = -EPROTO;
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 0ad0b0491e1f..e493d6048143 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -5203,8 +5203,8 @@ static int bpf_object__collect_map_relos(struct bpf_object *obj,
 	int i, j, nrels, new_sz;
 	const struct btf_var_secinfo *vi = NULL;
 	const struct btf_type *sec, *var, *def;
+	struct bpf_map *map = NULL, *targ_map;
 	const struct btf_member *member;
-	struct bpf_map *map, *targ_map;
 	const char *name, *mname;
 	Elf_Data *symbols;
 	unsigned int moff;
@@ -6925,7 +6925,7 @@ static const struct bpf_sec_def section_defs[] = {
 						BPF_XDP_DEVMAP),
 	BPF_EAPROG_SEC("xdp_cpumap/",		BPF_PROG_TYPE_XDP,
 						BPF_XDP_CPUMAP),
-	BPF_EAPROG_SEC("xdp",			BPF_PROG_TYPE_XDP,
+	BPF_APROG_SEC("xdp",			BPF_PROG_TYPE_XDP,
 						BPF_XDP),
 	BPF_PROG_SEC("perf_event",		BPF_PROG_TYPE_PERF_EVENT),
 	BPF_PROG_SEC("lwt_in",			BPF_PROG_TYPE_LWT_IN),
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 3ba566de821c..5acc18b32606 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -5259,7 +5259,7 @@ static int print_arg_pointer(struct trace_seq *s, const char *format, int plen,
 	default:
 		ret = 0;
 		val = eval_num_arg(data, size, event, arg);
-		trace_seq_printf(s, "%p", (void *)val);
+		trace_seq_printf(s, "%p", (void *)(intptr_t)val);
 		break;
 	}
 
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index e034a8f24f46..90a66891441a 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -619,7 +619,7 @@ static int add_jump_destinations(struct objtool_file *file)
 		if (!is_static_jump(insn))
 			continue;
 
-		if (insn->ignore || insn->offset == FAKE_JUMP_OFFSET)
+		if (insn->offset == FAKE_JUMP_OFFSET)
 			continue;
 
 		reloc = find_reloc_by_dest_range(file->elf, insn->sec,
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 3f72d8e261f3..bd50cdff08a8 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -33,6 +33,10 @@ OPTIONS
         - a raw PMU event (eventsel+umask) in the form of rNNN where NNN is a
 	  hexadecimal event descriptor.
 
+        - a symbolic or raw PMU event followed by an optional colon
+	  and a list of event modifiers, e.g., cpu-cycles:p.  See the
+	  linkperf:perf-list[1] man page for details on event modifiers.
+
 	- a symbolically formed PMU event like 'pmu/param1=0x3,param2/' where
 	  'param1', 'param2', etc are defined as formats for the PMU in
 	  /sys/bus/event_source/devices/<pmu>/format/*.
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index c9bfefc051fb..db420dd75e43 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -39,6 +39,10 @@ report::
 	- a raw PMU event (eventsel+umask) in the form of rNNN where NNN is a
 	  hexadecimal event descriptor.
 
+        - a symbolic or raw PMU event followed by an optional colon
+	  and a list of event modifiers, e.g., cpu-cycles:p.  See the
+	  linkperf:perf-list[1] man page for details on event modifiers.
+
 	- a symbolically formed event like 'pmu/param1=0x3,param2/' where
 	  param1 and param2 are defined as formats for the PMU in
 	  /sys/bus/event_source/devices/<pmu>/format/*
@@ -416,6 +420,9 @@ counts for all hardware threads in a core but show the sum counts per
 hardware thread. This is essentially a replacement for the any bit and
 convenient for post processing.
 
+--summary::
+Print summary for interval mode (-I).
+
 EXAMPLES
 --------
 
diff --git a/tools/perf/bench/sched-messaging.c b/tools/perf/bench/sched-messaging.c
index 71d830d7b923..cecce93ccc63 100644
--- a/tools/perf/bench/sched-messaging.c
+++ b/tools/perf/bench/sched-messaging.c
@@ -66,11 +66,10 @@ static void fdpair(int fds[2])
 /* Block until we're ready to go */
 static void ready(int ready_out, int wakefd)
 {
-	char dummy;
 	struct pollfd pollfd = { .fd = wakefd, .events = POLLIN };
 
 	/* Tell them we're ready. */
-	if (write(ready_out, &dummy, 1) != 1)
+	if (write(ready_out, "R", 1) != 1)
 		err(EXIT_FAILURE, "CLIENT: ready write");
 
 	/* Wait for "GO" signal */
@@ -85,6 +84,7 @@ static void *sender(struct sender_context *ctx)
 	unsigned int i, j;
 
 	ready(ctx->ready_out, ctx->wakefd);
+	memset(data, 'S', sizeof(data));
 
 	/* Now pump to every receiver. */
 	for (i = 0; i < nr_loops; i++) {
diff --git a/tools/perf/bench/synthesize.c b/tools/perf/bench/synthesize.c
index 8d624aea1c5e..b2924e3181dc 100644
--- a/tools/perf/bench/synthesize.c
+++ b/tools/perf/bench/synthesize.c
@@ -162,8 +162,8 @@ static int do_run_multi_threaded(struct target *target,
 	init_stats(&event_stats);
 	for (i = 0; i < multi_iterations; i++) {
 		session = perf_session__new(NULL, false, NULL);
-		if (!session)
-			return -ENOMEM;
+		if (IS_ERR(session))
+			return PTR_ERR(session);
 
 		atomic_set(&event_count, 0);
 		gettimeofday(&start, NULL);
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index f91352f847c0..772f1057647f 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -2452,7 +2452,7 @@ static struct option __record_options[] = {
 	OPT_BOOLEAN(0, "tail-synthesize", &record.opts.tail_synthesize,
 		    "synthesize non-sample events at the end of output"),
 	OPT_BOOLEAN(0, "overwrite", &record.opts.overwrite, "use overwrite mode"),
-	OPT_BOOLEAN(0, "no-bpf-event", &record.opts.no_bpf_event, "record bpf events"),
+	OPT_BOOLEAN(0, "no-bpf-event", &record.opts.no_bpf_event, "do not record bpf events"),
 	OPT_BOOLEAN(0, "strict-freq", &record.opts.strict_freq,
 		    "Fail if the specified frequency can't be used"),
 	OPT_CALLBACK('F', "freq", &record.opts, "freq or 'max'",
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index ece1cddfcd7c..3c74c9c0f3c3 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -1332,6 +1332,9 @@ int cmd_report(int argc, const char **argv)
 	if (report.mmaps_mode)
 		report.tasks_mode = true;
 
+	if (dump_trace)
+		report.tool.ordered_events = false;
+
 	if (quiet)
 		perf_quiet_option();
 
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 0c7d599fa555..e6fc297cee91 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -2584,7 +2584,8 @@ static int timehist_sched_change_event(struct perf_tool *tool,
 	}
 
 	if (!sched->idle_hist || thread->tid == 0) {
-		timehist_update_runtime_stats(tr, t, tprev);
+		if (!cpu_list || test_bit(sample->cpu, cpu_bitmap))
+			timehist_update_runtime_stats(tr, t, tprev);
 
 		if (sched->idle_hist) {
 			struct idle_thread_runtime *itr = (void *)tr;
@@ -2857,6 +2858,9 @@ static void timehist_print_summary(struct perf_sched *sched,
 
 	printf("\nIdle stats:\n");
 	for (i = 0; i < idle_max_cpu; ++i) {
+		if (cpu_list && !test_bit(i, cpu_bitmap))
+			continue;
+
 		t = idle_threads[i];
 		if (!t)
 			continue;
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 483a28ef4ec4..fddc97cac984 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -404,7 +404,7 @@ static void read_counters(struct timespec *rs)
 {
 	struct evsel *counter;
 
-	if (!stat_config.summary && (read_affinity_counters(rs) < 0))
+	if (!stat_config.stop_read_counter && (read_affinity_counters(rs) < 0))
 		return;
 
 	evlist__for_each_entry(evsel_list, counter) {
@@ -897,9 +897,9 @@ try_again_reset:
 	if (stat_config.walltime_run_table)
 		stat_config.walltime_run[run_idx] = t1 - t0;
 
-	if (interval) {
+	if (interval && stat_config.summary) {
 		stat_config.interval = 0;
-		stat_config.summary = true;
+		stat_config.stop_read_counter = true;
 		init_stats(&walltime_nsecs_stats);
 		update_stats(&walltime_nsecs_stats, t1 - t0);
 
