Merge branch 'x86/paravirt' into x86/entry

Merge in the recent paravirt changes to resolve conflicts caused
by objtool annotations.

Conflicts:
	arch/x86/xen/xen-asm.S

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

52 files changed, 1840 insertions, 468 deletions

diff --git a/tools/bootconfig/scripts/bconf2ftrace.sh b/tools/bootconfig/scripts/bconf2ftrace.sh
index 595e164dc352..feb30c2c7881 100755
--- a/tools/bootconfig/scripts/bconf2ftrace.sh
+++ b/tools/bootconfig/scripts/bconf2ftrace.sh
@@ -152,6 +152,7 @@ setup_instance() { # [instance]
 	set_array_of ${instance}.options ${instancedir}/trace_options
 	set_value_of ${instance}.trace_clock ${instancedir}/trace_clock
 	set_value_of ${instance}.cpumask ${instancedir}/tracing_cpumask
+	set_value_of ${instance}.tracing_on ${instancedir}/tracing_on
 	set_value_of ${instance}.tracer ${instancedir}/current_tracer
 	set_array_of ${instance}.ftrace.filters \
 		${instancedir}/set_ftrace_filter
diff --git a/tools/bootconfig/scripts/ftrace2bconf.sh b/tools/bootconfig/scripts/ftrace2bconf.sh
index 6c0d4b61e0c2..a0c3bcc6da4f 100755
--- a/tools/bootconfig/scripts/ftrace2bconf.sh
+++ b/tools/bootconfig/scripts/ftrace2bconf.sh
@@ -221,6 +221,10 @@ instance_options() { # [instance-name]
 	if [ `echo $val | sed -e s/f//g`x != x ]; then
 		emit_kv $PREFIX.cpumask = $val
 	fi
+	val=`cat $INSTANCE/tracing_on`
+	if [ `echo $val | sed -e s/f//g`x != x ]; then
+		emit_kv $PREFIX.tracing_on = $val
+	fi
 
 	val=
 	for i in `cat $INSTANCE/set_event`; do
diff --git a/tools/gpio/gpio-event-mon.c b/tools/gpio/gpio-event-mon.c
index cacd66ad7926..a2b233fdb572 100644
--- a/tools/gpio/gpio-event-mon.c
+++ b/tools/gpio/gpio-event-mon.c
@@ -107,8 +107,8 @@ int monitor_device(const char *device_name,
 			ret = -EIO;
 			break;
 		}
-		fprintf(stdout, "GPIO EVENT at %llu on line %d (%d|%d) ",
-			event.timestamp_ns, event.offset, event.line_seqno,
+		fprintf(stdout, "GPIO EVENT at %" PRIu64 " on line %d (%d|%d) ",
+			(uint64_t)event.timestamp_ns, event.offset, event.line_seqno,
 			event.seqno);
 		switch (event.id) {
 		case GPIO_V2_LINE_EVENT_RISING_EDGE:
diff --git a/tools/gpio/gpio-watch.c b/tools/gpio/gpio-watch.c
index f229ec62301b..41e76d244192 100644
--- a/tools/gpio/gpio-watch.c
+++ b/tools/gpio/gpio-watch.c
@@ -10,6 +10,7 @@
 #include <ctype.h>
 #include <errno.h>
 #include <fcntl.h>
+#include <inttypes.h>
 #include <linux/gpio.h>
 #include <poll.h>
 #include <stdbool.h>
@@ -86,8 +87,8 @@ int main(int argc, char **argv)
 				return EXIT_FAILURE;
 			}
 
-			printf("line %u: %s at %llu\n",
-			       chg.info.offset, event, chg.timestamp_ns);
+			printf("line %u: %s at %" PRIu64 "\n",
+			       chg.info.offset, event, (uint64_t)chg.timestamp_ns);
 		}
 	}
 
diff --git a/tools/include/linux/build_bug.h b/tools/include/linux/build_bug.h
index ce365d212768..cc7070c7439b 100644
--- a/tools/include/linux/build_bug.h
+++ b/tools/include/linux/build_bug.h
@@ -79,9 +79,4 @@
 #define __static_assert(expr, msg, ...) _Static_assert(expr, msg)
 #endif // static_assert
 
-#ifdef __GENKSYMS__
-/* genksyms gets confused by _Static_assert */
-#define _Static_assert(expr, ...)
-#endif
-
 #endif	/* _LINUX_BUILD_BUG_H */
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 886802b8ffba..374c67875cdb 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -251,6 +251,7 @@ struct kvm_hyperv_exit {
 #define KVM_EXIT_X86_RDMSR        29
 #define KVM_EXIT_X86_WRMSR        30
 #define KVM_EXIT_DIRTY_RING_FULL  31
+#define KVM_EXIT_AP_RESET_HOLD    32
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 /* Emulate instruction failed. */
@@ -573,6 +574,7 @@ struct kvm_vapic_addr {
 #define KVM_MP_STATE_CHECK_STOP        6
 #define KVM_MP_STATE_OPERATING         7
 #define KVM_MP_STATE_LOAD              8
+#define KVM_MP_STATE_AP_RESET_HOLD     9
 
 struct kvm_mp_state {
 	__u32 mp_state;
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 3c3f2bc6c652..9970a288dda5 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -240,11 +240,6 @@ static int btf_parse_hdr(struct btf *btf)
 	}
 
 	meta_left = btf->raw_size - sizeof(*hdr);
-	if (!meta_left) {
-		pr_debug("BTF has no data\n");
-		return -EINVAL;
-	}
-
 	if (meta_left < hdr->str_off + hdr->str_len) {
 		pr_debug("Invalid BTF total size:%u\n", btf->raw_size);
 		return -EINVAL;
diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c
index cfcdbd7be066..17465d454a0e 100644
--- a/tools/lib/perf/evlist.c
+++ b/tools/lib/perf/evlist.c
@@ -367,21 +367,13 @@ static struct perf_mmap* perf_evlist__alloc_mmap(struct perf_evlist *evlist, boo
 	return map;
 }
 
-static void perf_evlist__set_sid_idx(struct perf_evlist *evlist,
-				     struct perf_evsel *evsel, int idx, int cpu,
-				     int thread)
+static void perf_evsel__set_sid_idx(struct perf_evsel *evsel, int idx, int cpu, int thread)
 {
 	struct perf_sample_id *sid = SID(evsel, cpu, thread);
 
 	sid->idx = idx;
-	if (evlist->cpus && cpu >= 0)
-		sid->cpu = evlist->cpus->map[cpu];
-	else
-		sid->cpu = -1;
-	if (!evsel->system_wide && evlist->threads && thread >= 0)
-		sid->tid = perf_thread_map__pid(evlist->threads, thread);
-	else
-		sid->tid = -1;
+	sid->cpu = perf_cpu_map__cpu(evsel->cpus, cpu);
+	sid->tid = perf_thread_map__pid(evsel->threads, thread);
 }
 
 static struct perf_mmap*
@@ -500,8 +492,7 @@ mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,
 			if (perf_evlist__id_add_fd(evlist, evsel, cpu, thread,
 						   fd) < 0)
 				return -1;
-			perf_evlist__set_sid_idx(evlist, evsel, idx, cpu,
-						 thread);
+			perf_evsel__set_sid_idx(evsel, idx, cpu, thread);
 		}
 	}
 
diff --git a/tools/lib/perf/tests/test-cpumap.c b/tools/lib/perf/tests/test-cpumap.c
index c8d45091e7c2..c70e9e03af3e 100644
--- a/tools/lib/perf/tests/test-cpumap.c
+++ b/tools/lib/perf/tests/test-cpumap.c
@@ -27,5 +27,5 @@ int main(int argc, char **argv)
 	perf_cpu_map__put(cpus);
 
 	__T_END;
-	return 0;
+	return tests_failed == 0 ? 0 : -1;
 }
diff --git a/tools/lib/perf/tests/test-evlist.c b/tools/lib/perf/tests/test-evlist.c
index 6d8ebe0c2504..e2ac0b7f432e 100644
--- a/tools/lib/perf/tests/test-evlist.c
+++ b/tools/lib/perf/tests/test-evlist.c
@@ -208,13 +208,13 @@ static int test_mmap_thread(void)
 	char path[PATH_MAX];
 	int id, err, pid, go_pipe[2];
 	union perf_event *event;
-	char bf;
 	int count = 0;
 
 	snprintf(path, PATH_MAX, "%s/kernel/debug/tracing/events/syscalls/sys_enter_prctl/id",
 		 sysfs__mountpoint());
 
 	if (filename__read_int(path, &id)) {
+		tests_failed++;
 		fprintf(stderr, "error: failed to get tracepoint id: %s\n", path);
 		return -1;
 	}
@@ -229,6 +229,7 @@ static int test_mmap_thread(void)
 	pid = fork();
 	if (!pid) {
 		int i;
+		char bf;
 
 		read(go_pipe[0], &bf, 1);
 
@@ -266,7 +267,7 @@ static int test_mmap_thread(void)
 	perf_evlist__enable(evlist);
 
 	/* kick the child and wait for it to finish */
-	write(go_pipe[1], &bf, 1);
+	write(go_pipe[1], "A", 1);
 	waitpid(pid, NULL, 0);
 
 	/*
@@ -409,5 +410,5 @@ int main(int argc, char **argv)
 	test_mmap_cpus();
 
 	__T_END;
-	return 0;
+	return tests_failed == 0 ? 0 : -1;
 }
diff --git a/tools/lib/perf/tests/test-evsel.c b/tools/lib/perf/tests/test-evsel.c
index 135722ac965b..0ad82d7a2a51 100644
--- a/tools/lib/perf/tests/test-evsel.c
+++ b/tools/lib/perf/tests/test-evsel.c
@@ -131,5 +131,5 @@ int main(int argc, char **argv)
 	test_stat_thread_enable();
 
 	__T_END;
-	return 0;
+	return tests_failed == 0 ? 0 : -1;
 }
diff --git a/tools/lib/perf/tests/test-threadmap.c b/tools/lib/perf/tests/test-threadmap.c
index 7dc4d6fbedde..384471441b48 100644
--- a/tools/lib/perf/tests/test-threadmap.c
+++ b/tools/lib/perf/tests/test-threadmap.c
@@ -27,5 +27,5 @@ int main(int argc, char **argv)
 	perf_thread_map__put(threads);
 
 	__T_END;
-	return 0;
+	return tests_failed == 0 ? 0 : -1;
 }
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 62cd211ec45c..8e74210f4235 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -3036,14 +3036,10 @@ int check(struct objtool_file *file)
 	warnings += ret;
 
 out:
-	if (ret < 0) {
-		/*
-		 *  Fatal error.  The binary is corrupt or otherwise broken in
-		 *  some way, or objtool itself is broken.  Fail the kernel
-		 *  build.
-		 */
-		return ret;
-	}
-
+	/*
+	 *  For now, don't fail the kernel build on fatal warnings.  These
+	 *  errors are still fairly common due to the growing matrix of
+	 *  supported toolchains and their recent pace of change.
+	 */
 	return 0;
 }
diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c
index 43714ecd09f7..b4a89cbe83df 100644
--- a/tools/objtool/elf.c
+++ b/tools/objtool/elf.c
@@ -380,8 +380,11 @@ static int read_symbols(struct elf *elf)
 
 	symtab = find_section_by_name(elf, ".symtab");
 	if (!symtab) {
-		WARN("missing symbol table");
-		return -1;
+		/*
+		 * A missing symbol table is actually possible if it's an empty
+		 * .o file.  This can happen for thunk_64.o.
+		 */
+		return 0;
 	}
 
 	symtab_shndx = find_section_by_name(elf, ".symtab_shndx");
@@ -448,6 +451,13 @@ static int read_symbols(struct elf *elf)
 		list_add(&sym->list, entry);
 		elf_hash_add(elf->symbol_hash, &sym->hash, sym->idx);
 		elf_hash_add(elf->symbol_name_hash, &sym->name_hash, str_hash(sym->name));
+
+		/*
+		 * Don't store empty STT_NOTYPE symbols in the rbtree.  They
+		 * can exist within a function, confusing the sorting.
+		 */
+		if (!sym->len)
+			rb_erase(&sym->node, &sym->sec->symbol_tree);
 	}
 
 	if (stats)
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index edacfa98d073..42dad4a0f8cf 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -186,6 +186,7 @@ struct output_option {
 
 enum {
 	OUTPUT_TYPE_SYNTH = PERF_TYPE_MAX,
+	OUTPUT_TYPE_OTHER,
 	OUTPUT_TYPE_MAX
 };
 
@@ -283,6 +284,18 @@ static struct {
 
 		.invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT,
 	},
+
+	[OUTPUT_TYPE_OTHER] = {
+		.user_set = false,
+
+		.fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
+			      PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
+			      PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP |
+			      PERF_OUTPUT_SYM | PERF_OUTPUT_SYMOFFSET |
+			      PERF_OUTPUT_DSO | PERF_OUTPUT_PERIOD,
+
+		.invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT,
+	},
 };
 
 struct evsel_script {
@@ -343,8 +356,11 @@ static inline int output_type(unsigned int type)
 	case PERF_TYPE_SYNTH:
 		return OUTPUT_TYPE_SYNTH;
 	default:
-		return type;
+		if (type < PERF_TYPE_MAX)
+			return type;
 	}
+
+	return OUTPUT_TYPE_OTHER;
 }
 
 static inline unsigned int attr_type(unsigned int type)
diff --git a/tools/perf/examples/bpf/5sec.c b/tools/perf/examples/bpf/5sec.c
index 65c4ff6892d9..e6b6181c6dc6 100644
--- a/tools/perf/examples/bpf/5sec.c
+++ b/tools/perf/examples/bpf/5sec.c
@@ -39,7 +39,7 @@
    Copyright (C) 2018 Red Hat, Inc., Arnaldo Carvalho de Melo <acme@redhat.com>
 */
 
-#include <bpf/bpf.h>
+#include <bpf.h>
 
 #define NSEC_PER_SEC	1000000000L
 
diff --git a/tools/perf/tests/shell/stat+shadow_stat.sh b/tools/perf/tests/shell/stat+shadow_stat.sh
index 249dfe48cf6a..ebebd3596cf9 100755
--- a/tools/perf/tests/shell/stat+shadow_stat.sh
+++ b/tools/perf/tests/shell/stat+shadow_stat.sh
@@ -9,31 +9,29 @@ perf stat -a true > /dev/null 2>&1 || exit 2
 
 test_global_aggr()
 {
-	local cyc
-
 	perf stat -a --no-big-num -e cycles,instructions sleep 1  2>&1 | \
 	grep -e cycles -e instructions | \
 	while read num evt hash ipc rest
 	do
 		# skip not counted events
-		if [[ $num == "<not" ]]; then
+		if [ "$num" = "<not" ]; then
 			continue
 		fi
 
 		# save cycles count
-		if [[ $evt == "cycles" ]]; then
+		if [ "$evt" = "cycles" ]; then
 			cyc=$num
 			continue
 		fi
 
 		# skip if no cycles
-		if [[ -z $cyc ]]; then
+		if [ -z "$cyc" ]; then
 			continue
 		fi
 
 		# use printf for rounding and a leading zero
-		local res=`printf "%.2f" $(echo "scale=6; $num / $cyc" | bc -q)`
-		if [[ $ipc != $res ]]; then
+		res=`printf "%.2f" $(echo "scale=6; $num / $cyc" | bc -q)`
+		if [ "$ipc" != "$res" ]; then
 			echo "IPC is different: $res != $ipc  ($num / $cyc)"
 			exit 1
 		fi
@@ -42,32 +40,32 @@ test_global_aggr()
 
 test_no_aggr()
 {
-	declare -A results
-
 	perf stat -a -A --no-big-num -e cycles,instructions sleep 1  2>&1 | \
 	grep ^CPU | \
 	while read cpu num evt hash ipc rest
 	do
 		# skip not counted events
-		if [[ $num == "<not" ]]; then
+		if [ "$num" = "<not" ]; then
 			continue
 		fi
 
 		# save cycles count
-		if [[ $evt == "cycles" ]]; then
-			results[$cpu]=$num
+		if [ "$evt" = "cycles" ]; then
+			results="$results $cpu:$num"
 			continue
 		fi
 
+		cyc=${results##* $cpu:}
+		cyc=${cyc%% *}
+
 		# skip if no cycles
-		local cyc=${results[$cpu]}
-		if [[ -z $cyc ]]; then
+		if [ -z "$cyc" ]; then
 			continue
 		fi
 
 		# use printf for rounding and a leading zero
-		local res=`printf "%.2f" $(echo "scale=6; $num / $cyc" | bc -q)`
-		if [[ $ipc != $res ]]; then
+		res=`printf "%.2f" $(echo "scale=6; $num / $cyc" | bc -q)`
+		if [ "$ipc" != "$res" ]; then
 			echo "IPC is different for $cpu: $res != $ipc  ($num / $cyc)"
 			exit 1
 		fi
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 062383e225a3..c4ed3dc2c8f4 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -3323,6 +3323,14 @@ int perf_session__write_header(struct perf_session *session,
 	attr_offset = lseek(ff.fd, 0, SEEK_CUR);
 
 	evlist__for_each_entry(evlist, evsel) {
+		if (evsel->core.attr.size < sizeof(evsel->core.attr)) {
+			/*
+			 * We are likely in "perf inject" and have read
+			 * from an older file. Update attr size so that
+			 * reader gets the right offset to the ids.
+			 */
+			evsel->core.attr.size = sizeof(evsel->core.attr);
+		}
 		f_attr = (struct perf_file_attr){
 			.attr = evsel->core.attr,
 			.ids  = {
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index f841f3503cae..1e9d3f982b47 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -2980,7 +2980,7 @@ int machines__for_each_thread(struct machines *machines,
 
 pid_t machine__get_current_tid(struct machine *machine, int cpu)
 {
-	int nr_cpus = min(machine->env->nr_cpus_online, MAX_NR_CPUS);
+	int nr_cpus = min(machine->env->nr_cpus_avail, MAX_NR_CPUS);
 
 	if (cpu < 0 || cpu >= nr_cpus || !machine->current_tid)
 		return -1;
@@ -2992,7 +2992,7 @@ int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid,
 			     pid_t tid)
 {
 	struct thread *thread;
-	int nr_cpus = min(machine->env->nr_cpus_online, MAX_NR_CPUS);
+	int nr_cpus = min(machine->env->nr_cpus_avail, MAX_NR_CPUS);
 
 	if (cpu < 0)
 		return -EINVAL;
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index ee94d3e8dd65..e6d3452031e5 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -162,6 +162,14 @@ static bool contains_event(struct evsel **metric_events, int num_events,
 	return false;
 }
 
+static bool evsel_same_pmu(struct evsel *ev1, struct evsel *ev2)
+{
+	if (!ev1->pmu_name || !ev2->pmu_name)
+		return false;
+
+	return !strcmp(ev1->pmu_name, ev2->pmu_name);
+}
+
 /**
  * Find a group of events in perf_evlist that correspond to those from a parsed
  * metric expression. Note, as find_evsel_group is called in the same order as
@@ -280,8 +288,7 @@ static struct evsel *find_evsel_group(struct evlist *perf_evlist,
 			 */
 			if (!has_constraint &&
 			    ev->leader != metric_events[i]->leader &&
-			    !strcmp(ev->leader->pmu_name,
-				    metric_events[i]->leader->pmu_name))
+			    evsel_same_pmu(ev->leader, metric_events[i]->leader))
 				break;
 			if (!strcmp(metric_events[i]->name, ev->name)) {
 				set_bit(ev->idx, evlist_used);
@@ -766,7 +773,6 @@ int __weak arch_get_runtimeparam(struct pmu_event *pe __maybe_unused)
 struct metricgroup_add_iter_data {
 	struct list_head *metric_list;
 	const char *metric;
-	struct metric **m;
 	struct expr_ids *ids;
 	int *ret;
 	bool *has_match;
@@ -1058,12 +1064,13 @@ static int metricgroup__add_metric_sys_event_iter(struct pmu_event *pe,
 						  void *data)
 {
 	struct metricgroup_add_iter_data *d = data;
+	struct metric *m = NULL;
 	int ret;
 
 	if (!match_pe_metric(pe, d->metric))
 		return 0;
 
