workqueue: skip the node_nr_active update for non-unbound workqueuesgrafted

apply_wqattrs_commit() updates node_nr_active->max unconditionally.
wq->node_nr_active[] is only allocated for unbound workqueues, so guard
the call before per-cpu workqueues start using this path.

No functional change: only unbound workqueues reach apply_wqattrs_*()
today.

Signed-off-by: Breno Leitao <leitao@debian.org>
Signed-off-by: Tejun Heo <tj@kernel.org>

23 files changed, 3776 insertions, 0 deletions

diff --git a/tools/testing/selftests/futex/Makefile b/tools/testing/selftests/futex/Makefile
new file mode 100644
index 000000000..78ab2cd11
--- /dev/null
+++ b/tools/testing/selftests/futex/Makefile
@@ -0,0 +1,35 @@
+# SPDX-License-Identifier: GPL-2.0
+SUBDIRS := functional
+
+TEST_PROGS := run.sh
+
+include ../lib.mk
+
+all:
+	@for DIR in $(SUBDIRS); do		\
+		BUILD_TARGET=$(OUTPUT)/$$DIR;	\
+		mkdir $$BUILD_TARGET  -p;	\
+		$(MAKE) OUTPUT=$$BUILD_TARGET -C $$DIR $@;\
+		if [ -e $$DIR/$(TEST_PROGS) ]; then \
+			rsync -a $$DIR/$(TEST_PROGS) $$BUILD_TARGET/; \
+		fi \
+	done
+
+override define INSTALL_RULE
+	mkdir -p $(INSTALL_PATH)
+	install -t $(INSTALL_PATH) $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES)
+
+	@for SUBDIR in $(SUBDIRS); do \
+		BUILD_TARGET=$(OUTPUT)/$$SUBDIR;	\
+		mkdir $$BUILD_TARGET  -p;	\
+		$(MAKE) OUTPUT=$$BUILD_TARGET -C $$SUBDIR INSTALL_PATH=$(INSTALL_PATH)/$$SUBDIR install; \
+	done;
+endef
+
+override define CLEAN
+	@for DIR in $(SUBDIRS); do		\
+		BUILD_TARGET=$(OUTPUT)/$$DIR;	\
+		mkdir $$BUILD_TARGET  -p;	\
+		$(MAKE) OUTPUT=$$BUILD_TARGET -C $$DIR $@;\
+	done
+endef
diff --git a/tools/testing/selftests/futex/README b/tools/testing/selftests/futex/README
new file mode 100644
index 000000000..f3926c33e
--- /dev/null
+++ b/tools/testing/selftests/futex/README
@@ -0,0 +1,62 @@
+Futex Test
+==========
+Futex Test is intended to thoroughly test the Linux kernel futex system call
+API.
+
+Functional tests shall test the documented behavior of the futex operation
+code under test. This includes checking for proper behavior under normal use,
+odd corner cases, regression tests, and abject abuse and misuse.
+
+Futextest will also provide example implementation of mutual exclusion
+primitives. These can be used as is in user applications or can serve as
+examples for system libraries. These will likely be added to either a new lib/
+directory or purely as header files under include/, I'm leaning toward the
+latter.
+
+Quick Start
+-----------
+# make
+# ./run.sh
+
+Design and Implementation Goals
+-------------------------------
+o Tests should be as self contained as is practical so as to facilitate sharing
+  the individual tests on mailing list discussions and bug reports.
+o The build system shall remain as simple as possible, avoiding any archive or
+  shared object building and linking.
+o Where possible, any helper functions or other package-wide code shall be
+  implemented in header files, avoiding the need to compile intermediate object
+  files.
+o External dependencies shall remain as minimal as possible. Currently gcc
+  and glibc are the only dependencies.
+o Tests return 0 for success and < 0 for failure.
+
+Output Formatting
+-----------------
+Test output shall be easily parsable by both human and machine. Title and
+results are printed to stdout, while intermediate ERROR or FAIL messages are
+sent to stderr. Tests shall support the -c option to print PASS, FAIL, and
+ERROR strings in color for easy visual parsing. Output shall conform to the
+following format:
+
+test_name: Description of the test
+	Arguments: arg1=val1 #units specified for clarity where appropriate
+	ERROR: Description of unexpected error
+	 FAIL: Reason for test failure
+	# FIXME: Perhaps an " INFO: informational message" option would be
+	#        useful here. Using -v to toggle it them on and off, as with -c.
+	# there may be multiple ERROR or FAIL messages
+Result: (PASS|FAIL|ERROR)
+
+Naming
+------
+o FIXME: decide on a sane test naming scheme.  Currently the tests are named
+  based on the primary futex operation they test. Eventually this will become a
+  problem as we intend to write multiple tests which collide in this namespace.
+  Perhaps something like "wait-wake-1" "wait-wake-2" is adequate, leaving the
+  detailed description in the test source and the output.
+
+Coding Style
+------------
+o The Futex Test project adheres to the coding standards set forth by Linux
+  kernel as defined in the Linux source Documentation/process/coding-style.rst.
diff --git a/tools/testing/selftests/futex/functional/.gitignore b/tools/testing/selftests/futex/functional/.gitignore
new file mode 100644
index 000000000..23b9fea8d
--- /dev/null
+++ b/tools/testing/selftests/futex/functional/.gitignore
@@ -0,0 +1,15 @@
+# SPDX-License-Identifier: GPL-2.0-only
+futex_numa_mpol
+futex_priv_hash
+futex_requeue
+futex_requeue_pi
+futex_requeue_pi_mismatched_ops
+futex_requeue_pi_signal_restart
+futex_wait
+futex_wait_private_mapped_file
+futex_wait_timeout
+futex_wait_uninitialized_heap
+futex_wait_wouldblock
+futex_waitv
+futex_numa
+robust_list
diff --git a/tools/testing/selftests/futex/functional/Makefile b/tools/testing/selftests/futex/functional/Makefile
new file mode 100644
index 000000000..5c1c824f9
--- /dev/null
+++ b/tools/testing/selftests/futex/functional/Makefile
@@ -0,0 +1,35 @@
+# SPDX-License-Identifier: GPL-2.0
+PKG_CONFIG ?= pkg-config
+LIBNUMA_TEST = $(shell sh -c "$(PKG_CONFIG) numa --atleast-version 2.0.18 > /dev/null 2>&1 && echo SUFFICIENT || echo NO")
+
+INCLUDES := -I../include -I../../ $(KHDR_INCLUDES)
+CFLAGS := $(CFLAGS) -g -O2 -Wall -pthread -D_FILE_OFFSET_BITS=64 -D_TIME_BITS=64 $(INCLUDES) $(KHDR_INCLUDES) -DLIBNUMA_VER_$(LIBNUMA_TEST)=1
+LDLIBS := -lpthread -lrt
+ifeq ($(LIBNUMA_TEST),SUFFICIENT)
+LDLIBS += -lnuma
+endif
+
+LOCAL_HDRS := \
+	../include/futextest.h \
+	../include/atomic.h
+TEST_GEN_PROGS := \
+	futex_wait_timeout \
+	futex_wait_wouldblock \
+	futex_requeue_pi \
+	futex_requeue_pi_signal_restart \
+	futex_requeue_pi_mismatched_ops \
+	futex_wait_uninitialized_heap \
+	futex_wait_private_mapped_file \
+	futex_wait \
+	futex_requeue \
+	futex_priv_hash \
+	futex_numa_mpol \
+	futex_waitv \
+	futex_numa \
+	robust_list
+
+TEST_PROGS := run.sh
+
+top_srcdir = ../../../../..
+DEFAULT_INSTALL_HDR_PATH := 1
+include ../../lib.mk
diff --git a/tools/testing/selftests/futex/functional/futex_numa.c b/tools/testing/selftests/futex/functional/futex_numa.c
new file mode 100644
index 000000000..e0a33510c
--- /dev/null
+++ b/tools/testing/selftests/futex/functional/futex_numa.c
@@ -0,0 +1,263 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <pthread.h>
+#include <sys/shm.h>
+#include <sys/mman.h>
+#include <fcntl.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <time.h>
+#include <assert.h>
+#include "futextest.h"
+#include "futex2test.h"
+
+typedef u_int32_t u32;
+typedef int32_t   s32;
+typedef u_int64_t u64;
+
+static unsigned int fflags = (FUTEX2_SIZE_U32 | FUTEX2_PRIVATE);
+static int fnode = FUTEX_NO_NODE;
+
+/* fairly stupid test-and-set lock with a waiter flag */
+
+#define N_LOCK		0x0000001
+#define N_WAITERS	0x0001000
+
+struct futex_numa_32 {
+	union {
+		u64 full;
+		struct {
+			u32 val;
+			u32 node;
+		};
+	};
+};
+
+void futex_numa_32_lock(struct futex_numa_32 *lock)
+{
+	for (;;) {
+		struct futex_numa_32 new, old = {
+			.full = __atomic_load_n(&lock->full, __ATOMIC_RELAXED),
+		};
+
+		for (;;) {
+			new = old;
+			if (old.val == 0) {
+				/* no waiter, no lock -> first lock, set no-node */
+				new.node = fnode;
+			}
+			if (old.val & N_LOCK) {
+				/* contention, set waiter */
+				new.val |= N_WAITERS;
+			}
+			new.val |= N_LOCK;
+
+			/* nothing changed, ready to block */
+			if (old.full == new.full)
+				break;
+
+			/*
+			 * Use u64 cmpxchg to set the futex value and node in a
+			 * consistent manner.
+			 */
+			if (__atomic_compare_exchange_n(&lock->full,
+							&old.full, new.full,
+							/* .weak */ false,
+							__ATOMIC_ACQUIRE,
+							__ATOMIC_RELAXED)) {
+
+				/* if we just set N_LOCK, we own it */
+				if (!(old.val & N_LOCK))
+					return;
+
+				/* go block */
+				break;
+			}
+		}
+
+		futex2_wait(lock, new.val, fflags, NULL, 0);
+	}
+}
+
+void futex_numa_32_unlock(struct futex_numa_32 *lock)
+{
+	u32 val = __atomic_sub_fetch(&lock->val, N_LOCK, __ATOMIC_RELEASE);
+	assert((s32)val >= 0);
+	if (val & N_WAITERS) {
+		int woken = futex2_wake(lock, 1, fflags);
+		assert(val == N_WAITERS);
+		if (!woken) {
+			__atomic_compare_exchange_n(&lock->val, &val, 0U,
+						    false, __ATOMIC_RELAXED,
+						    __ATOMIC_RELAXED);
+		}
+	}
+}
+
+static long nanos = 50000;
+
+struct thread_args {
+	pthread_t tid;
+	volatile int * done;
+	struct futex_numa_32 *lock;
+	int val;
+	int *val1, *val2;
+	int node;
+};
+
+static void *threadfn(void *_arg)
+{
+	struct thread_args *args = _arg;
+	struct timespec ts = {
+		.tv_nsec = nanos,
+	};
+	int node;
+
+	while (!*args->done) {
+
+		futex_numa_32_lock(args->lock);
+		args->val++;
+
+		assert(*args->val1 == *args->val2);
+		(*args->val1)++;
+		nanosleep(&ts, NULL);
+		(*args->val2)++;
+
+		node = args->lock->node;
+		futex_numa_32_unlock(args->lock);
+
+		if (node != args->node) {
+			args->node = node;
+			printf("node: %d\n", node);
+		}
+
+		nanosleep(&ts, NULL);
+	}
+
+	return NULL;
+}
+
+static void *contendfn(void *_arg)
+{
+	struct thread_args *args = _arg;
+
+	while (!*args->done) {
+		/*
+		 * futex2_wait() will take hb-lock, verify *var == val and
+		 * queue/abort.  By knowingly setting val 'wrong' this will
+		 * abort and thereby generate hb-lock contention.