@@ -1164,6 +1164,8 @@ static struct option stat_options[] = {
 		    "Use with 'percore' event qualifier to show the event "
 		    "counts of one hardware thread by sum up total hardware "
 		    "threads of same physical core"),
+	OPT_BOOLEAN(0, "summary", &stat_config.summary,
+		       "print summary for interval mode"),
 #ifdef HAVE_LIBPFM
 	OPT_CALLBACK(0, "pfm-events", &evsel_list, "event",
 		"libpfm4 event selector. use 'perf list' to list available events",
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 994c230027bb..7c64134472c7 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -1746,6 +1746,7 @@ int cmd_top(int argc, const char **argv)
 		goto out_delete_evlist;
 	}
 
+#ifdef HAVE_LIBBPF_SUPPORT
 	if (!top.record_opts.no_bpf_event) {
 		top.sb_evlist = evlist__new();
 
@@ -1759,6 +1760,7 @@ int cmd_top(int argc, const char **argv)
 			goto out_delete_evlist;
 		}
 	}
+#endif
 
 	if (perf_evlist__start_sb_thread(top.sb_evlist, target)) {
 		pr_debug("Couldn't start the BPF side band thread:\nBPF programs starting from now on won't be annotatable\n");
diff --git a/tools/perf/pmu-events/arch/x86/amdzen1/core.json b/tools/perf/pmu-events/arch/x86/amdzen1/core.json
index 7e1aa8273935..653b11b23399 100644
--- a/tools/perf/pmu-events/arch/x86/amdzen1/core.json
+++ b/tools/perf/pmu-events/arch/x86/amdzen1/core.json
@@ -61,7 +61,7 @@
   {
     "EventName": "ex_ret_brn_ind_misp",
     "EventCode": "0xca",
-    "BriefDescription": "Retired Indirect Branch Instructions Mispredicted.",
+    "BriefDescription": "Retired Indirect Branch Instructions Mispredicted."
   },
   {
     "EventName": "ex_ret_mmx_fp_instr.sse_instr",
diff --git a/tools/perf/pmu-events/arch/x86/amdzen2/core.json b/tools/perf/pmu-events/arch/x86/amdzen2/core.json
index de89e5a44ff1..4b75183da94a 100644
--- a/tools/perf/pmu-events/arch/x86/amdzen2/core.json
+++ b/tools/perf/pmu-events/arch/x86/amdzen2/core.json
@@ -125,6 +125,6 @@
   {
     "EventName": "ex_ret_fus_brnch_inst",
     "EventCode": "0x1d0",
-    "BriefDescription": "Retired Fused Instructions. The number of fuse-branch instructions retired per cycle. The number of events logged per cycle can vary from 0-8.",
+    "BriefDescription": "Retired Fused Instructions. The number of fuse-branch instructions retired per cycle. The number of events logged per cycle can vary from 0-8."
   }
 ]
diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c
index fa86c5f997cc..fc9c158bfa13 100644
--- a/tools/perf/pmu-events/jevents.c
+++ b/tools/perf/pmu-events/jevents.c
@@ -137,7 +137,7 @@ static char *fixregex(char *s)
 		return s;
 
 	/* allocate space for a new string */
-	fixed = (char *) malloc(len + 1);
+	fixed = (char *) malloc(len + esc_count + 1);
 	if (!fixed)
 		return NULL;
 
diff --git a/tools/perf/tests/attr/README b/tools/perf/tests/attr/README
index 6cd408108595..a36f49fb4dbe 100644
--- a/tools/perf/tests/attr/README
+++ b/tools/perf/tests/attr/README
@@ -49,6 +49,7 @@ Following tests are defined (with perf commands):
   perf record --call-graph fp kill              (test-record-graph-fp)
   perf record --group -e cycles,instructions kill (test-record-group)
   perf record -e '{cycles,instructions}' kill   (test-record-group1)
+  perf record -e '{cycles/period=1/,instructions/period=2/}:S' kill (test-record-group2)
   perf record -D kill                           (test-record-no-delay)
   perf record -i kill                           (test-record-no-inherit)
   perf record -n kill                           (test-record-no-samples)
diff --git a/tools/perf/tests/attr/test-record-group2 b/tools/perf/tests/attr/test-record-group2
new file mode 100644
index 000000000000..6b9f8d182ce1
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-group2
@@ -0,0 +1,29 @@
+[config]
+command = record
+args    = --no-bpf-event -e '{cycles/period=1234000/,instructions/period=6789000/}:S' kill >/dev/null 2>&1
+ret     = 1
+
+[event-1:base-record]
+fd=1
+group_fd=-1
+config=0|1
+sample_period=1234000
+sample_type=87
+read_format=12
+inherit=0
+freq=0
+
+[event-2:base-record]
+fd=2
+group_fd=1
+config=0|1
+sample_period=6789000
+sample_type=87
+read_format=12
+disabled=0
+inherit=0
+mmap=0
+comm=0
+freq=0
+enable_on_exec=0
+task=0
diff --git a/tools/perf/tests/bp_signal.c b/tools/perf/tests/bp_signal.c
index da8ec1e8e064..cc9fbcedb364 100644
--- a/tools/perf/tests/bp_signal.c
+++ b/tools/perf/tests/bp_signal.c
@@ -45,10 +45,13 @@ volatile long the_var;
 #if defined (__x86_64__)
 extern void __test_function(volatile long *ptr);
 asm (
+	".pushsection .text;"
 	".globl __test_function\n"
+	".type __test_function, @function;"
 	"__test_function:\n"
 	"incq (%rdi)\n"
-	"ret\n");
+	"ret\n"
+	".popsection\n");
 #else
 static void __test_function(volatile long *ptr)
 {
diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c
index 5d20bf8397f0..cd77e334e577 100644
--- a/tools/perf/tests/bpf.c
+++ b/tools/perf/tests/bpf.c
@@ -197,7 +197,7 @@ static int do_test(struct bpf_object *obj, int (*func)(void),
 		perf_mmap__read_done(&md->core);
 	}
 
-	if (count != expect) {
+	if (count != expect * evlist->core.nr_entries) {
 		pr_debug("BPF filter result incorrect, expected %d, got %d samples\n", expect, count);
 		goto out_delete_evlist;
 	}
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 7f9f87a470c3..aae0fd9045c1 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -719,7 +719,7 @@ static int test__group2(struct evlist *evlist)
 	TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
 	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel);
 	TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv);
-	TEST_ASSERT_VAL("wrong exclude guest", !evsel->core.attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude guest", evsel->core.attr.exclude_guest);
 	TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip);
 	TEST_ASSERT_VAL("wrong leader", evsel__is_group_leader(evsel));
@@ -842,7 +842,7 @@ static int test__group3(struct evlist *evlist __maybe_unused)
 	TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
 	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel);
 	TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv);
-	TEST_ASSERT_VAL("wrong exclude guest", !evsel->core.attr.exclude_guest);
+	TEST_ASSERT_VAL("wrong exclude guest", evsel->core.attr.exclude_guest);
 	TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip);
 	TEST_ASSERT_VAL("wrong leader", evsel__is_group_leader(evsel));
diff --git a/tools/perf/tests/parse-metric.c b/tools/perf/tests/parse-metric.c
index fc0838a7abc2..cd7331aac3bd 100644
--- a/tools/perf/tests/parse-metric.c
+++ b/tools/perf/tests/parse-metric.c
@@ -70,6 +70,9 @@ static struct pmu_event pme_test[] = {
 {
 	.metric_expr	= "1/m3",
 	.metric_name	= "M3",
+},
+{
+	.name	= NULL,
 }
 };
 
@@ -150,8 +153,10 @@ static int __compute_metric(const char *name, struct value *vals,
 		return -ENOMEM;
 
 	cpus = perf_cpu_map__new("0");
-	if (!cpus)
+	if (!cpus) {
+		evlist__delete(evlist);
 		return -ENOMEM;
+	}
 
 	perf_evlist__set_maps(&evlist->core, cpus, NULL);
 
@@ -160,10 +165,11 @@ static int __compute_metric(const char *name, struct value *vals,
 					     false, false,
 					     &metric_events);
 	if (err)
-		return err;
+		goto out;
 
-	if (perf_evlist__alloc_stats(evlist, false))
-		return -1;
+	err = perf_evlist__alloc_stats(evlist, false);
+	if (err)
+		goto out;
 
 	/* Load the runtime stats with given numbers for events. */
 	runtime_stat__init(&st);
@@ -175,13 +181,14 @@ static int __compute_metric(const char *name, struct value *vals,
 	if (name2 && ratio2)
 		*ratio2 = compute_single(&metric_events, evlist, &st, name2);
 
+out:
 	/* ... clenup. */
 	metricgroup__rblist_exit(&metric_events);
 	runtime_stat__exit(&st);
 	perf_evlist__free_stats(evlist);
 	perf_cpu_map__put(cpus);
 	evlist__delete(evlist);
-	return 0;
+	return err;
 }
 
 static int compute_metric(const char *name, struct value *vals, double *ratio)
diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c
index eb19f9a0bc15..d3517a74d95e 100644
--- a/tools/perf/tests/pmu-events.c
+++ b/tools/perf/tests/pmu-events.c
@@ -274,6 +274,7 @@ static int __test__pmu_event_aliases(char *pmu_name, int *count)
 	int res = 0;
 	bool use_uncore_table;
 	struct pmu_events_map *map = __test_pmu_get_events_map();
+	struct perf_pmu_alias *a, *tmp;
 
 	if (!map)
 		return -1;
@@ -347,6 +348,10 @@ static int __test__pmu_event_aliases(char *pmu_name, int *count)
 			  pmu_name, alias->name);
 	}
 