-	ret = add_metric(d->metric_list, pe, d->metric_no_group, d->m, NULL, d->ids);
+	ret = add_metric(d->metric_list, pe, d->metric_no_group, &m, NULL, d->ids);
 	if (ret)
 		return ret;
 
@@ -1114,7 +1121,6 @@ static int metricgroup__add_metric(const char *metric, bool metric_no_group,
 				.metric_list = &list,
 				.metric = metric,
 				.metric_no_group = metric_no_group,
-				.m = &m,
 				.ids = &ids,
 				.has_match = &has_match,
 				.ret = &ret,
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 50ff9795a4f1..25adbcce0281 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -2404,7 +2404,7 @@ int perf_session__cpu_bitmap(struct perf_session *session,
 {
 	int i, err = -1;
 	struct perf_cpu_map *map;
-	int nr_cpus = min(session->header.env.nr_cpus_online, MAX_NR_CPUS);
+	int nr_cpus = min(session->header.env.nr_cpus_avail, MAX_NR_CPUS);
 
 	for (i = 0; i < PERF_TYPE_MAX; ++i) {
 		struct evsel *evsel;
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 901265127e36..12eafd12a693 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -8,6 +8,7 @@
 #include "evlist.h"
 #include "expr.h"
 #include "metricgroup.h"
+#include "cgroup.h"
 #include <linux/zalloc.h>
 
 /*
@@ -28,6 +29,7 @@ struct saved_value {
 	enum stat_type type;
 	int ctx;
 	int cpu;
+	struct cgroup *cgrp;
 	struct runtime_stat *stat;
 	struct stats stats;
 	u64 metric_total;
@@ -57,6 +59,9 @@ static int saved_value_cmp(struct rb_node *rb_node, const void *entry)
 	if (a->ctx != b->ctx)
 		return a->ctx - b->ctx;
 
+	if (a->cgrp != b->cgrp)
+		return (char *)a->cgrp < (char *)b->cgrp ? -1 : +1;
+
 	if (a->evsel == NULL && b->evsel == NULL) {
 		if (a->stat == b->stat)
 			return 0;
@@ -100,7 +105,8 @@ static struct saved_value *saved_value_lookup(struct evsel *evsel,
 					      bool create,
 					      enum stat_type type,
 					      int ctx,
-					      struct runtime_stat *st)
+					      struct runtime_stat *st,
+					      struct cgroup *cgrp)
 {
 	struct rblist *rblist;
 	struct rb_node *nd;
@@ -110,10 +116,15 @@ static struct saved_value *saved_value_lookup(struct evsel *evsel,
 		.type = type,
 		.ctx = ctx,
 		.stat = st,
+		.cgrp = cgrp,
 	};
 
 	rblist = &st->value_list;
 
+	/* don't use context info for clock events */
+	if (type == STAT_NSECS)
+		dm.ctx = 0;
+
 	nd = rblist__find(rblist, &dm);
 	if (nd)
 		return container_of(nd, struct saved_value, rb_node);
@@ -191,12 +202,18 @@ void perf_stat__reset_shadow_per_stat(struct runtime_stat *st)
 	reset_stat(st);
 }
 
+struct runtime_stat_data {
+	int ctx;
+	struct cgroup *cgrp;
+};
+
 static void update_runtime_stat(struct runtime_stat *st,
 				enum stat_type type,
-				int ctx, int cpu, u64 count)
+				int cpu, u64 count,
+				struct runtime_stat_data *rsd)
 {
-	struct saved_value *v = saved_value_lookup(NULL, cpu, true,
-						   type, ctx, st);
+	struct saved_value *v = saved_value_lookup(NULL, cpu, true, type,
+						   rsd->ctx, st, rsd->cgrp);
 
 	if (v)
 		update_stats(&v->stats, count);
@@ -210,82 +227,86 @@ static void update_runtime_stat(struct runtime_stat *st,
 void perf_stat__update_shadow_stats(struct evsel *counter, u64 count,
 				    int cpu, struct runtime_stat *st)
 {
-	int ctx = evsel_context(counter);
 	u64 count_ns = count;
 	struct saved_value *v;
+	struct runtime_stat_data rsd = {
+		.ctx = evsel_context(counter),
+		.cgrp = counter->cgrp,
+	};
 
 	count *= counter->scale;
 
 	if (evsel__is_clock(counter))
-		update_runtime_stat(st, STAT_NSECS, 0, cpu, count_ns);
+		update_runtime_stat(st, STAT_NSECS, cpu, count_ns, &rsd);
 	else if (evsel__match(counter, HARDWARE, HW_CPU_CYCLES))
-		update_runtime_stat(st, STAT_CYCLES, ctx, cpu, count);
+		update_runtime_stat(st, STAT_CYCLES, cpu, count, &rsd);
 	else if (perf_stat_evsel__is(counter, CYCLES_IN_TX))
-		update_runtime_stat(st, STAT_CYCLES_IN_TX, ctx, cpu, count);
+		update_runtime_stat(st, STAT_CYCLES_IN_TX, cpu, count, &rsd);
 	else if (perf_stat_evsel__is(counter, TRANSACTION_START))
-		update_runtime_stat(st, STAT_TRANSACTION, ctx, cpu, count);
+		update_runtime_stat(st, STAT_TRANSACTION, cpu, count, &rsd);
 	else if (perf_stat_evsel__is(counter, ELISION_START))
-		update_runtime_stat(st, STAT_ELISION, ctx, cpu, count);
+		update_runtime_stat(st, STAT_ELISION, cpu, count, &rsd);
 	else if (perf_stat_evsel__is(counter, TOPDOWN_TOTAL_SLOTS))
 		update_runtime_stat(st, STAT_TOPDOWN_TOTAL_SLOTS,
-				    ctx, cpu, count);
+				    cpu, count, &rsd);
 	else if (perf_stat_evsel__is(counter, TOPDOWN_SLOTS_ISSUED))
 		update_runtime_stat(st, STAT_TOPDOWN_SLOTS_ISSUED,
-				    ctx, cpu, count);
+				    cpu, count, &rsd);
 	else if (perf_stat_evsel__is(counter, TOPDOWN_SLOTS_RETIRED))
 		update_runtime_stat(st, STAT_TOPDOWN_SLOTS_RETIRED,
-				    ctx, cpu, count);
+				    cpu, count, &rsd);
 	else if (perf_stat_evsel__is(counter, TOPDOWN_FETCH_BUBBLES))
 		update_runtime_stat(st, STAT_TOPDOWN_FETCH_BUBBLES,
-				    ctx, cpu, count);
+				    cpu, count, &rsd);
 	else if (perf_stat_evsel__is(counter, TOPDOWN_RECOVERY_BUBBLES))
 		update_runtime_stat(st, STAT_TOPDOWN_RECOVERY_BUBBLES,
-				    ctx, cpu, count);
+				    cpu, count, &rsd);
 	else if (perf_stat_evsel__is(counter, TOPDOWN_RETIRING))
 		update_runtime_stat(st, STAT_TOPDOWN_RETIRING,
-				    ctx, cpu, count);
+				    cpu, count, &rsd);
 	else if (perf_stat_evsel__is(counter, TOPDOWN_BAD_SPEC))
 		update_runtime_stat(st, STAT_TOPDOWN_BAD_SPEC,
-				    ctx, cpu, count);
+				    cpu, count, &rsd);
 	else if (perf_stat_evsel__is(counter, TOPDOWN_FE_BOUND))
 		update_runtime_stat(st, STAT_TOPDOWN_FE_BOUND,
-				    ctx, cpu, count);
+				    cpu, count, &rsd);
 	else if (perf_stat_evsel__is(counter, TOPDOWN_BE_BOUND))
 		update_runtime_stat(st, STAT_TOPDOWN_BE_BOUND,
-				    ctx, cpu, count);
+				    cpu, count, &rsd);
 	else if (evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND))
 		update_runtime_stat(st, STAT_STALLED_CYCLES_FRONT,
-				    ctx, cpu, count);
+				    cpu, count, &rsd);
 	else if (evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_BACKEND))
 		update_runtime_stat(st, STAT_STALLED_CYCLES_BACK,
-				    ctx, cpu, count);
+				    cpu, count, &rsd);
 	else if (evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS))
-		update_runtime_stat(st, STAT_BRANCHES, ctx, cpu, count);
+		update_runtime_stat(st, STAT_BRANCHES, cpu, count, &rsd);
 	else if (evsel__match(counter, HARDWARE, HW_CACHE_REFERENCES))
-		update_runtime_stat(st, STAT_CACHEREFS, ctx, cpu, count);
+		update_runtime_stat(st, STAT_CACHEREFS, cpu, count, &rsd);
 	else if (evsel__match(counter, HW_CACHE, HW_CACHE_L1D))
-		update_runtime_stat(st, STAT_L1_DCACHE, ctx, cpu, count);
+		update_runtime_stat(st, STAT_L1_DCACHE, cpu, count, &rsd);
 	else if (evsel__match(counter, HW_CACHE, HW_CACHE_L1I))
-		update_runtime_stat(st, STAT_L1_ICACHE, ctx, cpu, count);
+		update_runtime_stat(st, STAT_L1_ICACHE, cpu, count, &rsd);
 	else if (evsel__match(counter, HW_CACHE, HW_CACHE_LL))
-		update_runtime_stat(st, STAT_LL_CACHE, ctx, cpu, count);
+		update_runtime_stat(st, STAT_LL_CACHE, cpu, count, &rsd);
 	else if (evsel__match(counter, HW_CACHE, HW_CACHE_DTLB))
-		update_runtime_stat(st, STAT_DTLB_CACHE, ctx, cpu, count);
+		update_runtime_stat(st, STAT_DTLB_CACHE, cpu, count, &rsd);
 	else if (evsel__match(counter, HW_CACHE, HW_CACHE_ITLB))
-		update_runtime_stat(st, STAT_ITLB_CACHE, ctx, cpu, count);
+		update_runtime_stat(st, STAT_ITLB_CACHE, cpu, count, &rsd);
 	else if (perf_stat_evsel__is(counter, SMI_NUM))
-		update_runtime_stat(st, STAT_SMI_NUM, ctx, cpu, count);
+		update_runtime_stat(st, STAT_SMI_NUM, cpu, count, &rsd);
 	else if (perf_stat_evsel__is(counter, APERF))
-		update_runtime_stat(st, STAT_APERF, ctx, cpu, count);
+		update_runtime_stat(st, STAT_APERF, cpu, count, &rsd);
 
 	if (counter->collect_stat) {
-		v = saved_value_lookup(counter, cpu, true, STAT_NONE, 0, st);
+		v = saved_value_lookup(counter, cpu, true, STAT_NONE, 0, st,
+				       rsd.cgrp);
 		update_stats(&v->stats, count);
 		if (counter->metric_leader)
 			v->metric_total += count;
 	} else if (counter->metric_leader) {
 		v = saved_value_lookup(counter->metric_leader,
-				       cpu, true, STAT_NONE, 0, st);
+				       cpu, true, STAT_NONE, 0, st, rsd.cgrp);
 		v->metric_total += count;
 		v->metric_other++;
 	}
@@ -422,11 +443,12 @@ void perf_stat__collect_metric_expr(struct evlist *evsel_list)
 }
 
 static double runtime_stat_avg(struct runtime_stat *st,
-			       enum stat_type type, int ctx, int cpu)
+			       enum stat_type type, int cpu,
+			       struct runtime_stat_data *rsd)
 {
 	struct saved_value *v;
 
-	v = saved_value_lookup(NULL, cpu, false, type, ctx, st);
+	v = saved_value_lookup(NULL, cpu, false, type, rsd->ctx, st, rsd->cgrp);
 	if (!v)
 		return 0.0;
 
@@ -434,11 +456,12 @@ static double runtime_stat_avg(struct runtime_stat *st,
 }
 
 static double runtime_stat_n(struct runtime_stat *st,
-			     enum stat_type type, int ctx, int cpu)
+			     enum stat_type type, int cpu,
+			     struct runtime_stat_data *rsd)
 {
 	struct saved_value *v;
 
-	v = saved_value_lookup(NULL, cpu, false, type, ctx, st);
+	v = saved_value_lookup(NULL, cpu, false, type, rsd->ctx, st, rsd->cgrp);
 	if (!v)
 		return 0.0;
 
@@ -446,16 +469,15 @@ static double runtime_stat_n(struct runtime_stat *st,
 }
 
 static void print_stalled_cycles_frontend(struct perf_stat_config *config,
-					  int cpu,
-					  struct evsel *evsel, double avg,
+					  int cpu, double avg,
 					  struct perf_stat_output_ctx *out,
-					  struct runtime_stat *st)
+					  struct runtime_stat *st,
+					  struct runtime_stat_data *rsd)
 {
 	double total, ratio = 0.0;
 	const char *color;
-	int ctx = evsel_context(evsel);
 
-	total = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu);
+	total = runtime_stat_avg(st, STAT_CYCLES, cpu, rsd);
 
 	if (total)
 		ratio = avg / total * 100.0;
@@ -470,16 +492,15 @@ static void print_stalled_cycles_frontend(struct perf_stat_config *config,
 }
 
 static void print_stalled_cycles_backend(struct perf_stat_config *config,
-					 int cpu,
-					 struct evsel *evsel, double avg,
+					 int cpu, double avg,
 					 struct perf_stat_output_ctx *out,
-					 struct runtime_stat *st)
+					 struct runtime_stat *st,
+					 struct runtime_stat_data *rsd)
 {
 	double total, ratio = 0.0;
 	const char *color;
-	int ctx = evsel_context(evsel);
 
-	total = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu);
+	total = runtime_stat_avg(st, STAT_CYCLES, cpu, rsd);
 
 	if (total)
 		ratio = avg / total * 100.0;
@@ -490,17 +511,15 @@ static void print_stalled_cycles_backend(struct perf_stat_config *config,
 }
 
 static void print_branch_misses(struct perf_stat_config *config,
-				int cpu,
-				struct evsel *evsel,
-				double avg,
+				int cpu, double avg,
 				struct perf_stat_output_ctx *out,
-				struct runtime_stat *st)
+				struct runtime_stat *st,
+				struct runtime_stat_data *rsd)
 {
 	double total, ratio = 0.0;
 	const char *color;
-	int ctx = evsel_context(evsel);
 
-	total = runtime_stat_avg(st, STAT_BRANCHES, ctx, cpu);
+	total = runtime_stat_avg(st, STAT_BRANCHES, cpu, rsd);
 
 	if (total)
 		ratio = avg / total * 100.0;
@@ -511,18 +530,15 @@ static void print_branch_misses(struct perf_stat_config *config,
 }
 
 static void print_l1_dcache_misses(struct perf_stat_config *config,
-				   int cpu,
-				   struct evsel *evsel,
-				   double avg,
+				   int cpu, double avg,
 				   struct perf_stat_output_ctx *out,
-				   struct runtime_stat *st)
-
+				   struct runtime_stat *st,
+				   struct runtime_stat_data *rsd)
 {
 	double total, ratio = 0.0;
 	const char *color;
-	int ctx = evsel_context(evsel);
 
-	total = runtime_stat_avg(st, STAT_L1_DCACHE, ctx, cpu);
+	total = runtime_stat_avg(st, STAT_L1_DCACHE, cpu, rsd);
 
 	if (total)
 		ratio = avg / total * 100.0;
@@ -533,18 +549,15 @@ static void print_l1_dcache_misses(struct perf_stat_config *config,
 }
 
 static void print_l1_icache_misses(struct perf_stat_config *config,
-				   int cpu,
-				   struct evsel *evsel,
-				   double avg,
+				   int cpu, double avg,
 				   struct perf_stat_output_ctx *out,
-				   struct runtime_stat *st)
-
+				   struct runtime_stat *st,
+				   struct runtime_stat_data *rsd)
 {
 	double total, ratio = 0.0;
 	const char *color;
-	int ctx = evsel_context(evsel);
 
-	total = runtime_stat_avg(st, STAT_L1_ICACHE, ctx, cpu);
+	total = runtime_stat_avg(st, STAT_L1_ICACHE, cpu, rsd);
 
 	if (total)
 		ratio = avg / total * 100.0;
@@ -554,17 +567,15 @@ static void print_l1_icache_misses(struct perf_stat_config *config,
 }
 
 static void print_dtlb_cache_misses(struct perf_stat_config *config,
-				    int cpu,
-				    struct evsel *evsel,
-				    double avg,
+				    int cpu, double avg,
 				    struct perf_stat_output_ctx *out,
-				    struct runtime_stat *st)
+				    struct runtime_stat *st,
+				    struct runtime_stat_data *rsd)
 {
 	double total, ratio = 0.0;
 	const char *color;
-	int ctx = evsel_context(evsel);
 
-	total = runtime_stat_avg(st, STAT_DTLB_CACHE, ctx, cpu);
+	total = runtime_stat_avg(st, STAT_DTLB_CACHE, cpu, rsd);
 
 	if (total)
 		ratio = avg / total * 100.0;
@@ -574,17 +585,15 @@ static void print_dtlb_cache_misses(struct perf_stat_config *config,
 }
 
 static void print_itlb_cache_misses(struct perf_stat_config *config,
-				    int cpu,
-				    struct evsel *evsel,
-				    double avg,
+				    int cpu, double avg,
 				    struct perf_stat_output_ctx *out,
-				    struct runtime_stat *st)
+				    struct runtime_stat *st,
+				    struct runtime_stat_data *rsd)
 {
 	double total, ratio = 0.0;
 	const char *color;
-	int ctx = evsel_context(evsel);
 
-	total = runtime_stat_avg(st, STAT_ITLB_CACHE, ctx, cpu);
+	total = runtime_stat_avg(st, STAT_ITLB_CACHE, cpu, rsd);
 
 	if (total)
 		ratio = avg / total * 100.0;
@@ -594,17 +603,15 @@ static void print_itlb_cache_misses(struct perf_stat_config *config,
 }
 
 static void print_ll_cache_misses(struct perf_stat_config *config,
-				  int cpu,
-				  struct evsel *evsel,
-				  double avg,
+				  int cpu, double avg,
 				  struct perf_stat_output_ctx *out,
-				  struct runtime_stat *st)
+				  struct runtime_stat *st,
+				  struct runtime_stat_data *rsd)
 {
 	double total, ratio = 0.0;
 	const char *color;
-	int ctx = evsel_context(evsel);
 
-	total = runtime_stat_avg(st, STAT_LL_CACHE, ctx, cpu);
+	total = runtime_stat_avg(st, STAT_LL_CACHE, cpu, rsd);
 
 	if (total)
 		ratio = avg / total * 100.0;
@@ -662,56 +669,61 @@ static double sanitize_val(double x)
 	return x;
 }
 
-static double td_total_slots(int ctx, int cpu, struct runtime_stat *st)
+static double td_total_slots(int cpu, struct runtime_stat *st,
+			     struct runtime_stat_data *rsd)
 {
-	return runtime_stat_avg(st, STAT_TOPDOWN_TOTAL_SLOTS, ctx, cpu);
+	return runtime_stat_avg(st, STAT_TOPDOWN_TOTAL_SLOTS, cpu, rsd);
 }
 
-static double td_bad_spec(int ctx, int cpu, struct runtime_stat *st)
+static double td_bad_spec(int cpu, struct runtime_stat *st,
+			  struct runtime_stat_data *rsd)
 {
 	double bad_spec = 0;
 	double total_slots;
 	double total;
 
-	total = runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_ISSUED, ctx, cpu) -
-		runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_RETIRED, ctx, cpu) +
-		runtime_stat_avg(st, STAT_TOPDOWN_RECOVERY_BUBBLES, ctx, cpu);
+	total = runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_ISSUED, cpu, rsd) -
+		runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_RETIRED, cpu, rsd) +
+		runtime_stat_avg(st, STAT_TOPDOWN_RECOVERY_BUBBLES, cpu, rsd);
 