+		 */
+		futex2_wait(&args->lock->val, ~0U, fflags, NULL, 0);
+		args->val++;
+	}
+
+	return NULL;
+}
+
+static volatile int done = 0;
+static struct futex_numa_32 lock = { .val = 0, };
+static int val1, val2;
+
+int main(int argc, char *argv[])
+{
+	struct thread_args *tas[512], *cas[512];
+	int c, t, threads = 2, contenders = 0;
+	int sleeps = 10;
+	int total = 0;
+
+	while ((c = getopt(argc, argv, "c:t:s:n:N::")) != -1) {
+		switch (c) {
+		case 'c':
+			contenders = atoi(optarg);
+			break;
+		case 't':
+			threads = atoi(optarg);
+			break;
+		case 's':
+			sleeps = atoi(optarg);
+			break;
+		case 'n':
+			nanos = atoi(optarg);
+			break;
+		case 'N':
+			fflags |= FUTEX2_NUMA;
+			if (optarg)
+				fnode = atoi(optarg);
+			break;
+		default:
+			exit(1);
+			break;
+		}
+	}
+
+	for (t = 0; t < contenders; t++) {
+		struct thread_args *args = calloc(1, sizeof(*args));
+		if (!args) {
+			perror("thread_args");
+			exit(-1);
+		}
+
+		args->done = &done;
+		args->lock = &lock;
+		args->val1 = &val1;
+		args->val2 = &val2;
+		args->node = -1;
+
+		if (pthread_create(&args->tid, NULL, contendfn, args)) {
+			perror("pthread_create");
+			exit(-1);
+		}
+
+		cas[t] = args;
+	}
+
+	for (t = 0; t < threads; t++) {
+		struct thread_args *args = calloc(1, sizeof(*args));
+		if (!args) {
+			perror("thread_args");
+			exit(-1);
+		}
+
+		args->done = &done;
+		args->lock = &lock;
+		args->val1 = &val1;
+		args->val2 = &val2;
+		args->node = -1;
+
+		if (pthread_create(&args->tid, NULL, threadfn, args)) {
+			perror("pthread_create");
+			exit(-1);
+		}
+
+		tas[t] = args;
+	}
+
+	sleep(sleeps);
+
+	done = true;
+
+	for (t = 0; t < threads; t++) {
+		struct thread_args *args = tas[t];
+
+		pthread_join(args->tid, NULL);
+		total += args->val;
+//		printf("tval: %d\n", args->val);
+	}
+	printf("total: %d\n", total);
+
+	if (contenders) {
+		total = 0;
+		for (t = 0; t < contenders; t++) {
+			struct thread_args *args = cas[t];
+
+			pthread_join(args->tid, NULL);
+			total += args->val;
+			//		printf("tval: %d\n", args->val);
+		}
+		printf("contenders: %d\n", total);
+	}
+
+	return 0;
+}
+
diff --git a/tools/testing/selftests/futex/functional/futex_numa_mpol.c b/tools/testing/selftests/futex/functional/futex_numa_mpol.c
new file mode 100644
index 000000000..78c0f7a59
--- /dev/null
+++ b/tools/testing/selftests/futex/functional/futex_numa_mpol.c
@@ -0,0 +1,216 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2025 Sebastian Andrzej Siewior <bigeasy@linutronix.de>
+ */
+
+#define _GNU_SOURCE
+
+#include <errno.h>
+#include <pthread.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#ifdef LIBNUMA_VER_SUFFICIENT
+#include <numa.h>
+#include <numaif.h>
+#endif
+
+#include <linux/futex.h>
+#include <sys/mman.h>
+
+#include "futextest.h"
+#include "futex2test.h"
+#include "kselftest_harness.h"
+
+#define MAX_THREADS	64
+
+static pthread_barrier_t barrier_main;
+static pthread_t threads[MAX_THREADS];
+
+struct thread_args {
+	void *futex_ptr;
+	unsigned int flags;
+	int result;
+};
+
+static struct thread_args thread_args[MAX_THREADS];
+
+#ifndef FUTEX_NO_NODE
+#define FUTEX_NO_NODE (-1)
+#endif
+
+#ifndef FUTEX2_MPOL
+#define FUTEX2_MPOL	0x08
+#endif
+
+static void *thread_lock_fn(void *arg)
+{
+	struct thread_args *args = arg;
+	int ret;
+
+	pthread_barrier_wait(&barrier_main);
+	ret = futex2_wait(args->futex_ptr, 0, args->flags, NULL, 0);
+	args->result = ret;
+	return NULL;
+}
+
+static void create_max_threads(void *futex_ptr)
+{
+	int i, ret;
+
+	for (i = 0; i < MAX_THREADS; i++) {
+		thread_args[i].futex_ptr = futex_ptr;
+		thread_args[i].flags = FUTEX2_SIZE_U32 | FUTEX_PRIVATE_FLAG | FUTEX2_NUMA;
+		thread_args[i].result = 0;
+		ret = pthread_create(&threads[i], NULL, thread_lock_fn, &thread_args[i]);
+		if (ret)
+			ksft_exit_fail_msg("pthread_create failed\n");
+	}
+}
+
+static void join_max_threads(void)
+{
+	int i, ret;
+
+	for (i = 0; i < MAX_THREADS; i++) {
+		ret = pthread_join(threads[i], NULL);
+		if (ret)
+			ksft_exit_fail_msg("pthread_join failed for thread %d\n", i);
+	}
+}
+
+static void __test_futex(void *futex_ptr, int err_value, unsigned int futex_flags)
+{
+	int to_wake, ret, i, need_exit = 0;
+
+	pthread_barrier_init(&barrier_main, NULL, MAX_THREADS + 1);
+	create_max_threads(futex_ptr);
+	pthread_barrier_wait(&barrier_main);
+	to_wake = MAX_THREADS;
+
+	do {
+		ret = futex2_wake(futex_ptr, to_wake, futex_flags);
+
+		if (err_value) {
+			if (ret >= 0)
+				ksft_exit_fail_msg("futex2_wake(%d, 0x%x) should fail, but didn't\n",
+						   to_wake, futex_flags);
+
+			if (errno != err_value)
+				ksft_exit_fail_msg("futex2_wake(%d, 0x%x) expected error was %d, but returned %d (%s)\n",
+						   to_wake, futex_flags, err_value, errno, strerror(errno));
+
+			break;
+		}
+		if (ret < 0) {
+			ksft_exit_fail_msg("Failed futex2_wake(%d, 0x%x): %m\n",
+					   to_wake, futex_flags);
+		}
+		if (!ret)
+			usleep(50);
+		to_wake -= ret;
+
+	} while (to_wake);
+	join_max_threads();
+
+	for (i = 0; i < MAX_THREADS; i++) {
+		if (err_value && thread_args[i].result != -1) {
+			ksft_print_msg("Thread %d should fail but succeeded (%d)\n",
+				       i, thread_args[i].result);
+			need_exit = 1;
+		}
+		if (!err_value && thread_args[i].result != 0) {
+			ksft_print_msg("Thread %d failed (%d)\n", i, thread_args[i].result);
+			need_exit = 1;
+		}
+	}
+	if (need_exit)
+		ksft_exit_fail_msg("Aborting due to earlier errors.\n");
+}
+
+static void test_futex(void *futex_ptr, int err_value)
+{
+	__test_futex(futex_ptr, err_value, FUTEX2_SIZE_U32 | FUTEX_PRIVATE_FLAG | FUTEX2_NUMA);
+}
+
+TEST(futex_numa_mpol)
+{
+	struct futex32_numa *futex_numa;
+	void *futex_ptr;
+	int mem_size;
+
+	mem_size = sysconf(_SC_PAGE_SIZE);
+	futex_ptr = mmap(NULL, mem_size * 2, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, 0, 0);
+	if (futex_ptr == MAP_FAILED)
+		ksft_exit_fail_msg("mmap() for %d bytes failed\n", mem_size);
+
+	/* Create an invalid memory region for the "Memory out of range" test */
+	mprotect(futex_ptr + mem_size, mem_size, PROT_NONE);
+
+	futex_numa = futex_ptr;
+
+	ksft_print_msg("Regular test\n");
+	futex_numa->futex = 0;
+	futex_numa->numa = FUTEX_NO_NODE;
+	test_futex(futex_ptr, 0);
+
+	if (futex_numa->numa == FUTEX_NO_NODE)
+		ksft_exit_fail_msg("NUMA node is left uninitialized\n");
+
+	/* FUTEX2_NUMA futex must be 8-byte aligned */
+	ksft_print_msg("Mis-aligned futex\n");
+	test_futex(futex_ptr + mem_size - 4, EINVAL);
+
+	ksft_print_msg("Memory out of range\n");
+	test_futex(futex_ptr + mem_size, EFAULT);
+
+	futex_numa->numa = FUTEX_NO_NODE;
+	mprotect(futex_ptr, mem_size, PROT_READ);
+	ksft_print_msg("Memory, RO\n");
+	test_futex(futex_ptr, EFAULT);
+
+	mprotect(futex_ptr, mem_size, PROT_NONE);
+	ksft_print_msg("Memory, no access\n");
+	test_futex(futex_ptr, EFAULT);
+
+	mprotect(futex_ptr, mem_size, PROT_READ | PROT_WRITE);
+	ksft_print_msg("Memory back to RW\n");
+	test_futex(futex_ptr, 0);
+
+	ksft_test_result_pass("futex2 memory boundary tests passed\n");
+
+	/* MPOL test. Does not work as expected */
+#ifdef LIBNUMA_VER_SUFFICIENT
+	for (int i = 0; i < 4; i++) {
+		unsigned long nodemask;
+		int ret;
+
+		nodemask = 1 << i;
+		ret = mbind(futex_ptr, mem_size, MPOL_BIND, &nodemask,
+			    sizeof(nodemask) * 8, 0);
+		if (ret == 0) {
+			ret = numa_set_mempolicy_home_node(futex_ptr, mem_size, i, 0);
+			if (ret != 0)
+				ksft_exit_fail_msg("Failed to set home node: %m, %d\n", errno);
+
+			ksft_print_msg("Node %d test\n", i);
+			futex_numa->futex = 0;
+			futex_numa->numa = FUTEX_NO_NODE;
+
+			ret = futex2_wake(futex_ptr, 0, FUTEX2_SIZE_U32 | FUTEX_PRIVATE_FLAG | FUTEX2_NUMA | FUTEX2_MPOL);
+			if (ret < 0)
+				ksft_test_result_fail("Failed to wake 0 with MPOL: %m\n");
+			if (futex_numa->numa != i) {
+				ksft_exit_fail_msg("Returned NUMA node is %d expected %d\n",
+						   futex_numa->numa, i);
+			}
+		}
+	}
+	ksft_test_result_pass("futex2 MPOL hints test passed\n");
+#else
+	ksft_test_result_skip("futex2 MPOL hints test requires libnuma 2.0.18+\n");
+#endif
+	munmap(futex_ptr, mem_size * 2);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/futex/functional/futex_priv_hash.c b/tools/testing/selftests/futex/functional/futex_priv_hash.c
new file mode 100644
index 000000000..e8079d7c6
--- /dev/null
+++ b/tools/testing/selftests/futex/functional/futex_priv_hash.c
@@ -0,0 +1,270 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2025 Sebastian Andrzej Siewior <bigeasy@linutronix.de>
+ */
+
+#define _GNU_SOURCE
+
+#include <errno.h>
+#include <pthread.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+
+#include <linux/prctl.h>
+#include <sys/prctl.h>
+
+#include "kselftest_harness.h"
+
+#define MAX_THREADS	64
+
+static pthread_barrier_t barrier_main;
+static pthread_mutex_t global_lock;
+static pthread_t threads[MAX_THREADS];
+static int counter;
+
+#ifndef PR_FUTEX_HASH
+#define PR_FUTEX_HASH			78
+# define PR_FUTEX_HASH_SET_SLOTS	1
+# define PR_FUTEX_HASH_GET_SLOTS	2
+#endif
+
+static int futex_hash_slots_set(unsigned int slots)
+{
+	return prctl(PR_FUTEX_HASH, PR_FUTEX_HASH_SET_SLOTS, slots, 0);
+}
+
+static int futex_hash_slots_get(void)
+{
+	return prctl(PR_FUTEX_HASH, PR_FUTEX_HASH_GET_SLOTS);
+}
+
+static void futex_hash_slots_set_verify(int slots)
+{
+	int ret;
+
+	ret = futex_hash_slots_set(slots);
+	if (ret != 0) {
+		ksft_test_result_fail("Failed to set slots to %d: %m\n", slots);
+		ksft_finished();
+	}
+	ret = futex_hash_slots_get();
+	if (ret != slots) {
+		ksft_test_result_fail("Set %d slots but PR_FUTEX_HASH_GET_SLOTS returns: %d, %m\n",
+		       slots, ret);
+		ksft_finished();
+	}
+	ksft_test_result_pass("SET and GET slots %d passed\n", slots);
+}
+
+static void futex_hash_slots_set_must_fail(int slots)
+{
+	int ret;
+
+	ret = futex_hash_slots_set(slots);
+	ksft_test_result(ret < 0, "futex_hash_slots_set(%d)\n",
+			 slots);
+}
+
+static void *thread_return_fn(void *arg)
+{
+	return NULL;
+}
+
+static void *thread_lock_fn(void *arg)
+{
+	pthread_barrier_wait(&barrier_main);
+
+	pthread_mutex_lock(&global_lock);
+	counter++;
+	usleep(20);
+	pthread_mutex_unlock(&global_lock);
+	return NULL;
+}
+
+static void create_max_threads(void *(*thread_fn)(void *))
+{
+	int i, ret;
+
+	for (i = 0; i < MAX_THREADS; i++) {
+		ret = pthread_create(&threads[i], NULL, thread_fn, NULL);
+		if (ret)
+			ksft_exit_fail_msg("pthread_create failed: %m\n");
+	}
+}
+
+static void join_max_threads(void)
+{
+	int i, ret;
+
+	for (i = 0; i < MAX_THREADS; i++) {
+		ret = pthread_join(threads[i], NULL);
+		if (ret)
+			ksft_exit_fail_msg("pthread_join failed for thread %d\n", i);
+	}
+}
+
+#define SEC_IN_NSEC	1000000000
+#define MSEC_IN_NSEC	1000000
+
+static void futex_dummy_op(void)
+{
+	pthread_mutex_t lock = PTHREAD_MUTEX_INITIALIZER;
+	struct timespec timeout;
+	int ret;
+
+	pthread_mutex_lock(&lock);
+	clock_gettime(CLOCK_REALTIME, &timeout);
+	timeout.tv_nsec += 100 * MSEC_IN_NSEC;
+	if (timeout.tv_nsec >=  SEC_IN_NSEC) {
+		timeout.tv_nsec -= SEC_IN_NSEC;
+		timeout.tv_sec++;
+	}
+	ret = pthread_mutex_timedlock(&lock, &timeout);
+	if (ret == 0)
+		ksft_exit_fail_msg("Successfully locked an already locked mutex.\n");
+
+	if (ret != ETIMEDOUT)
+		ksft_exit_fail_msg("pthread_mutex_timedlock() did not timeout: %d.\n", ret);
+}
+
+static const char *test_msg_auto_create = "Automatic hash bucket init on thread creation.\n";
+static const char *test_msg_auto_inc = "Automatic increase with more than 16 CPUs\n";
+
+TEST(priv_hash)
+{
+	int futex_slots1, futex_slotsn, online_cpus;
+	pthread_mutexattr_t mutex_attr_pi;
+	int ret, retry = 20;
+
+	ret = pthread_mutexattr_init(&mutex_attr_pi);
+	ret |= pthread_mutexattr_setprotocol(&mutex_attr_pi, PTHREAD_PRIO_INHERIT);
+	ret |= pthread_mutex_init(&global_lock, &mutex_attr_pi);
+	if (ret != 0) {
+		ksft_exit_fail_msg("Failed to initialize pthread mutex.\n");
+	}
+	/* First thread, expect to be 0, not yet initialized */
+	ret = futex_hash_slots_get();
+	if (ret != 0)
+		ksft_exit_fail_msg("futex_hash_slots_get() failed: %d, %m\n", ret);
+
+	ksft_test_result_pass("Basic get slots and immutable status.\n");
+	ret = pthread_create(&threads[0], NULL, thread_return_fn, NULL);
+	if (ret != 0)
+		ksft_exit_fail_msg("pthread_create() failed: %d, %m\n", ret);
+
+	ret = pthread_join(threads[0], NULL);
+	if (ret != 0)
+		ksft_exit_fail_msg("pthread_join() failed: %d, %m\n", ret);
+
+	/* First thread, has to initialize private hash */
+	futex_slots1 = futex_hash_slots_get();
+	if (futex_slots1 <= 0) {
+		ksft_print_msg("Current hash buckets: %d\n", futex_slots1);
+		ksft_exit_fail_msg("%s", test_msg_auto_create);
+	}
+
+	ksft_test_result_pass("%s", test_msg_auto_create);
+
+	online_cpus = sysconf(_SC_NPROCESSORS_ONLN);
+	ret = pthread_barrier_init(&barrier_main, NULL, MAX_THREADS + 1);
+	if (ret != 0)
+		ksft_exit_fail_msg("pthread_barrier_init failed: %m.\n");
+
+	ret = pthread_mutex_lock(&global_lock);
+	if (ret != 0)
+		ksft_exit_fail_msg("pthread_mutex_lock failed: %m.\n");
+
+	counter = 0;
+	create_max_threads(thread_lock_fn);
+	pthread_barrier_wait(&barrier_main);
+
+	/*
+	 * The current default size of hash buckets is 16. The auto increase
+	 * works only if more than 16 CPUs are available.
+	 */
+	ksft_print_msg("Online CPUs: %d\n", online_cpus);
+	if (online_cpus > 16) {
+retry_getslots:
+		futex_slotsn = futex_hash_slots_get();
+		if (futex_slotsn < 0 || futex_slots1 == futex_slotsn) {
+			retry--;
+			/*
+			 * Auto scaling on thread creation can be slightly delayed
+			 * because it waits for a RCU grace period twice. The new
+			 * private hash is assigned upon the first futex operation
+			 * after grace period.
+			 * To cover all this for testing purposes the function
+			 * below will acquire a lock and acquire it again with a
+			 * 100ms timeout which must timeout. This ensures we
+			 * sleep for 100ms and issue a futex operation.
+			 */
+			if (retry > 0) {
+				futex_dummy_op();
+				goto retry_getslots;
+			}
+			ksft_print_msg("Expected increase of hash buckets but got: %d -> %d\n",
+				       futex_slots1, futex_slotsn);
+			ksft_exit_fail_msg("%s", test_msg_auto_inc);
+		}
+		ksft_test_result_pass("%s", test_msg_auto_inc);
+	} else {
+		ksft_test_result_skip("%s", test_msg_auto_inc);
+	}
+	ret = pthread_mutex_unlock(&global_lock);
+
+	/* Once the user changes it, it has to be what is set */
+	futex_hash_slots_set_verify(2);
+	futex_hash_slots_set_verify(4);
+	futex_hash_slots_set_verify(8);
+	futex_hash_slots_set_verify(32);
+	futex_hash_slots_set_verify(16);
+
+	ret = futex_hash_slots_set(15);
+	ksft_test_result(ret < 0, "Use 15 slots\n");
+
+	futex_hash_slots_set_verify(2);
+	join_max_threads();
+	ksft_test_result(counter == MAX_THREADS, "Created and waited for %d of %d threads\n",
+			 counter, MAX_THREADS);
+	counter = 0;
+	/* Once the user set something, auto resize must be disabled */
+	ret = pthread_barrier_init(&barrier_main, NULL, MAX_THREADS);
+
+	create_max_threads(thread_lock_fn);
+	join_max_threads();
+
+	ret = futex_hash_slots_get();
+	ksft_test_result(ret == 2, "No more auto-resize after manual setting, got %d\n",
+			 ret);
+
+	futex_hash_slots_set_must_fail(1 << 29);
+	futex_hash_slots_set_verify(4);
+
+	/*
+	 * Once the global hash has been requested, then this requested can not
+	 * be undone.
+	 */
+	ret = futex_hash_slots_set(0);
+	ksft_test_result(ret == 0, "Global hash request\n");
+	if (ret != 0)
+		return;
+
+	futex_hash_slots_set_must_fail(4);
+	futex_hash_slots_set_must_fail(8);
+	futex_hash_slots_set_must_fail(8);
+	futex_hash_slots_set_must_fail(0);
+	futex_hash_slots_set_must_fail(6);
+
+	ret = pthread_barrier_init(&barrier_main, NULL, MAX_THREADS);
+	if (ret != 0)
+		ksft_exit_fail_msg("pthread_barrier_init failed: %m\n");
+
+	create_max_threads(thread_lock_fn);
+	join_max_threads();
+
+	ret = futex_hash_slots_get();
+	ksft_test_result(ret == 0, "Continue to use global hash\n");
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/futex/functional/futex_requeue.c b/tools/testing/selftests/futex/functional/futex_requeue.c
new file mode 100644
index 000000000..dcf0d5f2f
--- /dev/null
+++ b/tools/testing/selftests/futex/functional/futex_requeue.c
@@ -0,0 +1,73 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright Collabora Ltd., 2021
+ *
+ * futex cmp requeue test by André Almeida <andrealmeid@collabora.com>
+ */
+
+#include <pthread.h>
+#include <limits.h>
+
+#include "futextest.h"
+#include "kselftest_harness.h"
+
+#define timeout_ns  30000000
+#define WAKE_WAIT_US 10000
+
+volatile futex_t *f1;
+
+void *waiterfn(void *arg)
+{
+	struct timespec to;
+
+	to.tv_sec = 0;
+	to.tv_nsec = timeout_ns;
+
+	if (futex_wait(f1, *f1, &to, 0))
+		printf("waiter failed errno %d\n", errno);
+
+	return NULL;
+}
+
+TEST(requeue_single)
+{
+	volatile futex_t _f1 = 0;
+	volatile futex_t f2 = 0;
+	pthread_t waiter[10];
+
+	f1 = &_f1;
+
+	/*
+	 * Requeue a waiter from f1 to f2, and wake f2.