+	list_for_each_entry_safe(a, tmp, &aliases, list) {
+		list_del(&a->list);
+		perf_pmu_free_alias(a);
+	}
 	free(pmu);
 	return res;
 }
diff --git a/tools/perf/tests/pmu.c b/tools/perf/tests/pmu.c
index 5c11fe2b3040..714e6830a758 100644
--- a/tools/perf/tests/pmu.c
+++ b/tools/perf/tests/pmu.c
@@ -173,6 +173,7 @@ int test__pmu(struct test *test __maybe_unused, int subtest __maybe_unused)
 		ret = 0;
 	} while (0);
 
+	perf_pmu__del_formats(&formats);
 	test_format_dir_put(format);
 	return ret;
 }
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index be9c4c0549bc..a07626f07208 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -3629,8 +3629,8 @@ int perf_evlist__tui_browse_hists(struct evlist *evlist, const char *help,
 {
 	int nr_entries = evlist->core.nr_entries;
 
-single_entry:
 	if (perf_evlist__single_entry(evlist)) {
+single_entry: {
 		struct evsel *first = evlist__first(evlist);
 
 		return perf_evsel__hists_browse(first, nr_entries, help,
@@ -3638,6 +3638,7 @@ single_entry:
 						env, warn_lost_event,
 						annotation_opts);
 	}
+	}
 
 	if (symbol_conf.event_group) {
 		struct evsel *pos;
diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c
index 302a14d0aca9..93e063f22be5 100644
--- a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c
+++ b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c
@@ -182,15 +182,15 @@ static int arm_spe_read_record(struct arm_spe_decoder *decoder)
 			if (payload & BIT(EV_TLB_ACCESS))
 				decoder->record.type |= ARM_SPE_TLB_ACCESS;
 
-			if ((idx == 1 || idx == 2 || idx == 3) &&
+			if ((idx == 2 || idx == 4 || idx == 8) &&
 			    (payload & BIT(EV_LLC_MISS)))
 				decoder->record.type |= ARM_SPE_LLC_MISS;
 
-			if ((idx == 1 || idx == 2 || idx == 3) &&
+			if ((idx == 2 || idx == 4 || idx == 8) &&
 			    (payload & BIT(EV_LLC_ACCESS)))
 				decoder->record.type |= ARM_SPE_LLC_ACCESS;
 
-			if ((idx == 1 || idx == 2 || idx == 3) &&
+			if ((idx == 2 || idx == 4 || idx == 8) &&
 			    (payload & BIT(EV_REMOTE_ACCESS)))
 				decoder->record.type |= ARM_SPE_REMOTE_ACCESS;
 
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index c283223fb31f..a2a369e2fbb6 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -1344,8 +1344,15 @@ static int cs_etm__synth_events(struct cs_etm_auxtrace *etm,
 		attr.sample_type &= ~(u64)PERF_SAMPLE_ADDR;
 	}
 
-	if (etm->synth_opts.last_branch)
+	if (etm->synth_opts.last_branch) {
 		attr.sample_type |= PERF_SAMPLE_BRANCH_STACK;
+		/*
+		 * We don't use the hardware index, but the sample generation
+		 * code uses the new format branch_stack with this field,
+		 * so the event attributes must indicate that it's present.
+		 */
+		attr.branch_sample_type |= PERF_SAMPLE_BRANCH_HW_INDEX;
+	}
 
 	if (etm->synth_opts.instructions) {
 		attr.config = PERF_COUNT_HW_INSTRUCTIONS;
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index e3fa3bf7498a..c0768c61eb43 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -946,6 +946,10 @@ int perf_evlist__create_maps(struct evlist *evlist, struct target *target)
 
 	perf_evlist__set_maps(&evlist->core, cpus, threads);
 
+	/* as evlist now has references, put count here */
+	perf_cpu_map__put(cpus);
+	perf_thread_map__put(threads);
+
 	return 0;
 
 out_delete_threads:
@@ -1273,11 +1277,12 @@ static int perf_evlist__create_syswide_maps(struct evlist *evlist)
 		goto out_put;
 
 	perf_evlist__set_maps(&evlist->core, cpus, threads);
-out:
-	return err;
+
+	perf_thread_map__put(threads);
 out_put:
 	perf_cpu_map__put(cpus);
-	goto out;
+out:
+	return err;
 }
 
 int evlist__open(struct evlist *evlist)
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index fd865002cbbd..459b51e90063 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -976,16 +976,20 @@ void evsel__config(struct evsel *evsel, struct record_opts *opts,
 	 * We default some events to have a default interval. But keep
 	 * it a weak assumption overridable by the user.
 	 */
-	if (!attr->sample_period || (opts->user_freq != UINT_MAX ||
-				     opts->user_interval != ULLONG_MAX)) {
+	if (!attr->sample_period) {
 		if (opts->freq) {
-			evsel__set_sample_bit(evsel, PERIOD);
 			attr->freq		= 1;
 			attr->sample_freq	= opts->freq;
 		} else {
 			attr->sample_period = opts->default_interval;
 		}
 	}
+	/*
+	 * If attr->freq was set (here or earlier), ask for period
+	 * to be sampled.
+	 */
+	if (attr->freq)
+		evsel__set_sample_bit(evsel, PERIOD);
 
 	if (opts->no_samples)
 		attr->sample_freq = 0;
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 2a8d245351e7..0af4e81c46e2 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -3017,8 +3017,15 @@ static int intel_pt_synth_events(struct intel_pt *pt,
 
 	if (pt->synth_opts.callchain)
 		attr.sample_type |= PERF_SAMPLE_CALLCHAIN;
-	if (pt->synth_opts.last_branch)
+	if (pt->synth_opts.last_branch) {
 		attr.sample_type |= PERF_SAMPLE_BRANCH_STACK;
+		/*
+		 * We don't use the hardware index, but the sample generation
+		 * code uses the new format branch_stack with this field,
+		 * so the event attributes must indicate that it's present.
+		 */
+		attr.branch_sample_type |= PERF_SAMPLE_BRANCH_HW_INDEX;
+	}
 
 	if (pt->synth_opts.instructions) {
 		attr.config = PERF_COUNT_HW_INSTRUCTIONS;
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 208b813e00ea..85587de027a5 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -736,12 +736,6 @@ int machine__process_switch_event(struct machine *machine __maybe_unused,
 	return 0;
 }
 
-static int is_bpf_image(const char *name)
-{
-	return strncmp(name, "bpf_trampoline_", sizeof("bpf_trampoline_") - 1) == 0 ||
-	       strncmp(name, "bpf_dispatcher_", sizeof("bpf_dispatcher_") - 1) == 0;
-}
-
 static int machine__process_ksymbol_register(struct machine *machine,
 					     union perf_event *event,
 					     struct perf_sample *sample __maybe_unused)
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 1d7210804639..cc0faf8f1321 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -267,6 +267,22 @@ bool __map__is_bpf_prog(const struct map *map)
 	return name && (strstr(name, "bpf_prog_") == name);
 }
 
+bool __map__is_bpf_image(const struct map *map)
+{
+	const char *name;
+
+	if (map->dso->binary_type == DSO_BINARY_TYPE__BPF_IMAGE)
+		return true;
+
+	/*
+	 * If PERF_RECORD_KSYMBOL is not included, the dso will not have
+	 * type of DSO_BINARY_TYPE__BPF_IMAGE. In such cases, we can
+	 * guess the type based on name.
+	 */
+	name = map->dso->short_name;
+	return name && is_bpf_image(name);
+}
+
 bool __map__is_ool(const struct map *map)
 {
 	return map->dso && map->dso->binary_type == DSO_BINARY_TYPE__OOL;
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index 9e312ae2d656..c2f5d28fe73a 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -147,12 +147,14 @@ int map__set_kallsyms_ref_reloc_sym(struct map *map, const char *symbol_name,
 bool __map__is_kernel(const struct map *map);
 bool __map__is_extra_kernel_map(const struct map *map);
 bool __map__is_bpf_prog(const struct map *map);
+bool __map__is_bpf_image(const struct map *map);
 bool __map__is_ool(const struct map *map);
 
 static inline bool __map__is_kmodule(const struct map *map)
 {
 	return !__map__is_kernel(map) && !__map__is_extra_kernel_map(map) &&
-	       !__map__is_bpf_prog(map) && !__map__is_ool(map);
+	       !__map__is_bpf_prog(map) && !__map__is_ool(map) &&
+	       !__map__is_bpf_image(map);
 }
 
 bool map__has_symbols(const struct map *map);
@@ -164,4 +166,9 @@ static inline bool is_entry_trampoline(const char *name)
 	return !strcmp(name, ENTRY_TRAMPOLINE_NAME);
 }
 
