[PATCH v4 01/15] futex2: Implement wait and wake functions

@@ -7521,7 +7521,7 @@ F:	Documentation/locking/*futex*
 F:	include/asm-generic/futex.h
 F:	include/linux/futex.h
 F:	include/uapi/linux/futex.h
-F:	kernel/futex.c
+F:	kernel/futex*
 F:	tools/perf/bench/futex*
 F:	tools/testing/selftests/futex/
 

@@ -460,3 +460,5 @@
 444	common	landlock_create_ruleset		sys_landlock_create_ruleset
 445	common	landlock_add_rule		sys_landlock_add_rule
 446	common	landlock_restrict_self		sys_landlock_restrict_self
+447	common	futex_wait			sys_futex_wait
+448	common	futex_wake			sys_futex_wake

@@ -38,7 +38,7 @@
 #define __ARM_NR_compat_set_tls		(__ARM_NR_COMPAT_BASE + 5)
 #define __ARM_NR_COMPAT_END		(__ARM_NR_COMPAT_BASE + 0x800)
 
-#define __NR_compat_syscalls		447
+#define __NR_compat_syscalls		449
 #endif
 
 #define __ARCH_WANT_SYS_CLONE

@@ -900,6 +900,10 @@ __SYSCALL(__NR_landlock_create_ruleset, sys_landlock_create_ruleset)
 __SYSCALL(__NR_landlock_add_rule, sys_landlock_add_rule)
 #define __NR_landlock_restrict_self 446
 __SYSCALL(__NR_landlock_restrict_self, sys_landlock_restrict_self)
+#define __NR_futex_wait 447
+__SYSCALL(__NR_futex_wait, compat_sys_futex_wait)
+#define __NR_futex_wake 448
+__SYSCALL(__NR_futex_wake, sys_futex_wake)
 
 /*
  * Please add new compat syscalls above this comment and update

@@ -451,3 +451,5 @@
 444	i386	landlock_create_ruleset	sys_landlock_create_ruleset
 445	i386	landlock_add_rule	sys_landlock_add_rule
 446	i386	landlock_restrict_self	sys_landlock_restrict_self
+447	i386	futex_wait		sys_futex_wait			compat_sys_futex_wait
+448	i386	futex_wake		sys_futex_wake

@@ -368,6 +368,8 @@
 444	common	landlock_create_ruleset	sys_landlock_create_ruleset
 445	common	landlock_add_rule	sys_landlock_add_rule
 446	common	landlock_restrict_self	sys_landlock_restrict_self
+447	common	futex_wait		sys_futex_wait
+448	common	futex_wake		sys_futex_wake
 
 #
 # Due to a historical design error, certain syscalls are numbered differently

@@ -692,6 +692,11 @@ asmlinkage long
 compat_sys_get_robust_list(int pid, compat_uptr_t __user *head_ptr,
 			   compat_size_t __user *len_ptr);
 
+/* kernel/futex2.c */
+asmlinkage long
+compat_sys_futex_wait(void __user *uaddr, compat_u64 val, unsigned int flags,
+		      struct __kernel_timespec __user *timo);
+
 /* kernel/itimer.c */
 asmlinkage long compat_sys_getitimer(int which,
 				     struct old_itimerval32 __user *it);

@@ -623,6 +623,12 @@ asmlinkage long sys_get_robust_list(int pid,
 asmlinkage long sys_set_robust_list(struct robust_list_head __user *head,
 				    size_t len);
 
+/* kernel/futex2.c */
+asmlinkage long sys_futex_wait(void __user *uaddr, u64 val, unsigned int flags,
+			       struct __kernel_timespec __user *timo);
+asmlinkage long sys_futex_wake(void __user *uaddr, unsigned int nr_wake,
+			       unsigned int flags);
+
 /* kernel/hrtimer.c */
 asmlinkage long sys_nanosleep(struct __kernel_timespec __user *rqtp,
 			      struct __kernel_timespec __user *rmtp);