-	total_slots = td_total_slots(ctx, cpu, st);
+	total_slots = td_total_slots(cpu, st, rsd);
 	if (total_slots)
 		bad_spec = total / total_slots;
 	return sanitize_val(bad_spec);
 }
 
-static double td_retiring(int ctx, int cpu, struct runtime_stat *st)
+static double td_retiring(int cpu, struct runtime_stat *st,
+			  struct runtime_stat_data *rsd)
 {
 	double retiring = 0;
-	double total_slots = td_total_slots(ctx, cpu, st);
+	double total_slots = td_total_slots(cpu, st, rsd);
 	double ret_slots = runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_RETIRED,
-					    ctx, cpu);
+					    cpu, rsd);
 
 	if (total_slots)
 		retiring = ret_slots / total_slots;
 	return retiring;
 }
 
-static double td_fe_bound(int ctx, int cpu, struct runtime_stat *st)
+static double td_fe_bound(int cpu, struct runtime_stat *st,
+			  struct runtime_stat_data *rsd)
 {
 	double fe_bound = 0;
-	double total_slots = td_total_slots(ctx, cpu, st);
+	double total_slots = td_total_slots(cpu, st, rsd);
 	double fetch_bub = runtime_stat_avg(st, STAT_TOPDOWN_FETCH_BUBBLES,
-					    ctx, cpu);
+					    cpu, rsd);
 
 	if (total_slots)
 		fe_bound = fetch_bub / total_slots;
 	return fe_bound;
 }
 
-static double td_be_bound(int ctx, int cpu, struct runtime_stat *st)
+static double td_be_bound(int cpu, struct runtime_stat *st,
+			  struct runtime_stat_data *rsd)
 {
-	double sum = (td_fe_bound(ctx, cpu, st) +
-		      td_bad_spec(ctx, cpu, st) +
-		      td_retiring(ctx, cpu, st));
+	double sum = (td_fe_bound(cpu, st, rsd) +
+		      td_bad_spec(cpu, st, rsd) +
+		      td_retiring(cpu, st, rsd));
 	if (sum == 0)
 		return 0;
 	return sanitize_val(1.0 - sum);
@@ -722,15 +734,15 @@ static double td_be_bound(int ctx, int cpu, struct runtime_stat *st)
  * the ratios we need to recreate the sum.
  */
 
-static double td_metric_ratio(int ctx, int cpu,
-			      enum stat_type type,
-			      struct runtime_stat *stat)
+static double td_metric_ratio(int cpu, enum stat_type type,
+			      struct runtime_stat *stat,
+			      struct runtime_stat_data *rsd)
 {
-	double sum = runtime_stat_avg(stat, STAT_TOPDOWN_RETIRING, ctx, cpu) +
-		runtime_stat_avg(stat, STAT_TOPDOWN_FE_BOUND, ctx, cpu) +
-		runtime_stat_avg(stat, STAT_TOPDOWN_BE_BOUND, ctx, cpu) +
-		runtime_stat_avg(stat, STAT_TOPDOWN_BAD_SPEC, ctx, cpu);
-	double d = runtime_stat_avg(stat, type, ctx, cpu);
+	double sum = runtime_stat_avg(stat, STAT_TOPDOWN_RETIRING, cpu, rsd) +
+		runtime_stat_avg(stat, STAT_TOPDOWN_FE_BOUND, cpu, rsd) +
+		runtime_stat_avg(stat, STAT_TOPDOWN_BE_BOUND, cpu, rsd) +
+		runtime_stat_avg(stat, STAT_TOPDOWN_BAD_SPEC, cpu, rsd);
+	double d = runtime_stat_avg(stat, type, cpu, rsd);
 
 	if (sum)
 		return d / sum;
@@ -742,34 +754,33 @@ static double td_metric_ratio(int ctx, int cpu,
  * We allow two missing.
  */
 
-static bool full_td(int ctx, int cpu,
-		    struct runtime_stat *stat)
+static bool full_td(int cpu, struct runtime_stat *stat,
+		    struct runtime_stat_data *rsd)
 {
 	int c = 0;
 
-	if (runtime_stat_avg(stat, STAT_TOPDOWN_RETIRING, ctx, cpu) > 0)
+	if (runtime_stat_avg(stat, STAT_TOPDOWN_RETIRING, cpu, rsd) > 0)
 		c++;
-	if (runtime_stat_avg(stat, STAT_TOPDOWN_BE_BOUND, ctx, cpu) > 0)
+	if (runtime_stat_avg(stat, STAT_TOPDOWN_BE_BOUND, cpu, rsd) > 0)
 		c++;
-	if (runtime_stat_avg(stat, STAT_TOPDOWN_FE_BOUND, ctx, cpu) > 0)
+	if (runtime_stat_avg(stat, STAT_TOPDOWN_FE_BOUND, cpu, rsd) > 0)
 		c++;
-	if (runtime_stat_avg(stat, STAT_TOPDOWN_BAD_SPEC, ctx, cpu) > 0)
+	if (runtime_stat_avg(stat, STAT_TOPDOWN_BAD_SPEC, cpu, rsd) > 0)
 		c++;
 	return c >= 2;
 }
 
-static void print_smi_cost(struct perf_stat_config *config,
-			   int cpu, struct evsel *evsel,
+static void print_smi_cost(struct perf_stat_config *config, int cpu,
 			   struct perf_stat_output_ctx *out,
-			   struct runtime_stat *st)
+			   struct runtime_stat *st,
+			   struct runtime_stat_data *rsd)
 {
 	double smi_num, aperf, cycles, cost = 0.0;
-	int ctx = evsel_context(evsel);
 	const char *color = NULL;
 
-	smi_num = runtime_stat_avg(st, STAT_SMI_NUM, ctx, cpu);
-	aperf = runtime_stat_avg(st, STAT_APERF, ctx, cpu);
-	cycles = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu);
+	smi_num = runtime_stat_avg(st, STAT_SMI_NUM, cpu, rsd);
+	aperf = runtime_stat_avg(st, STAT_APERF, cpu, rsd);
+	cycles = runtime_stat_avg(st, STAT_CYCLES, cpu, rsd);
 
 	if ((cycles == 0) || (aperf == 0))
 		return;
@@ -804,7 +815,8 @@ static int prepare_metric(struct evsel **metric_events,
 			scale = 1e-9;
 		} else {
 			v = saved_value_lookup(metric_events[i], cpu, false,
-					       STAT_NONE, 0, st);
+					       STAT_NONE, 0, st,
+					       metric_events[i]->cgrp);
 			if (!v)
 				break;
 			stats = &v->stats;
@@ -930,12 +942,15 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 	print_metric_t print_metric = out->print_metric;
 	double total, ratio = 0.0, total2;
 	const char *color = NULL;
-	int ctx = evsel_context(evsel);
+	struct runtime_stat_data rsd = {
+		.ctx = evsel_context(evsel),
+		.cgrp = evsel->cgrp,
+	};
 	struct metric_event *me;
 	int num = 1;
 
 	if (evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) {
-		total = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu);
+		total = runtime_stat_avg(st, STAT_CYCLES, cpu, &rsd);
 
 		if (total) {
 			ratio = avg / total;
@@ -945,12 +960,11 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 			print_metric(config, ctxp, NULL, NULL, "insn per cycle", 0);
 		}
 
-		total = runtime_stat_avg(st, STAT_STALLED_CYCLES_FRONT,
-					 ctx, cpu);
+		total = runtime_stat_avg(st, STAT_STALLED_CYCLES_FRONT, cpu, &rsd);
 
 		total = max(total, runtime_stat_avg(st,
 						    STAT_STALLED_CYCLES_BACK,
-						    ctx, cpu));
+						    cpu, &rsd));
 
 		if (total && avg) {
 			out->new_line(config, ctxp);
@@ -960,8 +974,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 					ratio);
 		}
 	} else if (evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES)) {
-		if (runtime_stat_n(st, STAT_BRANCHES, ctx, cpu) != 0)
-			print_branch_misses(config, cpu, evsel, avg, out, st);
+		if (runtime_stat_n(st, STAT_BRANCHES, cpu, &rsd) != 0)
+			print_branch_misses(config, cpu, avg, out, st, &rsd);
 		else
 			print_metric(config, ctxp, NULL, NULL, "of all branches", 0);
 	} else if (
@@ -970,8 +984,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
 					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
 
-		if (runtime_stat_n(st, STAT_L1_DCACHE, ctx, cpu) != 0)
-			print_l1_dcache_misses(config, cpu, evsel, avg, out, st);
+		if (runtime_stat_n(st, STAT_L1_DCACHE, cpu, &rsd) != 0)
+			print_l1_dcache_misses(config, cpu, avg, out, st, &rsd);
 		else
 			print_metric(config, ctxp, NULL, NULL, "of all L1-dcache accesses", 0);
 	} else if (
@@ -980,8 +994,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
 					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
 
-		if (runtime_stat_n(st, STAT_L1_ICACHE, ctx, cpu) != 0)
-			print_l1_icache_misses(config, cpu, evsel, avg, out, st);
+		if (runtime_stat_n(st, STAT_L1_ICACHE, cpu, &rsd) != 0)
+			print_l1_icache_misses(config, cpu, avg, out, st, &rsd);
 		else
 			print_metric(config, ctxp, NULL, NULL, "of all L1-icache accesses", 0);
 	} else if (
@@ -990,8 +1004,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
 					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
 
-		if (runtime_stat_n(st, STAT_DTLB_CACHE, ctx, cpu) != 0)
-			print_dtlb_cache_misses(config, cpu, evsel, avg, out, st);
+		if (runtime_stat_n(st, STAT_DTLB_CACHE, cpu, &rsd) != 0)
+			print_dtlb_cache_misses(config, cpu, avg, out, st, &rsd);
 		else
 			print_metric(config, ctxp, NULL, NULL, "of all dTLB cache accesses", 0);
 	} else if (
@@ -1000,8 +1014,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
 					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
 
-		if (runtime_stat_n(st, STAT_ITLB_CACHE, ctx, cpu) != 0)
-			print_itlb_cache_misses(config, cpu, evsel, avg, out, st);
+		if (runtime_stat_n(st, STAT_ITLB_CACHE, cpu, &rsd) != 0)
+			print_itlb_cache_misses(config, cpu, avg, out, st, &rsd);
 		else
 			print_metric(config, ctxp, NULL, NULL, "of all iTLB cache accesses", 0);
 	} else if (
@@ -1010,27 +1024,27 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
 					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
 
-		if (runtime_stat_n(st, STAT_LL_CACHE, ctx, cpu) != 0)
-			print_ll_cache_misses(config, cpu, evsel, avg, out, st);
+		if (runtime_stat_n(st, STAT_LL_CACHE, cpu, &rsd) != 0)
+			print_ll_cache_misses(config, cpu, avg, out, st, &rsd);
 		else
 			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);
+		total = runtime_stat_avg(st, STAT_CACHEREFS, cpu, &rsd);
 
 		if (total)
 			ratio = avg * 100 / total;
 
-		if (runtime_stat_n(st, STAT_CACHEREFS, ctx, cpu) != 0)
+		if (runtime_stat_n(st, STAT_CACHEREFS, cpu, &rsd) != 0)
 			print_metric(config, ctxp, NULL, "%8.3f %%",
 				     "of all cache refs", ratio);
 		else
 			print_metric(config, ctxp, NULL, NULL, "of all cache refs", 0);
 	} else if (evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) {
-		print_stalled_cycles_frontend(config, cpu, evsel, avg, out, st);
+		print_stalled_cycles_frontend(config, cpu, avg, out, st, &rsd);
 	} else if (evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) {
-		print_stalled_cycles_backend(config, cpu, evsel, avg, out, st);
+		print_stalled_cycles_backend(config, cpu, avg, out, st, &rsd);
 	} else if (evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) {
-		total = runtime_stat_avg(st, STAT_NSECS, 0, cpu);
+		total = runtime_stat_avg(st, STAT_NSECS, cpu, &rsd);
 
 		if (total) {
 			ratio = avg / total;
@@ -1039,7 +1053,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 			print_metric(config, ctxp, NULL, NULL, "Ghz", 0);
 		}
 	} else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX)) {
-		total = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu);
+		total = runtime_stat_avg(st, STAT_CYCLES, cpu, &rsd);
 
 		if (total)
 			print_metric(config, ctxp, NULL,
@@ -1049,8 +1063,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 			print_metric(config, ctxp, NULL, NULL, "transactional cycles",
 				     0);
 	} else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX_CP)) {
-		total = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu);
-		total2 = runtime_stat_avg(st, STAT_CYCLES_IN_TX, ctx, cpu);
+		total = runtime_stat_avg(st, STAT_CYCLES, cpu, &rsd);
+		total2 = runtime_stat_avg(st, STAT_CYCLES_IN_TX, cpu, &rsd);
 
 		if (total2 < avg)
 			total2 = avg;
@@ -1060,21 +1074,19 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 		else
 			print_metric(config, ctxp, NULL, NULL, "aborted cycles", 0);
 	} else if (perf_stat_evsel__is(evsel, TRANSACTION_START)) {
-		total = runtime_stat_avg(st, STAT_CYCLES_IN_TX,
-					 ctx, cpu);
+		total = runtime_stat_avg(st, STAT_CYCLES_IN_TX, cpu, &rsd);
 
 		if (avg)
 			ratio = total / avg;
 
-		if (runtime_stat_n(st, STAT_CYCLES_IN_TX, ctx, cpu) != 0)
+		if (runtime_stat_n(st, STAT_CYCLES_IN_TX, cpu, &rsd) != 0)
 			print_metric(config, ctxp, NULL, "%8.0f",
 				     "cycles / transaction", ratio);
 		else
 			print_metric(config, ctxp, NULL, NULL, "cycles / transaction",
 				      0);
 	} else if (perf_stat_evsel__is(evsel, ELISION_START)) {
-		total = runtime_stat_avg(st, STAT_CYCLES_IN_TX,
-					 ctx, cpu);
+		total = runtime_stat_avg(st, STAT_CYCLES_IN_TX, cpu, &rsd);
 
 		if (avg)
 			ratio = total / avg;
@@ -1087,28 +1099,28 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 		else
 			print_metric(config, ctxp, NULL, NULL, "CPUs utilized", 0);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_FETCH_BUBBLES)) {
-		double fe_bound = td_fe_bound(ctx, cpu, st);
+		double fe_bound = td_fe_bound(cpu, st, &rsd);
 
 		if (fe_bound > 0.2)
 			color = PERF_COLOR_RED;
 		print_metric(config, ctxp, color, "%8.1f%%", "frontend bound",
 				fe_bound * 100.);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_SLOTS_RETIRED)) {
-		double retiring = td_retiring(ctx, cpu, st);
+		double retiring = td_retiring(cpu, st, &rsd);
 
 		if (retiring > 0.7)
 			color = PERF_COLOR_GREEN;
 		print_metric(config, ctxp, color, "%8.1f%%", "retiring",
 				retiring * 100.);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_RECOVERY_BUBBLES)) {
-		double bad_spec = td_bad_spec(ctx, cpu, st);
+		double bad_spec = td_bad_spec(cpu, st, &rsd);
 
 		if (bad_spec > 0.1)
 			color = PERF_COLOR_RED;
 		print_metric(config, ctxp, color, "%8.1f%%", "bad speculation",
 				bad_spec * 100.);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_SLOTS_ISSUED)) {
-		double be_bound = td_be_bound(ctx, cpu, st);
+		double be_bound = td_be_bound(cpu, st, &rsd);
 		const char *name = "backend bound";
 		static int have_recovery_bubbles = -1;
 
@@ -1121,43 +1133,43 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 
 		if (be_bound > 0.2)
 			color = PERF_COLOR_RED;
-		if (td_total_slots(ctx, cpu, st) > 0)
+		if (td_total_slots(cpu, st, &rsd) > 0)
 			print_metric(config, ctxp, color, "%8.1f%%", name,
 					be_bound * 100.);
 		else
 			print_metric(config, ctxp, NULL, NULL, name, 0);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_RETIRING) &&
-			full_td(ctx, cpu, st)) {
-		double retiring = td_metric_ratio(ctx, cpu,
-						  STAT_TOPDOWN_RETIRING, st);
-
+		   full_td(cpu, st, &rsd)) {
+		double retiring = td_metric_ratio(cpu,
+						  STAT_TOPDOWN_RETIRING, st,
+						  &rsd);
 		if (retiring > 0.7)
 			color = PERF_COLOR_GREEN;
 		print_metric(config, ctxp, color, "%8.1f%%", "retiring",
 				retiring * 100.);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_FE_BOUND) &&
-			full_td(ctx, cpu, st)) {
-		double fe_bound = td_metric_ratio(ctx, cpu,
-						  STAT_TOPDOWN_FE_BOUND, st);
-
+		   full_td(cpu, st, &rsd)) {
+		double fe_bound = td_metric_ratio(cpu,
+						  STAT_TOPDOWN_FE_BOUND, st,
+						  &rsd);
 		if (fe_bound > 0.2)
 			color = PERF_COLOR_RED;
 		print_metric(config, ctxp, color, "%8.1f%%", "frontend bound",
 				fe_bound * 100.);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_BE_BOUND) &&
-			full_td(ctx, cpu, st)) {
-		double be_bound = td_metric_ratio(ctx, cpu,
-						  STAT_TOPDOWN_BE_BOUND, st);
-
+		   full_td(cpu, st, &rsd)) {
+		double be_bound = td_metric_ratio(cpu,
+						  STAT_TOPDOWN_BE_BOUND, st,
+						  &rsd);
 		if (be_bound > 0.2)
 			color = PERF_COLOR_RED;
 		print_metric(config, ctxp, color, "%8.1f%%", "backend bound",
 				be_bound * 100.);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_BAD_SPEC) &&
-			full_td(ctx, cpu, st)) {
-		double bad_spec = td_metric_ratio(ctx, cpu,
-						  STAT_TOPDOWN_BAD_SPEC, st);
-
+		   full_td(cpu, st, &rsd)) {
+		double bad_spec = td_metric_ratio(cpu,
+						  STAT_TOPDOWN_BAD_SPEC, st,
+						  &rsd);
 		if (bad_spec > 0.1)
 			color = PERF_COLOR_RED;
 		print_metric(config, ctxp, color, "%8.1f%%", "bad speculation",
@@ -1165,11 +1177,11 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 	} else if (evsel->metric_expr) {
 		generic_metric(config, evsel->metric_expr, evsel->metric_events, NULL,
 				evsel->name, evsel->metric_name, NULL, 1, cpu, out, st);
-	} else if (runtime_stat_n(st, STAT_NSECS, 0, cpu) != 0) {
+	} else if (runtime_stat_n(st, STAT_NSECS, cpu, &rsd) != 0) {
 		char unit = 'M';
 		char unit_buf[10];
 
-		total = runtime_stat_avg(st, STAT_NSECS, 0, cpu);
+		total = runtime_stat_avg(st, STAT_NSECS, cpu, &rsd);
 
 		if (total)
 			ratio = 1000.0 * avg / total;
@@ -1180,7 +1192,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 		snprintf(unit_buf, sizeof(unit_buf), "%c/sec", unit);
 		print_metric(config, ctxp, NULL, "%8.3f", unit_buf, ratio);
 	} else if (perf_stat_evsel__is(evsel, SMI_NUM)) {
-		print_smi_cost(config, cpu, evsel, out, st);
+		print_smi_cost(config, cpu, out, st, &rsd);
 	} else {
 		num = 0;
 	}
diff --git a/tools/power/x86/intel-speed-select/isst-config.c b/tools/power/x86/intel-speed-select/isst-config.c
index 5390158cdb40..09cb3a6672f3 100644
--- a/tools/power/x86/intel-speed-select/isst-config.c
+++ b/tools/power/x86/intel-speed-select/isst-config.c
@@ -1249,6 +1249,8 @@ static void dump_isst_config(int arg)
 	isst_ctdp_display_information_end(outf);
 }
 