+static inline bool is_bpf_image(const char *name)
+{
+	return strncmp(name, "bpf_trampoline_", sizeof("bpf_trampoline_") - 1) == 0 ||
+	       strncmp(name, "bpf_dispatcher_", sizeof("bpf_dispatcher_") - 1) == 0;
+}
 #endif /* __PERF_MAP_H */
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index 8831b964288f..ab5030fcfed4 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -85,6 +85,7 @@ static void metric_event_delete(struct rblist *rblist __maybe_unused,
 
 	list_for_each_entry_safe(expr, tmp, &me->head, nd) {
 		free(expr->metric_refs);
+		free(expr->metric_events);
 		free(expr);
 	}
 
@@ -316,6 +317,7 @@ static int metricgroup__setup_events(struct list_head *groups,
 			if (!metric_refs) {
 				ret = -ENOMEM;
 				free(metric_events);
+				free(expr);
 				break;
 			}
 
@@ -530,6 +532,9 @@ void metricgroup__print(bool metrics, bool metricgroups, char *filter,
 						continue;
 					strlist__add(me->metrics, s);
 				}
+
+				if (!raw)
+					free(s);
 			}
 			free(omg);
 		}
@@ -667,7 +672,6 @@ static int __add_metric(struct list_head *metric_list,
 		m->has_constraint = metric_no_group || metricgroup__has_constraint(pe);
 		INIT_LIST_HEAD(&m->metric_refs);
 		m->metric_refs_cnt = 0;
-		*mp = m;
 
 		parent = expr_ids__alloc(ids);
 		if (!parent) {
@@ -680,6 +684,7 @@ static int __add_metric(struct list_head *metric_list,
 			free(m);
 			return -ENOMEM;
 		}
+		*mp = m;
 	} else {
 		/*
 		 * We got here for the referenced metric, via the
@@ -714,8 +719,11 @@ static int __add_metric(struct list_head *metric_list,
 	 * all the metric's IDs and add it to the parent context.
 	 */
 	if (expr__find_other(pe->metric_expr, NULL, &m->pctx, runtime) < 0) {
-		expr__ctx_clear(&m->pctx);
-		free(m);
+		if (m->metric_refs_cnt == 0) {
+			expr__ctx_clear(&m->pctx);
+			free(m);
+			*mp = NULL;
+		}
 		return -EINVAL;
 	}
 
@@ -934,7 +942,7 @@ static int metricgroup__add_metric(const char *metric, bool metric_no_group,
 
 		ret = add_metric(&list, pe, metric_no_group, &m, NULL, &ids);
 		if (ret)
-			return ret;
+			goto out;
 
 		/*
 		 * Process any possible referenced metrics
@@ -943,12 +951,14 @@ static int metricgroup__add_metric(const char *metric, bool metric_no_group,
 		ret = resolve_metric(metric_no_group,
 				     &list, map, &ids);
 		if (ret)
-			return ret;
+			goto out;
 	}
 
 	/* End of pmu events. */
-	if (!has_match)
-		return -EINVAL;
+	if (!has_match) {
+		ret = -EINVAL;
+		goto out;
+	}
 
 	list_for_each_entry(m, &list, nd) {
 		if (events->len > 0)
@@ -963,9 +973,14 @@ static int metricgroup__add_metric(const char *metric, bool metric_no_group,
 		}
 	}
 
+out:
+	/*
+	 * add to metric_list so that they can be released
+	 * even if it's failed
+	 */
 	list_splice(&list, metric_list);
 	expr_ids__exit(&ids);
-	return 0;
+	return ret;
 }
 
 static int metricgroup__add_metric_list(const char *list, bool metric_no_group,
@@ -1040,7 +1055,7 @@ static int parse_groups(struct evlist *perf_evlist, const char *str,
 	ret = metricgroup__add_metric_list(str, metric_no_group,
 					   &extra_events, &metric_list, map);
 	if (ret)
-		return ret;
+		goto out;
 	pr_debug("adding %s\n", extra_events.buf);
 	bzero(&parse_error, sizeof(parse_error));
 	ret = __parse_events(perf_evlist, extra_events.buf, &parse_error, fake_pmu);
@@ -1048,11 +1063,11 @@ static int parse_groups(struct evlist *perf_evlist, const char *str,
 		parse_events_print_error(&parse_error, extra_events.buf);
 		goto out;
 	}
-	strbuf_release(&extra_events);
 	ret = metricgroup__setup_events(&metric_list, metric_no_merge,
 					perf_evlist, metric_events);
 out:
 	metricgroup__free_metrics(&metric_list);
+	strbuf_release(&extra_events);
 	return ret;
 }
 
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 9f7260e69113..667cbca1547a 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -37,6 +37,7 @@
 #include "util/evsel_config.h"
 #include "util/event.h"
 #include "util/pfm.h"
+#include "perf.h"
 
 #define MAX_NAME_LEN 100
 
@@ -410,7 +411,7 @@ static int add_event_tool(struct list_head *list, int *idx,
 		return -ENOMEM;
 	evsel->tool_event = tool_event;
 	if (tool_event == PERF_TOOL_DURATION_TIME)
-		evsel->unit = strdup("ns");
+		evsel->unit = "ns";
 	return 0;
 }
 
@@ -1533,19 +1534,23 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,
 	evsel = __add_event(list, &parse_state->idx, &attr, true,
 			    get_config_name(head_config), pmu,
 			    &config_terms, auto_merge_stats, NULL);
-	if (evsel) {
-		evsel->unit = info.unit;
-		evsel->scale = info.scale;
-		evsel->per_pkg = info.per_pkg;
-		evsel->snapshot = info.snapshot;
-		evsel->metric_expr = info.metric_expr;
-		evsel->metric_name = info.metric_name;
-		evsel->pmu_name = name ? strdup(name) : NULL;
-		evsel->use_uncore_alias = use_uncore_alias;
-		evsel->percore = config_term_percore(&evsel->config_terms);
-	}
+	if (!evsel)
+		return -ENOMEM;
+
+	evsel->pmu_name = name ? strdup(name) : NULL;
+	evsel->use_uncore_alias = use_uncore_alias;
+	evsel->percore = config_term_percore(&evsel->config_terms);
 
-	return evsel ? 0 : -ENOMEM;
+	if (parse_state->fake_pmu)
+		return 0;
+
+	evsel->unit = info.unit;
+	evsel->scale = info.scale;
+	evsel->per_pkg = info.per_pkg;
+	evsel->snapshot = info.snapshot;
+	evsel->metric_expr = info.metric_expr;
+	evsel->metric_name = info.metric_name;
+	return 0;
 }
 
 int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
@@ -1794,6 +1799,8 @@ static int get_event_modifier(struct event_modifier *mod, char *str,
 		if (*str == 'u') {
 			if (!exclude)
 				exclude = eu = ek = eh = 1;
+			if (!exclude_GH && !perf_guest)
+				eG = 1;
 			eu = 0;
 		} else if (*str == 'k') {
 			if (!exclude)
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index b9fb91fdc5de..645bf4f1859f 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -511,7 +511,7 @@ PE_PREFIX_MEM PE_VALUE '/' PE_VALUE ':' PE_MODIFIER_BP sep_dc
 	list = alloc_list();
 	ABORT_ON(!list);
 	err = parse_events_add_breakpoint(list, &parse_state->idx,
-					(void *) $2, $6, $4);
+					(void *)(uintptr_t) $2, $6, $4);
 	free($6);
 	if (err) {
 		free(list);
@@ -528,7 +528,7 @@ PE_PREFIX_MEM PE_VALUE '/' PE_VALUE sep_dc
 	list = alloc_list();
 	ABORT_ON(!list);
 	if (parse_events_add_breakpoint(list, &parse_state->idx,
-						(void *) $2, NULL, $4)) {
+						(void *)(uintptr_t) $2, NULL, $4)) {
 		free(list);
 		YYABORT;
 	}
@@ -544,7 +544,7 @@ PE_PREFIX_MEM PE_VALUE ':' PE_MODIFIER_BP sep_dc
 	list = alloc_list();
 	ABORT_ON(!list);
 	err = parse_events_add_breakpoint(list, &parse_state->idx,
-					(void *) $2, $4, 0);
+					(void *)(uintptr_t) $2, $4, 0);
 	free($4);
 	if (err) {
 		free(list);
@@ -561,7 +561,7 @@ PE_PREFIX_MEM PE_VALUE sep_dc
 	list = alloc_list();
 	ABORT_ON(!list);
 	if (parse_events_add_breakpoint(list, &parse_state->idx,
-						(void *) $2, NULL, 0)) {
+						(void *)(uintptr_t) $2, NULL, 0)) {
 		free(list);
 		YYABORT;
 	}
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index f1688e1f6ed7..d41caeb35cf6 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -274,7 +274,7 @@ static void perf_pmu_update_alias(struct perf_pmu_alias *old,
 }
 