@@ -873,8 +873,14 @@ __SYSCALL(__NR_landlock_add_rule, sys_landlock_add_rule)
 #define __NR_landlock_restrict_self 446
 __SYSCALL(__NR_landlock_restrict_self, sys_landlock_restrict_self)
 
+#define __NR_futex_wait 447
+__SC_COMP(__NR_futex_wait, sys_futex_wait, compat_sys_futex_wait)
+
+#define __NR_futex_wake 448
+__SYSCALL(__NR_futex_wake, sys_futex_wake)
+
 #undef __NR_syscalls
-#define __NR_syscalls 447
+#define __NR_syscalls 449
 
 /*
  * 32 bit systems traditionally used different

@@ -41,6 +41,11 @@
 #define FUTEX_CMP_REQUEUE_PI_PRIVATE	(FUTEX_CMP_REQUEUE_PI | \
 					 FUTEX_PRIVATE_FLAG)
 
+/* Size argument to futex2 syscall */
+#define FUTEX_32	2
+
+#define FUTEX_SIZE_MASK	0x3
+
 /*
  * Support for robust futexes: the kernel cleans up held futexes at
  * thread exit time.

@@ -1555,6 +1555,13 @@ config FUTEX
 	  support for "fast userspace mutexes".  The resulting kernel may not
 	  run glibc-based applications correctly.
 
+config FUTEX2
+	bool "Enable futex2 support" if EXPERT
+	depends on FUTEX
+	default y
+	help
+	  Support for futex2 interface.
+
 config FUTEX_PI
 	bool
 	depends on FUTEX && RT_MUTEXES

@@ -60,6 +60,7 @@ obj-$(CONFIG_PROFILING) += profile.o
 obj-$(CONFIG_STACKTRACE) += stacktrace.o
 obj-y += time/
 obj-$(CONFIG_FUTEX) += futex.o
+obj-$(CONFIG_FUTEX2) += futex2.o
 obj-$(CONFIG_GENERIC_ISA_DMA) += dma.o
 obj-$(CONFIG_SMP) += smp.o
 ifneq ($(CONFIG_SMP),y)