+static void adjust_scaling_max_from_base_freq(int cpu);
+
 static void set_tdp_level_for_cpu(int cpu, void *arg1, void *arg2, void *arg3,
 				  void *arg4)
 {
@@ -1267,6 +1269,9 @@ static void set_tdp_level_for_cpu(int cpu, void *arg1, void *arg2, void *arg3,
 			int pkg_id = get_physical_package_id(cpu);
 			int die_id = get_physical_die_id(cpu);
 
+			/* Wait for updated base frequencies */
+			usleep(2000);
+
 			fprintf(stderr, "Option is set to online/offline\n");
 			ctdp_level.core_cpumask_size =
 				alloc_cpu_set(&ctdp_level.core_cpumask);
@@ -1283,6 +1288,7 @@ static void set_tdp_level_for_cpu(int cpu, void *arg1, void *arg2, void *arg3,
 					if (CPU_ISSET_S(i, ctdp_level.core_cpumask_size, ctdp_level.core_cpumask)) {
 						fprintf(stderr, "online cpu %d\n", i);
 						set_cpu_online_offline(i, 1);
+						adjust_scaling_max_from_base_freq(i);
 					} else {
 						fprintf(stderr, "offline cpu %d\n", i);
 						set_cpu_online_offline(i, 0);
@@ -1440,6 +1446,31 @@ static int set_cpufreq_scaling_min_max(int cpu, int max, int freq)
 	return 0;
 }
 
+static int no_turbo(void)
+{
+	return parse_int_file(0, "/sys/devices/system/cpu/intel_pstate/no_turbo");
+}
+
+static void adjust_scaling_max_from_base_freq(int cpu)
+{
+	int base_freq, scaling_max_freq;
+
+	scaling_max_freq = parse_int_file(0, "/sys/devices/system/cpu/cpu%d/cpufreq/scaling_max_freq", cpu);
+	base_freq = get_cpufreq_base_freq(cpu);
+	if (scaling_max_freq < base_freq || no_turbo())
+		set_cpufreq_scaling_min_max(cpu, 1, base_freq);
+}
+
+static void adjust_scaling_min_from_base_freq(int cpu)
+{
+	int base_freq, scaling_min_freq;
+
+	scaling_min_freq = parse_int_file(0, "/sys/devices/system/cpu/cpu%d/cpufreq/scaling_min_freq", cpu);
+	base_freq = get_cpufreq_base_freq(cpu);
+	if (scaling_min_freq < base_freq)
+		set_cpufreq_scaling_min_max(cpu, 0, base_freq);
+}
+
 static int set_clx_pbf_cpufreq_scaling_min_max(int cpu)
 {
 	struct isst_pkg_ctdp_level_info *ctdp_level;
@@ -1537,6 +1568,7 @@ static void set_scaling_min_to_cpuinfo_max(int cpu)
 			continue;
 
 		set_cpufreq_scaling_min_max_from_cpuinfo(i, 1, 0);
+		adjust_scaling_min_from_base_freq(i);
 	}
 }
 
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 389ea5209a83..a7c4f0772e53 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -1834,12 +1834,15 @@ int get_mp(int cpu, struct msr_counter *mp, unsigned long long *counterp)
 int get_epb(int cpu)
 {
 	char path[128 + PATH_BYTES];
+	unsigned long long msr;
 	int ret, epb = -1;
 	FILE *fp;
 
 	sprintf(path, "/sys/devices/system/cpu/cpu%d/power/energy_perf_bias", cpu);
 
-	fp = fopen_or_die(path, "r");
+	fp = fopen(path, "r");
+	if (!fp)
+		goto msr_fallback;
 
 	ret = fscanf(fp, "%d", &epb);
 	if (ret != 1)
@@ -1848,6 +1851,11 @@ int get_epb(int cpu)
 	fclose(fp);
 
 	return epb;
+
+msr_fallback:
+	get_msr(cpu, MSR_IA32_ENERGY_PERF_BIAS, &msr);
+
+	return msr & 0xf;
 }
 
 void get_apic_id(struct thread_data *t)
diff --git a/tools/testing/kunit/kunit.py b/tools/testing/kunit/kunit.py
index 21516e293d17..e808a47c839b 100755
--- a/tools/testing/kunit/kunit.py
+++ b/tools/testing/kunit/kunit.py
@@ -43,9 +43,9 @@ class KunitStatus(Enum):
 	BUILD_FAILURE = auto()
 	TEST_FAILURE = auto()
 
-def get_kernel_root_path():
-	parts = sys.argv[0] if not __file__ else __file__
-	parts = os.path.realpath(parts).split('tools/testing/kunit')
+def get_kernel_root_path() -> str:
+	path = sys.argv[0] if not __file__ else __file__
+	parts = os.path.realpath(path).split('tools/testing/kunit')
 	if len(parts) != 2:
 		sys.exit(1)
 	return parts[0]
@@ -171,7 +171,7 @@ def run_tests(linux: kunit_kernel.LinuxSourceTree,
 				exec_result.elapsed_time))
 	return parse_result
 
-def add_common_opts(parser):
+def add_common_opts(parser) -> None:
 	parser.add_argument('--build_dir',
 			    help='As in the make command, it specifies the build '
 			    'directory.',
@@ -183,13 +183,13 @@ def add_common_opts(parser):
 			    help='Run all KUnit tests through allyesconfig',
 			    action='store_true')
 
-def add_build_opts(parser):
+def add_build_opts(parser) -> None:
 	parser.add_argument('--jobs',
 			    help='As in the make command, "Specifies  the number of '
 			    'jobs (commands) to run simultaneously."',
 			    type=int, default=8, metavar='jobs')
 
-def add_exec_opts(parser):
+def add_exec_opts(parser) -> None:
 	parser.add_argument('--timeout',
 			    help='maximum number of seconds to allow for all tests '
 			    'to run. This does not include time taken to build the '
@@ -198,7 +198,7 @@ def add_exec_opts(parser):
 			    default=300,
 			    metavar='timeout')
 
-def add_parse_opts(parser):
+def add_parse_opts(parser) -> None:
 	parser.add_argument('--raw_output', help='don\'t format output from kernel',
 			    action='store_true')
 	parser.add_argument('--json',
@@ -256,10 +256,7 @@ def main(argv, linux=None):
 			os.mkdir(cli_args.build_dir)
 
 		if not linux:
-			linux = kunit_kernel.LinuxSourceTree()
-
-		linux.create_kunitconfig(cli_args.build_dir)
-		linux.read_kunitconfig(cli_args.build_dir)
+			linux = kunit_kernel.LinuxSourceTree(cli_args.build_dir)
 
 		request = KunitRequest(cli_args.raw_output,
 				       cli_args.timeout,
@@ -277,10 +274,7 @@ def main(argv, linux=None):
 			os.mkdir(cli_args.build_dir)
 
 		if not linux:
-			linux = kunit_kernel.LinuxSourceTree()
-
-		linux.create_kunitconfig(cli_args.build_dir)
-		linux.read_kunitconfig(cli_args.build_dir)
+			linux = kunit_kernel.LinuxSourceTree(cli_args.build_dir)
 
 		request = KunitConfigRequest(cli_args.build_dir,
 					     cli_args.make_options)
@@ -292,10 +286,7 @@ def main(argv, linux=None):
 			sys.exit(1)
 	elif cli_args.subcommand == 'build':
 		if not linux:
-			linux = kunit_kernel.LinuxSourceTree()
-
-		linux.create_kunitconfig(cli_args.build_dir)
-		linux.read_kunitconfig(cli_args.build_dir)
+			linux = kunit_kernel.LinuxSourceTree(cli_args.build_dir)
 
 		request = KunitBuildRequest(cli_args.jobs,
 					    cli_args.build_dir,
@@ -309,10 +300,7 @@ def main(argv, linux=None):
 			sys.exit(1)
 	elif cli_args.subcommand == 'exec':
 		if not linux:
-			linux = kunit_kernel.LinuxSourceTree()
-
-		linux.create_kunitconfig(cli_args.build_dir)
-		linux.read_kunitconfig(cli_args.build_dir)
+			linux = kunit_kernel.LinuxSourceTree(cli_args.build_dir)
 
 		exec_request = KunitExecRequest(cli_args.timeout,
 						cli_args.build_dir,
diff --git a/tools/testing/kunit/kunit_config.py b/tools/testing/kunit/kunit_config.py
index 02ffc3a3e5dc..bdd60230764b 100644
--- a/tools/testing/kunit/kunit_config.py
+++ b/tools/testing/kunit/kunit_config.py
@@ -8,6 +8,7 @@
 
 import collections
 import re
+from typing import List, Set
 
 CONFIG_IS_NOT_SET_PATTERN = r'^# CONFIG_(\w+) is not set$'
 CONFIG_PATTERN = r'^CONFIG_(\w+)=(\S+|".*")$'
@@ -30,10 +31,10 @@ class KconfigParseError(Exception):
 class Kconfig(object):
 	"""Represents defconfig or .config specified using the Kconfig language."""
 
-	def __init__(self):
-		self._entries = []
+	def __init__(self) -> None:
+		self._entries = []  # type: List[KconfigEntry]
 
-	def entries(self):
+	def entries(self) -> Set[KconfigEntry]:
 		return set(self._entries)
 
 	def add_entry(self, entry: KconfigEntry) -> None:
diff --git a/tools/testing/kunit/kunit_json.py b/tools/testing/kunit/kunit_json.py
index 624b31b2dbd6..f5cca5c38cac 100644
--- a/tools/testing/kunit/kunit_json.py
+++ b/tools/testing/kunit/kunit_json.py
@@ -13,7 +13,7 @@ import kunit_parser
 
 from kunit_parser import TestStatus
 
-def get_json_result(test_result, def_config, build_dir, json_path):
+def get_json_result(test_result, def_config, build_dir, json_path) -> str:
 	sub_groups = []
 
 	# Each test suite is mapped to a KernelCI sub_group
diff --git a/tools/testing/kunit/kunit_kernel.py b/tools/testing/kunit/kunit_kernel.py
index 698358c9c0d6..2076a5a2d060 100644
--- a/tools/testing/kunit/kunit_kernel.py
+++ b/tools/testing/kunit/kunit_kernel.py
@@ -11,6 +11,7 @@ import subprocess
 import os
 import shutil
 import signal
+from typing import Iterator
 
 from contextlib import ExitStack
 
@@ -39,7 +40,7 @@ class BuildError(Exception):
 class LinuxSourceTreeOperations(object):
 	"""An abstraction over command line operations performed on a source tree."""
 
-	def make_mrproper(self):
+	def make_mrproper(self) -> None:
 		try:
 			subprocess.check_output(['make', 'mrproper'], stderr=subprocess.STDOUT)
 		except OSError as e:
@@ -47,7 +48,7 @@ class LinuxSourceTreeOperations(object):
 		except subprocess.CalledProcessError as e:
 			raise ConfigError(e.output.decode())
 
-	def make_olddefconfig(self, build_dir, make_options):
+	def make_olddefconfig(self, build_dir, make_options) -> None:
 		command = ['make', 'ARCH=um', 'olddefconfig']
 		if make_options:
 			command.extend(make_options)
@@ -60,7 +61,7 @@ class LinuxSourceTreeOperations(object):
 		except subprocess.CalledProcessError as e:
 			raise ConfigError(e.output.decode())
 
-	def make_allyesconfig(self, build_dir, make_options):
+	def make_allyesconfig(self, build_dir, make_options) -> None:
 		kunit_parser.print_with_timestamp(
 			'Enabling all CONFIGs for UML...')
 		command = ['make', 'ARCH=um', 'allyesconfig']
@@ -82,7 +83,7 @@ class LinuxSourceTreeOperations(object):
 		kunit_parser.print_with_timestamp(
 			'Starting Kernel with all configs takes a few minutes...')
 
-	def make(self, jobs, build_dir, make_options):
+	def make(self, jobs, build_dir, make_options) -> None:
 		command = ['make', 'ARCH=um', '--jobs=' + str(jobs)]
 		if make_options:
 			command.extend(make_options)
@@ -100,7 +101,7 @@ class LinuxSourceTreeOperations(object):
 		if stderr:  # likely only due to build warnings
 			print(stderr.decode())
 
-	def linux_bin(self, params, timeout, build_dir):
+	def linux_bin(self, params, timeout, build_dir) -> None:
 		"""Runs the Linux UML binary. Must be named 'linux'."""
 		linux_bin = get_file_path(build_dir, 'linux')
 		outfile = get_outfile_path(build_dir)
@@ -110,41 +111,42 @@ class LinuxSourceTreeOperations(object):
 						   stderr=subprocess.STDOUT)
 			process.wait(timeout)
 
-def get_kconfig_path(build_dir):
+def get_kconfig_path(build_dir) -> str:
 	return get_file_path(build_dir, KCONFIG_PATH)
 
-def get_kunitconfig_path(build_dir):
+def get_kunitconfig_path(build_dir) -> str:
 	return get_file_path(build_dir, KUNITCONFIG_PATH)
 
-def get_outfile_path(build_dir):
+def get_outfile_path(build_dir) -> str:
 	return get_file_path(build_dir, OUTFILE_PATH)
 
 class LinuxSourceTree(object):
 	"""Represents a Linux kernel source tree with KUnit tests."""
 
-	def __init__(self):
-		self._ops = LinuxSourceTreeOperations()
+	def __init__(self, build_dir: str, load_config=True, defconfig=DEFAULT_KUNITCONFIG_PATH) -> None:
 		signal.signal(signal.SIGINT, self.signal_handler)
 
-	def clean(self):
-		try:
-			self._ops.make_mrproper()
-		except ConfigError as e:
-			logging.error(e)
-			return False
-		return True
+		self._ops = LinuxSourceTreeOperations()
+
+		if not load_config:
+			return
 
-	def create_kunitconfig(self, build_dir, defconfig=DEFAULT_KUNITCONFIG_PATH):
 		kunitconfig_path = get_kunitconfig_path(build_dir)
 		if not os.path.exists(kunitconfig_path):
 			shutil.copyfile(defconfig, kunitconfig_path)
 
-	def read_kunitconfig(self, build_dir):
-		kunitconfig_path = get_kunitconfig_path(build_dir)
 		self._kconfig = kunit_config.Kconfig()
 		self._kconfig.read_from_file(kunitconfig_path)
 
-	def validate_config(self, build_dir):
+	def clean(self) -> bool:
+		try:
+			self._ops.make_mrproper()
+		except ConfigError as e:
+			logging.error(e)
+			return False
+		return True
+
+	def validate_config(self, build_dir) -> bool:
 		kconfig_path = get_kconfig_path(build_dir)
 		validated_kconfig = kunit_config.Kconfig()
 		validated_kconfig.read_from_file(kconfig_path)
@@ -158,7 +160,7 @@ class LinuxSourceTree(object):
 			return False
 		return True
 
-	def build_config(self, build_dir, make_options):
+	def build_config(self, build_dir, make_options) -> bool:
 		kconfig_path = get_kconfig_path(build_dir)
 		if build_dir and not os.path.exists(build_dir):
 			os.mkdir(build_dir)
@@ -170,7 +172,7 @@ class LinuxSourceTree(object):
 			return False
 		return self.validate_config(build_dir)
 
-	def build_reconfig(self, build_dir, make_options):
+	def build_reconfig(self, build_dir, make_options) -> bool:
 		"""Creates a new .config if it is not a subset of the .kunitconfig."""
 		kconfig_path = get_kconfig_path(build_dir)
 		if os.path.exists(kconfig_path):
@@ -186,7 +188,7 @@ class LinuxSourceTree(object):
 			print('Generating .config ...')
 			return self.build_config(build_dir, make_options)
 
-	def build_um_kernel(self, alltests, jobs, build_dir, make_options):
+	def build_um_kernel(self, alltests, jobs, build_dir, make_options) -> bool:
 		try:
 			if alltests:
 				self._ops.make_allyesconfig(build_dir, make_options)
@@ -197,7 +199,7 @@ class LinuxSourceTree(object):
 			return False
 		return self.validate_config(build_dir)
 
-	def run_kernel(self, args=[], build_dir='', timeout=None):
+	def run_kernel(self, args=[], build_dir='', timeout=None) -> Iterator[str]:
 		args.extend(['mem=1G', 'console=tty'])
 		self._ops.linux_bin(args, timeout, build_dir)
 		outfile = get_outfile_path(build_dir)
@@ -206,6 +208,6 @@ class LinuxSourceTree(object):
 			for line in file:
 				yield line
 
-	def signal_handler(self, sig, frame):
+	def signal_handler(self, sig, frame) -> None:
 		logging.error('Build interruption occurred. Cleaning console.')
 		subprocess.call(['stty', 'sane'])
diff --git a/tools/testing/kunit/kunit_parser.py b/tools/testing/kunit/kunit_parser.py
index 6614ec4d0898..e8bcc139702e 100644
--- a/tools/testing/kunit/kunit_parser.py
+++ b/tools/testing/kunit/kunit_parser.py
@@ -12,32 +12,32 @@ from collections import namedtuple
 from datetime import datetime
 from enum import Enum, auto
 from functools import reduce
-from typing import List, Optional, Tuple
+from typing import Iterable, Iterator, List, Optional, Tuple
 
 TestResult = namedtuple('TestResult', ['status','suites','log'])
 
 class TestSuite(object):
-	def __init__(self):
-		self.status = None
-		self.name = None
-		self.cases = []
+	def __init__(self) -> None:
+		self.status = TestStatus.SUCCESS
+		self.name = ''
+		self.cases = []  # type: List[TestCase]
 
-	def __str__(self):
-		return 'TestSuite(' + self.status + ',' + self.name + ',' + str(self.cases) + ')'
+	def __str__(self) -> str:
+		return 'TestSuite(' + str(self.status) + ',' + self.name + ',' + str(self.cases) + ')'
 
-	def __repr__(self):
+	def __repr__(self) -> str:
 		return str(self)
 
 class TestCase(object):
-	def __init__(self):
-		self.status = None
+	def __init__(self) -> None:
+		self.status = TestStatus.SUCCESS
 		self.name = ''
-		self.log = []
+		self.log = []  # type: List[str]
 
-	def __str__(self):
-		return 'TestCase(' + self.status + ',' + self.name + ',' + str(self.log) + ')'
+	def __str__(self) -> str:
+		return 'TestCase(' + str(self.status) + ',' + self.name + ',' + str(self.log) + ')'
 
-	def __repr__(self):
+	def __repr__(self) -> str:
 		return str(self)
 
 class TestStatus(Enum):
@@ -51,7 +51,7 @@ kunit_start_re = re.compile(r'TAP version [0-9]+$')
 kunit_end_re = re.compile('(List of all partitions:|'
 			  'Kernel panic - not syncing: VFS:)')
 
-def isolate_kunit_output(kernel_output):
+def isolate_kunit_output(kernel_output) -> Iterator[str]:
 	started = False
 	for line in kernel_output:
 		line = line.rstrip()  # line always has a trailing \n
@@ -64,7 +64,7 @@ def isolate_kunit_output(kernel_output):
 		elif started:
 			yield line[prefix_len:] if prefix_len > 0 else line
 
-def raw_output(kernel_output):
+def raw_output(kernel_output) -> None:
 	for line in kernel_output:
 		print(line.rstrip())
 
@@ -72,36 +72,36 @@ DIVIDER = '=' * 60
 
 RESET = '\033[0;0m'
 
-def red(text):
+def red(text) -> str:
 	return '\033[1;31m' + text + RESET
 
-def yellow(text):
+def yellow(text) -> str:
 	return '\033[1;33m' + text + RESET
 
-def green(text):
+def green(text) -> str:
 	return '\033[1;32m' + text + RESET
 
-def print_with_timestamp(message):
+def print_with_timestamp(message) -> None:
 	print('[%s] %s' % (datetime.now().strftime('%H:%M:%S'), message))
 
-def format_suite_divider(message):
+def format_suite_divider(message) -> str:
 	return '======== ' + message + ' ========'
 
-def print_suite_divider(message):
+def print_suite_divider(message) -> None:
 	print_with_timestamp(DIVIDER)
 	print_with_timestamp(format_suite_divider(message))
 
-def print_log(log):
+def print_log(log) -> None:
 	for m in log:
 		print_with_timestamp(m)
 