 /* Delete an alias entry. */
-static void perf_pmu_free_alias(struct perf_pmu_alias *newalias)
+void perf_pmu_free_alias(struct perf_pmu_alias *newalias)
 {
 	zfree(&newalias->name);
 	zfree(&newalias->desc);
@@ -1354,6 +1354,17 @@ void perf_pmu__set_format(unsigned long *bits, long from, long to)
 		set_bit(b, bits);
 }
 
+void perf_pmu__del_formats(struct list_head *formats)
+{
+	struct perf_pmu_format *fmt, *tmp;
+
+	list_for_each_entry_safe(fmt, tmp, formats, list) {
+		list_del(&fmt->list);
+		free(fmt->name);
+		free(fmt);
+	}
+}
+
 static int sub_non_neg(int a, int b)
 {
 	if (b > a)
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 44ccbdbb1c37..a64e9c9ce731 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -94,6 +94,7 @@ int perf_pmu__new_format(struct list_head *list, char *name,
 			 int config, unsigned long *bits);
 void perf_pmu__set_format(unsigned long *bits, long from, long to);
 int perf_pmu__format_parse(char *dir, struct list_head *head);
+void perf_pmu__del_formats(struct list_head *formats);
 
 struct perf_pmu *perf_pmu__scan(struct perf_pmu *pmu);
 
@@ -113,6 +114,7 @@ void pmu_add_cpu_aliases_map(struct list_head *head, struct perf_pmu *pmu,
 
 struct pmu_events_map *perf_pmu__find_map(struct perf_pmu *pmu);
 bool pmu_uncore_alias_match(const char *pmu_name, const char *name);
+void perf_pmu_free_alias(struct perf_pmu_alias *alias);
 
 int perf_pmu__convert_scale(const char *scale, char **end, double *sval);
 
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index a4cc11592f6b..ea9aa1d7cf50 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -2,6 +2,7 @@
 #include "debug.h"
 #include "evlist.h"
 #include "evsel.h"
+#include "evsel_config.h"
 #include "parse-events.h"
 #include <errno.h>
 #include <limits.h>
@@ -33,11 +34,24 @@ static struct evsel *evsel__read_sampler(struct evsel *evsel, struct evlist *evl
 	return leader;
 }
 
+static u64 evsel__config_term_mask(struct evsel *evsel)
+{
+	struct evsel_config_term *term;
+	struct list_head *config_terms = &evsel->config_terms;
+	u64 term_types = 0;
+
+	list_for_each_entry(term, config_terms, list) {
+		term_types |= 1 << term->type;
+	}
+	return term_types;
+}
+
 static void evsel__config_leader_sampling(struct evsel *evsel, struct evlist *evlist)
 {
 	struct perf_event_attr *attr = &evsel->core.attr;
 	struct evsel *leader = evsel->leader;
 	struct evsel *read_sampler;
+	u64 term_types, freq_mask;
 
 	if (!leader->sample_read)
 		return;
@@ -47,16 +61,20 @@ static void evsel__config_leader_sampling(struct evsel *evsel, struct evlist *ev
 	if (evsel == read_sampler)
 		return;
 
+	term_types = evsel__config_term_mask(evsel);
 	/*
-	 * Disable sampling for all group members other than the leader in
-	 * case the leader 'leads' the sampling, except when the leader is an
-	 * AUX area event, in which case the 2nd event in the group is the one
-	 * that 'leads' the sampling.
+	 * Disable sampling for all group members except those with explicit
+	 * config terms or the leader. In the case of an AUX area event, the 2nd
+	 * event in the group is the one that 'leads' the sampling.
 	 */
-	attr->freq           = 0;
-	attr->sample_freq    = 0;
-	attr->sample_period  = 0;
-	attr->write_backward = 0;
+	freq_mask = (1 << EVSEL__CONFIG_TERM_FREQ) | (1 << EVSEL__CONFIG_TERM_PERIOD);
+	if ((term_types & freq_mask) == 0) {
+		attr->freq           = 0;
+		attr->sample_freq    = 0;
+		attr->sample_period  = 0;
+	}
+	if ((term_types & (1 << EVSEL__CONFIG_TERM_OVERWRITE)) == 0)
+		attr->write_backward = 0;
 
 	/*
 	 * We don't get a sample for slave events, we make them when delivering
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index ffbc9d35a383..7a5f03764702 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -87,7 +87,7 @@ static int perf_session__process_compressed_event(struct perf_session *session,
 		session->decomp_last = decomp;
 	}
 
-	pr_debug("decomp (B): %ld to %ld\n", src_size, decomp_size);
+	pr_debug("decomp (B): %zd to %zd\n", src_size, decomp_size);
 
 	return 0;
 }
diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
index 57d0706e1330..493ec372fdec 100644
--- a/tools/perf/util/stat-display.c
+++ b/tools/perf/util/stat-display.c
@@ -117,7 +117,7 @@ static void aggr_printout(struct perf_stat_config *config,
 				cpu_map__id_to_die(id),
 				config->csv_output ? 0 : -3,
 				cpu_map__id_to_cpu(id), config->csv_sep);
-		} else {
+		} else if (id > -1) {
 			fprintf(config->output, "CPU%*d%s",
 				config->csv_output ? 0 : -7,
 				evsel__cpus(evsel)->map[id],
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index e1ba6c1b916a..924b54d15d54 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -517,7 +517,7 @@ static void print_l1_dcache_misses(struct perf_stat_config *config,
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
 
-	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all L1-dcache hits", ratio);
+	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all L1-dcache accesses", ratio);
 }
 
 static void print_l1_icache_misses(struct perf_stat_config *config,
@@ -538,7 +538,7 @@ static void print_l1_icache_misses(struct perf_stat_config *config,
 		ratio = avg / total * 100.0;
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all L1-icache hits", ratio);
+	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all L1-icache accesses", ratio);
 }
 
 static void print_dtlb_cache_misses(struct perf_stat_config *config,
@@ -558,7 +558,7 @@ static void print_dtlb_cache_misses(struct perf_stat_config *config,
 		ratio = avg / total * 100.0;
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all dTLB cache hits", ratio);
+	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all dTLB cache accesses", ratio);
 }
 
 static void print_itlb_cache_misses(struct perf_stat_config *config,
@@ -578,7 +578,7 @@ static void print_itlb_cache_misses(struct perf_stat_config *config,
 		ratio = avg / total * 100.0;
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all iTLB cache hits", ratio);
+	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all iTLB cache accesses", ratio);
 }
 
 static void print_ll_cache_misses(struct perf_stat_config *config,
@@ -598,7 +598,7 @@ static void print_ll_cache_misses(struct perf_stat_config *config,
 		ratio = avg / total * 100.0;
 
 	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all LL-cache hits", ratio);
+	out->print_metric(config, out->ctx, color, "%7.2f%%", "of all LL-cache accesses", ratio);
 }
 
 /*
@@ -853,14 +853,16 @@ static void generic_metric(struct perf_stat_config *config,
 double test_generic_metric(struct metric_expr *mexp, int cpu, struct runtime_stat *st)
 {
 	struct expr_parse_ctx pctx;
-	double ratio;
+	double ratio = 0.0;
 
 	if (prepare_metric(mexp->metric_events, mexp->metric_refs, &pctx, cpu, st) < 0)
-		return 0.;
+		goto out;
 
 	if (expr__parse(&ratio, &pctx, mexp->metric_expr, 1))
-		return 0.;
+		ratio = 0.0;
 