@@ -0,0 +1,619 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * futex2 system call interface by André Almeida <andrealmeid@collabora.com>
+ *
+ * Copyright 2021 Collabora Ltd.
+ *
+ * Based on original futex implementation by:
+ *  (C) 2002 Rusty Russell, IBM
+ *  (C) 2003, 2006 Ingo Molnar, Red Hat Inc.
+ *  (C) 2003, 2004 Jamie Lokier
+ *  (C) 2006 Thomas Gleixner, Timesys Corp.
+ *  (C) 2007 Eric Dumazet
+ *  (C) 2009 Darren Hart, IBM
+ */
+
+#include <linux/freezer.h>
+#include <linux/jhash.h>
+#include <linux/memblock.h>
+#include <linux/sched/wake_q.h>
+#include <linux/spinlock.h>
+#include <linux/syscalls.h>
+#include <uapi/linux/futex.h>
+
+/**
+ * struct futex_key - Components to build unique key for a futex
+ * @pointer: Pointer to current->mm
+ * @index: Start address of the page containing futex
+ * @offset: Address offset of uaddr in a page
+ */
+struct futex_key {
+	u64 pointer;
+	unsigned long index;
+	unsigned long offset;
+};
+
+/**
+ * struct futex_waiter - List entry for a waiter
+ * @uaddr:        Virtual address of userspace futex
+ * @key:          Information that uniquely identify a futex
+ * @list:	  List node struct
+ * @val:	  Expected value for this waiter
+ * @flags:        Flags
+ * @bucket:       Pointer to the bucket for this waiter
+ * @index:        Index of waiter in futexv list
+ */
+struct futex_waiter {
+	void __user *uaddr;
+	struct futex_key key;
+	struct list_head list;
+	u64 val;
+	unsigned int flags;
+	struct futex_bucket *bucket;
+	unsigned int index;
+};
+
+/**
+ * struct futex_waiter_head - List of futexes to be waited
+ * @task:    Task to be awaken
+ * @hint:    Was someone on this list awakened?
+ * @objects: List of futexes
+ */
+struct futex_waiter_head {
+	struct task_struct *task;
+	bool hint;
+	struct futex_waiter objects[0];
+};
+
+/**
+ * struct futex_bucket - A bucket of futex's hash table
+ * @waiters: Number of waiters in the bucket
+ * @lock:    Bucket lock
+ * @list:    List of waiters on this bucket
+ */
+struct futex_bucket {
+	atomic_t waiters;
+	spinlock_t lock;
+	struct list_head list;
+};
+
+/* Mask for futex2 flag operations */
+#define FUTEX2_MASK (FUTEX_SIZE_MASK | FUTEX_CLOCK_REALTIME)
+
+static struct futex_bucket *futex_table;
+static unsigned int futex2_hashsize;
+
+/*
+ * Reflects a new waiter being added to the waitqueue.
+ */
+static inline void bucket_inc_waiters(struct futex_bucket *bucket)
+{
+#ifdef CONFIG_SMP
+	atomic_inc(&bucket->waiters);
+	/*
+	 * Issue a barrier after adding so futex_wake() will see that the
+	 * value had increased
+	 */
+	smp_mb__after_atomic();
+#endif
+}
+
+/*
+ * Reflects a waiter being removed from the waitqueue by wakeup
+ * paths.
+ */
+static inline void bucket_dec_waiters(struct futex_bucket *bucket)
+{
+#ifdef CONFIG_SMP
+	atomic_dec(&bucket->waiters);
+#endif
+}
+
+/*
+ * Get the number of waiters in a bucket
+ */
+static inline int bucket_get_waiters(struct futex_bucket *bucket)
+{
+#ifdef CONFIG_SMP
+	/*
+	 * Issue a barrier before reading so we get an updated value from
+	 * futex_wait()
+	 */
+	smp_mb();
+	return atomic_read(&bucket->waiters);
+#else
+	return 1;
+#endif
+}
+
+/**
+ * futex_get_bucket - Check if the user address is valid, prepare internal
+ *                    data and calculate the hash
+ * @uaddr:   futex user address
+ * @key:     data that uniquely identifies a futex
+ *
+ * Return: address of bucket on success, error code otherwise
+ */
+static struct futex_bucket *futex_get_bucket(void __user *uaddr,
+					     struct futex_key *key)
+{
+	uintptr_t address = (uintptr_t)uaddr;
+	u32 hash_key;
+
+	/* Checking if uaddr is valid and accessible */
+	if (unlikely(!IS_ALIGNED(address, sizeof(u32))))
+		return ERR_PTR(-EINVAL);
+	if (unlikely(!access_ok(uaddr, sizeof(u32))))
+		return ERR_PTR(-EFAULT);
+
+	key->offset = address % PAGE_SIZE;
+	address -= key->offset;
+	key->pointer = (u64)address;
+	key->index = (unsigned long)current->mm;
+
+	/* Generate hash key for this futex using uaddr and current->mm */
+	hash_key = jhash2((u32 *)key, sizeof(*key) / sizeof(u32), 0);
+
+	/* Since HASH_SIZE is 2^n, subtracting 1 makes a perfect bit mask */