 TAP_ENTRIES = re.compile(r'^(TAP|[\s]*ok|[\s]*not ok|[\s]*[0-9]+\.\.[0-9]+|[\s]*#).*$')
 
-def consume_non_diagnositic(lines: List[str]) -> None:
+def consume_non_diagnostic(lines: List[str]) -> None:
 	while lines and not TAP_ENTRIES.match(lines[0]):
 		lines.pop(0)
 
-def save_non_diagnositic(lines: List[str], test_case: TestCase) -> None:
+def save_non_diagnostic(lines: List[str], test_case: TestCase) -> None:
 	while lines and not TAP_ENTRIES.match(lines[0]):
 		test_case.log.append(lines[0])
 		lines.pop(0)
@@ -113,7 +113,7 @@ OK_NOT_OK_SUBTEST = re.compile(r'^[\s]+(ok|not ok) [0-9]+ - (.*)$')
 OK_NOT_OK_MODULE = re.compile(r'^(ok|not ok) ([0-9]+) - (.*)$')
 
 def parse_ok_not_ok_test_case(lines: List[str], test_case: TestCase) -> bool:
-	save_non_diagnositic(lines, test_case)
+	save_non_diagnostic(lines, test_case)
 	if not lines:
 		test_case.status = TestStatus.TEST_CRASHED
 		return True
@@ -139,7 +139,7 @@ SUBTEST_DIAGNOSTIC = re.compile(r'^[\s]+# (.*)$')
 DIAGNOSTIC_CRASH_MESSAGE = re.compile(r'^[\s]+# .*?: kunit test case crashed!$')
 
 def parse_diagnostic(lines: List[str], test_case: TestCase) -> bool:
-	save_non_diagnositic(lines, test_case)
+	save_non_diagnostic(lines, test_case)
 	if not lines:
 		return False
 	line = lines[0]
@@ -155,7 +155,7 @@ def parse_diagnostic(lines: List[str], test_case: TestCase) -> bool:
 
 def parse_test_case(lines: List[str]) -> Optional[TestCase]:
 	test_case = TestCase()
-	save_non_diagnositic(lines, test_case)
+	save_non_diagnostic(lines, test_case)
 	while parse_diagnostic(lines, test_case):
 		pass
 	if parse_ok_not_ok_test_case(lines, test_case):
@@ -166,7 +166,7 @@ def parse_test_case(lines: List[str]) -> Optional[TestCase]:
 SUBTEST_HEADER = re.compile(r'^[\s]+# Subtest: (.*)$')
 
 def parse_subtest_header(lines: List[str]) -> Optional[str]:
-	consume_non_diagnositic(lines)
+	consume_non_diagnostic(lines)
 	if not lines:
 		return None
 	match = SUBTEST_HEADER.match(lines[0])
@@ -179,7 +179,7 @@ def parse_subtest_header(lines: List[str]) -> Optional[str]:
 SUBTEST_PLAN = re.compile(r'[\s]+[0-9]+\.\.([0-9]+)')
 
 def parse_subtest_plan(lines: List[str]) -> Optional[int]:
-	consume_non_diagnositic(lines)
+	consume_non_diagnostic(lines)
 	match = SUBTEST_PLAN.match(lines[0])
 	if match:
 		lines.pop(0)
@@ -202,7 +202,7 @@ def max_status(left: TestStatus, right: TestStatus) -> TestStatus:
 def parse_ok_not_ok_test_suite(lines: List[str],
 			       test_suite: TestSuite,
 			       expected_suite_index: int) -> bool:
-	consume_non_diagnositic(lines)
+	consume_non_diagnostic(lines)
 	if not lines:
 		test_suite.status = TestStatus.TEST_CRASHED
 		return False
@@ -224,18 +224,17 @@ def parse_ok_not_ok_test_suite(lines: List[str],
 	else:
 		return False
 
-def bubble_up_errors(to_status, status_container_list) -> TestStatus:
-	status_list = map(to_status, status_container_list)
-	return reduce(max_status, status_list, TestStatus.SUCCESS)
+def bubble_up_errors(statuses: Iterable[TestStatus]) -> TestStatus:
+	return reduce(max_status, statuses, TestStatus.SUCCESS)
 
 def bubble_up_test_case_errors(test_suite: TestSuite) -> TestStatus:
-	max_test_case_status = bubble_up_errors(lambda x: x.status, test_suite.cases)
+	max_test_case_status = bubble_up_errors(x.status for x in test_suite.cases)
 	return max_status(max_test_case_status, test_suite.status)
 
 def parse_test_suite(lines: List[str], expected_suite_index: int) -> Optional[TestSuite]:
 	if not lines:
 		return None
-	consume_non_diagnositic(lines)
+	consume_non_diagnostic(lines)
 	test_suite = TestSuite()
 	test_suite.status = TestStatus.SUCCESS
 	name = parse_subtest_header(lines)
@@ -264,7 +263,7 @@ def parse_test_suite(lines: List[str], expected_suite_index: int) -> Optional[Te
 TAP_HEADER = re.compile(r'^TAP version 14$')
 
 def parse_tap_header(lines: List[str]) -> bool:
-	consume_non_diagnositic(lines)
+	consume_non_diagnostic(lines)
 	if TAP_HEADER.match(lines[0]):
 		lines.pop(0)
 		return True
@@ -274,7 +273,7 @@ def parse_tap_header(lines: List[str]) -> bool:
 TEST_PLAN = re.compile(r'[0-9]+\.\.([0-9]+)')
 
 def parse_test_plan(lines: List[str]) -> Optional[int]:
-	consume_non_diagnositic(lines)
+	consume_non_diagnostic(lines)
 	match = TEST_PLAN.match(lines[0])
 	if match:
 		lines.pop(0)
@@ -282,11 +281,11 @@ def parse_test_plan(lines: List[str]) -> Optional[int]:
 	else:
 		return None
 
-def bubble_up_suite_errors(test_suite_list: List[TestSuite]) -> TestStatus:
-	return bubble_up_errors(lambda x: x.status, test_suite_list)
+def bubble_up_suite_errors(test_suites: Iterable[TestSuite]) -> TestStatus:
+	return bubble_up_errors(x.status for x in test_suites)
 
 def parse_test_result(lines: List[str]) -> TestResult:
-	consume_non_diagnositic(lines)
+	consume_non_diagnostic(lines)
 	if not lines or not parse_tap_header(lines):
 		return TestResult(TestStatus.NO_TESTS, [], lines)
 	expected_test_suite_num = parse_test_plan(lines)
diff --git a/tools/testing/nvdimm/config_check.c b/tools/testing/nvdimm/config_check.c
index cac891028cd1..3e3a5f518864 100644
--- a/tools/testing/nvdimm/config_check.c
+++ b/tools/testing/nvdimm/config_check.c
@@ -12,7 +12,8 @@ void check(void)
 	BUILD_BUG_ON(!IS_MODULE(CONFIG_ND_BTT));
 	BUILD_BUG_ON(!IS_MODULE(CONFIG_ND_PFN));
 	BUILD_BUG_ON(!IS_MODULE(CONFIG_ND_BLK));
-	BUILD_BUG_ON(!IS_MODULE(CONFIG_ACPI_NFIT));
+	if (IS_ENABLED(CONFIG_ACPI_NFIT))
+		BUILD_BUG_ON(!IS_MODULE(CONFIG_ACPI_NFIT));
 	BUILD_BUG_ON(!IS_MODULE(CONFIG_DEV_DAX));
 	BUILD_BUG_ON(!IS_MODULE(CONFIG_DEV_DAX_PMEM));
 }
diff --git a/tools/testing/nvdimm/test/Kbuild b/tools/testing/nvdimm/test/Kbuild
index 75baebf8f4ba..197bcb2b7f35 100644
--- a/tools/testing/nvdimm/test/Kbuild
+++ b/tools/testing/nvdimm/test/Kbuild
@@ -5,5 +5,9 @@ ccflags-y += -I$(srctree)/drivers/acpi/nfit/
 obj-m += nfit_test.o
 obj-m += nfit_test_iomap.o
 