+out:
+	expr__ctx_clear(&pctx);
 	return ratio;
 }
 
@@ -918,7 +920,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 		if (runtime_stat_n(st, STAT_L1_DCACHE, ctx, cpu) != 0)
 			print_l1_dcache_misses(config, cpu, evsel, avg, out, st);
 		else
-			print_metric(config, ctxp, NULL, NULL, "of all L1-dcache hits", 0);
+			print_metric(config, ctxp, NULL, NULL, "of all L1-dcache accesses", 0);
 	} else if (
 		evsel->core.attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->core.attr.config ==  ( PERF_COUNT_HW_CACHE_L1I |
@@ -928,7 +930,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 		if (runtime_stat_n(st, STAT_L1_ICACHE, ctx, cpu) != 0)
 			print_l1_icache_misses(config, cpu, evsel, avg, out, st);
 		else
-			print_metric(config, ctxp, NULL, NULL, "of all L1-icache hits", 0);
+			print_metric(config, ctxp, NULL, NULL, "of all L1-icache accesses", 0);
 	} else if (
 		evsel->core.attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->core.attr.config ==  ( PERF_COUNT_HW_CACHE_DTLB |
@@ -938,7 +940,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 		if (runtime_stat_n(st, STAT_DTLB_CACHE, ctx, cpu) != 0)
 			print_dtlb_cache_misses(config, cpu, evsel, avg, out, st);
 		else
-			print_metric(config, ctxp, NULL, NULL, "of all dTLB cache hits", 0);
+			print_metric(config, ctxp, NULL, NULL, "of all dTLB cache accesses", 0);
 	} else if (
 		evsel->core.attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->core.attr.config ==  ( PERF_COUNT_HW_CACHE_ITLB |
@@ -948,7 +950,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 		if (runtime_stat_n(st, STAT_ITLB_CACHE, ctx, cpu) != 0)
 			print_itlb_cache_misses(config, cpu, evsel, avg, out, st);
 		else
-			print_metric(config, ctxp, NULL, NULL, "of all iTLB cache hits", 0);
+			print_metric(config, ctxp, NULL, NULL, "of all iTLB cache accesses", 0);
 	} else if (
 		evsel->core.attr.type == PERF_TYPE_HW_CACHE &&
 		evsel->core.attr.config ==  ( PERF_COUNT_HW_CACHE_LL |
@@ -958,7 +960,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 		if (runtime_stat_n(st, STAT_LL_CACHE, ctx, cpu) != 0)
 			print_ll_cache_misses(config, cpu, evsel, avg, out, st);
 		else
-			print_metric(config, ctxp, NULL, NULL, "of all LL-cache hits", 0);
+			print_metric(config, ctxp, NULL, NULL, "of all LL-cache accesses", 0);
 	} else if (evsel__match(evsel, HARDWARE, HW_CACHE_MISSES)) {
 		total = runtime_stat_avg(st, STAT_CACHEREFS, ctx, cpu);
 
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index f8778cffd941..aa3bed48511b 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -113,6 +113,7 @@ struct perf_stat_config {
 	bool			 summary;
 	bool			 metric_no_group;
 	bool			 metric_no_merge;
+	bool			 stop_read_counter;
 	FILE			*output;
 	unsigned int		 interval;
 	unsigned int		 timeout;
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 1f5fcb828a21..5151a8c0b791 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -663,6 +663,7 @@ static bool symbol__is_idle(const char *name)
 		"exit_idle",
 		"mwait_idle",
 		"mwait_idle_with_hints",
+		"mwait_idle_with_hints.constprop.0",
 		"poll_idle",
 		"ppc64_runlatch_off",
 		"pseries_dedicated_idle_sleep",
diff --git a/tools/perf/util/zstd.c b/tools/perf/util/zstd.c
index d2202392ffdb..48dd2b018c47 100644
--- a/tools/perf/util/zstd.c
+++ b/tools/perf/util/zstd.c
@@ -99,7 +99,7 @@ size_t zstd_decompress_stream(struct zstd_data *data, void *src, size_t src_size
 	while (input.pos < input.size) {
 		ret = ZSTD_decompressStream(data->dstream, &output, &input);
 		if (ZSTD_isError(ret)) {
-			pr_err("failed to decompress (B): %ld -> %ld, dst_size %ld : %s\n",
+			pr_err("failed to decompress (B): %zd -> %zd, dst_size %zd : %s\n",
 			       src_size, output.size, dst_size, ZSTD_getErrorName(ret));
 			break;
 		}
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_hash_map.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_hash_map.c
index 07ddbfdbcab7..6dfce3fd68bc 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_hash_map.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_hash_map.c
@@ -47,7 +47,10 @@ int dump_bpf_hash_map(struct bpf_iter__bpf_map_elem *ctx)
 	__u32 seq_num = ctx->meta->seq_num;
 	struct bpf_map *map = ctx->map;
 	struct key_t *key = ctx->key;
+	struct key_t tmp_key;
 	__u64 *val = ctx->value;
+	__u64 tmp_val = 0;
+	int ret;
 
 	if (in_test_mode) {
 		/* test mode is used by selftests to
@@ -61,6 +64,18 @@ int dump_bpf_hash_map(struct bpf_iter__bpf_map_elem *ctx)
 		if (key == (void *)0 || val == (void *)0)
 			return 0;
 
+		/* update the value and then delete the <key, value> pair.
+		 * it should not impact the existing 'val' which is still
+		 * accessible under rcu.
+		 */
+		__builtin_memcpy(&tmp_key, key, sizeof(struct key_t));
+		ret = bpf_map_update_elem(&hashmap1, &tmp_key, &tmp_val, 0);
+		if (ret)
+			return 0;
+		ret = bpf_map_delete_elem(&hashmap1, &tmp_key);
+		if (ret)
+			return 0;
+
 		key_sum_a += key->a;
 		key_sum_b += key->b;
 		key_sum_c += key->c;
diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c
index 754cf611723e..0d92ebcb335d 100644
--- a/tools/testing/selftests/bpf/test_maps.c
+++ b/tools/testing/selftests/bpf/test_maps.c
@@ -1274,6 +1274,8 @@ static void __run_parallel(unsigned int tasks,
 	pid_t pid[tasks];
 	int i;
 
+	fflush(stdout);
+
 	for (i = 0; i < tasks; i++) {
 		pid[i] = fork();
 		if (pid[i] == 0) {
diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index b1e4dadacd9b..22943b58d752 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -618,7 +618,9 @@ int cd_flavor_subdir(const char *exec_name)
 	if (!flavor)
 		return 0;
 	flavor++;
-	fprintf(stdout, "Switching to flavor '%s' subdirectory...\n", flavor);
+	if (env.verbosity > VERBOSE_NONE)
+		fprintf(stdout,	"Switching to flavor '%s' subdirectory...\n", flavor);
+
 	return chdir(flavor);
 }
 
diff --git a/tools/testing/selftests/kvm/x86_64/debug_regs.c b/tools/testing/selftests/kvm/x86_64/debug_regs.c
index b8d14f9db5f9..2fc6b3af81a1 100644
--- a/tools/testing/selftests/kvm/x86_64/debug_regs.c
+++ b/tools/testing/selftests/kvm/x86_64/debug_regs.c
@@ -73,7 +73,7 @@ int main(void)
 	int i;
 	/* Instruction lengths starting at ss_start */
 	int ss_size[4] = {
-		3,		/* xor */
+		2,		/* xor */
 		2,		/* cpuid */
 		5,		/* mov */
 		2,		/* rdmsr */
diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh
index 7c38a909f8b8..8a2fe6d64bf2 100755
--- a/tools/testing/selftests/net/rtnetlink.sh
+++ b/tools/testing/selftests/net/rtnetlink.sh
@@ -1175,6 +1175,51 @@ kci_test_neigh_get()
 	echo "PASS: neigh get"
 }
 
+kci_test_bridge_parent_id()
+{
+	local ret=0
+	sysfsnet=/sys/bus/netdevsim/devices/netdevsim
+	probed=false
+
+	if [ ! -w /sys/bus/netdevsim/new_device ] ; then
+		modprobe -q netdevsim
+		check_err $?
+		if [ $ret -ne 0 ]; then
+			echo "SKIP: bridge_parent_id can't load netdevsim"
+			return $ksft_skip
+		fi
+		probed=true
+	fi
+
+	echo "10 1" > /sys/bus/netdevsim/new_device
+	while [ ! -d ${sysfsnet}10 ] ; do :; done
+	echo "20 1" > /sys/bus/netdevsim/new_device
+	while [ ! -d ${sysfsnet}20 ] ; do :; done
+	udevadm settle
+	dev10=`ls ${sysfsnet}10/net/`
+	dev20=`ls ${sysfsnet}20/net/`
+
+	ip link add name test-bond0 type bond mode 802.3ad
+	ip link set dev $dev10 master test-bond0
+	ip link set dev $dev20 master test-bond0
+	ip link add name test-br0 type bridge
+	ip link set dev test-bond0 master test-br0
+	check_err $?
+
+	# clean up any leftovers
+	ip link del dev test-br0
+	ip link del dev test-bond0
+	echo 20 > /sys/bus/netdevsim/del_device
+	echo 10 > /sys/bus/netdevsim/del_device
+	$probed && rmmod netdevsim
+
+	if [ $ret -ne 0 ]; then
+		echo "FAIL: bridge_parent_id"
+		return 1
+	fi
+	echo "PASS: bridge_parent_id"
+}
+
 kci_test_rtnl()
 {
 	local ret=0
@@ -1224,6 +1269,8 @@ kci_test_rtnl()
 	check_err $?
 	kci_test_neigh_get
 	check_err $?
+	kci_test_bridge_parent_id
+	check_err $?
 