+	 */
+	ASSERT_EQ(0, pthread_create(&waiter[0], NULL, waiterfn, NULL));
+
+	usleep(WAKE_WAIT_US);
+
+	EXPECT_EQ(1, futex_cmp_requeue(f1, 0, &f2, 0, 1, 0));
+	EXPECT_EQ(1, futex_wake(&f2, 1, 0));
+}
+
+TEST(requeue_multiple)
+{
+	volatile futex_t _f1 = 0;
+	volatile futex_t f2 = 0;
+	pthread_t waiter[10];
+	int i;
+
+	f1 = &_f1;
+
+	/*
+	 * Create 10 waiters at f1. At futex_requeue, wake 3 and requeue 7.
+	 * At futex_wake, wake INT_MAX (should be exactly 7).
+	 */
+	for (i = 0; i < 10; i++)
+		ASSERT_EQ(0, pthread_create(&waiter[i], NULL, waiterfn, NULL));
+
+	usleep(WAKE_WAIT_US);
+
+	EXPECT_EQ(10, futex_cmp_requeue(f1, 0, &f2, 3, 7, 0));
+	EXPECT_EQ(7, futex_wake(&f2, INT_MAX, 0));
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/futex/functional/futex_requeue_pi.c b/tools/testing/selftests/futex/functional/futex_requeue_pi.c
new file mode 100644
index 000000000..46d2858e1
--- /dev/null
+++ b/tools/testing/selftests/futex/functional/futex_requeue_pi.c
@@ -0,0 +1,400 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/******************************************************************************
+ *
+ *   Copyright © International Business Machines  Corp., 2006-2008
+ *
+ * DESCRIPTION
+ *      This test excercises the futex syscall op codes needed for requeuing
+ *      priority inheritance aware POSIX condition variables and mutexes.
+ *
+ * AUTHORS
+ *      Sripathi Kodi <sripathik@in.ibm.com>
+ *      Darren Hart <dvhart@linux.intel.com>
+ *
+ * HISTORY
+ *      2008-Jan-13: Initial version by Sripathi Kodi <sripathik@in.ibm.com>
+ *      2009-Nov-6: futex test adaptation by Darren Hart <dvhart@linux.intel.com>
+ *
+ *****************************************************************************/
+
+#define _GNU_SOURCE
+
+#include <errno.h>
+#include <limits.h>
+#include <pthread.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <signal.h>
+#include <string.h>
+
+#include "atomic.h"
+#include "futextest.h"
+#include "kselftest_harness.h"
+
+#define MAX_WAKE_ITERS 1000
+#define THREAD_MAX 10
+#define SIGNAL_PERIOD_US 100
+
+atomic_t waiters_blocked = ATOMIC_INITIALIZER;
+atomic_t waiters_woken = ATOMIC_INITIALIZER;
+
+futex_t f1 = FUTEX_INITIALIZER;
+futex_t f2 = FUTEX_INITIALIZER;
+futex_t wake_complete = FUTEX_INITIALIZER;
+
+struct thread_arg {
+	long id;
+	struct timespec *timeout;
+	int lock;
+	int ret;
+};
+#define THREAD_ARG_INITIALIZER { 0, NULL, 0, 0 }
+
+FIXTURE(args)
+{
+};
+
+FIXTURE_SETUP(args)
+{
+};
+
+FIXTURE_TEARDOWN(args)
+{
+};
+
+FIXTURE_VARIANT(args)
+{
+	long timeout_ns;
+	bool broadcast;
+	bool owner;
+	bool locked;
+};
+
+/*
+ * For a given timeout value, this macro creates a test input with all the
+ * possible combinations of valid arguments
+ */
+#define FIXTURE_VARIANT_ADD_TIMEOUT(timeout)		\
+							\
+FIXTURE_VARIANT_ADD(args, t_##timeout)			\
+{							\
+	.timeout_ns = timeout,				\
+};							\
+							\
+FIXTURE_VARIANT_ADD(args, t_##timeout##_broadcast)	\
+{							\
+	.timeout_ns = timeout,				\
+	.broadcast = true,				\
+};							\
+							\
+FIXTURE_VARIANT_ADD(args, t_##timeout##_broadcast_locked) \
+{							\
+	.timeout_ns = timeout,				\
+	.broadcast = true,				\
+	.locked = true,					\
+};							\
+							\
+FIXTURE_VARIANT_ADD(args, t_##timeout##_broadcast_owner) \
+{							\
+	.timeout_ns = timeout,				\
+	.broadcast = true,				\
+	.owner = true,					\
+};							\
+							\
+FIXTURE_VARIANT_ADD(args, t_##timeout##_locked)		\
+{							\
+	.timeout_ns = timeout,				\
+	.locked = true,					\
+};							\
+							\
+FIXTURE_VARIANT_ADD(args, t_##timeout##_owner)		\
+{							\
+	.timeout_ns = timeout,				\
+	.owner = true,					\
+};							\
+
+FIXTURE_VARIANT_ADD_TIMEOUT(0);
+FIXTURE_VARIANT_ADD_TIMEOUT(5000);
+FIXTURE_VARIANT_ADD_TIMEOUT(500000);
+FIXTURE_VARIANT_ADD_TIMEOUT(2000000000);
+
+int create_rt_thread(pthread_t *pth, void*(*func)(void *), void *arg,
+		     int policy, int prio)
+{
+	int ret;
+	struct sched_param schedp;
+	pthread_attr_t attr;
+
+	pthread_attr_init(&attr);
+	memset(&schedp, 0, sizeof(schedp));
+
+	ret = pthread_attr_setinheritsched(&attr, PTHREAD_EXPLICIT_SCHED);
+	if (ret) {
+		ksft_exit_fail_msg("pthread_attr_setinheritsched\n");
+		return -1;
+	}
+
+	ret = pthread_attr_setschedpolicy(&attr, policy);
+	if (ret) {
+		ksft_exit_fail_msg("pthread_attr_setschedpolicy\n");
+		return -1;
+	}
+
+	schedp.sched_priority = prio;
+	ret = pthread_attr_setschedparam(&attr, &schedp);
+	if (ret) {
+		ksft_exit_fail_msg("pthread_attr_setschedparam\n");
+		return -1;
+	}
+
+	ret = pthread_create(pth, &attr, func, arg);
+	if (ret) {
+		ksft_exit_fail_msg("pthread_create\n");
+		return -1;
+	}
+	return 0;
+}
+
+
+void *waiterfn(void *arg)
+{
+	struct thread_arg *args = (struct thread_arg *)arg;
+	futex_t old_val;
+
+	ksft_print_dbg_msg("Waiter %ld: running\n", args->id);
+	/* Each thread sleeps for a different amount of time
+	 * This is to avoid races, because we don't lock the
+	 * external mutex here */
+	usleep(1000 * (long)args->id);
+
+	old_val = f1;
+	atomic_inc(&waiters_blocked);
+	ksft_print_dbg_msg("Calling futex_wait_requeue_pi: %p (%u) -> %p\n",
+	     &f1, f1, &f2);
+	args->ret = futex_wait_requeue_pi(&f1, old_val, &f2, args->timeout,
+					  FUTEX_PRIVATE_FLAG);
+
+	ksft_print_dbg_msg("waiter %ld woke with %d %s\n", args->id, args->ret,
+	     args->ret < 0 ? strerror(errno) : "");
+	atomic_inc(&waiters_woken);
+	if (args->ret < 0) {
+		if (args->timeout && errno == ETIMEDOUT)
+			args->ret = 0;
+		else {
+			ksft_exit_fail_msg("futex_wait_requeue_pi\n");
+		}
+		futex_lock_pi(&f2, NULL, 0, FUTEX_PRIVATE_FLAG);
+	}
+	futex_unlock_pi(&f2, FUTEX_PRIVATE_FLAG);
+
+	ksft_print_dbg_msg("Waiter %ld: exiting with %d\n", args->id, args->ret);
+	pthread_exit((void *)&args->ret);
+}
+
+void *broadcast_wakerfn(void *arg)
+{
+	struct thread_arg *args = (struct thread_arg *)arg;
+	int nr_requeue = INT_MAX;
+	int task_count = 0;
+	futex_t old_val;
+	int nr_wake = 1;
+	int i = 0;
+
+	ksft_print_dbg_msg("Waker: waiting for waiters to block\n");
+	while (waiters_blocked.val < THREAD_MAX)
+		usleep(1000);
+	usleep(1000);
+
+	ksft_print_dbg_msg("Waker: Calling broadcast\n");
+	if (args->lock) {
+		ksft_print_dbg_msg("Calling FUTEX_LOCK_PI on mutex=%x @ %p\n", f2, &f2);
+		futex_lock_pi(&f2, NULL, 0, FUTEX_PRIVATE_FLAG);
+	}
+ continue_requeue:
+	old_val = f1;
+	args->ret = futex_cmp_requeue_pi(&f1, old_val, &f2, nr_wake, nr_requeue,
+				   FUTEX_PRIVATE_FLAG);
+	if (args->ret < 0) {
+		ksft_exit_fail_msg("FUTEX_CMP_REQUEUE_PI failed\n");
+	} else if (++i < MAX_WAKE_ITERS) {
+		task_count += args->ret;
+		if (task_count < THREAD_MAX - waiters_woken.val)
+			goto continue_requeue;
+	} else {
+		ksft_exit_fail_msg("max broadcast iterations (%d) reached with %d/%d tasks woken or requeued\n",
+		       MAX_WAKE_ITERS, task_count, THREAD_MAX);
+	}
+
+	futex_wake(&wake_complete, 1, FUTEX_PRIVATE_FLAG);
+
+	if (args->lock)
+		futex_unlock_pi(&f2, FUTEX_PRIVATE_FLAG);
+
+	if (args->ret > 0)
+		args->ret = task_count;
+
+	ksft_print_dbg_msg("Waker: exiting with %d\n", args->ret);
+	pthread_exit((void *)&args->ret);
+}
+
+void *signal_wakerfn(void *arg)
+{
+	struct thread_arg *args = (struct thread_arg *)arg;
+	unsigned int old_val;
+	int nr_requeue = 0;
+	int task_count = 0;
+	int nr_wake = 1;
+	int i = 0;
+
+	ksft_print_dbg_msg("Waker: waiting for waiters to block\n");
+	while (waiters_blocked.val < THREAD_MAX)
+		usleep(1000);
+	usleep(1000);
+
+	while (task_count < THREAD_MAX && waiters_woken.val < THREAD_MAX) {
+		ksft_print_dbg_msg("task_count: %d, waiters_woken: %d\n",
+		     task_count, waiters_woken.val);
+		if (args->lock) {
+			ksft_print_dbg_msg("Calling FUTEX_LOCK_PI on mutex=%x @ %p\n",
+			    f2, &f2);
+			futex_lock_pi(&f2, NULL, 0, FUTEX_PRIVATE_FLAG);
+		}
+		ksft_print_dbg_msg("Waker: Calling signal\n");
+		/* cond_signal */
+		old_val = f1;
+		args->ret = futex_cmp_requeue_pi(&f1, old_val, &f2,
+						 nr_wake, nr_requeue,
+						 FUTEX_PRIVATE_FLAG);
+		if (args->ret < 0)
+			args->ret = -errno;
+		ksft_print_dbg_msg("futex: %x\n", f2);
+		if (args->lock) {
+			ksft_print_dbg_msg("Calling FUTEX_UNLOCK_PI on mutex=%x @ %p\n",
+			    f2, &f2);
+			futex_unlock_pi(&f2, FUTEX_PRIVATE_FLAG);
+		}
+		ksft_print_dbg_msg("futex: %x\n", f2);
+		if (args->ret < 0)
+			ksft_exit_fail_msg("FUTEX_CMP_REQUEUE_PI failed\n");
+
+		task_count += args->ret;
+		usleep(SIGNAL_PERIOD_US);
+		i++;
+		/* we have to loop at least THREAD_MAX times */
+		if (i > MAX_WAKE_ITERS + THREAD_MAX) {
+			ksft_exit_fail_msg("max signaling iterations (%d) reached, giving up on pending waiters.\n",
+			      MAX_WAKE_ITERS + THREAD_MAX);
+		}
+	}
+
+	futex_wake(&wake_complete, 1, FUTEX_PRIVATE_FLAG);
+
+	if (args->ret >= 0)
+		args->ret = task_count;
+
+	ksft_print_dbg_msg("Waker: exiting with %d\n", args->ret);
+	ksft_print_dbg_msg("Waker: waiters_woken: %d\n", waiters_woken.val);
+	pthread_exit((void *)&args->ret);
+}
+
+void *third_party_blocker(void *arg)
+{
+	struct thread_arg *args = (struct thread_arg *)arg;
+	int ret2 = 0;
+
+	args->ret = futex_lock_pi(&f2, NULL, 0, FUTEX_PRIVATE_FLAG);
+	if (args->ret)
+		goto out;
+	args->ret = futex_wait(&wake_complete, wake_complete, NULL,
+			       FUTEX_PRIVATE_FLAG);
+	ret2 = futex_unlock_pi(&f2, FUTEX_PRIVATE_FLAG);
+
+ out:
+	if (args->ret || ret2)
+		ksft_exit_fail_msg("third_party_blocker() futex error");
+
+	pthread_exit((void *)&args->ret);
+}
+
+TEST_F(args, futex_requeue_pi)
+{
+	struct thread_arg blocker_arg = THREAD_ARG_INITIALIZER;
+	struct thread_arg waker_arg = THREAD_ARG_INITIALIZER;
+	pthread_t waiter[THREAD_MAX], waker, blocker;
+	void *(*wakerfn)(void *) = signal_wakerfn;
+	bool third_party_owner = variant->owner;
+	long timeout_ns = variant->timeout_ns;
+	bool broadcast = variant->broadcast;
+	struct thread_arg args[THREAD_MAX];
+	struct timespec ts, *tsp = NULL;
+	bool lock = variant->locked;
+	int *waiter_ret, i, ret = 0;
+
+	ksft_print_msg(
+		"\tArguments: broadcast=%d locked=%d owner=%d timeout=%ldns\n",
+		broadcast, lock, third_party_owner, timeout_ns);
+
+	if (timeout_ns) {
+		time_t secs;
+
+		ksft_print_dbg_msg("timeout_ns = %ld\n", timeout_ns);
+		ret = clock_gettime(CLOCK_MONOTONIC, &ts);
+		secs = (ts.tv_nsec + timeout_ns) / 1000000000;
+		ts.tv_nsec = ((int64_t)ts.tv_nsec + timeout_ns) % 1000000000;
+		ts.tv_sec += secs;
+		ksft_print_dbg_msg("ts.tv_sec  = %ld\n", ts.tv_sec);
+		ksft_print_dbg_msg("ts.tv_nsec = %ld\n", ts.tv_nsec);
+		tsp = &ts;
+	}
+
+	if (broadcast)
+		wakerfn = broadcast_wakerfn;
+
+	if (third_party_owner) {
+		if (create_rt_thread(&blocker, third_party_blocker,
+				     (void *)&blocker_arg, SCHED_FIFO, 1)) {
+			ksft_exit_fail_msg("Creating third party blocker thread failed\n");
+		}
+	}
+
+	atomic_set(&waiters_woken, 0);
+	for (i = 0; i < THREAD_MAX; i++) {
+		args[i].id = i;
+		args[i].timeout = tsp;
+		ksft_print_dbg_msg("Starting thread %d\n", i);
+		if (create_rt_thread(&waiter[i], waiterfn, (void *)&args[i],
+				     SCHED_FIFO, 1)) {
+			ksft_exit_fail_msg("Creating waiting thread failed\n");
+		}
+	}
+	waker_arg.lock = lock;
+	if (create_rt_thread(&waker, wakerfn, (void *)&waker_arg,
+			     SCHED_FIFO, 1)) {
+		ksft_exit_fail_msg("Creating waker thread failed\n");
+	}
+
+	/* Wait for threads to finish */
+	/* Store the first error or failure encountered in waiter_ret */
+	waiter_ret = &args[0].ret;
+	for (i = 0; i < THREAD_MAX; i++)
+		pthread_join(waiter[i],
+			     *waiter_ret ? NULL : (void **)&waiter_ret);
+
+	if (third_party_owner)
+		pthread_join(blocker, NULL);
+	pthread_join(waker, NULL);
+
+	if (!ret) {
+		if (*waiter_ret)
+			ret = *waiter_ret;
+		else if (waker_arg.ret < 0)
+			ret = waker_arg.ret;
+		else if (blocker_arg.ret)
+			ret = blocker_arg.ret;
+	}
+
+	if (ret)
+		ksft_test_result_fail("fail");
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/futex/functional/futex_requeue_pi_mismatched_ops.c b/tools/testing/selftests/futex/functional/futex_requeue_pi_mismatched_ops.c
new file mode 100644
index 000000000..f686e6053
--- /dev/null
+++ b/tools/testing/selftests/futex/functional/futex_requeue_pi_mismatched_ops.c
@@ -0,0 +1,93 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/******************************************************************************
+ *
+ *   Copyright © International Business Machines  Corp., 2009
+ *
+ * DESCRIPTION
+ *      1. Block a thread using FUTEX_WAIT
+ *      2. Attempt to use FUTEX_CMP_REQUEUE_PI on the futex from 1.
