Merge tag 'v5.9-rc7' into patchwork

Linux 5.9-rc7

* tag 'v5.9-rc7': (683 commits)
  Linux 5.9-rc7
  mm/thp: Split huge pmds/puds if they're pinned when fork()
  mm: Do early cow for pinned pages during fork() for ptes
  mm/fork: Pass new vma pointer into copy_page_range()
  mm: Introduce mm_struct.has_pinned
  mm: validate pmd after splitting
  mm: don't rely on system state to detect hot-plug operations
  mm: replace memmap_context by meminit_context
  arch/x86/lib/usercopy_64.c: fix __copy_user_flushcache() cache writeback
  lib/memregion.c: include memregion.h
  lib/string.c: implement stpcpy
  mm/migrate: correct thp migration stats
  mm/gup: fix gup_fast with dynamic page table folding
  mm: memcontrol: fix missing suffix of workingset_restore
  mm, THP, swap: fix allocating cluster for swapfile by mistake
  mm: slab: fix potential double free in ___cache_free
  Documentation/llvm: Fix clang target examples
  io_uring: ensure async buffered read-retry is setup properly
  KVM: SVM: Add a dedicated INVD intercept routine
  io_uring: don't unconditionally set plug->nowait = true
  ...

33 files changed, 262 insertions, 63 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/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/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/libbpf.c b/tools/lib/bpf/libbpf.c
index 0ad0b0491e1f..7253b833576c 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;
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/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/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/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/parse-metric.c b/tools/perf/tests/parse-metric.c
index 23db8acc492d..cd7331aac3bd 100644
--- a/tools/perf/tests/parse-metric.c
+++ b/tools/perf/tests/parse-metric.c
@@ -153,8 +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);
 
@@ -163,10 +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);
@@ -178,13 +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/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/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 c4d2394e2b2d..667cbca1547a 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -411,7 +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;
 }
 
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/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/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/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/powerpc/mm/prot_sao.c b/tools/testing/selftests/powerpc/mm/prot_sao.c
index e0cf8ebbf8cd..30b71b1d78d5 100644
--- a/tools/testing/selftests/powerpc/mm/prot_sao.c
+++ b/tools/testing/selftests/powerpc/mm/prot_sao.c
@@ -7,6 +7,7 @@
 #include <stdlib.h>
 #include <string.h>
 #include <sys/mman.h>
+#include <unistd.h>
 
 #include <asm/cputable.h>
 
@@ -18,9 +19,13 @@ int test_prot_sao(void)
 {
 	char *p;
 
-	/* SAO was introduced in 2.06 and removed in 3.1 */
+	/*
+	 * 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));
+		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.
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);