-nfit_test-y := nfit.o
+ifeq  ($(CONFIG_ACPI_NFIT),m)
+	nfit_test-y := nfit.o
+else
+	nfit_test-y := ndtest.o
+endif
 nfit_test_iomap-y := iomap.o
diff --git a/tools/testing/nvdimm/test/ndtest.c b/tools/testing/nvdimm/test/ndtest.c
new file mode 100644
index 000000000000..6862915f1fb0
--- /dev/null
+++ b/tools/testing/nvdimm/test/ndtest.c
@@ -0,0 +1,1129 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/platform_device.h>
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/genalloc.h>
+#include <linux/vmalloc.h>
+#include <linux/dma-mapping.h>
+#include <linux/list_sort.h>
+#include <linux/libnvdimm.h>
+#include <linux/ndctl.h>
+#include <nd-core.h>
+#include <linux/printk.h>
+#include <linux/seq_buf.h>
+
+#include "../watermark.h"
+#include "nfit_test.h"
+#include "ndtest.h"
+
+enum {
+	DIMM_SIZE = SZ_32M,
+	LABEL_SIZE = SZ_128K,
+	NUM_INSTANCES = 2,
+	NUM_DCR = 4,
+	NDTEST_MAX_MAPPING = 6,
+};
+
+#define NDTEST_SCM_DIMM_CMD_MASK	   \
+	((1ul << ND_CMD_GET_CONFIG_SIZE) | \
+	 (1ul << ND_CMD_GET_CONFIG_DATA) | \
+	 (1ul << ND_CMD_SET_CONFIG_DATA) | \
+	 (1ul << ND_CMD_CALL))
+
+#define NFIT_DIMM_HANDLE(node, socket, imc, chan, dimm)			\
+	(((node & 0xfff) << 16) | ((socket & 0xf) << 12)		\
+	 | ((imc & 0xf) << 8) | ((chan & 0xf) << 4) | (dimm & 0xf))
+
+static DEFINE_SPINLOCK(ndtest_lock);
+static struct ndtest_priv *instances[NUM_INSTANCES];
+static struct class *ndtest_dimm_class;
+static struct gen_pool *ndtest_pool;
+
+static struct ndtest_dimm dimm_group1[] = {
+	{
+		.size = DIMM_SIZE,
+		.handle = NFIT_DIMM_HANDLE(0, 0, 0, 0, 0),
+		.uuid_str = "1e5c75d2-b618-11ea-9aa3-507b9ddc0f72",
+		.physical_id = 0,
+		.num_formats = 2,
+	},
+	{
+		.size = DIMM_SIZE,
+		.handle = NFIT_DIMM_HANDLE(0, 0, 0, 0, 1),
+		.uuid_str = "1c4d43ac-b618-11ea-be80-507b9ddc0f72",
+		.physical_id = 1,
+		.num_formats = 2,
+	},
+	{
+		.size = DIMM_SIZE,
+		.handle = NFIT_DIMM_HANDLE(0, 0, 1, 0, 0),
+		.uuid_str = "a9f17ffc-b618-11ea-b36d-507b9ddc0f72",
+		.physical_id = 2,
+		.num_formats = 2,
+	},
+	{
+		.size = DIMM_SIZE,
+		.handle = NFIT_DIMM_HANDLE(0, 0, 1, 0, 1),
+		.uuid_str = "b6b83b22-b618-11ea-8aae-507b9ddc0f72",
+		.physical_id = 3,
+		.num_formats = 2,
+	},
+	{
+		.size = DIMM_SIZE,
+		.handle = NFIT_DIMM_HANDLE(0, 1, 0, 0, 0),
+		.uuid_str = "bf9baaee-b618-11ea-b181-507b9ddc0f72",
+		.physical_id = 4,
+		.num_formats = 2,
+	},
+};
+
+static struct ndtest_dimm dimm_group2[] = {
+	{
+		.size = DIMM_SIZE,
+		.handle = NFIT_DIMM_HANDLE(1, 0, 0, 0, 0),
+		.uuid_str = "ca0817e2-b618-11ea-9db3-507b9ddc0f72",
+		.physical_id = 0,
+		.num_formats = 1,
+		.flags = PAPR_PMEM_UNARMED | PAPR_PMEM_EMPTY |
+			 PAPR_PMEM_SAVE_FAILED | PAPR_PMEM_SHUTDOWN_DIRTY |
+			 PAPR_PMEM_HEALTH_FATAL,
+	},
+};
+
+static struct ndtest_mapping region0_mapping[] = {
+	{
+		.dimm = 0,
+		.position = 0,
+		.start = 0,
+		.size = SZ_16M,
+	},
+	{
+		.dimm = 1,
+		.position = 1,
+		.start = 0,
+		.size = SZ_16M,
+	}
+};
+
+static struct ndtest_mapping region1_mapping[] = {
+	{
+		.dimm = 0,
+		.position = 0,
+		.start = SZ_16M,
+		.size = SZ_16M,
+	},
+	{
+		.dimm = 1,
+		.position = 1,
+		.start = SZ_16M,
+		.size = SZ_16M,
+	},
+	{
+		.dimm = 2,
+		.position = 2,
+		.start = SZ_16M,
+		.size = SZ_16M,
+	},
+	{
+		.dimm = 3,
+		.position = 3,
+		.start = SZ_16M,
+		.size = SZ_16M,
+	},
+};
+
+static struct ndtest_mapping region2_mapping[] = {
+	{
+		.dimm = 0,
+		.position = 0,
+		.start = 0,
+		.size = DIMM_SIZE,
+	},
+};
+
+static struct ndtest_mapping region3_mapping[] = {
+	{
+		.dimm = 1,
+		.start = 0,
+		.size = DIMM_SIZE,
+	}
+};
+
+static struct ndtest_mapping region4_mapping[] = {
+	{
+		.dimm = 2,
+		.start = 0,
+		.size = DIMM_SIZE,
+	}
+};
+
+static struct ndtest_mapping region5_mapping[] = {
+	{
+		.dimm = 3,
+		.start = 0,
+		.size = DIMM_SIZE,
+	}
+};
+
+static struct ndtest_region bus0_regions[] = {
+	{
+		.type = ND_DEVICE_NAMESPACE_PMEM,
+		.num_mappings = ARRAY_SIZE(region0_mapping),
+		.mapping = region0_mapping,
+		.size = DIMM_SIZE,
+		.range_index = 1,
+	},
+	{
+		.type = ND_DEVICE_NAMESPACE_PMEM,
+		.num_mappings = ARRAY_SIZE(region1_mapping),
+		.mapping = region1_mapping,
+		.size = DIMM_SIZE * 2,
+		.range_index = 2,
+	},
+	{
+		.type = ND_DEVICE_NAMESPACE_BLK,
+		.num_mappings = ARRAY_SIZE(region2_mapping),
+		.mapping = region2_mapping,
+		.size = DIMM_SIZE,
+		.range_index = 3,
+	},
+	{
+		.type = ND_DEVICE_NAMESPACE_BLK,
+		.num_mappings = ARRAY_SIZE(region3_mapping),
+		.mapping = region3_mapping,
+		.size = DIMM_SIZE,
+		.range_index = 4,
+	},
+	{
+		.type = ND_DEVICE_NAMESPACE_BLK,
+		.num_mappings = ARRAY_SIZE(region4_mapping),
+		.mapping = region4_mapping,
+		.size = DIMM_SIZE,
+		.range_index = 5,
+	},
+	{
+		.type = ND_DEVICE_NAMESPACE_BLK,
+		.num_mappings = ARRAY_SIZE(region5_mapping),
+		.mapping = region5_mapping,
+		.size = DIMM_SIZE,
+		.range_index = 6,
+	},
+};
+
+static struct ndtest_mapping region6_mapping[] = {
+	{
+		.dimm = 0,
+		.position = 0,
+		.start = 0,
+		.size = DIMM_SIZE,
+	},
+};
+
+static struct ndtest_region bus1_regions[] = {
+	{
+		.type = ND_DEVICE_NAMESPACE_IO,
+		.num_mappings = ARRAY_SIZE(region6_mapping),
+		.mapping = region6_mapping,
+		.size = DIMM_SIZE,
+		.range_index = 1,
+	},
+};
+
+static struct ndtest_config bus_configs[NUM_INSTANCES] = {
+	/* bus 1 */
+	{
+		.dimm_start = 0,
+		.dimm_count = ARRAY_SIZE(dimm_group1),
+		.dimms = dimm_group1,
+		.regions = bus0_regions,
+		.num_regions = ARRAY_SIZE(bus0_regions),
+	},
+	/* bus 2 */
+	{
+		.dimm_start = ARRAY_SIZE(dimm_group1),
+		.dimm_count = ARRAY_SIZE(dimm_group2),
+		.dimms = dimm_group2,
+		.regions = bus1_regions,
+		.num_regions = ARRAY_SIZE(bus1_regions),
+	},
+};
+
+static inline struct ndtest_priv *to_ndtest_priv(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+
+	return container_of(pdev, struct ndtest_priv, pdev);
+}
+
+static int ndtest_config_get(struct ndtest_dimm *p, unsigned int buf_len,
+			     struct nd_cmd_get_config_data_hdr *hdr)
+{
+	unsigned int len;
+
+	if ((hdr->in_offset + hdr->in_length) > LABEL_SIZE)
+		return -EINVAL;
+
+	hdr->status = 0;
+	len = min(hdr->in_length, LABEL_SIZE - hdr->in_offset);
+	memcpy(hdr->out_buf, p->label_area + hdr->in_offset, len);
+
+	return buf_len - len;
+}
+
+static int ndtest_config_set(struct ndtest_dimm *p, unsigned int buf_len,
+			     struct nd_cmd_set_config_hdr *hdr)
+{
+	unsigned int len;
+
+	if ((hdr->in_offset + hdr->in_length) > LABEL_SIZE)
+		return -EINVAL;
+
+	len = min(hdr->in_length, LABEL_SIZE - hdr->in_offset);
+	memcpy(p->label_area + hdr->in_offset, hdr->in_buf, len);
+
+	return buf_len - len;
+}
+
+static int ndtest_get_config_size(struct ndtest_dimm *dimm, unsigned int buf_len,
+				  struct nd_cmd_get_config_size *size)
+{
+	size->status = 0;
+	size->max_xfer = 8;
+	size->config_size = dimm->config_size;
+
+	return 0;
+}
+
+static int ndtest_ctl(struct nvdimm_bus_descriptor *nd_desc,
+		      struct nvdimm *nvdimm, unsigned int cmd, void *buf,
+		      unsigned int buf_len, int *cmd_rc)
+{
+	struct ndtest_dimm *dimm;
+	int _cmd_rc;
+
+	if (!cmd_rc)
+		cmd_rc = &_cmd_rc;
+
+	*cmd_rc = 0;
+
+	if (!nvdimm)
+		return -EINVAL;
+
+	dimm = nvdimm_provider_data(nvdimm);
+	if (!dimm)
+		return -EINVAL;
+
+	switch (cmd) {
+	case ND_CMD_GET_CONFIG_SIZE:
+		*cmd_rc = ndtest_get_config_size(dimm, buf_len, buf);
+		break;
+	case ND_CMD_GET_CONFIG_DATA:
+		*cmd_rc = ndtest_config_get(dimm, buf_len, buf);
+		break;
+	case ND_CMD_SET_CONFIG_DATA:
+		*cmd_rc = ndtest_config_set(dimm, buf_len, buf);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/* Failures for a DIMM can be injected using fail_cmd and
+	 * fail_cmd_code, see the device attributes below
+	 */
+	if ((1 << cmd) & dimm->fail_cmd)
+		return dimm->fail_cmd_code ? dimm->fail_cmd_code : -EIO;
+
+	return 0;
+}
+
+static int ndtest_blk_do_io(struct nd_blk_region *ndbr, resource_size_t dpa,
+		void *iobuf, u64 len, int rw)
+{
+	struct ndtest_dimm *dimm = ndbr->blk_provider_data;
+	struct ndtest_blk_mmio *mmio = dimm->mmio;
+	struct nd_region *nd_region = &ndbr->nd_region;
+	unsigned int lane;
+
+	if (!mmio)
+		return -ENOMEM;
+
+	lane = nd_region_acquire_lane(nd_region);
+	if (rw)
+		memcpy(mmio->base + dpa, iobuf, len);
+	else {
+		memcpy(iobuf, mmio->base + dpa, len);
+		arch_invalidate_pmem(mmio->base + dpa, len);
+	}
+
+	nd_region_release_lane(nd_region, lane);
+
+	return 0;
+}
+
+static int ndtest_blk_region_enable(struct nvdimm_bus *nvdimm_bus,
+				    struct device *dev)
+{
+	struct nd_blk_region *ndbr = to_nd_blk_region(dev);
+	struct nvdimm *nvdimm;
+	struct ndtest_dimm *dimm;
+	struct ndtest_blk_mmio *mmio;
+
+	nvdimm = nd_blk_region_to_dimm(ndbr);
+	dimm = nvdimm_provider_data(nvdimm);
+
+	nd_blk_region_set_provider_data(ndbr, dimm);
+	dimm->blk_region = to_nd_region(dev);
+
+	mmio = devm_kzalloc(dev, sizeof(struct ndtest_blk_mmio), GFP_KERNEL);
+	if (!mmio)
+		return -ENOMEM;
+
+	mmio->base = (void __iomem *) devm_nvdimm_memremap(
+		dev, dimm->address, 12, nd_blk_memremap_flags(ndbr));
+	if (!mmio->base) {
+		dev_err(dev, "%s failed to map blk dimm\n", nvdimm_name(nvdimm));
+		return -ENOMEM;
+	}
+	mmio->size = dimm->size;
+	mmio->base_offset = 0;
+
+	dimm->mmio = mmio;
+
+	return 0;
+}
+
+static struct nfit_test_resource *ndtest_resource_lookup(resource_size_t addr)
+{
+	int i;
+
+	for (i = 0; i < NUM_INSTANCES; i++) {
+		struct nfit_test_resource *n, *nfit_res = NULL;
+		struct ndtest_priv *t = instances[i];
+
+		if (!t)
+			continue;
+		spin_lock(&ndtest_lock);
+		list_for_each_entry(n, &t->resources, list) {
+			if (addr >= n->res.start && (addr < n->res.start
+						+ resource_size(&n->res))) {
+				nfit_res = n;
+				break;
+			} else if (addr >= (unsigned long) n->buf
+					&& (addr < (unsigned long) n->buf
+						+ resource_size(&n->res))) {
+				nfit_res = n;
+				break;
+			}
+		}
+		spin_unlock(&ndtest_lock);
+		if (nfit_res)
+			return nfit_res;
+	}
+
+	pr_warn("Failed to get resource\n");
+
+	return NULL;
+}
+
+static void ndtest_release_resource(void *data)
+{
+	struct nfit_test_resource *res  = data;
+
+	spin_lock(&ndtest_lock);
+	list_del(&res->list);
+	spin_unlock(&ndtest_lock);
+
+	if (resource_size(&res->res) >= DIMM_SIZE)
+		gen_pool_free(ndtest_pool, res->res.start,
+				resource_size(&res->res));
+	vfree(res->buf);
+	kfree(res);
+}
+
+static void *ndtest_alloc_resource(struct ndtest_priv *p, size_t size,
+				   dma_addr_t *dma)
+{
+	dma_addr_t __dma;
+	void *buf;
+	struct nfit_test_resource *res;
+	struct genpool_data_align data = {
+		.align = SZ_128M,
+	};
+
+	res = kzalloc(sizeof(*res), GFP_KERNEL);
+	if (!res)
+		return NULL;
+
+	buf = vmalloc(size);
+	if (size >= DIMM_SIZE)
+		__dma = gen_pool_alloc_algo(ndtest_pool, size,
+					    gen_pool_first_fit_align, &data);
+	else
+		__dma = (unsigned long) buf;
+
+	if (!__dma)
+		goto buf_err;
+
+	INIT_LIST_HEAD(&res->list);
+	res->dev = &p->pdev.dev;
+	res->buf = buf;
+	res->res.start = __dma;
+	res->res.end = __dma + size - 1;
+	res->res.name = "NFIT";
+	spin_lock_init(&res->lock);
+	INIT_LIST_HEAD(&res->requests);
+	spin_lock(&ndtest_lock);
+	list_add(&res->list, &p->resources);
+	spin_unlock(&ndtest_lock);
+
+	if (dma)
+		*dma = __dma;
+
+	if (!devm_add_action(&p->pdev.dev, ndtest_release_resource, res))
+		return res->buf;
+
+buf_err:
+	if (__dma && size >= DIMM_SIZE)
+		gen_pool_free(ndtest_pool, __dma, size);
+	if (buf)
+		vfree(buf);
+	kfree(res);
+
+	return NULL;
+}
+
+static ssize_t range_index_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nd_region *nd_region = to_nd_region(dev);
+	struct ndtest_region *region = nd_region_provider_data(nd_region);
+
+	return sprintf(buf, "%d\n", region->range_index);
+}
+static DEVICE_ATTR_RO(range_index);
+
+static struct attribute *ndtest_region_attributes[] = {
+	&dev_attr_range_index.attr,
+	NULL,
+};
+
+static const struct attribute_group ndtest_region_attribute_group = {
+	.name = "papr",
+	.attrs = ndtest_region_attributes,
+};
+
+static const struct attribute_group *ndtest_region_attribute_groups[] = {
+	&ndtest_region_attribute_group,
+	NULL,
+};
+
+static int ndtest_create_region(struct ndtest_priv *p,
+				struct ndtest_region *region)
+{
+	struct nd_mapping_desc mappings[NDTEST_MAX_MAPPING];
+	struct nd_blk_region_desc ndbr_desc;
+	struct nd_interleave_set *nd_set;
+	struct nd_region_desc *ndr_desc;
+	struct resource res;
+	int i, ndimm = region->mapping[0].dimm;
+	u64 uuid[2];
+
+	memset(&res, 0, sizeof(res));
+	memset(&mappings, 0, sizeof(mappings));
+	memset(&ndbr_desc, 0, sizeof(ndbr_desc));
+	ndr_desc = &ndbr_desc.ndr_desc;
+
+	if (!ndtest_alloc_resource(p, region->size, &res.start))
+		return -ENOMEM;
+
+	res.end = res.start + region->size - 1;
+	ndr_desc->mapping = mappings;
+	ndr_desc->res = &res;
+	ndr_desc->provider_data = region;
+	ndr_desc->attr_groups = ndtest_region_attribute_groups;
+
+	if (uuid_parse(p->config->dimms[ndimm].uuid_str, (uuid_t *)uuid)) {
+		pr_err("failed to parse UUID\n");
+		return -ENXIO;
+	}
+
+	nd_set = devm_kzalloc(&p->pdev.dev, sizeof(*nd_set), GFP_KERNEL);
+	if (!nd_set)
+		return -ENOMEM;
+
+	nd_set->cookie1 = cpu_to_le64(uuid[0]);
+	nd_set->cookie2 = cpu_to_le64(uuid[1]);
+	nd_set->altcookie = nd_set->cookie1;
+	ndr_desc->nd_set = nd_set;
+
+	if (region->type == ND_DEVICE_NAMESPACE_BLK) {
+		mappings[0].start = 0;
+		mappings[0].size = DIMM_SIZE;
+		mappings[0].nvdimm = p->config->dimms[ndimm].nvdimm;
+
+		ndr_desc->mapping = &mappings[0];
+		ndr_desc->num_mappings = 1;
+		ndr_desc->num_lanes = 1;
+		ndbr_desc.enable = ndtest_blk_region_enable;
+		ndbr_desc.do_io = ndtest_blk_do_io;
+		region->region = nvdimm_blk_region_create(p->bus, ndr_desc);
+
+		goto done;
+	}
+
+	for (i = 0; i < region->num_mappings; i++) {
+		ndimm = region->mapping[i].dimm;
+		mappings[i].start = region->mapping[i].start;
+		mappings[i].size = region->mapping[i].size;
+		mappings[i].position = region->mapping[i].position;
+		mappings[i].nvdimm = p->config->dimms[ndimm].nvdimm;
+	}
+
+	ndr_desc->num_mappings = region->num_mappings;
+	region->region = nvdimm_pmem_region_create(p->bus, ndr_desc);
+
+done:
+	if (!region->region) {
+		dev_err(&p->pdev.dev, "Error registering region %pR\n",
+			ndr_desc->res);
+		return -ENXIO;
+	}
+
+	return 0;
+}
+
+static int ndtest_init_regions(struct ndtest_priv *p)
+{
+	int i, ret = 0;
+
+	for (i = 0; i < p->config->num_regions; i++) {
+		ret = ndtest_create_region(p, &p->config->regions[i]);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static void put_dimms(void *data)
+{
+	struct ndtest_priv *p = data;
+	int i;
+
+	for (i = 0; i < p->config->dimm_count; i++)
+		if (p->config->dimms[i].dev) {
+			device_unregister(p->config->dimms[i].dev);
+			p->config->dimms[i].dev = NULL;
+		}
+}
+
+static ssize_t handle_show(struct device *dev, struct device_attribute *attr,
+		char *buf)
+{
+	struct ndtest_dimm *dimm = dev_get_drvdata(dev);
+
+	return sprintf(buf, "%#x\n", dimm->handle);
+}
+static DEVICE_ATTR_RO(handle);
+
+static ssize_t fail_cmd_show(struct device *dev, struct device_attribute *attr,
+		char *buf)
+{
+	struct ndtest_dimm *dimm = dev_get_drvdata(dev);
+
+	return sprintf(buf, "%#x\n", dimm->fail_cmd);
+}
+
+static ssize_t fail_cmd_store(struct device *dev, struct device_attribute *attr,
+		const char *buf, size_t size)
+{
+	struct ndtest_dimm *dimm = dev_get_drvdata(dev);
+	unsigned long val;
+	ssize_t rc;
+
+	rc = kstrtol(buf, 0, &val);
+	if (rc)
+		return rc;
+
+	dimm->fail_cmd = val;
+
+	return size;
+}
+static DEVICE_ATTR_RW(fail_cmd);
+
+static ssize_t fail_cmd_code_show(struct device *dev, struct device_attribute *attr,
+		char *buf)
+{
+	struct ndtest_dimm *dimm = dev_get_drvdata(dev);
+
+	return sprintf(buf, "%d\n", dimm->fail_cmd_code);
+}
+
+static ssize_t fail_cmd_code_store(struct device *dev, struct device_attribute *attr,
+		const char *buf, size_t size)
+{
+	struct ndtest_dimm *dimm = dev_get_drvdata(dev);
+	unsigned long val;
+	ssize_t rc;
+
+	rc = kstrtol(buf, 0, &val);
+	if (rc)
+		return rc;
+
+	dimm->fail_cmd_code = val;
+	return size;
+}
+static DEVICE_ATTR_RW(fail_cmd_code);
+
+static struct attribute *dimm_attributes[] = {
+	&dev_attr_handle.attr,
+	&dev_attr_fail_cmd.attr,
+	&dev_attr_fail_cmd_code.attr,
+	NULL,
+};
+
+static struct attribute_group dimm_attribute_group = {
+	.attrs = dimm_attributes,
+};
+
+static const struct attribute_group *dimm_attribute_groups[] = {
+	&dimm_attribute_group,
+	NULL,
+};
+
+static ssize_t phys_id_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nvdimm *nvdimm = to_nvdimm(dev);
+	struct ndtest_dimm *dimm = nvdimm_provider_data(nvdimm);
+
+	return sprintf(buf, "%#x\n", dimm->physical_id);
+}
+static DEVICE_ATTR_RO(phys_id);
+
+static ssize_t vendor_show(struct device *dev,
+			   struct device_attribute *attr, char *buf)
+{
+	return sprintf(buf, "0x1234567\n");
+}
+static DEVICE_ATTR_RO(vendor);
+
+static ssize_t id_show(struct device *dev,
+		       struct device_attribute *attr, char *buf)
+{
+	struct nvdimm *nvdimm = to_nvdimm(dev);
+	struct ndtest_dimm *dimm = nvdimm_provider_data(nvdimm);
+
+	return sprintf(buf, "%04x-%02x-%04x-%08x", 0xabcd,
+		       0xa, 2016, ~(dimm->handle));
+}
+static DEVICE_ATTR_RO(id);
+
+static ssize_t nvdimm_handle_show(struct device *dev,
+				  struct device_attribute *attr, char *buf)
+{
+	struct nvdimm *nvdimm = to_nvdimm(dev);
+	struct ndtest_dimm *dimm = nvdimm_provider_data(nvdimm);
+
+	return sprintf(buf, "%#x\n", dimm->handle);
+}
+
+static struct device_attribute dev_attr_nvdimm_show_handle =  {
+	.attr	= { .name = "handle", .mode = 0444 },
+	.show	= nvdimm_handle_show,
+};
+
+static ssize_t subsystem_vendor_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	return sprintf(buf, "0x%04x\n", 0);
+}
+static DEVICE_ATTR_RO(subsystem_vendor);
+
+static ssize_t dirty_shutdown_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	return sprintf(buf, "%d\n", 42);
+}
+static DEVICE_ATTR_RO(dirty_shutdown);
+
+static ssize_t formats_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nvdimm *nvdimm = to_nvdimm(dev);
+	struct ndtest_dimm *dimm = nvdimm_provider_data(nvdimm);
+
+	return sprintf(buf, "%d\n", dimm->num_formats);
+}
+static DEVICE_ATTR_RO(formats);
+
+static ssize_t format_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nvdimm *nvdimm = to_nvdimm(dev);
+	struct ndtest_dimm *dimm = nvdimm_provider_data(nvdimm);
+
+	if (dimm->num_formats > 1)
+		return sprintf(buf, "0x201\n");
+
+	return sprintf(buf, "0x101\n");
+}
+static DEVICE_ATTR_RO(format);
+
+static ssize_t format1_show(struct device *dev, struct device_attribute *attr,
+			    char *buf)
+{
+	return sprintf(buf, "0x301\n");
+}
+static DEVICE_ATTR_RO(format1);
+
+static umode_t ndtest_nvdimm_attr_visible(struct kobject *kobj,
+					struct attribute *a, int n)
+{
+	struct device *dev = container_of(kobj, struct device, kobj);
+	struct nvdimm *nvdimm = to_nvdimm(dev);
+	struct ndtest_dimm *dimm = nvdimm_provider_data(nvdimm);
+
+	if (a == &dev_attr_format1.attr && dimm->num_formats <= 1)
+		return 0;
+
+	return a->mode;
+}
+
+static ssize_t flags_show(struct device *dev,
+			  struct device_attribute *attr, char *buf)
+{
+	struct nvdimm *nvdimm = to_nvdimm(dev);
+	struct ndtest_dimm *dimm = nvdimm_provider_data(nvdimm);
+	struct seq_buf s;
+	u64 flags;
+
+	flags = dimm->flags;
+
+	seq_buf_init(&s, buf, PAGE_SIZE);
+	if (flags & PAPR_PMEM_UNARMED_MASK)
+		seq_buf_printf(&s, "not_armed ");
+
+	if (flags & PAPR_PMEM_BAD_SHUTDOWN_MASK)
+		seq_buf_printf(&s, "flush_fail ");
+
+	if (flags & PAPR_PMEM_BAD_RESTORE_MASK)
+		seq_buf_printf(&s, "restore_fail ");
+
+	if (flags & PAPR_PMEM_SAVE_MASK)
+		seq_buf_printf(&s, "save_fail ");
+
+	if (flags & PAPR_PMEM_SMART_EVENT_MASK)
+		seq_buf_printf(&s, "smart_notify ");
+
+
+	if (seq_buf_used(&s))
+		seq_buf_printf(&s, "\n");
+
+	return seq_buf_used(&s);
+}
+static DEVICE_ATTR_RO(flags);
+
+static struct attribute *ndtest_nvdimm_attributes[] = {
+	&dev_attr_nvdimm_show_handle.attr,
+	&dev_attr_vendor.attr,
+	&dev_attr_id.attr,
+	&dev_attr_phys_id.attr,
+	&dev_attr_subsystem_vendor.attr,
+	&dev_attr_dirty_shutdown.attr,
+	&dev_attr_formats.attr,
+	&dev_attr_format.attr,
+	&dev_attr_format1.attr,
+	&dev_attr_flags.attr,
+	NULL,
+};
+
+static const struct attribute_group ndtest_nvdimm_attribute_group = {
+	.name = "papr",
+	.attrs = ndtest_nvdimm_attributes,
+	.is_visible = ndtest_nvdimm_attr_visible,
+};
+
+static const struct attribute_group *ndtest_nvdimm_attribute_groups[] = {
+	&ndtest_nvdimm_attribute_group,
+	NULL,
+};
+
+static int ndtest_dimm_register(struct ndtest_priv *priv,
+				struct ndtest_dimm *dimm, int id)
+{
+	struct device *dev = &priv->pdev.dev;
+	unsigned long dimm_flags = dimm->flags;
+
+	if (dimm->num_formats > 1) {
+		set_bit(NDD_ALIASING, &dimm_flags);
+		set_bit(NDD_LABELING, &dimm_flags);
+	}
+
+	if (dimm->flags & PAPR_PMEM_UNARMED_MASK)
+		set_bit(NDD_UNARMED, &dimm_flags);
+
+	dimm->nvdimm = nvdimm_create(priv->bus, dimm,
+				    ndtest_nvdimm_attribute_groups, dimm_flags,
+				    NDTEST_SCM_DIMM_CMD_MASK, 0, NULL);
+	if (!dimm->nvdimm) {
+		dev_err(dev, "Error creating DIMM object for %pOF\n", priv->dn);
+		return -ENXIO;
+	}
+
+	dimm->dev = device_create_with_groups(ndtest_dimm_class,
+					     &priv->pdev.dev,
+					     0, dimm, dimm_attribute_groups,
+					     "test_dimm%d", id);
+	if (!dimm->dev) {
+		pr_err("Could not create dimm device attributes\n");
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static int ndtest_nvdimm_init(struct ndtest_priv *p)
+{
+	struct ndtest_dimm *d;
+	void *res;
+	int i, id;
+
+	for (i = 0; i < p->config->dimm_count; i++) {
+		d = &p->config->dimms[i];
+		d->id = id = p->config->dimm_start + i;
+		res = ndtest_alloc_resource(p, LABEL_SIZE, NULL);
+		if (!res)
+			return -ENOMEM;
+
+		d->label_area = res;
+		sprintf(d->label_area, "label%d", id);
+		d->config_size = LABEL_SIZE;
+
+		if (!ndtest_alloc_resource(p, d->size,
+					   &p->dimm_dma[id]))
+			return -ENOMEM;
+
+		if (!ndtest_alloc_resource(p, LABEL_SIZE,
+					   &p->label_dma[id]))
+			return -ENOMEM;
+
+		if (!ndtest_alloc_resource(p, LABEL_SIZE,
+					   &p->dcr_dma[id]))
+			return -ENOMEM;
+
+		d->address = p->dimm_dma[id];
+
+		ndtest_dimm_register(p, d, id);
+	}
+
+	return 0;
+}
+
+static ssize_t compatible_show(struct device *dev,
+			       struct device_attribute *attr, char *buf)
+{
+	return sprintf(buf, "nvdimm_test");
+}
+static DEVICE_ATTR_RO(compatible);
+
+static struct attribute *of_node_attributes[] = {
+	&dev_attr_compatible.attr,
+	NULL
+};
+
+static const struct attribute_group of_node_attribute_group = {
+	.name = "of_node",
+	.attrs = of_node_attributes,
+};
+
+static const struct attribute_group *ndtest_attribute_groups[] = {
+	&of_node_attribute_group,
+	NULL,
+};
+
+static int ndtest_bus_register(struct ndtest_priv *p)
+{
+	p->config = &bus_configs[p->pdev.id];
+
+	p->bus_desc.ndctl = ndtest_ctl;
+	p->bus_desc.module = THIS_MODULE;
+	p->bus_desc.provider_name = NULL;
+	p->bus_desc.attr_groups = ndtest_attribute_groups;
+
+	p->bus = nvdimm_bus_register(&p->pdev.dev, &p->bus_desc);
+	if (!p->bus) {
+		dev_err(&p->pdev.dev, "Error creating nvdimm bus %pOF\n", p->dn);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static int ndtest_remove(struct platform_device *pdev)
+{
+	struct ndtest_priv *p = to_ndtest_priv(&pdev->dev);
+
+	nvdimm_bus_unregister(p->bus);
+	return 0;
+}
+
+static int ndtest_probe(struct platform_device *pdev)
+{
+	struct ndtest_priv *p;
+	int rc;
+
+	p = to_ndtest_priv(&pdev->dev);
+	if (ndtest_bus_register(p))
+		return -ENOMEM;
+
+	p->dcr_dma = devm_kcalloc(&p->pdev.dev, NUM_DCR,
+				 sizeof(dma_addr_t), GFP_KERNEL);
+	p->label_dma = devm_kcalloc(&p->pdev.dev, NUM_DCR,
+				   sizeof(dma_addr_t), GFP_KERNEL);
+	p->dimm_dma = devm_kcalloc(&p->pdev.dev, NUM_DCR,
+				  sizeof(dma_addr_t), GFP_KERNEL);
+
+	rc = ndtest_nvdimm_init(p);
+	if (rc)
+		goto err;
+
+	rc = ndtest_init_regions(p);
+	if (rc)
+		goto err;
+
+	rc = devm_add_action_or_reset(&pdev->dev, put_dimms, p);
+	if (rc)
+		goto err;
+
+	platform_set_drvdata(pdev, p);
+
+	return 0;
+
+err:
+	pr_err("%s:%d Failed nvdimm init\n", __func__, __LINE__);
+	return rc;
+}
+
+static const struct platform_device_id ndtest_id[] = {
+	{ KBUILD_MODNAME },
+	{ },
+};
+
+static struct platform_driver ndtest_driver = {
+	.probe = ndtest_probe,
+	.remove = ndtest_remove,
+	.driver = {
+		.name = KBUILD_MODNAME,
+	},
+	.id_table = ndtest_id,
+};
+
+static void ndtest_release(struct device *dev)
+{
+	struct ndtest_priv *p = to_ndtest_priv(dev);
+
+	kfree(p);
+}
+
+static void cleanup_devices(void)
+{
+	int i;
+
+	for (i = 0; i < NUM_INSTANCES; i++)
+		if (instances[i])
+			platform_device_unregister(&instances[i]->pdev);
+
+	nfit_test_teardown();
+
+	if (ndtest_pool)
+		gen_pool_destroy(ndtest_pool);
+
+
+	if (ndtest_dimm_class)
+		class_destroy(ndtest_dimm_class);
+}
+
+static __init int ndtest_init(void)
+{
+	int rc, i;
+
+	pmem_test();
+	libnvdimm_test();
+	device_dax_test();
+	dax_pmem_test();
+	dax_pmem_core_test();
+#ifdef CONFIG_DEV_DAX_PMEM_COMPAT
+	dax_pmem_compat_test();
+#endif
+
+	nfit_test_setup(ndtest_resource_lookup, NULL);
+
+	ndtest_dimm_class = class_create(THIS_MODULE, "nfit_test_dimm");
+	if (IS_ERR(ndtest_dimm_class)) {
+		rc = PTR_ERR(ndtest_dimm_class);
+		goto err_register;
+	}
+
+	ndtest_pool = gen_pool_create(ilog2(SZ_4M), NUMA_NO_NODE);
+	if (!ndtest_pool) {
+		rc = -ENOMEM;
+		goto err_register;
+	}
+
+	if (gen_pool_add(ndtest_pool, SZ_4G, SZ_4G, NUMA_NO_NODE)) {
+		rc = -ENOMEM;
+		goto err_register;
+	}
+
+	/* Each instance can be taken as a bus, which can have multiple dimms */
+	for (i = 0; i < NUM_INSTANCES; i++) {
+		struct ndtest_priv *priv;
+		struct platform_device *pdev;
+
+		priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+		if (!priv) {
+			rc = -ENOMEM;
+			goto err_register;
+		}
+
+		INIT_LIST_HEAD(&priv->resources);
+		pdev = &priv->pdev;
+		pdev->name = KBUILD_MODNAME;
+		pdev->id = i;
+		pdev->dev.release = ndtest_release;
+		rc = platform_device_register(pdev);
+		if (rc) {
+			put_device(&pdev->dev);
+			goto err_register;
+		}
+		get_device(&pdev->dev);
+
+		instances[i] = priv;
+	}
+
+	rc = platform_driver_register(&ndtest_driver);
+	if (rc)
+		goto err_register;
+
+	return 0;
+
+err_register:
+	pr_err("Error registering platform device\n");
+	cleanup_devices();
+
+	return rc;
+}
+
+static __exit void ndtest_exit(void)
+{
+	cleanup_devices();
+	platform_driver_unregister(&ndtest_driver);
+}
+
+module_init(ndtest_init);
+module_exit(ndtest_exit);
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("IBM Corporation");
diff --git a/tools/testing/nvdimm/test/ndtest.h b/tools/testing/nvdimm/test/ndtest.h
new file mode 100644
index 000000000000..2c54c9cbb90c
--- /dev/null
+++ b/tools/testing/nvdimm/test/ndtest.h
@@ -0,0 +1,109 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef NDTEST_H
+#define NDTEST_H
+
+#include <linux/platform_device.h>
+#include <linux/libnvdimm.h>
+
+/* SCM device is unable to persist memory contents */
+#define PAPR_PMEM_UNARMED                   (1ULL << (63 - 0))
+/* SCM device failed to persist memory contents */
+#define PAPR_PMEM_SHUTDOWN_DIRTY            (1ULL << (63 - 1))
+/* SCM device contents are not persisted from previous IPL */
+#define PAPR_PMEM_EMPTY                     (1ULL << (63 - 3))
+#define PAPR_PMEM_HEALTH_CRITICAL           (1ULL << (63 - 4))
+/* SCM device will be garded off next IPL due to failure */
+#define PAPR_PMEM_HEALTH_FATAL              (1ULL << (63 - 5))
+/* SCM contents cannot persist due to current platform health status */
+#define PAPR_PMEM_HEALTH_UNHEALTHY          (1ULL << (63 - 6))
+
+/* Bits status indicators for health bitmap indicating unarmed dimm */
+#define PAPR_PMEM_UNARMED_MASK (PAPR_PMEM_UNARMED |		\
+				PAPR_PMEM_HEALTH_UNHEALTHY)
+
+#define PAPR_PMEM_SAVE_FAILED                (1ULL << (63 - 10))
+
+/* Bits status indicators for health bitmap indicating unflushed dimm */
+#define PAPR_PMEM_BAD_SHUTDOWN_MASK (PAPR_PMEM_SHUTDOWN_DIRTY)
+
+/* Bits status indicators for health bitmap indicating unrestored dimm */
+#define PAPR_PMEM_BAD_RESTORE_MASK  (PAPR_PMEM_EMPTY)
+
+/* Bit status indicators for smart event notification */
+#define PAPR_PMEM_SMART_EVENT_MASK (PAPR_PMEM_HEALTH_CRITICAL | \
+				    PAPR_PMEM_HEALTH_FATAL |	\
+				    PAPR_PMEM_HEALTH_UNHEALTHY)
+
+#define PAPR_PMEM_SAVE_MASK                (PAPR_PMEM_SAVE_FAILED)
+
+struct ndtest_config;
+
+struct ndtest_priv {
+	struct platform_device pdev;
+	struct device_node *dn;
+	struct list_head resources;
+	struct nvdimm_bus_descriptor bus_desc;
+	struct nvdimm_bus *bus;
+	struct ndtest_config *config;
+
+	dma_addr_t *dcr_dma;
+	dma_addr_t *label_dma;
+	dma_addr_t *dimm_dma;
+};
+
+struct ndtest_blk_mmio {
+	void __iomem *base;
+	u64 size;
+	u64 base_offset;
+	u32 line_size;
+	u32 num_lines;
+	u32 table_size;
+};
+
+struct ndtest_dimm {
+	struct device *dev;
+	struct nvdimm *nvdimm;
+	struct ndtest_blk_mmio *mmio;
+	struct nd_region *blk_region;
+
+	dma_addr_t address;
+	unsigned long long flags;
+	unsigned long config_size;
+	void *label_area;
+	char *uuid_str;
+
+	unsigned int size;
+	unsigned int handle;
+	unsigned int fail_cmd;
+	unsigned int physical_id;
+	unsigned int num_formats;
+	int id;
+	int fail_cmd_code;
+	u8 no_alias;
+};
+
+struct ndtest_mapping {
+	u64 start;
+	u64 size;
+	u8 position;
+	u8 dimm;
+};
+
+struct ndtest_region {
+	struct nd_region *region;
+	struct ndtest_mapping *mapping;
+	u64 size;
+	u8 type;
+	u8 num_mappings;
+	u8 range_index;
+};
+
+struct ndtest_config {
+	struct ndtest_dimm *dimms;
+	struct ndtest_region *regions;
+	unsigned int dimm_count;
+	unsigned int dimm_start;
+	u8 num_regions;
+};
+
+#endif /* NDTEST_H */
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index afbab4aeef3c..8a917cb4426a 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -77,8 +77,10 @@ TARGETS += zram
 TARGETS_HOTPLUG = cpu-hotplug
 TARGETS_HOTPLUG += memory-hotplug
 