+ *      3. The kernel must detect the mismatch and return -EINVAL.
+ *
+ * AUTHOR
+ *      Darren Hart <dvhart@linux.intel.com>
+ *
+ * HISTORY
+ *      2009-Nov-9: Initial version by Darren Hart <dvhart@linux.intel.com>
+ *
+ *****************************************************************************/
+
+#include <errno.h>
+#include <getopt.h>
+#include <pthread.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <time.h>
+
+#include "futextest.h"
+#include "kselftest_harness.h"
+
+futex_t f1 = FUTEX_INITIALIZER;
+futex_t f2 = FUTEX_INITIALIZER;
+int child_ret = 0;
+
+void *blocking_child(void *arg)
+{
+	child_ret = futex_wait(&f1, f1, NULL, FUTEX_PRIVATE_FLAG);
+	if (child_ret < 0) {
+		child_ret = -errno;
+		ksft_exit_fail_msg("futex_wait\n");
+	}
+	return (void *)&child_ret;
+}
+
+TEST(requeue_pi_mismatched_ops)
+{
+	pthread_t child;
+	int ret;
+
+	if (pthread_create(&child, NULL, blocking_child, NULL))
+		ksft_exit_fail_msg("pthread_create\n");
+
+	/* Allow the child to block in the kernel. */
+	sleep(1);
+
+	/*
+	 * The kernel should detect the waiter did not setup the
+	 * q->requeue_pi_key and return -EINVAL. If it does not,
+	 * it likely gave the lock to the child, which is now hung
+	 * in the kernel.
+	 */
+	ret = futex_cmp_requeue_pi(&f1, f1, &f2, 1, 0, FUTEX_PRIVATE_FLAG);
+	if (ret < 0) {
+		if (errno == EINVAL) {
+			/*
+			 * The kernel correctly detected the mismatched
+			 * requeue_pi target and aborted. Wake the child with
+			 * FUTEX_WAKE.
+			 */
+			ret = futex_wake(&f1, 1, FUTEX_PRIVATE_FLAG);
+			if (ret == 1)
+				ret = 0;
+			else if (ret < 0)
+				ksft_exit_fail_msg("futex_wake\n");
+			else
+				ksft_exit_fail_msg("futex_wake did not wake the child\n");
+		} else {
+			ksft_exit_fail_msg("futex_cmp_requeue_pi\n");
+		}
+	} else if (ret > 0) {
+		ksft_test_result_fail("futex_cmp_requeue_pi failed to detect the mismatch\n");
+	} else {
+		ksft_exit_fail_msg("futex_cmp_requeue_pi found no waiters\n");
+	}
+
+	pthread_join(child, NULL);
+
+	if (!ret && !child_ret)
+		ksft_test_result_pass("futex_requeue_pi_mismatched_ops passed\n");
+	else
+		ksft_test_result_pass("futex_requeue_pi_mismatched_ops failed\n");
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/futex/functional/futex_requeue_pi_signal_restart.c b/tools/testing/selftests/futex/functional/futex_requeue_pi_signal_restart.c
new file mode 100644
index 000000000..a18ccae73
--- /dev/null
+++ b/tools/testing/selftests/futex/functional/futex_requeue_pi_signal_restart.c
@@ -0,0 +1,167 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/******************************************************************************
+ *
+ *   Copyright © International Business Machines  Corp., 2006-2008
+ *
+ * DESCRIPTION
+ *      This test exercises the futex_wait_requeue_pi() signal handling both
+ *      before and after the requeue. The first should be restarted by the
+ *      kernel. The latter should return EWOULDBLOCK to the waiter.
+ *
+ * AUTHORS
+ *      Darren Hart <dvhart@linux.intel.com>
+ *
+ * HISTORY
+ *      2008-May-5: Initial version by Darren Hart <dvhart@linux.intel.com>
+ *
+ *****************************************************************************/
+
+#include <errno.h>
+#include <getopt.h>
+#include <limits.h>
+#include <pthread.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include "atomic.h"
+#include "futextest.h"
+#include "kselftest_harness.h"
+
+#define DELAY_US 100
+
+futex_t f1 = FUTEX_INITIALIZER;
+futex_t f2 = FUTEX_INITIALIZER;
+atomic_t requeued = ATOMIC_INITIALIZER;
+
+int waiter_ret = 0;
+
+int create_rt_thread(pthread_t *pth, void*(*func)(void *), void *arg,
+		     int policy, int prio)
+{
+	struct sched_param schedp;
+	pthread_attr_t attr;
+	int ret;
+
+	pthread_attr_init(&attr);
+	memset(&schedp, 0, sizeof(schedp));
+
+	ret = pthread_attr_setinheritsched(&attr, PTHREAD_EXPLICIT_SCHED);
+	if (ret)
+		ksft_exit_fail_msg("pthread_attr_setinheritsched\n");
+
+	ret = pthread_attr_setschedpolicy(&attr, policy);
+	if (ret)
+		ksft_exit_fail_msg("pthread_attr_setschedpolicy\n");
+
+	schedp.sched_priority = prio;
+	ret = pthread_attr_setschedparam(&attr, &schedp);
+	if (ret)
+		ksft_exit_fail_msg("pthread_attr_setschedparam\n");
+
+	ret = pthread_create(pth, &attr, func, arg);
+	if (ret)
+		ksft_exit_fail_msg("pthread_create\n");
+
+	return 0;
+}
+
+void handle_signal(int signo)
+{
+	ksft_print_dbg_msg("signal received %s requeue\n",
+	     requeued.val ? "after" : "prior to");
+}
+
+void *waiterfn(void *arg)
+{
+	unsigned int old_val;
+	int res;
+
+	ksft_print_dbg_msg("Waiter running\n");
+	ksft_print_dbg_msg("Calling FUTEX_LOCK_PI on f2=%x @ %p\n", f2, &f2);
+	old_val = f1;
+	res = futex_wait_requeue_pi(&f1, old_val, &(f2), NULL,
+				    FUTEX_PRIVATE_FLAG);
+	if (!requeued.val || errno != EWOULDBLOCK) {
+		ksft_test_result_fail("unexpected return from futex_wait_requeue_pi: %d (%s)\n",
+		     res, strerror(errno));
+		ksft_print_dbg_msg("w2:futex: %x\n", f2);
+		if (!res)
+			futex_unlock_pi(&f2, FUTEX_PRIVATE_FLAG);
+	}
+
+	pthread_exit(NULL);
+}
+
+
+TEST(futex_requeue_pi_signal_restart)
+{
+	unsigned int old_val;
+	struct sigaction sa;
+	pthread_t waiter;
+	int res;
+
+	sa.sa_handler = handle_signal;
+	sigemptyset(&sa.sa_mask);
+	sa.sa_flags = 0;
+	if (sigaction(SIGUSR1, &sa, NULL))
+		ksft_exit_fail_msg("sigaction\n");
+
+	ksft_print_dbg_msg("m1:f2: %x\n", f2);
+	ksft_print_dbg_msg("Creating waiter\n");
+	res = create_rt_thread(&waiter, waiterfn, NULL, SCHED_FIFO, 1);
+	if (res)
+		ksft_exit_fail_msg("Creating waiting thread failed");
+
+	ksft_print_dbg_msg("Calling FUTEX_LOCK_PI on f2=%x @ %p\n", f2, &f2);
+	ksft_print_dbg_msg("m2:f2: %x\n", f2);
+	futex_lock_pi(&f2, 0, 0, FUTEX_PRIVATE_FLAG);
+	ksft_print_dbg_msg("m3:f2: %x\n", f2);
+
+	while (1) {
+		/*
+		 * signal the waiter before requeue, waiter should automatically
+		 * restart futex_wait_requeue_pi() in the kernel. Wait for the
+		 * waiter to block on f1 again.
+		 */
+		ksft_print_dbg_msg("Issuing SIGUSR1 to waiter\n");
+		pthread_kill(waiter, SIGUSR1);
+		usleep(DELAY_US);
+
+		ksft_print_dbg_msg("Requeueing waiter via FUTEX_CMP_REQUEUE_PI\n");
+		old_val = f1;
+		res = futex_cmp_requeue_pi(&f1, old_val, &(f2), 1, 0,
+					   FUTEX_PRIVATE_FLAG);
+		/*
+		 * If res is non-zero, we either requeued the waiter or hit an
+		 * error, break out and handle it. If it is zero, then the
+		 * signal may have hit before the waiter was blocked on f1.
+		 * Try again.
+		 */
+		if (res > 0) {
+			atomic_set(&requeued, 1);
+			break;
+		} else if (res < 0) {
+			ksft_exit_fail_msg("FUTEX_CMP_REQUEUE_PI failed\n");
+		}
+	}
+	ksft_print_dbg_msg("m4:f2: %x\n", f2);
+
+	/*
+	 * Signal the waiter after requeue, waiter should return from
+	 * futex_wait_requeue_pi() with EWOULDBLOCK. Join the thread here so the
+	 * futex_unlock_pi() can't happen before the signal wakeup is detected
+	 * in the kernel.
+	 */
+	ksft_print_dbg_msg("Issuing SIGUSR1 to waiter\n");
+	pthread_kill(waiter, SIGUSR1);
+	ksft_print_dbg_msg("Waiting for waiter to return\n");
+	pthread_join(waiter, NULL);
+
+	ksft_print_dbg_msg("Calling FUTEX_UNLOCK_PI on mutex=%x @ %p\n", f2, &f2);
+	futex_unlock_pi(&f2, FUTEX_PRIVATE_FLAG);
+	ksft_print_dbg_msg("m5:f2: %x\n", f2);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/futex/functional/futex_wait.c b/tools/testing/selftests/futex/functional/futex_wait.c
new file mode 100644
index 000000000..7b8879409
--- /dev/null
+++ b/tools/testing/selftests/futex/functional/futex_wait.c
@@ -0,0 +1,146 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright Collabora Ltd., 2021
+ *
+ * futex cmp requeue test by André Almeida <andrealmeid@collabora.com>
+ */
+
+#include <pthread.h>
+#include <sys/shm.h>
+#include <sys/mman.h>
+#include <fcntl.h>
+
+#include "futextest.h"
+#include "kselftest_harness.h"
+
+#define timeout_ns  30000000
+#define WAKE_WAIT_US 10000
+#define SHM_PATH "futex_shm_file"
+
+void *futex;
+
+static void *waiterfn(void *arg)
+{
+	struct timespec to;
+	unsigned int flags = 0;
+
+	if (arg)
+		flags = *((unsigned int *) arg);
+
+	to.tv_sec = 0;
+	to.tv_nsec = timeout_ns;
+
+	if (futex_wait(futex, 0, &to, flags))
+		printf("waiter failed errno %d\n", errno);
+
+	return NULL;
+}
+
+TEST(private_futex)
+{
+	unsigned int flags = FUTEX_PRIVATE_FLAG;
+	u_int32_t f_private = 0;
+	pthread_t waiter;
+	int res;
+
+	futex = &f_private;
+
+	/* Testing a private futex */
+	ksft_print_dbg_msg("Calling private futex_wait on futex: %p\n", futex);
+	if (pthread_create(&waiter, NULL, waiterfn, (void *) &flags))
+		ksft_exit_fail_msg("pthread_create failed\n");
+
+	usleep(WAKE_WAIT_US);
+
+	ksft_print_dbg_msg("Calling private futex_wake on futex: %p\n", futex);
+	res = futex_wake(futex, 1, FUTEX_PRIVATE_FLAG);
+	if (res != 1) {
+		ksft_test_result_fail("futex_wake private returned: %d %s\n",
+				      errno, strerror(errno));
+	} else {
+		ksft_test_result_pass("futex_wake private succeeds\n");
+	}
+}
+
+TEST(anon_page)
+{
+	u_int32_t *shared_data;
+	pthread_t waiter;
+	int res, shm_id;
+
+	/* Testing an anon page shared memory */
+	shm_id = shmget(IPC_PRIVATE, 4096, IPC_CREAT | 0666);
+	if (shm_id < 0) {
+		if (errno == ENOSYS)
+			ksft_exit_skip("shmget syscall not supported\n");
+		perror("shmget");
+		exit(1);
+	}
+
+	shared_data = shmat(shm_id, NULL, 0);
+
+	*shared_data = 0;
+	futex = shared_data;
+
+	ksft_print_dbg_msg("Calling shared (page anon) futex_wait on futex: %p\n", futex);
+	if (pthread_create(&waiter, NULL, waiterfn, NULL))
+		ksft_exit_fail_msg("pthread_create failed\n");
+
+	usleep(WAKE_WAIT_US);
+
+	ksft_print_dbg_msg("Calling shared (page anon) futex_wake on futex: %p\n", futex);
+	res = futex_wake(futex, 1, 0);
+	if (res != 1) {
+		ksft_test_result_fail("futex_wake shared (page anon) returned: %d %s\n",
+				      errno, strerror(errno));
+	} else {
+		ksft_test_result_pass("futex_wake shared (page anon) succeeds\n");
+	}
+
+	shmdt(shared_data);
+}
+
+TEST(file_backed)
+{
+	u_int32_t f_private = 0;
+	pthread_t waiter;
+	int res, fd;
+	void *shm;
+
+	/* Testing a file backed shared memory */
+	fd = open(SHM_PATH, O_RDWR | O_CREAT, S_IRUSR | S_IWUSR);
+	if (fd < 0)
+		ksft_exit_fail_msg("open\n");
+
+	if (ftruncate(fd, sizeof(f_private)))
+		ksft_exit_fail_msg("ftruncate\n");
+
+	shm = mmap(NULL, sizeof(f_private), PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0);
+	if (shm == MAP_FAILED)
+		ksft_exit_fail_msg("mmap\n");
+
+	memcpy(shm, &f_private, sizeof(f_private));
+
+	futex = shm;
+
+	ksft_print_dbg_msg("Calling shared (file backed) futex_wait on futex: %p\n", futex);
+	if (pthread_create(&waiter, NULL, waiterfn, NULL))
+		ksft_exit_fail_msg("pthread_create failed\n");
+
+	usleep(WAKE_WAIT_US);
+
+	ksft_print_dbg_msg("Calling shared (file backed) futex_wake on futex: %p\n", futex);
+	res = futex_wake(shm, 1, 0);
+	if (res != 1) {
+		ksft_test_result_fail("futex_wake shared (file backed) returned: %d %s\n",
+				      errno, strerror(errno));
+	} else {
+		ksft_test_result_pass("futex_wake shared (file backed) succeeds\n");
+	}
+
+	munmap(shm, sizeof(f_private));
+	remove(SHM_PATH);
+	close(fd);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/futex/functional/futex_wait_private_mapped_file.c b/tools/testing/selftests/futex/functional/futex_wait_private_mapped_file.c
new file mode 100644
index 000000000..2a749f9b1
--- /dev/null
+++ b/tools/testing/selftests/futex/functional/futex_wait_private_mapped_file.c
@@ -0,0 +1,82 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/******************************************************************************
+ *
+ * Copyright FUJITSU LIMITED 2010
+ * Copyright KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
+ *
+ * DESCRIPTION
+ *      Internally, Futex has two handling mode, anon and file. The private file
+ *      mapping is special. At first it behave as file, but after write anything
+ *      it behave as anon. This test is intent to test such case.