 	kci_del_dummy
 	return $ret
diff --git a/tools/testing/selftests/netfilter/nft_flowtable.sh b/tools/testing/selftests/netfilter/nft_flowtable.sh
index a47d1d832210..431296c0f91c 100755
--- a/tools/testing/selftests/netfilter/nft_flowtable.sh
+++ b/tools/testing/selftests/netfilter/nft_flowtable.sh
@@ -11,7 +11,7 @@
 # result in fragmentation and/or PMTU discovery.
 #
 # You can check with different Orgininator/Link/Responder MTU eg:
-# sh nft_flowtable.sh -o1000 -l500 -r100
+# nft_flowtable.sh -o8000 -l1500 -r2000
 #
 
 
@@ -27,8 +27,7 @@ ns2out=""
 log_netns=$(sysctl -n net.netfilter.nf_log_all_netns)
 
 checktool (){
-	$1 > /dev/null 2>&1
-	if [ $? -ne 0 ];then
+	if ! $1 > /dev/null 2>&1; then
 		echo "SKIP: Could not $2"
 		exit $ksft_skip
 	fi
@@ -87,19 +86,36 @@ omtu=9000
 lmtu=1500
 rmtu=2000
 
+usage(){
+	echo "nft_flowtable.sh [OPTIONS]"
+	echo
+	echo "MTU options"
+	echo "   -o originator"
+	echo "   -l link"
+	echo "   -r responder"
+	exit 1
+}
+
 while getopts "o:l:r:" o
 do
 	case $o in
 		o) omtu=$OPTARG;;
 		l) lmtu=$OPTARG;;
 		r) rmtu=$OPTARG;;
+		*) usage;;
 	esac
 done
 
-ip -net nsr1 link set veth0 mtu $omtu
+if ! ip -net nsr1 link set veth0 mtu $omtu; then
+	exit 1
+fi
+
 ip -net ns1 link set eth0 mtu $omtu
 
-ip -net nsr2 link set veth1 mtu $rmtu
+if ! ip -net nsr2 link set veth1 mtu $rmtu; then
+	exit 1
+fi
+
 ip -net ns2 link set eth0 mtu $rmtu
 
 # transfer-net between nsr1 and nsr2.
@@ -120,7 +136,10 @@ for i in 1 2; do
   ip -net ns$i route add default via 10.0.$i.1
   ip -net ns$i addr add dead:$i::99/64 dev eth0
   ip -net ns$i route add default via dead:$i::1
-  ip netns exec ns$i sysctl net.ipv4.tcp_no_metrics_save=1 > /dev/null
+  if ! ip netns exec ns$i sysctl net.ipv4.tcp_no_metrics_save=1 > /dev/null; then
+	echo "ERROR: Check Originator/Responder values (problem during address addition)"
+	exit 1
+  fi
 
   # don't set ip DF bit for first two tests
   ip netns exec ns$i sysctl net.ipv4.ip_no_pmtu_disc=1 > /dev/null
@@ -178,15 +197,13 @@ if [ $? -ne 0 ]; then
 fi
 
 # test basic connectivity
-ip netns exec ns1 ping -c 1 -q 10.0.2.99 > /dev/null
-if [ $? -ne 0 ];then
+if ! ip netns exec ns1 ping -c 1 -q 10.0.2.99 > /dev/null; then
   echo "ERROR: ns1 cannot reach ns2" 1>&2
   bash
   exit 1
 fi
 
-ip netns exec ns2 ping -c 1 -q 10.0.1.99 > /dev/null
-if [ $? -ne 0 ];then
+if ! ip netns exec ns2 ping -c 1 -q 10.0.1.99 > /dev/null; then
   echo "ERROR: ns2 cannot reach ns1" 1>&2
   exit 1
 fi
@@ -203,7 +220,6 @@ ns2out=$(mktemp)
 make_file()
 {
 	name=$1
-	who=$2
 
 	SIZE=$((RANDOM % (1024 * 8)))
 	TSIZE=$((SIZE * 1024))
@@ -222,8 +238,7 @@ check_transfer()
 	out=$2
 	what=$3
 
-	cmp "$in" "$out" > /dev/null 2>&1
-	if [ $? -ne 0 ] ;then
+	if ! cmp "$in" "$out" > /dev/null 2>&1; then
 		echo "FAIL: file mismatch for $what" 1>&2
 		ls -l "$in"
 		ls -l "$out"
@@ -260,13 +275,11 @@ test_tcp_forwarding_ip()
 
 	wait
 
-	check_transfer "$ns1in" "$ns2out" "ns1 -> ns2"
-	if [ $? -ne 0 ];then
+	if ! check_transfer "$ns1in" "$ns2out" "ns1 -> ns2"; then
 		lret=1
 	fi
 
-	check_transfer "$ns2in" "$ns1out" "ns1 <- ns2"
-	if [ $? -ne 0 ];then
+	if ! check_transfer "$ns2in" "$ns1out" "ns1 <- ns2"; then
 		lret=1
 	fi
 
@@ -295,13 +308,12 @@ test_tcp_forwarding_nat()
 	return $lret
 }
 
-make_file "$ns1in" "ns1"
-make_file "$ns2in" "ns2"
+make_file "$ns1in"
+make_file "$ns2in"
 
 # First test:
 # No PMTU discovery, nsr1 is expected to fragment packets from ns1 to ns2 as needed.
-test_tcp_forwarding ns1 ns2
-if [ $? -eq 0 ] ;then
+if test_tcp_forwarding ns1 ns2; then
 	echo "PASS: flow offloaded for ns1/ns2"
 else
 	echo "FAIL: flow offload for ns1/ns2:" 1>&2
@@ -332,9 +344,7 @@ table ip nat {
 }
 EOF
 
-test_tcp_forwarding_nat ns1 ns2
-
-if [ $? -eq 0 ] ;then
+if test_tcp_forwarding_nat ns1 ns2; then
 	echo "PASS: flow offloaded for ns1/ns2 with NAT"
 else
 	echo "FAIL: flow offload for ns1/ns2 with NAT" 1>&2
@@ -346,8 +356,7 @@ fi
 # Same as second test, but with PMTU discovery enabled.
 handle=$(ip netns exec nsr1 nft -a list table inet filter | grep something-to-grep-for | cut -d \# -f 2)
 
-ip netns exec nsr1 nft delete rule inet filter forward $handle
-if [ $? -ne 0 ] ;then
+if ! ip netns exec nsr1 nft delete rule inet filter forward $handle; then
 	echo "FAIL: Could not delete large-packet accept rule"
 	exit 1
 fi
@@ -355,8 +364,7 @@ fi
 ip netns exec ns1 sysctl net.ipv4.ip_no_pmtu_disc=0 > /dev/null
 ip netns exec ns2 sysctl net.ipv4.ip_no_pmtu_disc=0 > /dev/null
 
-test_tcp_forwarding_nat ns1 ns2
-if [ $? -eq 0 ] ;then
+if test_tcp_forwarding_nat ns1 ns2; then
 	echo "PASS: flow offloaded for ns1/ns2 with NAT and pmtu discovery"
 else
 	echo "FAIL: flow offload for ns1/ns2 with NAT and pmtu discovery" 1>&2
@@ -402,8 +410,7 @@ ip -net ns2 route del 192.168.10.1 via 10.0.2.1
 ip -net ns2 route add default via 10.0.2.1
 ip -net ns2 route add default via dead:2::1
 
-test_tcp_forwarding ns1 ns2
-if [ $? -eq 0 ] ;then
+if test_tcp_forwarding ns1 ns2; then
 	echo "PASS: ipsec tunnel mode for ns1/ns2"
 else
 	echo "FAIL: ipsec tunnel mode for ns1/ns2"
diff --git a/tools/testing/selftests/powerpc/mm/.gitignore b/tools/testing/selftests/powerpc/mm/.gitignore
index 91c775c23c66..aac4a59f9e28 100644
--- a/tools/testing/selftests/powerpc/mm/.gitignore
+++ b/tools/testing/selftests/powerpc/mm/.gitignore
@@ -2,6 +2,7 @@
 hugetlb_vs_thp_test
 subpage_prot
 tempfile
+prot_sao
 segv_errors
 wild_bctr
 large_vm_fork_separation
diff --git a/tools/testing/selftests/powerpc/mm/Makefile b/tools/testing/selftests/powerpc/mm/Makefile
index 250ce172e0da..defe488d6bf1 100644
--- a/tools/testing/selftests/powerpc/mm/Makefile
+++ b/tools/testing/selftests/powerpc/mm/Makefile
@@ -2,7 +2,7 @@
 noarg:
 	$(MAKE) -C ../
 
-TEST_GEN_PROGS := hugetlb_vs_thp_test subpage_prot segv_errors wild_bctr \
+TEST_GEN_PROGS := hugetlb_vs_thp_test subpage_prot prot_sao segv_errors wild_bctr \
 		  large_vm_fork_separation bad_accesses pkey_exec_prot \
 		  pkey_siginfo stack_expansion_signal stack_expansion_ldst
 