+	return &futex_table[hash_key & (futex2_hashsize - 1)];
+}
+
+/**
+ * futex_get_user - Get the userspace value on this address
+ * @uval:  variable to store the value
+ * @uaddr: userspace address
+ *
+ * Check the comment at futex_enqueue() for more information.
+ */
+static int futex_get_user(u32 *uval, u32 __user *uaddr)
+{
+	int ret;
+
+	pagefault_disable();
+	ret = __get_user(*uval, uaddr);
+	pagefault_enable();
+
+	return ret;
+}
+
+/**
+ * futex_setup_time - Prepare the timeout mechanism and start it.
+ * @timo:    Timeout value from userspace
+ * @timeout: Pointer to hrtimer handler
+ * @flags: Flags from userspace, to decide which clockid to use
+ *
+ * Return: 0 on success, error code otherwise
+ */
+static int futex_setup_time(struct __kernel_timespec __user *timo,
+			    struct hrtimer_sleeper *timeout,
+			    unsigned int flags)
+{
+	ktime_t time;
+	struct timespec64 ts;
+	clockid_t clockid = (flags & FUTEX_CLOCK_REALTIME) ?
+			    CLOCK_REALTIME : CLOCK_MONOTONIC;
+
+	if (get_timespec64(&ts, timo))
+		return -EFAULT;
+
+	if (!timespec64_valid(&ts))
+		return -EINVAL;
+
+	time = timespec64_to_ktime(ts);
+
+	hrtimer_init_sleeper(timeout, clockid, HRTIMER_MODE_ABS);
+
+	hrtimer_set_expires(&timeout->timer, time);
+
+	hrtimer_sleeper_start_expires(timeout, HRTIMER_MODE_ABS);
+
+	return 0;
+}
+
+/**
+ * futex_dequeue_multiple - Remove multiple futexes from hash table
+ * @futexv: list of waiters
+ * @nr:     number of futexes to be removed
+ *
+ * This function is used if (a) something went wrong while enqueuing, and we
+ * need to undo our work (then nr <= nr_futexes) or (b) we woke up, and thus
+ * need to remove every waiter, check if some was indeed woken and return.
+ * Before removing a waiter, we check if it's on the list, since we have no
+ * clue who have been waken.
+ *
+ * Return:
+ *  * -1  - If no futex was woken during the removal
+ *  * 0>= - At least one futex was found woken, index of the last one
+ */
+static int futex_dequeue_multiple(struct futex_waiter_head *futexv, unsigned int nr)
+{
+	int i, ret = -1;
+
+	for (i = 0; i < nr; i++) {
+		spin_lock(&futexv->objects[i].bucket->lock);
+		if (!list_empty(&futexv->objects[i].list)) {
+			list_del_init(&futexv->objects[i].list);
+			bucket_dec_waiters(futexv->objects[i].bucket);
+		} else {
+			ret = i;
+		}
+		spin_unlock(&futexv->objects[i].bucket->lock);
+	}
+
+	return ret;
+}
+
+/**
+ * futex_enqueue - Check the value and enqueue a futex on a wait list
+ *
+ * @futexv:     List of futexes
+ * @nr_futexes: Number of futexes in the list
+ * @awakened:	If a futex was awakened during enqueueing, store the index here
+ *
+ * Get the value from the userspace address and compares with the expected one.
+ *
+ * Getting the value from user futex address:
+ *
+ * Since we are in a hurry, we use a spin lock and we can't sleep.
+ * Try to get the value with page fault disabled (when enable, we might
+ * sleep).
+ *
+ * If we fail, we aren't sure if the address is invalid or is just a
+ * page fault. Then, release the lock (so we can sleep) and try to get
+ * the value with page fault enabled. In order to trigger a page fault
+ * handling, we just call __get_user() again. If we sleep with enqueued
+ * futexes, we might miss a wake, so dequeue everything before sleeping.
+ *
+ * If get_user succeeds, this mean that the address is valid and we do
+ * the work again. Since we just handled the page fault, the page is
+ * likely pinned in memory and we should be luckier this time and be
+ * able to get the value. If we fail anyway, we will try again.
+ *
+ * If even with page faults enabled we get and error, this means that
+ * the address is not valid and we return from the syscall.
+ *
+ * If we got an unexpected value or need to treat a page fault and realized that
+ * a futex was awakened, we can priority this and return success.
+ *
+ * In success, enqueue the futex in the correct bucket
+ *
+ * Return:
+ * * 1  - We were awake in the process and nothing is enqueued
+ * * 0  - Everything is enqueued and we are ready to sleep
+ * * 0< - Something went wrong, nothing is enqueued, return error code
+ */
+static int futex_enqueue(struct futex_waiter_head *futexv, unsigned int nr_futexes,