+ *
+ * AUTHOR
+ *      KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
+ *
+ * HISTORY
+ *      2010-Jan-6: Initial version by KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
+ *
+ *****************************************************************************/
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <syscall.h>
+#include <unistd.h>
+#include <errno.h>
+#include <linux/futex.h>
+#include <pthread.h>
+#include <libgen.h>
+#include <signal.h>
+
+#include "futextest.h"
+#include "kselftest_harness.h"
+
+#define PAGE_SZ 4096
+
+char pad[PAGE_SZ] = {1};
+futex_t val = 1;
+char pad2[PAGE_SZ] = {1};
+
+#define WAKE_WAIT_US 3000000
+struct timespec wait_timeout = { .tv_sec = 5, .tv_nsec = 0};
+
+void *thr_futex_wait(void *arg)
+{
+	int ret;
+
+	ksft_print_dbg_msg("futex wait\n");
+	ret = futex_wait(&val, 1, &wait_timeout, 0);
+	if (ret && errno != EWOULDBLOCK && errno != ETIMEDOUT)
+		ksft_exit_fail_msg("futex error.\n");
+
+	if (ret && errno == ETIMEDOUT)
+		ksft_exit_fail_msg("waiter timedout\n");
+
+	ksft_print_dbg_msg("futex_wait: ret = %d, errno = %d\n", ret, errno);
+
+	return NULL;
+}
+
+TEST(wait_private_mapped_file)
+{
+	pthread_t thr;
+	int res;
+
+	res = pthread_create(&thr, NULL, thr_futex_wait, NULL);
+	if (res < 0)
+		ksft_exit_fail_msg("pthread_create error\n");
+
+	ksft_print_dbg_msg("wait a while\n");
+	usleep(WAKE_WAIT_US);
+	val = 2;
+	res = futex_wake(&val, 1, 0);
+	ksft_print_dbg_msg("futex_wake %d\n", res);
+	if (res != 1)
+		ksft_exit_fail_msg("FUTEX_WAKE didn't find the waiting thread.\n");
+
+	ksft_print_dbg_msg("join\n");
+	pthread_join(thr, NULL);
+
+	ksft_test_result_pass("wait_private_mapped_file");
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/futex/functional/futex_wait_timeout.c b/tools/testing/selftests/futex/functional/futex_wait_timeout.c
new file mode 100644
index 000000000..674dd13af
--- /dev/null
+++ b/tools/testing/selftests/futex/functional/futex_wait_timeout.c
@@ -0,0 +1,187 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/******************************************************************************
+ *
+ *   Copyright © International Business Machines  Corp., 2009
+ *
+ * DESCRIPTION
+ *      Block on a futex and wait for timeout.
+ *
+ * AUTHOR
+ *      Darren Hart <dvhart@linux.intel.com>
+ *
+ * HISTORY
+ *      2009-Nov-6: Initial version by Darren Hart <dvhart@linux.intel.com>
+ *      2021-Apr-26: More test cases by André Almeida <andrealmeid@collabora.com>
+ *
+ *****************************************************************************/
+
+#include <pthread.h>
+
+#include "futextest.h"
+#include "futex2test.h"
+#include "kselftest_harness.h"
+
+static long timeout_ns = 100000;	/* 100us default timeout */
+static futex_t futex_pi;
+static pthread_barrier_t barrier;
+
+/*
+ * Get a PI lock and hold it forever, so the main thread lock_pi will block
+ * and we can test the timeout
+ */
+void *get_pi_lock(void *arg)
+{
+	int ret;
+	volatile futex_t lock = 0;
+
+	ret = futex_lock_pi(&futex_pi, NULL, 0, 0);
+	if (ret != 0)
+		ksft_exit_fail_msg("futex_lock_pi failed\n");
+
+	pthread_barrier_wait(&barrier);
+
+	/* Blocks forever */
+	ret = futex_wait(&lock, 0, NULL, 0);
+	ksft_exit_fail_msg("futex_wait failed\n");
+
+	return NULL;
+}
+
+/*
+ * Check if the function returned the expected error
+ */
+static void test_timeout(int res, char *test_name, int err)
+{
+	if (!res || errno != err) {
+		ksft_test_result_fail("%s returned %d\n", test_name,
+				      res < 0 ? errno : res);
+	} else {
+		ksft_test_result_pass("%s succeeds\n", test_name);
+	}
+}
+
+/*
+ * Calculate absolute timeout and correct overflow
+ */
+static int futex_get_abs_timeout(clockid_t clockid, struct timespec *to,
+				 long timeout_ns)
+{
+	if (clock_gettime(clockid, to))
+		ksft_exit_fail_msg("clock_gettime failed\n");
+
+	to->tv_nsec += timeout_ns;
+
+	if (to->tv_nsec >= 1000000000) {
+		to->tv_sec++;
+		to->tv_nsec -= 1000000000;
+	}
+
+	return 0;
+}
+
+TEST(wait_bitset)
+{
+	futex_t f1 = FUTEX_INITIALIZER;
+	struct timespec to;
+	int res;
+
+	/* initialize relative timeout */
+	to.tv_sec = 0;
+	to.tv_nsec = timeout_ns;
+
+	res = futex_wait(&f1, f1, &to, 0);
+	test_timeout(res, "futex_wait relative", ETIMEDOUT);
+
+	/* FUTEX_WAIT_BITSET with CLOCK_REALTIME */
+	if (futex_get_abs_timeout(CLOCK_REALTIME, &to, timeout_ns))
+		ksft_test_result_error("get_time error");
+	res = futex_wait_bitset(&f1, f1, &to, 1, FUTEX_CLOCK_REALTIME);
+	test_timeout(res, "futex_wait_bitset realtime", ETIMEDOUT);
+
+	/* FUTEX_WAIT_BITSET with CLOCK_MONOTONIC */
+	if (futex_get_abs_timeout(CLOCK_MONOTONIC, &to, timeout_ns))
+		ksft_test_result_error("get_time error");
+	res = futex_wait_bitset(&f1, f1, &to, 1, 0);
+	test_timeout(res, "futex_wait_bitset monotonic", ETIMEDOUT);
+}
+
+TEST(requeue_pi)
+{
+	futex_t f1 = FUTEX_INITIALIZER;
+	struct timespec to;
+	int res;
+
+	/* FUTEX_WAIT_REQUEUE_PI with CLOCK_REALTIME */
+	if (futex_get_abs_timeout(CLOCK_REALTIME, &to, timeout_ns))
+		ksft_test_result_error("get_time error");
+	res = futex_wait_requeue_pi(&f1, f1, &futex_pi, &to, FUTEX_CLOCK_REALTIME);
+	test_timeout(res, "futex_wait_requeue_pi realtime", ETIMEDOUT);
+
+	/* FUTEX_WAIT_REQUEUE_PI with CLOCK_MONOTONIC */
+	if (futex_get_abs_timeout(CLOCK_MONOTONIC, &to, timeout_ns))
+		ksft_test_result_error("get_time error");
+	res = futex_wait_requeue_pi(&f1, f1, &futex_pi, &to, 0);
+	test_timeout(res, "futex_wait_requeue_pi monotonic", ETIMEDOUT);
+
+}
+
+TEST(lock_pi)
+{
+	struct timespec to;
+	pthread_t thread;
+	int res;
+
+	/* Create a thread that will lock forever so any waiter will timeout */
+	pthread_barrier_init(&barrier, NULL, 2);
+	pthread_create(&thread, NULL, get_pi_lock, NULL);
+
+	/* Wait until the other thread calls futex_lock_pi() */
+	pthread_barrier_wait(&barrier);
+	pthread_barrier_destroy(&barrier);
+
+	/*
+	 * FUTEX_LOCK_PI with CLOCK_REALTIME
+	 * Due to historical reasons, FUTEX_LOCK_PI supports only realtime
+	 * clock, but requires the caller to not set CLOCK_REALTIME flag.
+	 *
+	 * If you call FUTEX_LOCK_PI with a monotonic clock, it'll be
+	 * interpreted as a realtime clock, and (unless you mess your machine's
+	 * time or your time machine) the monotonic clock value is always
+	 * smaller than realtime and the syscall will timeout immediately.
+	 */
+	if (futex_get_abs_timeout(CLOCK_REALTIME, &to, timeout_ns))
+		ksft_test_result_error("get_time error");
+	res = futex_lock_pi(&futex_pi, &to, 0, 0);
+	test_timeout(res, "futex_lock_pi realtime", ETIMEDOUT);
+
+	/* Test operations that don't support FUTEX_CLOCK_REALTIME */
+	res = futex_lock_pi(&futex_pi, NULL, 0, FUTEX_CLOCK_REALTIME);
+	test_timeout(res, "futex_lock_pi invalid timeout flag", ENOSYS);
+}
+
+TEST(waitv)
+{
+	futex_t f1 = FUTEX_INITIALIZER;
+	struct futex_waitv waitv = {
+		.uaddr		= (uintptr_t)&f1,
+		.val		= f1,
+		.flags		= FUTEX_32,
+		.__reserved	= 0,
+	};
+	struct timespec to;
+	int res;
+
+	/* futex_waitv with CLOCK_MONOTONIC */
+	if (futex_get_abs_timeout(CLOCK_MONOTONIC, &to, timeout_ns))
+		ksft_test_result_error("get_time error");
+	res = futex_waitv(&waitv, 1, 0, &to, CLOCK_MONOTONIC);
+	test_timeout(res, "futex_waitv monotonic", ETIMEDOUT);
+
+	/* futex_waitv with CLOCK_REALTIME */
+	if (futex_get_abs_timeout(CLOCK_REALTIME, &to, timeout_ns))
+		ksft_test_result_error("get_time error");
+	res = futex_waitv(&waitv, 1, 0, &to, CLOCK_REALTIME);
+	test_timeout(res, "futex_waitv realtime", ETIMEDOUT);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/futex/functional/futex_wait_uninitialized_heap.c b/tools/testing/selftests/futex/functional/futex_wait_uninitialized_heap.c
new file mode 100644
index 000000000..b07d68a67
--- /dev/null
+++ b/tools/testing/selftests/futex/functional/futex_wait_uninitialized_heap.c
@@ -0,0 +1,83 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/******************************************************************************
+ *
+ * Copyright FUJITSU LIMITED 2010
+ * Copyright KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
+ *
+ * DESCRIPTION
+ *      Wait on uninitialized heap. It shold be zero and FUTEX_WAIT should
+ *      return immediately. This test is intent to test zero page handling in
+ *      futex.
+ *
+ * AUTHOR
+ *      KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
+ *
+ * HISTORY
+ *      2010-Jan-6: Initial version by KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
+ *
+ *****************************************************************************/
+
+#include <pthread.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <sys/mman.h>
+#include <syscall.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
+#include <errno.h>
+#include <linux/futex.h>
+#include <libgen.h>
+
+#include "futextest.h"
+#include "kselftest_harness.h"
+
+#define WAIT_US 5000000
+
+static int child_blocked = 1;
+static bool child_ret;
+void *buf;
+
+void *wait_thread(void *arg)
+{
+	int res;
+
+	child_ret = true;
+	res = futex_wait(buf, 1, NULL, 0);
+	child_blocked = 0;
+
+	if (res != 0 && errno != EWOULDBLOCK) {
+		ksft_exit_fail_msg("futex failure\n");
+		child_ret = false;
+	}
+	pthread_exit(NULL);
+}
+
+TEST(futex_wait_uninitialized_heap)
+{
+	long page_size;
+	pthread_t thr;
+	int ret;
+
+	page_size = sysconf(_SC_PAGESIZE);
+
+	buf = mmap(NULL, page_size, PROT_READ|PROT_WRITE,
+		   MAP_PRIVATE|MAP_ANONYMOUS, 0, 0);
+	if (buf == (void *)-1)
+		ksft_exit_fail_msg("mmap\n");
+
+	ret = pthread_create(&thr, NULL, wait_thread, NULL);
+	if (ret)
+		ksft_exit_fail_msg("pthread_create\n");
+
+	ksft_print_dbg_msg("waiting %dus for child to return\n", WAIT_US);
+	usleep(WAIT_US);
+
+	if (child_blocked)
+		ksft_test_result_fail("child blocked in kernel\n");
+
+	if (!child_ret)
+		ksft_test_result_fail("child error\n");
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/futex/functional/futex_wait_wouldblock.c b/tools/testing/selftests/futex/functional/futex_wait_wouldblock.c
new file mode 100644
index 000000000..9ff936ecf
--- /dev/null
+++ b/tools/testing/selftests/futex/functional/futex_wait_wouldblock.c
@@ -0,0 +1,81 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/******************************************************************************
+ *
+ *   Copyright © International Business Machines  Corp., 2009
+ *
+ * DESCRIPTION
+ *      Test if FUTEX_WAIT op returns -EWOULDBLOCK if the futex value differs
+ *      from the expected one.
+ *
+ * AUTHOR
+ *      Gowrishankar <gowrishankar.m@in.ibm.com>
+ *
+ * HISTORY
+ *      2009-Nov-14: Initial version by Gowrishankar <gowrishankar.m@in.ibm.com>
+ *
+ *****************************************************************************/
+
+#include <errno.h>
+#include <getopt.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <time.h>
+
+#include "futextest.h"
+#include "futex2test.h"
+#include "kselftest_harness.h"
+
+#define timeout_ns 100000
+
+TEST(futex_wait_wouldblock)
+{
+	struct timespec to = {.tv_sec = 0, .tv_nsec = timeout_ns};
+	futex_t f1 = FUTEX_INITIALIZER;
+	int res;
+
+	ksft_print_dbg_msg("Calling futex_wait on f1: %u @ %p with val=%u\n", f1, &f1, f1+1);
+	res = futex_wait(&f1, f1+1, &to, FUTEX_PRIVATE_FLAG);
+	if (!res || errno != EWOULDBLOCK) {
+		ksft_test_result_fail("futex_wait returned: %d %s\n",
+				      res ? errno : res,
+				      res ? strerror(errno) : "");
+	} else {
+		ksft_test_result_pass("futex_wait\n");
+	}
+}
+
+TEST(futex_waitv_wouldblock)
+{
+	struct timespec to = {.tv_sec = 0, .tv_nsec = timeout_ns};
+	futex_t f1 = FUTEX_INITIALIZER;
+	struct futex_waitv waitv = {
+		.uaddr		= (uintptr_t)&f1,
+		.val		= f1 + 1,
+		.flags		= FUTEX_32,
+		.__reserved	= 0,
+	};
+	int res;
+
+	if (clock_gettime(CLOCK_MONOTONIC, &to))
+		ksft_exit_fail_msg("clock_gettime failed %d\n", errno);
+
+	to.tv_nsec += timeout_ns;
+
+	if (to.tv_nsec >= 1000000000) {
+		to.tv_sec++;
+		to.tv_nsec -= 1000000000;
+	}
+
+	ksft_print_dbg_msg("Calling futex_waitv on f1: %u @ %p with val=%u\n", f1, &f1, f1+1);
+	res = futex_waitv(&waitv, 1, 0, &to, CLOCK_MONOTONIC);
+	if (!res || errno != EWOULDBLOCK) {
+		ksft_test_result_fail("futex_waitv returned: %d %s\n",
+				      res ? errno : res,
+				      res ? strerror(errno) : "");
+	} else {
+		ksft_test_result_pass("futex_waitv\n");
+	}
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/futex/functional/futex_waitv.c b/tools/testing/selftests/futex/functional/futex_waitv.c
new file mode 100644
index 000000000..b5ada9fdb
--- /dev/null
+++ b/tools/testing/selftests/futex/functional/futex_waitv.c
@@ -0,0 +1,228 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * futex_waitv() test by André Almeida <andrealmeid@collabora.com>
+ *
+ * Copyright 2021 Collabora Ltd.