-# User can optionally provide a TARGETS skiplist.
-SKIP_TARGETS ?=
+# User can optionally provide a TARGETS skiplist.  By default we skip
+# BPF since it has cutting edge build time dependencies which require
+# more effort to install.
+SKIP_TARGETS ?= bpf
 ifneq ($(SKIP_TARGETS),)
 	TMP := $(filter-out $(SKIP_TARGETS), $(TARGETS))
 	override TARGETS := $(TMP)
diff --git a/tools/testing/selftests/arm64/fp/fpsimd-test.S b/tools/testing/selftests/arm64/fp/fpsimd-test.S
index 1c5556bdd11d..0dbd594c2747 100644
--- a/tools/testing/selftests/arm64/fp/fpsimd-test.S
+++ b/tools/testing/selftests/arm64/fp/fpsimd-test.S
@@ -457,7 +457,7 @@ function barf
 	mov	x11, x1	// actual data
 	mov	x12, x2	// data size
 
-	puts	"Mistatch: PID="
+	puts	"Mismatch: PID="
 	mov	x0, x20
 	bl	putdec
 	puts	", iteration="
diff --git a/tools/testing/selftests/arm64/fp/sve-test.S b/tools/testing/selftests/arm64/fp/sve-test.S
index f95074c9b48b..9210691aa998 100644
--- a/tools/testing/selftests/arm64/fp/sve-test.S
+++ b/tools/testing/selftests/arm64/fp/sve-test.S
@@ -625,7 +625,7 @@ function barf
 	mov	x11, x1	// actual data
 	mov	x12, x2	// data size
 
-	puts	"Mistatch: PID="
+	puts	"Mismatch: PID="
 	mov	x0, x20
 	bl	putdec
 	puts	", iteration="
diff --git a/tools/testing/selftests/bpf/prog_tests/test_local_storage.c b/tools/testing/selftests/bpf/prog_tests/test_local_storage.c
index c0fe73a17ed1..3bfcf00c0a67 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_local_storage.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_local_storage.c
@@ -34,61 +34,6 @@ struct storage {
 	struct bpf_spin_lock lock;
 };
 
-/* Copies an rm binary to a temp file. dest is a mkstemp template */
-static int copy_rm(char *dest)
-{
-	int fd_in, fd_out = -1, ret = 0;
-	struct stat stat;
-	char *buf = NULL;
-
-	fd_in = open("/bin/rm", O_RDONLY);
-	if (fd_in < 0)
-		return -errno;
-
-	fd_out = mkstemp(dest);
-	if (fd_out < 0) {
-		ret = -errno;
-		goto out;
-	}
-
-	ret = fstat(fd_in, &stat);
-	if (ret == -1) {
-		ret = -errno;
-		goto out;
-	}
-
-	buf = malloc(stat.st_blksize);
-	if (!buf) {
-		ret = -errno;
-		goto out;
-	}
-
-	while (ret = read(fd_in, buf, stat.st_blksize), ret > 0) {
-		ret = write(fd_out, buf, ret);
-		if (ret < 0) {
-			ret = -errno;
-			goto out;
-
-		}
-	}
-	if (ret < 0) {
-		ret = -errno;
-		goto out;
-
-	}
-
-	/* Set executable permission on the copied file */
-	ret = chmod(dest, 0100);
-	if (ret == -1)
-		ret = -errno;
-
-out:
-	free(buf);
-	close(fd_in);
-	close(fd_out);
-	return ret;
-}
-
 /* Fork and exec the provided rm binary and return the exit code of the
  * forked process and its pid.
  */
@@ -168,9 +113,11 @@ static bool check_syscall_operations(int map_fd, int obj_fd)
 
 void test_test_local_storage(void)
 {
-	char tmp_exec_path[PATH_MAX] = "/tmp/copy_of_rmXXXXXX";
+	char tmp_dir_path[64] = "/tmp/local_storageXXXXXX";
 	int err, serv_sk = -1, task_fd = -1, rm_fd = -1;
 	struct local_storage *skel = NULL;
+	char tmp_exec_path[64];
+	char cmd[256];
 
 	skel = local_storage__open_and_load();
 	if (CHECK(!skel, "skel_load", "lsm skeleton failed\n"))
@@ -189,18 +136,24 @@ void test_test_local_storage(void)
 				      task_fd))
 		goto close_prog;
 
-	err = copy_rm(tmp_exec_path);
-	if (CHECK(err < 0, "copy_rm", "err %d errno %d\n", err, errno))
+	if (CHECK(!mkdtemp(tmp_dir_path), "mkdtemp",
+		  "unable to create tmpdir: %d\n", errno))
 		goto close_prog;
 
+	snprintf(tmp_exec_path, sizeof(tmp_exec_path), "%s/copy_of_rm",
+		 tmp_dir_path);
+	snprintf(cmd, sizeof(cmd), "cp /bin/rm %s", tmp_exec_path);
+	if (CHECK_FAIL(system(cmd)))
+		goto close_prog_rmdir;
+
 	rm_fd = open(tmp_exec_path, O_RDONLY);
 	if (CHECK(rm_fd < 0, "open", "failed to open %s err:%d, errno:%d",
 		  tmp_exec_path, rm_fd, errno))
-		goto close_prog;
+		goto close_prog_rmdir;
 
 	if (!check_syscall_operations(bpf_map__fd(skel->maps.inode_storage_map),
 				      rm_fd))
-		goto close_prog;
+		goto close_prog_rmdir;
 
 	/* Sets skel->bss->monitored_pid to the pid of the forked child
 	 * forks a child process that executes tmp_exec_path and tries to
@@ -209,33 +162,36 @@ void test_test_local_storage(void)
 	 */
 	err = run_self_unlink(&skel->bss->monitored_pid, tmp_exec_path);
 	if (CHECK(err != EPERM, "run_self_unlink", "err %d want EPERM\n", err))
-		goto close_prog_unlink;
+		goto close_prog_rmdir;
 
 	/* Set the process being monitored to be the current process */
 	skel->bss->monitored_pid = getpid();
 
-	/* Remove the temporary created executable */
-	err = unlink(tmp_exec_path);
-	if (CHECK(err != 0, "unlink", "unable to unlink %s: %d", tmp_exec_path,
-		  errno))
-		goto close_prog_unlink;
+	/* Move copy_of_rm to a new location so that it triggers the
+	 * inode_rename LSM hook with a new_dentry that has a NULL inode ptr.
+	 */
+	snprintf(cmd, sizeof(cmd), "mv %s/copy_of_rm %s/check_null_ptr",
+		 tmp_dir_path, tmp_dir_path);
+	if (CHECK_FAIL(system(cmd)))
+		goto close_prog_rmdir;
 
 	CHECK(skel->data->inode_storage_result != 0, "inode_storage_result",
 	      "inode_local_storage not set\n");
 
 	serv_sk = start_server(AF_INET6, SOCK_STREAM, NULL, 0, 0);
 	if (CHECK(serv_sk < 0, "start_server", "failed to start server\n"))
-		goto close_prog;
+		goto close_prog_rmdir;
 
 	CHECK(skel->data->sk_storage_result != 0, "sk_storage_result",
 	      "sk_local_storage not set\n");
 
 	if (!check_syscall_operations(bpf_map__fd(skel->maps.sk_storage_map),
 				      serv_sk))
-		goto close_prog;
+		goto close_prog_rmdir;
 
-close_prog_unlink:
-	unlink(tmp_exec_path);
+close_prog_rmdir:
+	snprintf(cmd, sizeof(cmd), "rm -rf %s", tmp_dir_path);
+	system(cmd);
 close_prog:
 	close(serv_sk);
 	close(rm_fd);
diff --git a/tools/testing/selftests/bpf/progs/local_storage.c b/tools/testing/selftests/bpf/progs/local_storage.c
index 3e3de130f28f..95868bc7ada9 100644
--- a/tools/testing/selftests/bpf/progs/local_storage.c
+++ b/tools/testing/selftests/bpf/progs/local_storage.c
@@ -50,7 +50,6 @@ int BPF_PROG(unlink_hook, struct inode *dir, struct dentry *victim)
 	__u32 pid = bpf_get_current_pid_tgid() >> 32;
 	struct local_storage *storage;
 	bool is_self_unlink;
-	int err;
 
 	if (pid != monitored_pid)
 		return 0;
@@ -66,8 +65,27 @@ int BPF_PROG(unlink_hook, struct inode *dir, struct dentry *victim)
 			return -EPERM;
 	}
 
-	storage = bpf_inode_storage_get(&inode_storage_map, victim->d_inode, 0,
-					BPF_LOCAL_STORAGE_GET_F_CREATE);
+	return 0;
+}
+
+SEC("lsm/inode_rename")
+int BPF_PROG(inode_rename, struct inode *old_dir, struct dentry *old_dentry,
+	     struct inode *new_dir, struct dentry *new_dentry,
+	     unsigned int flags)
+{
+	__u32 pid = bpf_get_current_pid_tgid() >> 32;
+	struct local_storage *storage;
+	int err;
+
+	/* new_dentry->d_inode can be NULL when the inode is renamed to a file
+	 * that did not exist before. The helper should be able to handle this
+	 * NULL pointer.
+	 */
+	bpf_inode_storage_get(&inode_storage_map, new_dentry->d_inode, 0,
+			      BPF_LOCAL_STORAGE_GET_F_CREATE);
+
+	storage = bpf_inode_storage_get(&inode_storage_map, old_dentry->d_inode,
+					0, 0);
 	if (!storage)
 		return 0;
 
@@ -76,7 +94,7 @@ int BPF_PROG(unlink_hook, struct inode *dir, struct dentry *victim)
 		inode_storage_result = -1;
 	bpf_spin_unlock(&storage->lock);
 
-	err = bpf_inode_storage_delete(&inode_storage_map, victim->d_inode);
+	err = bpf_inode_storage_delete(&inode_storage_map, old_dentry->d_inode);
 	if (!err)
 		inode_storage_result = err;
 
@@ -133,37 +151,18 @@ int BPF_PROG(socket_post_create, struct socket *sock, int family, int type,
 	return 0;
 }
 
-SEC("lsm/file_open")
-int BPF_PROG(file_open, struct file *file)
-{
-	__u32 pid = bpf_get_current_pid_tgid() >> 32;
-	struct local_storage *storage;
-
-	if (pid != monitored_pid)
-		return 0;
-
-	if (!file->f_inode)
-		return 0;
-
-	storage = bpf_inode_storage_get(&inode_storage_map, file->f_inode, 0,
-					BPF_LOCAL_STORAGE_GET_F_CREATE);
-	if (!storage)
-		return 0;
-
-	bpf_spin_lock(&storage->lock);
-	storage->value = DUMMY_STORAGE_VALUE;
-	bpf_spin_unlock(&storage->lock);
-	return 0;
-}
-
 /* This uses the local storage to remember the inode of the binary that a
  * process was originally executing.
  */
 SEC("lsm/bprm_committed_creds")
 void BPF_PROG(exec, struct linux_binprm *bprm)
 {
+	__u32 pid = bpf_get_current_pid_tgid() >> 32;
 	struct local_storage *storage;
 