+			 int *awakened)
+{
+	int i, ret;
+	u32 uval, val;
+	u32 __user *uaddr;
+	struct futex_bucket *bucket;
+
+retry:
+	set_current_state(TASK_INTERRUPTIBLE);
+
+	for (i = 0; i < nr_futexes; i++) {
+		uaddr = (u32 __user *)futexv->objects[i].uaddr;
+		val = (u32)futexv->objects[i].val;
+
+		bucket = futexv->objects[i].bucket;
+
+		bucket_inc_waiters(bucket);
+		spin_lock(&bucket->lock);
+
+		ret = futex_get_user(&uval, uaddr);
+
+		if (unlikely(ret)) {
+			spin_unlock(&bucket->lock);
+
+			bucket_dec_waiters(bucket);
+			__set_current_state(TASK_RUNNING);
+			*awakened = futex_dequeue_multiple(futexv, i);
+
+			if (*awakened >= 0)
+				return 1;
+
+			if (__get_user(uval, uaddr))
+				return -EFAULT;
+
+			goto retry;
+		}
+
+		if (uval != val) {
+			spin_unlock(&bucket->lock);
+
+			bucket_dec_waiters(bucket);
+			__set_current_state(TASK_RUNNING);
+			*awakened = futex_dequeue_multiple(futexv, i);
+
+			if (*awakened >= 0)
+				return 1;
+
+			return -EAGAIN;
+		}
+
+		list_add_tail(&futexv->objects[i].list, &bucket->list);
+		spin_unlock(&bucket->lock);
+	}
+
+	return 0;
+}
+
+/**
+ * __futex_waitv - Enqueue the list of futexes and wait to be woken
+ * @futexv: List of futexes to wait
+ * @nr_futexes: Length of futexv
+ * @timo:	Timeout
+ * @flags:	Timeout flags
+ *
+ * Return:
+ * * 0 >= - Hint of which futex woke us
+ * * 0 <  - Error code
+ */
+static int __futex_waitv(struct futex_waiter_head *futexv, unsigned int nr_futexes,
+			 struct __kernel_timespec __user *timo,
+			 unsigned int flags)
+{
+	int ret;
+	struct hrtimer_sleeper timeout;
+
+	if (timo) {
+		ret = futex_setup_time(timo, &timeout, flags);
+		if (ret)
+			return ret;
+	}
+
+	while (1) {
+		int awakened = -1;
+
+		ret = futex_enqueue(futexv, nr_futexes, &awakened);
+
+		if (ret) {
+			if (awakened >= 0)
+				ret = awakened;
+			break;
+		}
+
+		/* Before sleeping, check if someone was woken */
+		if (!futexv->hint && (!timo || timeout.task))
+			freezable_schedule();
+
+		__set_current_state(TASK_RUNNING);
+
+		/*
+		 * One of those things triggered this wake:
+		 *
+		 * * We have been removed from the bucket. futex_wake() woke
+		 *   us. We just need to dequeue and return 0 to userspace.
+		 *
+		 * However, if no futex was dequeued by a futex_wake():
+		 *
+		 * * If the there's a timeout and it has expired,
+		 *   return -ETIMEDOUT.
+		 *
+		 * * If there is a signal pending, something wants to kill our
+		 *   thread, return -ERESTARTSYS.
+		 *
+		 * * If there's no signal pending, it was a spurious wake
+		 *   (scheduler gave us a chance to do some work, even if we
+		 *   don't want to). We need to remove ourselves from the
+		 *   bucket and add again, to prevent losing wakeups in the
+		 *   meantime.
+		 */
+
+		ret = futex_dequeue_multiple(futexv, nr_futexes);
+
+		/* Normal wake */
+		if (ret >= 0)
+			break;
+
+		if (timo && !timeout.task) {
+			ret = -ETIMEDOUT;
+			break;
+		}
+
+		if (signal_pending(current)) {
+			ret = -ERESTARTSYS;
+			break;
+		}
+
+		/* Spurious wake, do everything again */
+	}
+
+	if (timo)
+		hrtimer_cancel(&timeout.timer);
+
+	return ret;
+}
+
+static long ksys_futex_wait(void __user *uaddr, u64 val, unsigned int flags,
+			    struct __kernel_timespec __user *timo)
+{
+	unsigned int size = flags & FUTEX_SIZE_MASK;
+	struct futex_waiter *waiter;
+	struct futex_waiter_head *futexv;
+
+	/* Wrapper for a futexv_waiter_head with one element */
+	struct {
+		struct futex_waiter_head futexv;
+		struct futex_waiter waiter;
+	} __packed wait_single;
+
+	if (flags & ~FUTEX2_MASK)
+		return -EINVAL;
+
+	if (size != FUTEX_32)
+		return -EINVAL;
+
+	futexv = &wait_single.futexv;
+	futexv->task = current;
+	futexv->hint = false;
+
+	waiter = &wait_single.waiter;
+	waiter->index = 0;
+	waiter->val = val;
+	waiter->uaddr = uaddr;
+	memset(&wait_single.waiter.key, 0, sizeof(struct futex_key));
+
+	INIT_LIST_HEAD(&waiter->list);
+
+	/* Get an unlocked hash bucket */
+	waiter->bucket = futex_get_bucket(uaddr, &waiter->key);
+	if (IS_ERR(waiter->bucket))
+		return PTR_ERR(waiter->bucket);
+
+	return __futex_waitv(futexv, 1, timo, flags);
+}
+
+#ifdef CONFIG_COMPAT