+ */
+
+#include <errno.h>
+#include <error.h>
+#include <getopt.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <time.h>
+#include <pthread.h>
+#include <stdint.h>
+#include <sys/shm.h>
+
+#include "futextest.h"
+#include "futex2test.h"
+#include "kselftest_harness.h"
+
+#define WAKE_WAIT_US 10000
+#define NR_FUTEXES 30
+static struct futex_waitv waitv[NR_FUTEXES];
+u_int32_t futexes[NR_FUTEXES] = {0};
+
+void *waiterfn(void *arg)
+{
+	struct timespec to;
+	int res;
+
+	/* setting absolute timeout for futex2 */
+	if (clock_gettime(CLOCK_MONOTONIC, &to))
+		ksft_exit_fail_msg("gettime64 failed\n");
+
+	to.tv_sec++;
+
+	res = futex_waitv(waitv, NR_FUTEXES, 0, &to, CLOCK_MONOTONIC);
+	if (res < 0) {
+		ksft_test_result_fail("futex_waitv returned: %d %s\n",
+				      errno, strerror(errno));
+	} else if (res != NR_FUTEXES - 1) {
+		ksft_test_result_fail("futex_waitv returned: %d, expecting %d\n",
+				      res, NR_FUTEXES - 1);
+	}
+
+	return NULL;
+}
+
+TEST(private_waitv)
+{
+	pthread_t waiter;
+	int res, i;
+
+	for (i = 0; i < NR_FUTEXES; i++) {
+		waitv[i].uaddr = (uintptr_t)&futexes[i];
+		waitv[i].flags = FUTEX_32 | FUTEX_PRIVATE_FLAG;
+		waitv[i].val = 0;
+		waitv[i].__reserved = 0;
+	}
+
+	/* Private waitv */
+	if (pthread_create(&waiter, NULL, waiterfn, NULL))
+		ksft_exit_fail_msg("pthread_create failed\n");
+
+	usleep(WAKE_WAIT_US);
+
+	res = futex_wake(u64_to_ptr(waitv[NR_FUTEXES - 1].uaddr), 1, FUTEX_PRIVATE_FLAG);
+	if (res != 1) {
+		ksft_test_result_fail("futex_wake private returned: %d %s\n",
+				      res ? errno : res,
+				      res ? strerror(errno) : "");
+	} else {
+		ksft_test_result_pass("futex_waitv private\n");
+	}
+}
+
+TEST(shared_waitv)
+{
+	pthread_t waiter;
+	int res, i;
+
+	/* Shared waitv */
+	for (i = 0; i < NR_FUTEXES; i++) {
+		int shm_id = shmget(IPC_PRIVATE, 4096, IPC_CREAT | 0666);
+
+		if (shm_id < 0) {
+			if (errno == ENOSYS)
+				ksft_exit_skip("shmget syscall not supported\n");
+			perror("shmget");
+			exit(1);
+		}
+
+		unsigned int *shared_data = shmat(shm_id, NULL, 0);
+
+		*shared_data = 0;
+		waitv[i].uaddr = (uintptr_t)shared_data;
+		waitv[i].flags = FUTEX_32;
+		waitv[i].val = 0;
+		waitv[i].__reserved = 0;
+	}
+
+	if (pthread_create(&waiter, NULL, waiterfn, NULL))
+		ksft_exit_fail_msg("pthread_create failed\n");
+
+	usleep(WAKE_WAIT_US);
+
+	res = futex_wake(u64_to_ptr(waitv[NR_FUTEXES - 1].uaddr), 1, 0);
+	if (res != 1) {
+		ksft_test_result_fail("futex_wake shared returned: %d %s\n",
+				      res ? errno : res,
+				      res ? strerror(errno) : "");
+	} else {
+		ksft_test_result_pass("futex_waitv shared\n");
+	}
+
+	for (i = 0; i < NR_FUTEXES; i++)
+		shmdt(u64_to_ptr(waitv[i].uaddr));
+}
+
+TEST(invalid_flag)
+{
+	struct timespec to;
+	int res;
+
+	/* Testing a waiter without FUTEX_32 flag */
+	waitv[0].flags = FUTEX_PRIVATE_FLAG;
+
+	if (clock_gettime(CLOCK_MONOTONIC, &to))
+		ksft_exit_fail_msg("gettime64 failed\n");
+
+	to.tv_sec++;
+
+	res = futex_waitv(waitv, NR_FUTEXES, 0, &to, CLOCK_MONOTONIC);
+	if (res == EINVAL) {
+		ksft_test_result_fail("futex_waitv private returned: %d %s\n",
+				      res ? errno : res,
+				      res ? strerror(errno) : "");
+	} else {
+		ksft_test_result_pass("futex_waitv without FUTEX_32\n");
+	}
+}
+
+TEST(unaligned_address)
+{
+	struct timespec to;
+	int res;
+
+	/* Testing a waiter with an unaligned address */
+	waitv[0].flags = FUTEX_PRIVATE_FLAG | FUTEX_32;
+	waitv[0].uaddr = 1;
+
+	if (clock_gettime(CLOCK_MONOTONIC, &to))
+		ksft_exit_fail_msg("gettime64 failed\n");
+
+	to.tv_sec++;
+
+	res = futex_waitv(waitv, NR_FUTEXES, 0, &to, CLOCK_MONOTONIC);
+	if (res == EINVAL) {
+		ksft_test_result_fail("futex_wake private returned: %d %s\n",
+				      res ? errno : res,
+				      res ? strerror(errno) : "");
+	} else {
+		ksft_test_result_pass("futex_waitv with an unaligned address\n");
+	}
+}
+
+TEST(null_address)
+{
+	struct timespec to;
+	int res;
+
+	/* Testing a NULL address for waiters.uaddr */
+	waitv[0].uaddr = 0x00000000;
+
+	if (clock_gettime(CLOCK_MONOTONIC, &to))
+		ksft_exit_fail_msg("gettime64 failed\n");
+
+	to.tv_sec++;
+
+	res = futex_waitv(waitv, NR_FUTEXES, 0, &to, CLOCK_MONOTONIC);
+	if (res == EINVAL) {
+		ksft_test_result_fail("futex_waitv private returned: %d %s\n",
+				      res ? errno : res,
+				      res ? strerror(errno) : "");
+	} else {
+		ksft_test_result_pass("futex_waitv NULL address in waitv.uaddr\n");
+	}
+
+	/* Testing a NULL address for *waiters */
+	if (clock_gettime(CLOCK_MONOTONIC, &to))
+		ksft_exit_fail_msg("gettime64 failed\n");
+
+	to.tv_sec++;
+
+	res = futex_waitv(NULL, NR_FUTEXES, 0, &to, CLOCK_MONOTONIC);
+	if (res == EINVAL) {
+		ksft_test_result_fail("futex_waitv private returned: %d %s\n",
+				      res ? errno : res,
+				      res ? strerror(errno) : "");
+	} else {
+		ksft_test_result_pass("futex_waitv NULL address in *waiters\n");
+	}
+}
+
+TEST(invalid_clockid)
+{
+	struct timespec to;
+	int res;
+
+	/* Testing an invalid clockid */
+	if (clock_gettime(CLOCK_MONOTONIC, &to))
+		ksft_exit_fail_msg("gettime64 failed\n");
+
+	to.tv_sec++;
+
+	res = futex_waitv(NULL, NR_FUTEXES, 0, &to, CLOCK_TAI);
+	if (res == EINVAL) {
+		ksft_test_result_fail("futex_waitv private returned: %d %s\n",
+				      res ? errno : res,
+				      res ? strerror(errno) : "");
+	} else {
+		ksft_test_result_pass("futex_waitv invalid clockid\n");
+	}
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/futex/functional/robust_list.c b/tools/testing/selftests/futex/functional/robust_list.c
new file mode 100644
index 000000000..b3fab6018
--- /dev/null
+++ b/tools/testing/selftests/futex/functional/robust_list.c
@@ -0,0 +1,791 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2025 Igalia S.L.
+ *
+ * Robust list test by André Almeida <andrealmeid@igalia.com>
+ *
+ * The robust list uAPI allows userspace to create "robust" locks, in the sense
+ * that if the lock holder thread dies, the remaining threads that are waiting
+ * for the lock won't block forever, waiting for a lock that will never be
+ * released.
+ *
+ * This is achieve by userspace setting a list where a thread can enter all the
+ * locks (futexes) that it is holding. The robust list is a linked list, and
+ * userspace register the start of the list with the syscall set_robust_list().
+ * If such thread eventually dies, the kernel will walk this list, waking up one
+ * thread waiting for each futex and marking the futex word with the flag
+ * FUTEX_OWNER_DIED.
+ *
+ * See also
+ *	man set_robust_list
+ *	Documententation/locking/robust-futex-ABI.rst
+ *	Documententation/locking/robust-futexes.rst
+ */
+
+#define _GNU_SOURCE
+
+#include "futextest.h"
+#include "../../kselftest_harness.h"
+
+#include <dlfcn.h>
+#include <errno.h>
+#include <pthread.h>
+#include <signal.h>
+#include <stdint.h>
+#include <stdatomic.h>
+#include <stdbool.h>
+#include <stddef.h>
+#include <sys/auxv.h>
+#include <sys/mman.h>
+#include <sys/wait.h>
+
+#define STACK_SIZE (1024 * 1024)
+
+#define FUTEX_TIMEOUT 3
+
+#define SLEEP_US 100
+
+#if __SIZEOF_LONG__ == 8
+# define BUILD_64
+#endif
+
+static pthread_barrier_t barrier, barrier2;
+
+static int set_robust_list(struct robust_list_head *head, size_t len)
+{
+	return syscall(SYS_set_robust_list, head, len);
+}
+
+static int get_robust_list(int pid, struct robust_list_head **head, size_t *len_ptr)
+{
+	return syscall(SYS_get_robust_list, pid, head, len_ptr);
+}
+
+static int sys_futex_robust_unlock(_Atomic(uint32_t) *uaddr, unsigned int op, int val,
+				   void *list_op_pending, unsigned int val3)
+{
+	return syscall(SYS_futex, uaddr, op, val, NULL, list_op_pending, val3, 0);
+}
+
+/*
+ * Basic lock struct, contains just the futex word and the robust list element
+ * Real implementations have also a *prev to easily walk in the list
+ */
+struct lock_struct {
+	_Atomic(unsigned int)	futex;
+	struct robust_list	list;
+};
+
+/*
+ * Helper function to spawn a child thread. Returns -1 on error, pid on success
+ */
+static int create_child(int (*fn)(void *arg), void *arg)
+{
+	char *stack;
+	pid_t pid;
+
+	stack = mmap(NULL, STACK_SIZE, PROT_READ | PROT_WRITE,
+		     MAP_PRIVATE | MAP_ANONYMOUS | MAP_STACK, -1, 0);
+	if (stack == MAP_FAILED)
+		return -1;
+
+	stack += STACK_SIZE;
+
+	pid = clone(fn, stack, CLONE_VM | SIGCHLD, arg);
+
+	if (pid == -1)
+		return -1;
+
+	return pid;
+}
+
+/*
+ * Helper function to prepare and register a robust list
+ */
+static int set_list(struct robust_list_head *head)
+{
+	int ret;
+
+	ret = set_robust_list(head, sizeof(*head));
+	if (ret)
+		return ret;
+
+	head->futex_offset = (size_t) offsetof(struct lock_struct, futex) -
+			     (size_t) offsetof(struct lock_struct, list);
+	head->list.next = &head->list;
+	head->list_op_pending = NULL;
+
+	return 0;
+}
+
+/*
+ * A basic (and incomplete) mutex lock function with robustness
+ */
+static int mutex_lock(struct lock_struct *lock, struct robust_list_head *head, bool error_inject)
+{
+	_Atomic(unsigned int) *futex = &lock->futex;
+	unsigned int zero = 0;
+	pid_t tid = gettid();
+	int ret = -1;
+
+	/*
+	 * Set list_op_pending before starting the lock, so the kernel can catch
+	 * the case where the thread died during the lock operation
+	 */
+	head->list_op_pending = &lock->list;
+
+	if (atomic_compare_exchange_strong(futex, &zero, tid)) {
+		/*
+		 * We took the lock, insert it in the robust list
+		 */
+		struct robust_list *list = &head->list;
+
+		/* Error injection to test list_op_pending */
+		if (error_inject)
+			return 0;
+
+		while (list->next != &head->list)
+			list = list->next;
+
+		list->next = &lock->list;
+		lock->list.next = &head->list;
+
+		ret = 0;
+	} else {
+		/*
+		 * We didn't take the lock, wait until the owner wakes (or dies)
+		 */
+		struct timespec to;
+
+		to.tv_sec = FUTEX_TIMEOUT;
+		to.tv_nsec = 0;
+
+		tid = atomic_load(futex);
+		/* Kernel ignores futexes without the waiters flag */
+		tid |= FUTEX_WAITERS;
+		atomic_store(futex, tid);
+
+		ret = futex_wait((futex_t *) futex, tid, &to, 0);
+
+		/*
+		 * A real mutex_lock() implementation would loop here to finally
+		 * take the lock. We don't care about that, so we stop here.
+		 */
+	}
+
+	head->list_op_pending = NULL;
+
+	return ret;
+}
+
+/*
+ * This child thread will succeed taking the lock, and then will exit holding it
+ */
+static int child_fn_lock(void *arg)
+{
+	struct lock_struct *lock = arg;
+	struct robust_list_head head;
+	int ret;
+
+	ret = set_list(&head);
+	if (ret) {
+		ksft_test_result_fail("set_robust_list error\n");
+		return ret;
+	}
+
+	ret = mutex_lock(lock, &head, false);
+	if (ret) {
+		ksft_test_result_fail("mutex_lock error\n");
+		return ret;
+	}
+
+	pthread_barrier_wait(&barrier);
+
+	/*
+	 * There's a race here: the parent thread needs to be inside
+	 * futex_wait() before the child thread dies, otherwise it will miss the
+	 * wakeup from handle_futex_death() that this child will emit. We wait a
+	 * little bit just to make sure that this happens.
+	 */
+	usleep(SLEEP_US);
+
+	return 0;
+}
+
+/*
+ * Spawns a child thread that will set a robust list, take the lock, register it
+ * in the robust list and die. The parent thread will wait on this futex, and
+ * should be waken up when the child exits.
+ */
+TEST(test_robustness)
+{
+	struct lock_struct lock = { .futex = 0 };
+	_Atomic(unsigned int) *futex = &lock.futex;
+	struct robust_list_head head;
+	int ret, pid, wstatus;
+
+	ret = set_list(&head);
+	ASSERT_EQ(ret, 0);
+
+	/*
+	 * Lets use a barrier to ensure that the child thread takes the lock
+	 * before the parent
+	 */
+	ret = pthread_barrier_init(&barrier, NULL, 2);
+	ASSERT_EQ(ret, 0);
+
+	pid = create_child(&child_fn_lock, &lock);
+	ASSERT_NE(pid, -1);
+
+	pthread_barrier_wait(&barrier);
+	ret = mutex_lock(&lock, &head, false);
+
+	/*
+	 * futex_wait() should return 0 and the futex word should be marked with
+	 * FUTEX_OWNER_DIED
+	 */
+	ASSERT_EQ(ret, 0);
+
+	ASSERT_TRUE(*futex & FUTEX_OWNER_DIED);
+
+	wait(&wstatus);
+	pthread_barrier_destroy(&barrier);
+
+	/* Pass only if the child hasn't return error */
+	if (!WEXITSTATUS(wstatus))
+		ksft_test_result_pass("%s\n", __func__);
+}
+
+/*
+ * The only valid value for len is sizeof(*head)
+ */
+TEST(test_set_robust_list_invalid_size)
+{
+	struct robust_list_head head;
+	size_t head_size = sizeof(head);
+	int ret;
+
+	ret = set_robust_list(&head, head_size);
+	ASSERT_EQ(ret, 0);
+
+	ret = set_robust_list(&head, head_size * 2);
+	ASSERT_EQ(ret, -1);
+	ASSERT_EQ(errno, EINVAL);
+
+	ret = set_robust_list(&head, head_size - 1);
+	ASSERT_EQ(ret, -1);
+	ASSERT_EQ(errno, EINVAL);
+
+	ret = set_robust_list(&head, 0);
+	ASSERT_EQ(ret, -1);
+	ASSERT_EQ(errno, EINVAL);
+
+	ksft_test_result_pass("%s\n", __func__);
+}
+
+/*
+ * Test get_robust_list with pid = 0, getting the list of the running thread
+ */
+TEST(test_get_robust_list_self)
+{
+	struct robust_list_head head, head2, *get_head;
+	size_t head_size = sizeof(head), len_ptr;
+	int ret;
+
+	ret = set_robust_list(&head, head_size);
+	ASSERT_EQ(ret, 0);
+
+	ret = get_robust_list(0, &get_head, &len_ptr);
+	ASSERT_EQ(ret, 0);
+	ASSERT_EQ(get_head, &head);
+	ASSERT_EQ(head_size, len_ptr);
+
+	ret = set_robust_list(&head2, head_size);
+	ASSERT_EQ(ret, 0);
+
+	ret = get_robust_list(0, &get_head, &len_ptr);
+	ASSERT_EQ(ret, 0);
+	ASSERT_EQ(get_head, &head2);
+	ASSERT_EQ(head_size, len_ptr);
+
+	ksft_test_result_pass("%s\n", __func__);
+}
+
+static int child_list(void *arg)
+{
+	struct robust_list_head *head = arg;
+	int ret;
+
+	ret = set_robust_list(head, sizeof(*head));
+	if (ret) {
+		ksft_test_result_fail("set_robust_list error\n");
+		return -1;
+	}
+
+	/*
+	 * After setting the list head, wait until the main thread can call
+	 * get_robust_list() for this thread before exiting.