+	if (pid != monitored_pid)
+		return;
+
 	storage = bpf_task_storage_get(&task_storage_map,
 				       bpf_get_current_task_btf(), 0,
 				       BPF_LOCAL_STORAGE_GET_F_CREATE);
@@ -172,4 +171,13 @@ void BPF_PROG(exec, struct linux_binprm *bprm)
 		storage->exec_inode = bprm->file->f_inode;
 		bpf_spin_unlock(&storage->lock);
 	}
+
+	storage = bpf_inode_storage_get(&inode_storage_map, bprm->file->f_inode,
+					0, BPF_LOCAL_STORAGE_GET_F_CREATE);
+	if (!storage)
+		return;
+
+	bpf_spin_lock(&storage->lock);
+	storage->value = DUMMY_STORAGE_VALUE;
+	bpf_spin_unlock(&storage->lock);
 }
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 777a81404fdb..f8569f04064b 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -50,7 +50,7 @@
 #define MAX_INSNS	BPF_MAXINSNS
 #define MAX_TEST_INSNS	1000000
 #define MAX_FIXUPS	8
-#define MAX_NR_MAPS	20
+#define MAX_NR_MAPS	21
 #define MAX_TEST_RUNS	8
 #define POINTER_VALUE	0xcafe4all
 #define TEST_DATA_LEN	64
@@ -87,6 +87,7 @@ struct bpf_test {
 	int fixup_sk_storage_map[MAX_FIXUPS];
 	int fixup_map_event_output[MAX_FIXUPS];
 	int fixup_map_reuseport_array[MAX_FIXUPS];
+	int fixup_map_ringbuf[MAX_FIXUPS];
 	const char *errstr;
 	const char *errstr_unpriv;
 	uint32_t insn_processed;
@@ -640,6 +641,7 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type,
 	int *fixup_sk_storage_map = test->fixup_sk_storage_map;
 	int *fixup_map_event_output = test->fixup_map_event_output;
 	int *fixup_map_reuseport_array = test->fixup_map_reuseport_array;
+	int *fixup_map_ringbuf = test->fixup_map_ringbuf;
 
 	if (test->fill_helper) {
 		test->fill_insns = calloc(MAX_TEST_INSNS, sizeof(struct bpf_insn));
@@ -817,6 +819,14 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type,
 			fixup_map_reuseport_array++;
 		} while (*fixup_map_reuseport_array);
 	}
+	if (*fixup_map_ringbuf) {
+		map_fds[20] = create_map(BPF_MAP_TYPE_RINGBUF, 0,
+					   0, 4096);
+		do {
+			prog[*fixup_map_ringbuf].imm = map_fds[20];
+			fixup_map_ringbuf++;
+		} while (*fixup_map_ringbuf);
+	}
 }
 
 struct libcap {
diff --git a/tools/testing/selftests/bpf/verifier/spill_fill.c b/tools/testing/selftests/bpf/verifier/spill_fill.c
index 45d43bf82f26..0b943897aaf6 100644
--- a/tools/testing/selftests/bpf/verifier/spill_fill.c
+++ b/tools/testing/selftests/bpf/verifier/spill_fill.c
@@ -29,6 +29,36 @@
 	.result_unpriv = ACCEPT,
 },
 {
+	"check valid spill/fill, ptr to mem",
+	.insns = {
+	/* reserve 8 byte ringbuf memory */
+	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_MOV64_IMM(BPF_REG_2, 8),
+	BPF_MOV64_IMM(BPF_REG_3, 0),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ringbuf_reserve),
+	/* store a pointer to the reserved memory in R6 */
+	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+	/* check whether the reservation was successful */
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
+	/* spill R6(mem) into the stack */
+	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_6, -8),
+	/* fill it back in R7 */
+	BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_10, -8),
+	/* should be able to access *(R7) = 0 */
+	BPF_ST_MEM(BPF_DW, BPF_REG_7, 0, 0),
+	/* submit the reserved ringbuf memory */
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
+	BPF_MOV64_IMM(BPF_REG_2, 0),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ringbuf_submit),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_ringbuf = { 1 },
+	.result = ACCEPT,
+	.result_unpriv = ACCEPT,
+},
+{
 	"check corrupted spill/fill",
 	.insns = {
 	/* spill R1(ctx) into stack */
diff --git a/tools/testing/selftests/dma/dma_map_benchmark.c b/tools/testing/selftests/dma/dma_map_benchmark.c
index 7065163a8388..537d65968c48 100644
--- a/tools/testing/selftests/dma/dma_map_benchmark.c
+++ b/tools/testing/selftests/dma/dma_map_benchmark.c
@@ -6,6 +6,7 @@
 #include <fcntl.h>
 #include <stdio.h>
 #include <stdlib.h>
+#include <string.h>
 #include <unistd.h>
 #include <sys/ioctl.h>
 #include <sys/mman.h>
@@ -35,7 +36,7 @@ struct map_benchmark {
 	__s32 node; /* which numa node this benchmark will run on */
 	__u32 dma_bits; /* DMA addressing capability */
 	__u32 dma_dir; /* DMA data direction */
-	__u64 expansion[10];	/* For future use */
+	__u8 expansion[84];	/* For future use */
 };
 
 int main(int argc, char **argv)
@@ -102,6 +103,7 @@ int main(int argc, char **argv)
 		exit(1);
 	}
 
+	memset(&map, 0, sizeof(map));
 	map.seconds = seconds;
 	map.threads = threads;
 	map.node = node;
diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh
index 84205c3a55eb..2b5707738609 100755
--- a/tools/testing/selftests/net/fib_tests.sh
+++ b/tools/testing/selftests/net/fib_tests.sh
@@ -1055,7 +1055,6 @@ ipv6_addr_metric_test()
 
 	check_route6 "2001:db8:104::1 dev dummy2 proto kernel metric 260"
 	log_test $? 0 "Set metric with peer route on local side"
-	log_test $? 0 "User specified metric on local address"
 	check_route6 "2001:db8:104::2 dev dummy2 proto kernel metric 260"
 	log_test $? 0 "Set metric with peer route on peer side"
 
diff --git a/tools/testing/selftests/net/forwarding/router_mpath_nh.sh b/tools/testing/selftests/net/forwarding/router_mpath_nh.sh
index 388e4492b81b..76efb1f8375e 100755
--- a/tools/testing/selftests/net/forwarding/router_mpath_nh.sh
+++ b/tools/testing/selftests/net/forwarding/router_mpath_nh.sh
@@ -203,7 +203,7 @@ multipath4_test()
 	t0_rp12=$(link_stats_tx_packets_get $rp12)
 	t0_rp13=$(link_stats_tx_packets_get $rp13)
 
-	ip vrf exec vrf-h1 $MZ -q -p 64 -A 192.0.2.2 -B 198.51.100.2 \
+	ip vrf exec vrf-h1 $MZ $h1 -q -p 64 -A 192.0.2.2 -B 198.51.100.2 \
 		-d 1msec -t udp "sp=1024,dp=0-32768"
 
 	t1_rp12=$(link_stats_tx_packets_get $rp12)
diff --git a/tools/testing/selftests/net/forwarding/router_multipath.sh b/tools/testing/selftests/net/forwarding/router_multipath.sh
index 79a209927962..464821c587a5 100755
--- a/tools/testing/selftests/net/forwarding/router_multipath.sh
+++ b/tools/testing/selftests/net/forwarding/router_multipath.sh
@@ -178,7 +178,7 @@ multipath4_test()
        t0_rp12=$(link_stats_tx_packets_get $rp12)
        t0_rp13=$(link_stats_tx_packets_get $rp13)
 
-       ip vrf exec vrf-h1 $MZ -q -p 64 -A 192.0.2.2 -B 198.51.100.2 \
+       ip vrf exec vrf-h1 $MZ $h1 -q -p 64 -A 192.0.2.2 -B 198.51.100.2 \
 	       -d 1msec -t udp "sp=1024,dp=0-32768"
 
        t1_rp12=$(link_stats_tx_packets_get $rp12)
diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c
index cb0d1890a860..e0088c2d38a5 100644
--- a/tools/testing/selftests/net/tls.c
+++ b/tools/testing/selftests/net/tls.c
@@ -103,8 +103,8 @@ FIXTURE(tls)
 
 FIXTURE_VARIANT(tls)
 {
-	u16 tls_version;
-	u16 cipher_type;
+	uint16_t tls_version;
+	uint16_t cipher_type;
 };
 
 FIXTURE_VARIANT_ADD(tls, 12_gcm)
diff --git a/tools/testing/selftests/net/xfrm_policy.sh b/tools/testing/selftests/net/xfrm_policy.sh
index 7a1bf94c5bd3..bdf450eaf60c 100755
--- a/tools/testing/selftests/net/xfrm_policy.sh
+++ b/tools/testing/selftests/net/xfrm_policy.sh
@@ -202,7 +202,7 @@ check_xfrm() {
 	# 1: iptables -m policy rule count != 0
 	rval=$1
 	ip=$2
-	lret=0
+	local lret=0
 
 	ip netns exec ns1 ping -q -c 1 10.0.2.$ip > /dev/null
 
@@ -287,6 +287,47 @@ check_hthresh_repeat()
 	return 0
 }
 
+# insert non-overlapping policies in a random order and check that
+# all of them can be fetched using the traffic selectors.
+check_random_order()
+{
+	local ns=$1
+	local log=$2
+
+	for i in $(seq 100); do
+		ip -net $ns xfrm policy flush
+		for j in $(seq 0 16 255 | sort -R); do
+			ip -net $ns xfrm policy add dst $j.0.0.0/24 dir out priority 10 action allow
+		done
+		for j in $(seq 0 16 255); do
+			if ! ip -net $ns xfrm policy get dst $j.0.0.0/24 dir out > /dev/null; then
+				echo "FAIL: $log" 1>&2
+				return 1
+			fi
+		done
+	done
+
+	for i in $(seq 100); do
+		ip -net $ns xfrm policy flush
+		for j in $(seq 0 16 255 | sort -R); do
+			local addr=$(printf "e000:0000:%02x00::/56" $j)
+			ip -net $ns xfrm policy add dst $addr dir out priority 10 action allow
+		done
+		for j in $(seq 0 16 255); do
+			local addr=$(printf "e000:0000:%02x00::/56" $j)
+			if ! ip -net $ns xfrm policy get dst $addr dir out > /dev/null; then
+				echo "FAIL: $log" 1>&2
+				return 1
+			fi
+		done
+	done
+
+	ip -net $ns xfrm policy flush
+
+	echo "PASS: $log"
+	return 0
+}
+
 #check for needed privileges
 if [ "$(id -u)" -ne 0 ];then
 	echo "SKIP: Need root privileges"
@@ -438,6 +479,8 @@ check_exceptions "exceptions and block policies after htresh change to normal"
 
 check_hthresh_repeat "policies with repeated htresh change"
 
+check_random_order ns3 "policies inserted in random order"
+
 for i in 1 2 3 4;do ip netns del ns$i;done
 
 exit $ret
diff --git a/tools/testing/selftests/netfilter/nft_conntrack_helper.sh b/tools/testing/selftests/netfilter/nft_conntrack_helper.sh
index edf0a48da6bf..bf6b9626c7dd 100755
--- a/tools/testing/selftests/netfilter/nft_conntrack_helper.sh
+++ b/tools/testing/selftests/netfilter/nft_conntrack_helper.sh
@@ -94,7 +94,13 @@ check_for_helper()
 	local message=$2
 	local port=$3
 
-	ip netns exec ${netns} conntrack -L -p tcp --dport $port 2> /dev/null |grep -q 'helper=ftp'
+	if echo $message |grep -q 'ipv6';then
+		local family="ipv6"
+	else
+		local family="ipv4"
+	fi
+
+	ip netns exec ${netns} conntrack -L -f $family -p tcp --dport $port 2> /dev/null |grep -q 'helper=ftp'
 	if [ $? -ne 0 ] ; then
 		echo "FAIL: ${netns} did not show attached helper $message" 1>&2
 		ret=1
@@ -111,8 +117,8 @@ test_helper()
 
 	sleep 3 | ip netns exec ${ns2} nc -w 2 -l -p $port > /dev/null &
 
-	sleep 1
 	sleep 1 | ip netns exec ${ns1} nc -w 2 10.0.1.2 $port > /dev/null &
+	sleep 1
 
 	check_for_helper "$ns1" "ip $msg" $port
 	check_for_helper "$ns2" "ip $msg" $port
@@ -128,8 +134,8 @@ test_helper()
 
 	sleep 3 | ip netns exec ${ns2} nc -w 2 -6 -l -p $port > /dev/null &
 
-	sleep 1
 	sleep 1 | ip netns exec ${ns1} nc -w 2 -6 dead:1::2 $port > /dev/null &
+	sleep 1
 
 	check_for_helper "$ns1" "ipv6 $msg" $port
 	check_for_helper "$ns2" "ipv6 $msg" $port
diff --git a/tools/testing/selftests/powerpc/alignment/alignment_handler.c b/tools/testing/selftests/powerpc/alignment/alignment_handler.c
index cb53a8b777e6..c25cf7cd45e9 100644
--- a/tools/testing/selftests/powerpc/alignment/alignment_handler.c
+++ b/tools/testing/selftests/powerpc/alignment/alignment_handler.c
@@ -443,7 +443,6 @@ int test_alignment_handler_integer(void)
 	LOAD_DFORM_TEST(ldu);
 	LOAD_XFORM_TEST(ldx);
 	LOAD_XFORM_TEST(ldux);
-	LOAD_DFORM_TEST(lmw);
 	STORE_DFORM_TEST(stb);
 	STORE_XFORM_TEST(stbx);
 	STORE_DFORM_TEST(stbu);
@@ -462,7 +461,11 @@ int test_alignment_handler_integer(void)
 	STORE_XFORM_TEST(stdx);
 	STORE_DFORM_TEST(stdu);
 	STORE_XFORM_TEST(stdux);
+
+#ifdef __BIG_ENDIAN__
+	LOAD_DFORM_TEST(lmw);
 	STORE_DFORM_TEST(stmw);
+#endif
 
 	return rc;
 }
diff --git a/tools/testing/selftests/powerpc/mm/pkey_exec_prot.c b/tools/testing/selftests/powerpc/mm/pkey_exec_prot.c
index 9e5c7f3f498a..0af4f02669a1 100644
--- a/tools/testing/selftests/powerpc/mm/pkey_exec_prot.c
+++ b/tools/testing/selftests/powerpc/mm/pkey_exec_prot.c
@@ -290,5 +290,5 @@ static int test(void)
 
 int main(void)
 {
-	test_harness(test, "pkey_exec_prot");
+	return test_harness(test, "pkey_exec_prot");
 }
diff --git a/tools/testing/selftests/powerpc/mm/pkey_siginfo.c b/tools/testing/selftests/powerpc/mm/pkey_siginfo.c
index 4f815d7c1214..2db76e56d4cb 100644
--- a/tools/testing/selftests/powerpc/mm/pkey_siginfo.c
+++ b/tools/testing/selftests/powerpc/mm/pkey_siginfo.c
@@ -329,5 +329,5 @@ static int test(void)
 
 int main(void)
 {
-	test_harness(test, "pkey_siginfo");
+	return test_harness(test, "pkey_siginfo");
 }
diff --git a/tools/testing/selftests/syscall_user_dispatch/sud_benchmark.c b/tools/testing/selftests/syscall_user_dispatch/sud_benchmark.c
index 6689f1183dbf..073a03702ff5 100644
--- a/tools/testing/selftests/syscall_user_dispatch/sud_benchmark.c
+++ b/tools/testing/selftests/syscall_user_dispatch/sud_benchmark.c
@@ -22,6 +22,8 @@
 # define PR_SET_SYSCALL_USER_DISPATCH	59
 # define PR_SYS_DISPATCH_OFF	0
 # define PR_SYS_DISPATCH_ON	1
+# define SYSCALL_DISPATCH_FILTER_ALLOW	0
+# define SYSCALL_DISPATCH_FILTER_BLOCK	1
 #endif
 
 #ifdef __NR_syscalls
@@ -55,8 +57,8 @@ unsigned long trapped_call_count = 0;
 unsigned long native_call_count = 0;
 
 char selector;
-#define SYSCALL_BLOCK   (selector = PR_SYS_DISPATCH_ON)
-#define SYSCALL_UNBLOCK (selector = PR_SYS_DISPATCH_OFF)
+#define SYSCALL_BLOCK   (selector = SYSCALL_DISPATCH_FILTER_BLOCK)
+#define SYSCALL_UNBLOCK (selector = SYSCALL_DISPATCH_FILTER_ALLOW)
 
 #define CALIBRATION_STEP 100000
 #define CALIBRATE_TO_SECS 5
@@ -170,7 +172,7 @@ int main(void)
 	syscall(MAGIC_SYSCALL_1);
 
 #ifdef TEST_BLOCKED_RETURN
-	if (selector == PR_SYS_DISPATCH_OFF) {
+	if (selector == SYSCALL_DISPATCH_FILTER_ALLOW) {
 		fprintf(stderr, "Failed to return with selector blocked.\n");
 		exit(-1);
 	}
diff --git a/tools/testing/selftests/syscall_user_dispatch/sud_test.c b/tools/testing/selftests/syscall_user_dispatch/sud_test.c
index 6498b050ef89..b5d592d4099e 100644
--- a/tools/testing/selftests/syscall_user_dispatch/sud_test.c
+++ b/tools/testing/selftests/syscall_user_dispatch/sud_test.c
@@ -18,6 +18,8 @@
 # define PR_SET_SYSCALL_USER_DISPATCH	59
 # define PR_SYS_DISPATCH_OFF	0
 # define PR_SYS_DISPATCH_ON	1
+# define SYSCALL_DISPATCH_FILTER_ALLOW	0
+# define SYSCALL_DISPATCH_FILTER_BLOCK	1
 #endif
 
 #ifndef SYS_USER_DISPATCH
@@ -30,8 +32,8 @@
 # define MAGIC_SYSCALL_1 (0xff00)  /* Bad Linux syscall number */
 #endif
 
-#define SYSCALL_DISPATCH_ON(x) ((x) = 1)
-#define SYSCALL_DISPATCH_OFF(x) ((x) = 0)
+#define SYSCALL_DISPATCH_ON(x) ((x) = SYSCALL_DISPATCH_FILTER_BLOCK)
+#define SYSCALL_DISPATCH_OFF(x) ((x) = SYSCALL_DISPATCH_FILTER_ALLOW)
 
 /* Test Summary:
  *
@@ -56,7 +58,7 @@
 
 TEST_SIGNAL(dispatch_trigger_sigsys, SIGSYS)
 {
-	char sel = 0;
+	char sel = SYSCALL_DISPATCH_FILTER_ALLOW;
 	struct sysinfo info;
 	int ret;
 
@@ -79,7 +81,7 @@ TEST_SIGNAL(dispatch_trigger_sigsys, SIGSYS)
 
 TEST(bad_prctl_param)
 {
-	char sel = 0;
+	char sel = SYSCALL_DISPATCH_FILTER_ALLOW;
 	int op;
 
 	/* Invalid op */
@@ -220,7 +222,7 @@ TEST_SIGNAL(bad_selector, SIGSYS)
 	sigset_t mask;
 	struct sysinfo info;
 
-	glob_sel = 0;
+	glob_sel = SYSCALL_DISPATCH_FILTER_ALLOW;
 	nr_syscalls_emulated = 0;
 	si_code = 0;
 	si_errno = 0;
@@ -288,7 +290,7 @@ TEST(direct_dispatch_range)
 {
 	int ret = 0;
 	struct sysinfo info;
-	char sel = 0;
+	char sel = SYSCALL_DISPATCH_FILTER_ALLOW;
 
 	/*
 	 * Instead of calculating libc addresses; allow the entire