+COMPAT_SYSCALL_DEFINE4(compat_futex_wait, void __user *, uaddr, compat_u64, val,
+		       unsigned int, flags,
+		       struct __kernel_timespec __user *, timo)
+{
+	return ksys_futex_wait(uaddr, val, flags, timo);
+}
+#endif
+
+/**
+ * sys_futex_wait - Wait on a futex address if (*uaddr) == val
+ * @uaddr: User address of futex
+ * @val:   Expected value of futex
+ * @flags: Specify the size of futex and the clockid
+ * @timo:  Optional absolute timeout.
+ *
+ * The user thread is put to sleep, waiting for a futex_wake() at uaddr, if the
+ * value at *uaddr is the same as val (otherwise, the syscall returns
+ * immediately with -EAGAIN).
+ *
+ * Returns 0 on success, error code otherwise.
+ */
+SYSCALL_DEFINE4(futex_wait, void __user *, uaddr, u64, val, unsigned int, flags,
+		struct __kernel_timespec __user *, timo)
+{
+
+	return ksys_futex_wait(uaddr, val, flags, timo);
+}
+
+/**
+ * futex_get_parent - For a given futex in a futexv list, get a pointer to the futexv
+ * @waiter: Address of futex in the list
+ * @index: Index of futex in the list
+ *
+ * Return: A pointer to its futexv struct
+ */
+static inline struct futex_waiter_head *futex_get_parent(uintptr_t waiter,
+							 unsigned int index)
+{
+	uintptr_t parent = waiter - sizeof(struct futex_waiter_head)
+			   - (uintptr_t)(index * sizeof(struct futex_waiter));
+
+	return (struct futex_waiter_head *)parent;
+}
+
+/**
+ * futex_mark_wake - Find the task to be wake and add it in wake queue
+ * @waiter: Waiter to be wake
+ * @bucket: Bucket to be decremented
+ * @wake_q: Wake queue to insert the task
+ */
+static void futex_mark_wake(struct futex_waiter *waiter,
+			    struct futex_bucket *bucket,
+			    struct wake_q_head *wake_q)
+{
+	struct task_struct *task;
+	struct futex_waiter_head *parent = futex_get_parent((uintptr_t)waiter,
+							    waiter->index);
+
+	lockdep_assert_held(&bucket->lock);
+	parent->hint = true;
+	task = parent->task;
+	get_task_struct(task);
+	list_del_init(&waiter->list);
+	wake_q_add_safe(wake_q, task);
+	bucket_dec_waiters(bucket);
+}
+
+static inline bool futex_match(struct futex_key key1, struct futex_key key2)
+{
+	return (key1.index == key2.index &&
+		key1.pointer == key2.pointer &&
+		key1.offset == key2.offset);
+}
+
+/**
+ * sys_futex_wake - Wake a number of futexes waiting on an address
+ * @uaddr:   Address of futex to be woken up
+ * @nr_wake: Number of futexes waiting in uaddr to be woken up
+ * @flags:   Flags for size and shared
+ *
+ * Wake `nr_wake` threads waiting at uaddr.
+ *
+ * Returns the number of woken threads on success, error code otherwise.
+ */
+SYSCALL_DEFINE3(futex_wake, void __user *, uaddr, unsigned int, nr_wake,
+		unsigned int, flags)
+{
+	unsigned int size = flags & FUTEX_SIZE_MASK;
+	struct futex_waiter waiter, *aux, *tmp;
+	struct futex_bucket *bucket;
+	DEFINE_WAKE_Q(wake_q);
+	int ret = 0;
+
+	if (flags & ~FUTEX2_MASK)
+		return -EINVAL;
+
+	if (size != FUTEX_32)
+		return -EINVAL;
+
+	bucket = futex_get_bucket(uaddr, &waiter.key);
+	if (IS_ERR(bucket))
+		return PTR_ERR(bucket);
+
+	if (!bucket_get_waiters(bucket) || !nr_wake)
+		return 0;
+
+	spin_lock(&bucket->lock);
+	list_for_each_entry_safe(aux, tmp, &bucket->list, list) {
+		if (futex_match(waiter.key, aux->key)) {
+			futex_mark_wake(aux, bucket, &wake_q);
+			if (++ret >= nr_wake)
+				break;
+		}
+	}
+	spin_unlock(&bucket->lock);
+
+	wake_up_q(&wake_q);
+
+	return ret;
+}
+
+static int __init futex2_init(void)
+{
+	int i;
+	unsigned int futex_shift;
+
+#if CONFIG_BASE_SMALL
+	futex2_hashsize = 16;
+#else
+	futex2_hashsize = roundup_pow_of_two(256 * num_possible_cpus());
+#endif
+
+	futex_table = alloc_large_system_hash("futex2", sizeof(struct futex_bucket),
+					      futex2_hashsize, 0,
+					      futex2_hashsize < 256 ? HASH_SMALL : 0,
+					      &futex_shift, NULL,
+					      futex2_hashsize, futex2_hashsize);
+	futex2_hashsize = 1UL << futex_shift;
+
+	BUG_ON(!is_power_of_2(futex2_hashsize));
+
+	for (i = 0; i < futex2_hashsize; i++) {
+		INIT_LIST_HEAD(&futex_table[i].list);
+		spin_lock_init(&futex_table[i].lock);
+		atomic_set(&futex_table[i].waiters, 0);
+	}
+
+	return 0;
+}
+core_initcall(futex2_init);