+	 */
+	pthread_barrier_wait(&barrier);
+	pthread_barrier_wait(&barrier2);
+
+	return 0;
+}
+
+/*
+ * Test get_robust_list from another thread. We use two barriers here to ensure
+ * that:
+ *   1) the child thread set the list before we try to get it from the
+ * parent
+ *   2) the child thread still alive when we try to get the list from it
+ */
+TEST(test_get_robust_list_child)
+{
+	struct robust_list_head head, *get_head;
+	int ret, wstatus;
+	size_t len_ptr;
+	pid_t tid;
+
+	ret = pthread_barrier_init(&barrier, NULL, 2);
+	ret = pthread_barrier_init(&barrier2, NULL, 2);
+	ASSERT_EQ(ret, 0);
+
+	tid = create_child(&child_list, &head);
+	ASSERT_NE(tid, -1);
+
+	pthread_barrier_wait(&barrier);
+
+	ret = get_robust_list(tid, &get_head, &len_ptr);
+	ASSERT_EQ(ret, 0);
+	ASSERT_EQ(&head, get_head);
+
+	pthread_barrier_wait(&barrier2);
+
+	wait(&wstatus);
+	pthread_barrier_destroy(&barrier);
+	pthread_barrier_destroy(&barrier2);
+
+	/* Pass only if the child hasn't return error */
+	if (!WEXITSTATUS(wstatus))
+		ksft_test_result_pass("%s\n", __func__);
+}
+
+static int child_fn_lock_with_error(void *arg)
+{
+	struct lock_struct *lock = arg;
+	struct robust_list_head head;
+	int ret;
+
+	ret = set_list(&head);
+	if (ret) {
+		ksft_test_result_fail("set_robust_list error\n");
+		return -1;
+	}
+
+	ret = mutex_lock(lock, &head, true);
+	if (ret) {
+		ksft_test_result_fail("mutex_lock error\n");
+		return -1;
+	}
+
+	pthread_barrier_wait(&barrier);
+
+	/* See comment at child_fn_lock() */
+	usleep(SLEEP_US);
+
+	return 0;
+}
+
+/*
+ * Same as robustness test, but inject an error where the mutex_lock() exits
+ * earlier, just after setting list_op_pending and taking the lock, to test the
+ * list_op_pending mechanism
+ */
+TEST(test_set_list_op_pending)
+{
+	struct lock_struct lock = { .futex = 0 };
+	_Atomic(unsigned int) *futex = &lock.futex;
+	struct robust_list_head head;
+	int ret, wstatus;
+
+	ret = set_list(&head);
+	ASSERT_EQ(ret, 0);
+
+	ret = pthread_barrier_init(&barrier, NULL, 2);
+	ASSERT_EQ(ret, 0);
+
+	ret = create_child(&child_fn_lock_with_error, &lock);
+	ASSERT_NE(ret, -1);
+
+	pthread_barrier_wait(&barrier);
+	ret = mutex_lock(&lock, &head, false);
+
+	ASSERT_EQ(ret, 0);
+
+	ASSERT_TRUE(*futex & FUTEX_OWNER_DIED);
+
+	wait(&wstatus);
+	pthread_barrier_destroy(&barrier);
+
+	/* Pass only if the child hasn't return error */
+	if (!WEXITSTATUS(wstatus))
+		ksft_test_result_pass("%s\n", __func__);
+	else
+		ksft_test_result_fail("%s\n", __func__);
+}
+
+#define CHILD_NR 10
+
+static int child_lock_holder(void *arg)
+{
+	struct lock_struct *locks = arg;
+	struct robust_list_head head;
+	int i;
+
+	set_list(&head);
+
+	for (i = 0; i < CHILD_NR; i++) {
+		locks[i].futex = 0;
+		mutex_lock(&locks[i], &head, false);
+	}
+
+	pthread_barrier_wait(&barrier);
+	pthread_barrier_wait(&barrier2);
+
+	/* See comment at child_fn_lock() */
+	usleep(SLEEP_US);
+
+	return 0;
+}
+
+static int child_wait_lock(void *arg)
+{
+	struct lock_struct *lock = arg;
+	struct robust_list_head head;
+	int ret;
+
+	pthread_barrier_wait(&barrier2);
+	ret = mutex_lock(lock, &head, false);
+
+	if (ret) {
+		ksft_test_result_fail("mutex_lock error\n");
+		return -1;
+	}
+
+	if (!(lock->futex & FUTEX_OWNER_DIED)) {
+		ksft_test_result_fail("futex not marked with FUTEX_OWNER_DIED\n");
+		return -1;
+	}
+
+	return 0;
+}
+
+/*
+ * Test a robust list of more than one element. All the waiters should wake when
+ * the holder dies
+ */
+TEST(test_robust_list_multiple_elements)
+{
+	struct lock_struct locks[CHILD_NR];
+	pid_t pids[CHILD_NR + 1];
+	int i, ret, wstatus;
+
+	ret = pthread_barrier_init(&barrier, NULL, 2);
+	ASSERT_EQ(ret, 0);
+	ret = pthread_barrier_init(&barrier2, NULL, CHILD_NR + 1);
+	ASSERT_EQ(ret, 0);
+
+	pids[0] = create_child(&child_lock_holder, &locks);
+
+	/* Wait until the locker thread takes the look */
+	pthread_barrier_wait(&barrier);
+
+	for (i = 0; i < CHILD_NR; i++)
+		pids[i+1] = create_child(&child_wait_lock, &locks[i]);
+
+	/* Wait for all children to return */
+	ret = 0;
+
+	for (i = 0; i < CHILD_NR; i++) {
+		waitpid(pids[i], &wstatus, 0);
+		if (WEXITSTATUS(wstatus))
+			ret = -1;
+	}
+
+	pthread_barrier_destroy(&barrier);
+	pthread_barrier_destroy(&barrier2);
+
+	/* Pass only if the child hasn't return error */
+	if (!ret)
+		ksft_test_result_pass("%s\n", __func__);
+}
+
+static int child_circular_list(void *arg)
+{
+	static struct robust_list_head head;
+	struct lock_struct a, b, c;
+	int ret;
+
+	ret = set_list(&head);
+	if (ret) {
+		ksft_test_result_fail("set_list error\n");
+		return -1;
+	}
+
+	head.list.next = &a.list;
+
+	/*
+	 * The last element should point to head list, but we short circuit it
+	 */
+	a.list.next = &b.list;
+	b.list.next = &c.list;
+	c.list.next = &a.list;
+
+	return 0;
+}
+
+/*
+ * Create a circular robust list. The kernel should be able to destroy the list
+ * while processing it so it won't be trapped in an infinite loop while handling
+ * a process exit
+ */
+TEST(test_circular_list)
+{
+	int wstatus;
+
+	create_child(child_circular_list, NULL);
+
+	wait(&wstatus);
+
+	/* Pass only if the child hasn't return error */
+	if (!WEXITSTATUS(wstatus))
+		ksft_test_result_pass("%s\n", __func__);
+}
+
+/*
+ * Below are tests for the fix of robust release race condition. Please read the following
+ * thread to learn more about the issue in the first place and why the following functions fix it:
+ * https://lore.kernel.org/lkml/20260316162316.356674433@kernel.org/
+ */
+
+/*
+ * Auxiliary code for binding the vDSO functions
+ */
+static void *get_vdso_func_addr(const char *function)
+{
+	const char *vdso_names[] = {
+		"linux-vdso.so.1", "linux-gate.so.1", "linux-vdso32.so.1", "linux-vdso64.so.1",
+	};
+
+	for (int i = 0; i < ARRAY_SIZE(vdso_names); i++) {
+		void *vdso = dlopen(vdso_names[i], RTLD_LAZY | RTLD_LOCAL | RTLD_NOLOAD);
+
+		if (vdso)
+			return dlsym(vdso, function);
+	}
+	return NULL;
+}
+
+/*
+ * These are the real vDSO function signatures:
+ *
+ *	__vdso_futex_robust_list64_try_unlock(__u32 *lock, __u32 tid, __u64 *pop)
+ *	__vdso_futex_robust_list32_try_unlock(__u32 *lock, __u32 tid, __u32 *pop)
+ *
+ * So for the generic entry point we need to use a void pointer as the last argument
+ */
+FIXTURE(vdso_unlock)
+{
+	uint32_t (*vdso)(_Atomic(uint32_t) *lock, uint32_t tid, void *pop);
+};
+
+FIXTURE_VARIANT(vdso_unlock)
+{
+	bool is_32;
+	char func_name[];
+};
+
+FIXTURE_SETUP(vdso_unlock)
+{
+	self->vdso = get_vdso_func_addr(variant->func_name);
+}
+
+FIXTURE_TEARDOWN(vdso_unlock) {}
+
+FIXTURE_VARIANT_ADD(vdso_unlock, 32)
+{
+	.func_name = "__vdso_futex_robust_list32_try_unlock",
+	.is_32 = true,
+};
+
+FIXTURE_VARIANT_ADD(vdso_unlock, 64)
+{
+	.func_name = "__vdso_futex_robust_list64_try_unlock",
+	.is_32 = false,
+};
+
+/*
+ * Test the vDSO robust_listXX_try_unlock() for the uncontended case. The virtual syscall should
+ * return the thread ID of the lock owner, the lock word must be 0 and the list_op_pending should
+ * be NULL.
+ */
+TEST_F(vdso_unlock, test_robust_try_unlock_uncontended)
+{
+	struct lock_struct lock = { .futex = 0 };
+	_Atomic(unsigned int) *futex = &lock.futex;
+	struct robust_list_head head;
+	uintptr_t exp = (uintptr_t) NULL;
+	pid_t tid = gettid();
+	int ret;
+
+	if (!self->vdso) {
+		ksft_test_result_skip("%s not found\n", variant->func_name);
+		return;
+	}
+
+	*futex = tid;
+
+	ret = set_list(&head);
+	if (ret)
+		ksft_test_result_fail("set_robust_list error\n");
+
+	head.list_op_pending = &lock.list;
+
+	ret = self->vdso(futex, tid, &head.list_op_pending);
+
+	ASSERT_EQ(ret, tid);
+	ASSERT_EQ(*futex, 0);
+
+	/* Check only the lower 32 bits for the 32-bit entry point */
+	if (variant->is_32) {
+		exp = (uintptr_t)(unsigned long)&lock.list;
+		exp &= ~0xFFFFFFFFULL;
+	}
+
+	ASSERT_EQ((uintptr_t)(unsigned long)head.list_op_pending, exp);
+}
+
+/*
+ * If the lock is contended, the operation fails. The return value is the value found at the
+ * futex word (tid | FUTEX_WAITERS), the futex word is not modified and the list_op_pending is_32
+ * not cleared.
+ */
+TEST_F(vdso_unlock, test_robust_try_unlock_contended)
+{
+	struct lock_struct lock = { .futex = 0 };
+	_Atomic(unsigned int) *futex = &lock.futex;
+	struct robust_list_head head;
+	pid_t tid = gettid();
+	int ret;
+
+	if (!self->vdso) {
+		ksft_test_result_skip("%s not found\n", variant->func_name);
+		return;
+	}
+
+	*futex = tid | FUTEX_WAITERS;
+
+	ret = set_list(&head);
+	if (ret)
+		ksft_test_result_fail("set_robust_list error\n");
+
+	head.list_op_pending = &lock.list;
+
+	ret = self->vdso(futex, tid, &head.list_op_pending);
+
+	ASSERT_EQ(ret, tid | FUTEX_WAITERS);
+	ASSERT_EQ(*futex, tid | FUTEX_WAITERS);
+	ASSERT_EQ(head.list_op_pending, &lock.list);
+}
+
+FIXTURE(futex_op) {};
+
+FIXTURE_VARIANT(futex_op)
+{
+	unsigned int op;
+	unsigned int val3;
+};
+
+FIXTURE_SETUP(futex_op) {}
+
+FIXTURE_TEARDOWN(futex_op) {}
+
+FIXTURE_VARIANT_ADD(futex_op, wake)
+{
+	.op = FUTEX_WAKE,
+	.val3 = 0,
+};
+
+FIXTURE_VARIANT_ADD(futex_op, wake_bitset)
+{
+	.op = FUTEX_WAKE_BITSET,
+	.val3 = FUTEX_BITSET_MATCH_ANY,
+};
+
+FIXTURE_VARIANT_ADD(futex_op, unlock_pi)
+{
+	.op = FUTEX_UNLOCK_PI,
+	.val3 = 0,
+};
+
+FIXTURE_VARIANT_ADD(futex_op, wake32)
+{
+	.op = FUTEX_WAKE | FUTEX_ROBUST_LIST32,
+	.val3 = 0,
+};
+
+FIXTURE_VARIANT_ADD(futex_op, wake_bitset32)
+{
+	.op = FUTEX_WAKE_BITSET | FUTEX_ROBUST_LIST32,
+	.val3 = FUTEX_BITSET_MATCH_ANY,
+};
+
+FIXTURE_VARIANT_ADD(futex_op, unlock_pi32)
+{
+	.op = FUTEX_UNLOCK_PI | FUTEX_ROBUST_LIST32,
+	.val3 = 0,
+};
+
+/*
+ * The syscall should return the number of tasks waken (for this test, 0), clear the futex word and
+ * clear list_op_pending
+ */
+TEST_F(futex_op, test_futex_robust_unlock)
+{
+	struct lock_struct lock = { .futex = 0 };
+	_Atomic(unsigned int) *futex = &lock.futex;
+	uintptr_t exp = (uintptr_t) NULL;
+	struct robust_list_head head;
+	pid_t tid = gettid();
+	int ret;
+
+#ifndef BUILD_64
+	if (!(variant->op & FUTEX_ROBUST_LIST32)) {
+		ksft_test_result_skip("Not supported for 32 bit build\n");
+		return;
+	}
+#endif
+
+	*futex = tid | FUTEX_WAITERS;
+
+	ret = set_list(&head);
+	if (ret)
+		ksft_test_result_fail("set_robust_list error\n");
+
+	head.list_op_pending = &lock.list;
+
+	ret = sys_futex_robust_unlock(futex, FUTEX_ROBUST_UNLOCK | variant->op, tid,
+				      &head.list_op_pending, variant->val3);
+
+	ASSERT_EQ(ret, 0);
+	ASSERT_EQ(*futex, 0);
+
+	if (variant->op & FUTEX_ROBUST_LIST32) {
+		exp = (uint64_t)(unsigned long)&lock.list;
+		exp &= ~0xFFFFFFFFULL;
+	}
+
+	ASSERT_EQ((uintptr_t)(unsigned long)head.list_op_pending, exp);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/futex/functional/run.sh b/tools/testing/selftests/futex/functional/run.sh
new file mode 100755
index 000000000..e88545c06
--- /dev/null
+++ b/tools/testing/selftests/futex/functional/run.sh
@@ -0,0 +1,53 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0-or-later
+
+###############################################################################
+#
+#   Copyright © International Business Machines  Corp., 2009
+#
+# DESCRIPTION
+#      Run tests in the current directory.
+#
+# AUTHOR
+#      Darren Hart <dvhart@linux.intel.com>
+#
+# HISTORY
+#      2009-Nov-9: Initial version by Darren Hart <dvhart@linux.intel.com>
+#      2010-Jan-6: Add futex_wait_uninitialized_heap and futex_wait_private_mapped_file
+#                  by KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
+#
+###############################################################################
+
+echo
+./futex_requeue_pi
+
+echo
+./futex_requeue_pi_mismatched_ops
+
+echo
+./futex_requeue_pi_signal_restart
+
+echo
+./futex_wait_timeout
+
+echo
+./futex_wait_wouldblock
+
+echo
+./futex_wait_uninitialized_heap
+./futex_wait_private_mapped_file
+
+echo
+./futex_wait
+
+echo
+./futex_requeue
+
+echo
+./futex_waitv
+
+echo
+./futex_priv_hash
+
+echo
+./futex_numa_mpol
diff --git a/tools/testing/selftests/futex/include/atomic.h b/tools/testing/selftests/futex/include/atomic.h
new file mode 100644
index 000000000..428bcd921
--- /dev/null
+++ b/tools/testing/selftests/futex/include/atomic.h
@@ -0,0 +1,79 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/******************************************************************************
+ *
+ *   Copyright © International Business Machines  Corp., 2009
+ *
+ * DESCRIPTION
+ *      GCC atomic builtin wrappers
+ *      http://gcc.gnu.org/onlinedocs/gcc-4.1.0/gcc/Atomic-Builtins.html
+ *
+ * AUTHOR
+ *      Darren Hart <dvhart@linux.intel.com>
+ *
+ * HISTORY
+ *      2009-Nov-17: Initial version by Darren Hart <dvhart@linux.intel.com>
+ *
+ *****************************************************************************/
+
+#ifndef _ATOMIC_H
+#define _ATOMIC_H
+
+typedef struct {
+	volatile int val;
+} atomic_t;
+
+#define ATOMIC_INITIALIZER { 0 }
+
+/**
+ * atomic_cmpxchg() - Atomic compare and exchange
+ * @uaddr:	The address of the futex to be modified
+ * @oldval:	The expected value of the futex
+ * @newval:	The new value to try and assign the futex
+ *
+ * Return the old value of addr->val.