@@ -14,6 +14,8 @@ include ../../lib.mk
 
 $(TEST_GEN_PROGS): ../harness.c ../utils.c
 
+$(OUTPUT)/prot_sao: ../utils.c
+
 $(OUTPUT)/wild_bctr: CFLAGS += -m64
 $(OUTPUT)/large_vm_fork_separation: CFLAGS += -m64
 $(OUTPUT)/bad_accesses: CFLAGS += -m64
diff --git a/tools/testing/selftests/powerpc/mm/prot_sao.c b/tools/testing/selftests/powerpc/mm/prot_sao.c
new file mode 100644
index 000000000000..30b71b1d78d5
--- /dev/null
+++ b/tools/testing/selftests/powerpc/mm/prot_sao.c
@@ -0,0 +1,48 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright 2016, Michael Ellerman, IBM Corp.
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/mman.h>
+#include <unistd.h>
+
+#include <asm/cputable.h>
+
+#include "utils.h"
+
+#define SIZE (64 * 1024)
+
+int test_prot_sao(void)
+{
+	char *p;
+
+	/*
+	 * SAO was introduced in 2.06 and removed in 3.1. It's disabled in
+	 * guests/LPARs by default, so also skip if we are running in a guest.
+	 */
+	SKIP_IF(!have_hwcap(PPC_FEATURE_ARCH_2_06) ||
+		have_hwcap2(PPC_FEATURE2_ARCH_3_1) ||
+		access("/proc/device-tree/rtas/ibm,hypertas-functions", F_OK) == 0);
+
+	/*
+	 * Ensure we can ask for PROT_SAO.
+	 * We can't really verify that it does the right thing, but at least we
+	 * confirm the kernel will accept it.
+	 */
+	p = mmap(NULL, SIZE, PROT_READ | PROT_WRITE | PROT_SAO,
+		 MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
+	FAIL_IF(p == MAP_FAILED);
+
+	/* Write to the mapping, to at least cause a fault */
+	memset(p, 0xaa, SIZE);
+
+	return 0;
+}
+
+int main(void)
+{
+	return test_harness(test_prot_sao, "prot-sao");
+}
diff --git a/tools/testing/selftests/timers/Makefile b/tools/testing/selftests/timers/Makefile
index 7656c7ce79d9..0e73a16874c4 100644
--- a/tools/testing/selftests/timers/Makefile
+++ b/tools/testing/selftests/timers/Makefile
@@ -13,6 +13,7 @@ DESTRUCTIVE_TESTS = alarmtimer-suspend valid-adjtimex adjtick change_skew \
 
 TEST_GEN_PROGS_EXTENDED = $(DESTRUCTIVE_TESTS)
 
+TEST_FILES := settings
 
 include ../lib.mk
 
diff --git a/tools/testing/selftests/timers/settings b/tools/testing/selftests/timers/settings
new file mode 100644
index 000000000000..e7b9417537fb
--- /dev/null
+++ b/tools/testing/selftests/timers/settings
@@ -0,0 +1 @@
+timeout=0
diff --git a/tools/testing/selftests/vm/map_hugetlb.c b/tools/testing/selftests/vm/map_hugetlb.c
index 6af951900aa3..312889edb84a 100644
--- a/tools/testing/selftests/vm/map_hugetlb.c
+++ b/tools/testing/selftests/vm/map_hugetlb.c
@@ -83,7 +83,7 @@ int main(int argc, char **argv)
 	}
 
 	if (shift)
-		printf("%u kB hugepages\n", 1 << shift);
+		printf("%u kB hugepages\n", 1 << (shift - 10));
 	else
 		printf("Default size hugepages\n");
 	printf("Mapping %lu Mbytes\n", (unsigned long)length >> 20);
diff --git a/tools/testing/selftests/x86/test_vsyscall.c b/tools/testing/selftests/x86/test_vsyscall.c
index c41f24b517f4..65c141ebfbbd 100644
--- a/tools/testing/selftests/x86/test_vsyscall.c
+++ b/tools/testing/selftests/x86/test_vsyscall.c
@@ -462,6 +462,17 @@ static int test_vsys_x(void)
 	return 0;
 }
 
+/*
+ * Debuggers expect ptrace() to be able to peek at the vsyscall page.
+ * Use process_vm_readv() as a proxy for ptrace() to test this.  We
+ * want it to work in the vsyscall=emulate case and to fail in the
+ * vsyscall=xonly case.
+ *
+ * It's worth noting that this ABI is a bit nutty.  write(2) can't
+ * read from the vsyscall page on any kernel version or mode.  The
+ * fact that ptrace() ever worked was a nice courtesy of old kernels,
+ * but the code to support it is fairly gross.
+ */
 static int test_process_vm_readv(void)
 {
 #ifdef __x86_64__
@@ -477,8 +488,12 @@ static int test_process_vm_readv(void)
 	remote.iov_len = 4096;
 	ret = process_vm_readv(getpid(), &local, 1, &remote, 1, 0);
 	if (ret != 4096) {
-		printf("[OK]\tprocess_vm_readv() failed (ret = %d, errno = %d)\n", ret, errno);
-		return 0;
+		/*
+		 * We expect process_vm_readv() to work if and only if the
+		 * vsyscall page is readable.
+		 */
+		printf("[%s]\tprocess_vm_readv() failed (ret = %d, errno = %d)\n", vsyscall_map_r ? "FAIL" : "OK", ret, errno);
+		return vsyscall_map_r ? 1 : 0;
 	}
 
 	if (vsyscall_map_r) {
@@ -488,6 +503,9 @@ static int test_process_vm_readv(void)
 			printf("[FAIL]\tIt worked but returned incorrect data\n");
 			return 1;
 		}
+	} else {
+		printf("[FAIL]\tprocess_rm_readv() succeeded, but it should have failed in this configuration\n");
+		return 1;
 	}
 #endif
 
diff --git a/tools/usb/Build b/tools/usb/Build
new file mode 100644
index 000000000000..2ad6f9745816
--- /dev/null
+++ b/tools/usb/Build
@@ -0,0 +1,2 @@
+testusb-y += testusb.o
+ffs-test-y += ffs-test.o
diff --git a/tools/usb/Makefile b/tools/usb/Makefile
index 01d758d73b6d..1b128e551b2e 100644
--- a/tools/usb/Makefile
+++ b/tools/usb/Makefile
@@ -1,14 +1,51 @@
 # SPDX-License-Identifier: GPL-2.0
 # Makefile for USB tools
+include ../scripts/Makefile.include
 
-PTHREAD_LIBS = -lpthread
-WARNINGS = -Wall -Wextra
-CFLAGS = $(WARNINGS) -g -I../include
-LDFLAGS = $(PTHREAD_LIBS)
+bindir ?= /usr/bin
 
-all: testusb ffs-test
-%: %.c
-	$(CC) $(CFLAGS) -o $@ $^ $(LDFLAGS)
+ifeq ($(srctree),)
+srctree := $(patsubst %/,%,$(dir $(CURDIR)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+endif
+
+# Do not use make's built-in rules
+# (this improves performance and avoids hard-to-debug behaviour);
+MAKEFLAGS += -r
+
+override CFLAGS += -O2 -Wall -Wextra -g -D_GNU_SOURCE -I$(OUTPUT)include -I$(srctree)/tools/include
+override LDFLAGS += -lpthread
+
+ALL_TARGETS := testusb ffs-test
+ALL_PROGRAMS := $(patsubst %,$(OUTPUT)%,$(ALL_TARGETS))
+
+all: $(ALL_PROGRAMS)
+
+export srctree OUTPUT CC LD CFLAGS
+include $(srctree)/tools/build/Makefile.include
+
+TESTUSB_IN := $(OUTPUT)testusb-in.o
+$(TESTUSB_IN): FORCE
+	$(Q)$(MAKE) $(build)=testusb
+$(OUTPUT)testusb: $(TESTUSB_IN)
+	$(QUIET_LINK)$(CC) $(CFLAGS) $< -o $@ $(LDFLAGS)
+
+FFS_TEST_IN := $(OUTPUT)ffs-test-in.o
+$(FFS_TEST_IN): FORCE
+	$(Q)$(MAKE) $(build)=ffs-test
+$(OUTPUT)ffs-test: $(FFS_TEST_IN)
+	$(QUIET_LINK)$(CC) $(CFLAGS) $< -o $@ $(LDFLAGS)
 
 clean:
-	$(RM) testusb ffs-test
+	rm -f $(ALL_PROGRAMS)
+	find $(if $(OUTPUT),$(OUTPUT),.) -name '*.o' -delete -o -name '\.*.d' -delete -o -name '\.*.o.cmd' -delete
+
+install: $(ALL_PROGRAMS)
+	install -d -m 755 $(DESTDIR)$(bindir);		\
+	for program in $(ALL_PROGRAMS); do		\
+		install $$program $(DESTDIR)$(bindir);	\
+	done
+
+FORCE:
+
+.PHONY: all install clean FORCE prepare