@@ -151,6 +151,11 @@ COND_SYSCALL_COMPAT(set_robust_list);
 COND_SYSCALL(get_robust_list);
 COND_SYSCALL_COMPAT(get_robust_list);
 
+/* kernel/futex2.c */
+COND_SYSCALL(futex_wait);
+COND_SYSCALL_COMPAT(futex_wait);
+COND_SYSCALL(futex_wake);
+
 /* kernel/hrtimer.c */
 
 /* kernel/itimer.c */

@@ -873,8 +873,14 @@ __SYSCALL(__NR_landlock_add_rule, sys_landlock_add_rule)
 #define __NR_landlock_restrict_self 446
 __SYSCALL(__NR_landlock_restrict_self, sys_landlock_restrict_self)
 
+#define __NR_futex_wait 447
+__SYSCALL(__NR_futex_wait, sys_futex_wait)
+
+#define __NR_futex_wake 448
+__SYSCALL(__NR_futex_wake, sys_futex_wake)
+
 #undef __NR_syscalls
-#define __NR_syscalls 447
+#define __NR_syscalls 449
 
 /*
  * 32 bit systems traditionally used different

@@ -368,6 +368,8 @@
 444	common	landlock_create_ruleset	sys_landlock_create_ruleset
 445	common	landlock_add_rule	sys_landlock_add_rule
 446	common	landlock_restrict_self	sys_landlock_restrict_self
+447	common  futex_wait              sys_futex_wait
+448	common  futex_wake              sys_futex_wake
 
 #
 # Due to a historical design error, certain syscalls are numbered differently