+ */
+static inline int
+atomic_cmpxchg(atomic_t *addr, int oldval, int newval)
+{
+	return __sync_val_compare_and_swap(&addr->val, oldval, newval);
+}
+
+/**
+ * atomic_inc() - Atomic incrememnt
+ * @addr:	Address of the variable to increment
+ *
+ * Return the new value of addr->val.
+ */
+static inline int
+atomic_inc(atomic_t *addr)
+{
+	return __sync_add_and_fetch(&addr->val, 1);
+}
+
+/**
+ * atomic_dec() - Atomic decrement
+ * @addr:	Address of the variable to decrement
+ *
+ * Return the new value of addr-val.
+ */
+static inline int
+atomic_dec(atomic_t *addr)
+{
+	return __sync_sub_and_fetch(&addr->val, 1);
+}
+
+/**
+ * atomic_set() - Atomic set
+ * @addr:	Address of the variable to set
+ * @newval:	New value for the atomic_t
+ *
+ * Return the new value of addr->val.
+ */
+static inline int
+atomic_set(atomic_t *addr, int newval)
+{
+	addr->val = newval;
+	return newval;
+}
+
+#endif
diff --git a/tools/testing/selftests/futex/include/futex2test.h b/tools/testing/selftests/futex/include/futex2test.h
new file mode 100644
index 000000000..1f625b399
--- /dev/null
+++ b/tools/testing/selftests/futex/include/futex2test.h
@@ -0,0 +1,98 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Futex2 library addons for futex tests
+ *
+ * Copyright 2021 Collabora Ltd.
+ */
+#include <linux/time_types.h>
+#include <stdint.h>
+
+#define u64_to_ptr(x) ((void *)(uintptr_t)(x))
+
+#ifndef __NR_futex_waitv
+#define __NR_futex_waitv 449
+struct futex_waitv {
+	__u64 val;
+	__u64 uaddr;
+	__u32 flags;
+	__u32 __reserved;
+};
+#endif
+
+#ifndef __NR_futex_wake
+#define __NR_futex_wake 454
+#endif
+
+#ifndef __NR_futex_wait
+#define __NR_futex_wait 455
+#endif
+
+#ifndef FUTEX2_SIZE_U32
+#define FUTEX2_SIZE_U32 0x02
+#endif
+
+#ifndef FUTEX2_NUMA
+#define FUTEX2_NUMA 0x04
+#endif
+
+#ifndef FUTEX2_MPOL
+#define FUTEX2_MPOL 0x08
+#endif
+
+#ifndef FUTEX2_PRIVATE
+#define FUTEX2_PRIVATE FUTEX_PRIVATE_FLAG
+#endif
+
+#ifndef FUTEX2_NO_NODE
+#define FUTEX_NO_NODE (-1)
+#endif
+
+#ifndef FUTEX_32
+#define FUTEX_32 FUTEX2_SIZE_U32
+#endif
+
+struct futex32_numa {
+	futex_t futex;
+	futex_t numa;
+};
+
+/**
+ * futex_waitv - Wait at multiple futexes, wake on any
+ * @waiters:    Array of waiters
+ * @nr_waiters: Length of waiters array
+ * @flags: Operation flags
+ * @timo:  Optional timeout for operation
+ */
+static inline int futex_waitv(volatile struct futex_waitv *waiters, unsigned long nr_waiters,
+			      unsigned long flags, struct timespec *timo, clockid_t clockid)
+{
+		struct __kernel_timespec ts = {
+			.tv_sec = timo->tv_sec,
+			.tv_nsec = timo->tv_nsec,
+		};
+
+		return syscall(__NR_futex_waitv, waiters, nr_waiters, flags, &ts, clockid);
+}
+
+/*
+ * futex_wait() - block on uaddr with optional timeout
+ * @val:	Expected value
+ * @flags:	FUTEX2 flags
+ * @timeout:	Relative timeout
+ * @clockid:	Clock id for the timeout
+ */
+static inline int futex2_wait(void *uaddr, long val, unsigned int flags,
+			      struct timespec *timeout, clockid_t clockid)
+{
+	return syscall(__NR_futex_wait, uaddr, val, ~0U, flags, timeout, clockid);
+}
+
+/*
+ * futex2_wake() - Wake a number of futexes
+ * @nr:		Number of threads to wake at most
+ * @flags:	FUTEX2 flags
+ */
+static inline int futex2_wake(void *uaddr, int nr, unsigned int flags)
+{
+	return syscall(__NR_futex_wake, uaddr, ~0U, nr, flags);
+}
diff --git a/tools/testing/selftests/futex/include/futextest.h b/tools/testing/selftests/futex/include/futextest.h
new file mode 100644
index 000000000..df33f31d6
--- /dev/null
+++ b/tools/testing/selftests/futex/include/futextest.h
@@ -0,0 +1,290 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/******************************************************************************
+ *
+ *   Copyright © International Business Machines  Corp., 2009
+ *
+ * DESCRIPTION
+ *      Glibc independent futex library for testing kernel functionality.
+ *
+ * AUTHOR
+ *      Darren Hart <dvhart@linux.intel.com>
+ *
+ * HISTORY
+ *      2009-Nov-6: Initial version by Darren Hart <dvhart@linux.intel.com>
+ *
+ *****************************************************************************/
+
+#ifndef _FUTEXTEST_H
+#define _FUTEXTEST_H
+
+#include <unistd.h>
+#include <sys/syscall.h>
+#include <sys/types.h>
+#include <linux/futex.h>
+
+typedef volatile u_int32_t futex_t;
+#define FUTEX_INITIALIZER 0
+
+/* Define the newer op codes if the system header file is not up to date. */
+#ifndef FUTEX_WAIT_BITSET
+#define FUTEX_WAIT_BITSET		9
+#endif
+#ifndef FUTEX_WAKE_BITSET
+#define FUTEX_WAKE_BITSET		10
+#endif
+#ifndef FUTEX_WAIT_REQUEUE_PI
+#define FUTEX_WAIT_REQUEUE_PI		11
+#endif
+#ifndef FUTEX_CMP_REQUEUE_PI
+#define FUTEX_CMP_REQUEUE_PI		12
+#endif
+#ifndef FUTEX_ROBUST_UNLOCK
+#define FUTEX_ROBUST_UNLOCK		512
+#endif
+#ifndef FUTEX_ROBUST_LIST32
+#define FUTEX_ROBUST_LIST32		1024
+#endif
+#ifndef FUTEX_WAIT_REQUEUE_PI_PRIVATE
+#define FUTEX_WAIT_REQUEUE_PI_PRIVATE	(FUTEX_WAIT_REQUEUE_PI | \
+					 FUTEX_PRIVATE_FLAG)
+#endif
+#ifndef FUTEX_REQUEUE_PI_PRIVATE
+#define FUTEX_CMP_REQUEUE_PI_PRIVATE	(FUTEX_CMP_REQUEUE_PI | \
+					 FUTEX_PRIVATE_FLAG)
+#endif
+
+/*
+ * SYS_futex is expected from system C library, in glibc some 32-bit
+ * architectures (e.g. RV32) are using 64-bit time_t, therefore it doesn't have
+ * SYS_futex defined but just SYS_futex_time64. Define SYS_futex as
+ * SYS_futex_time64 in this situation to ensure the compilation and the
+ * compatibility.
+ */
+#if !defined(SYS_futex) && defined(SYS_futex_time64)
+#define SYS_futex SYS_futex_time64
+#endif
+
+/*
+ * On 32bit systems if we use "-D_FILE_OFFSET_BITS=64 -D_TIME_BITS=64" or if
+ * we are using a newer compiler then the size of the timestamps will be 64bit,
+ * however, the SYS_futex will still point to the 32bit futex system call.
+ */
+#if __SIZEOF_POINTER__ == 4 && defined(SYS_futex_time64) && \
+	defined(_TIME_BITS) && _TIME_BITS == 64
+# undef SYS_futex
+# define SYS_futex SYS_futex_time64
+#endif
+
+/**
+ * futex() - SYS_futex syscall wrapper
+ * @uaddr:	address of first futex
+ * @op:		futex op code
+ * @val:	typically expected value of uaddr, but varies by op
+ * @timeout:	typically an absolute struct timespec (except where noted
+ *              otherwise). Overloaded by some ops
+ * @uaddr2:	address of second futex for some ops\
+ * @val3:	varies by op
+ * @opflags:	flags to be bitwise OR'd with op, such as FUTEX_PRIVATE_FLAG
+ *
+ * futex() is used by all the following futex op wrappers. It can also be
+ * used for misuse and abuse testing. Generally, the specific op wrappers
+ * should be used instead. It is a macro instead of an static inline function as
+ * some of the types over overloaded (timeout is used for nr_requeue for
+ * example).
+ *
+ * These argument descriptions are the defaults for all
+ * like-named arguments in the following wrappers except where noted below.
+ */
+#define futex(uaddr, op, val, timeout, uaddr2, val3, opflags) \
+	syscall(SYS_futex, uaddr, op | opflags, val, timeout, uaddr2, val3)
+
+/**
+ * futex_wait() - block on uaddr with optional timeout
+ * @timeout:	relative timeout
+ */
+static inline int
+futex_wait(futex_t *uaddr, futex_t val, struct timespec *timeout, int opflags)
+{
+	return futex(uaddr, FUTEX_WAIT, val, timeout, NULL, 0, opflags);
+}
+
+/**
+ * futex_wake() - wake one or more tasks blocked on uaddr
+ * @nr_wake:	wake up to this many tasks
+ */
+static inline int
+futex_wake(futex_t *uaddr, int nr_wake, int opflags)
+{
+	return futex(uaddr, FUTEX_WAKE, nr_wake, NULL, NULL, 0, opflags);
+}
+
+/**
+ * futex_wait_bitset() - block on uaddr with bitset
+ * @bitset:	bitset to be used with futex_wake_bitset
+ */
+static inline int
+futex_wait_bitset(futex_t *uaddr, futex_t val, struct timespec *timeout,
+		  u_int32_t bitset, int opflags)
+{
+	return futex(uaddr, FUTEX_WAIT_BITSET, val, timeout, NULL, bitset,
+		     opflags);
+}
+
+/**
+ * futex_wake_bitset() - wake one or more tasks blocked on uaddr with bitset
+ * @bitset:	bitset to compare with that used in futex_wait_bitset
+ */
+static inline int
+futex_wake_bitset(futex_t *uaddr, int nr_wake, u_int32_t bitset, int opflags)
+{
+	return futex(uaddr, FUTEX_WAKE_BITSET, nr_wake, NULL, NULL, bitset,
+		     opflags);
+}
+
+/**
+ * futex_lock_pi() - block on uaddr as a PI mutex
+ * @detect:	whether (1) or not (0) to perform deadlock detection
+ */
+static inline int
+futex_lock_pi(futex_t *uaddr, struct timespec *timeout, int detect,
+	      int opflags)
+{
+	return futex(uaddr, FUTEX_LOCK_PI, detect, timeout, NULL, 0, opflags);
+}
+
+/**
+ * futex_unlock_pi() - release uaddr as a PI mutex, waking the top waiter
+ */
+static inline int
+futex_unlock_pi(futex_t *uaddr, int opflags)
+{
+	return futex(uaddr, FUTEX_UNLOCK_PI, 0, NULL, NULL, 0, opflags);
+}
+
+/**
+ * futex_wake_op() - FIXME: COME UP WITH A GOOD ONE LINE DESCRIPTION
+ */
+static inline int
+futex_wake_op(futex_t *uaddr, futex_t *uaddr2, int nr_wake, int nr_wake2,
+	      int wake_op, int opflags)
+{
+	return futex(uaddr, FUTEX_WAKE_OP, nr_wake, nr_wake2, uaddr2, wake_op,
+		     opflags);
+}
+
+/**
+ * futex_requeue() - requeue without expected value comparison, deprecated
+ * @nr_wake:	wake up to this many tasks
+ * @nr_requeue:	requeue up to this many tasks
+ *
+ * Due to its inherently racy implementation, futex_requeue() is deprecated in
+ * favor of futex_cmp_requeue().
+ */
+static inline int
+futex_requeue(futex_t *uaddr, futex_t *uaddr2, int nr_wake, int nr_requeue,
+	      int opflags)
+{
+	return futex(uaddr, FUTEX_REQUEUE, nr_wake, nr_requeue, uaddr2, 0,
+		     opflags);
+}
+
+/**
+ * futex_cmp_requeue() - requeue tasks from uaddr to uaddr2
+ * @nr_wake:	wake up to this many tasks
+ * @nr_requeue:	requeue up to this many tasks
+ */
+static inline int
+futex_cmp_requeue(futex_t *uaddr, futex_t val, futex_t *uaddr2, int nr_wake,
+		  int nr_requeue, int opflags)
+{
+	return futex(uaddr, FUTEX_CMP_REQUEUE, nr_wake, nr_requeue, uaddr2,
+		     val, opflags);
+}
+
+/**
+ * futex_wait_requeue_pi() - block on uaddr and prepare to requeue to uaddr2
+ * @uaddr:	non-PI futex source
+ * @uaddr2:	PI futex target
+ *
+ * This is the first half of the requeue_pi mechanism. It shall always be
+ * paired with futex_cmp_requeue_pi().
+ */
+static inline int
+futex_wait_requeue_pi(futex_t *uaddr, futex_t val, futex_t *uaddr2,
+		      struct timespec *timeout, int opflags)
+{
+	return futex(uaddr, FUTEX_WAIT_REQUEUE_PI, val, timeout, uaddr2, 0,
+		     opflags);
+}
+
+/**
+ * futex_cmp_requeue_pi() - requeue tasks from uaddr to uaddr2 (PI aware)
+ * @uaddr:	non-PI futex source
+ * @uaddr2:	PI futex target
+ * @nr_wake:	wake up to this many tasks
+ * @nr_requeue:	requeue up to this many tasks
+ */
+static inline int
+futex_cmp_requeue_pi(futex_t *uaddr, futex_t val, futex_t *uaddr2, int nr_wake,
+		     int nr_requeue, int opflags)
+{
+	return futex(uaddr, FUTEX_CMP_REQUEUE_PI, nr_wake, nr_requeue, uaddr2,
+		     val, opflags);
+}
+
+/**
+ * futex_cmpxchg() - atomic compare and exchange
+ * @uaddr:	The address of the futex to be modified
+ * @oldval:	The expected value of the futex
+ * @newval:	The new value to try and assign the futex
+ *
+ * Implement cmpxchg using gcc atomic builtins.
+ * http://gcc.gnu.org/onlinedocs/gcc-4.1.0/gcc/Atomic-Builtins.html
+ *
+ * Return the old futex value.
+ */
+static inline u_int32_t
+futex_cmpxchg(futex_t *uaddr, u_int32_t oldval, u_int32_t newval)
+{
+	return __sync_val_compare_and_swap(uaddr, oldval, newval);
+}
+
+/**
+ * futex_dec() - atomic decrement of the futex value
+ * @uaddr:	The address of the futex to be modified
+ *
+ * Return the new futex value.
+ */
+static inline u_int32_t
+futex_dec(futex_t *uaddr)
+{
+	return __sync_sub_and_fetch(uaddr, 1);
+}
+
+/**
+ * futex_inc() - atomic increment of the futex value
+ * @uaddr:	the address of the futex to be modified
+ *
+ * Return the new futex value.
+ */
+static inline u_int32_t
+futex_inc(futex_t *uaddr)
+{
+	return __sync_add_and_fetch(uaddr, 1);
+}
+
+/**
+ * futex_set() - atomic decrement of the futex value
+ * @uaddr:	the address of the futex to be modified
+ * @newval:	New value for the atomic_t
+ *
+ * Return the new futex value.
+ */
+static inline u_int32_t
+futex_set(futex_t *uaddr, u_int32_t newval)
+{
+	*uaddr = newval;
+	return newval;
+}
+
+#endif
diff --git a/tools/testing/selftests/futex/run.sh b/tools/testing/selftests/futex/run.sh
new file mode 100755
index 000000000..5e76ea18f
--- /dev/null
+++ b/tools/testing/selftests/futex/run.sh
@@ -0,0 +1,29 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0-or-later
+
+###############################################################################
+#
+#   Copyright © International Business Machines  Corp., 2009
+#
+# DESCRIPTION
+#      Run all tests under the functional, performance, and stress directories.
+#      Format and summarize the results.
+#
+# AUTHOR
+#      Darren Hart <dvhart@linux.intel.com>
+#
+# HISTORY
+#      2009-Nov-9: Initial version by Darren Hart <dvhart@linux.intel.com>
+#
+###############################################################################
+
+# Test for a color capable shell and pass the result to the subdir scripts
+USE_COLOR=0
+tput setf 7 || tput setaf 7
+if [ $? -eq 0 ]; then
+    USE_COLOR=1
+    tput sgr0
+fi
+export USE_COLOR
+
+(cd functional; ./run.sh)