Resguardo inicial

linux-7.2.3/kernel/futex/Makefile

@@ -0,0 +1,5 @@
+# SPDX-License-Identifier: GPL-2.0
+
+CONTEXT_ANALYSIS := y
+
+obj-y += core.o syscalls.o pi.o requeue.o waitwake.o

linux-7.2.3/kernel/futex/futex.h

@@ -0,0 +1,481 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _FUTEX_H
+#define _FUTEX_H
+
+#include <linux/futex.h>
+#include <linux/rtmutex.h>
+#include <linux/sched/wake_q.h>
+#include <linux/compat.h>
+#include <linux/uaccess.h>
+#include <linux/cleanup.h>
+
+#ifdef CONFIG_PREEMPT_RT
+#include <linux/rcuwait.h>
+#endif
+
+#include <asm/futex.h>
+
+/*
+ * Futex flags used to encode options to functions and preserve them across
+ * restarts.
+ */
+#define FLAGS_SIZE_8		0x0000
+#define FLAGS_SIZE_16		0x0001
+#define FLAGS_SIZE_32		0x0002
+#define FLAGS_SIZE_64		0x0003
+
+#define FLAGS_SIZE_MASK		0x0003
+
+#ifdef CONFIG_MMU
+# define FLAGS_SHARED		0x0010
+#else
+/*
+ * NOMMU does not have per process address space. Let the compiler optimize
+ * code away.
+ */
+# define FLAGS_SHARED		0x0000
+#endif
+#define FLAGS_CLOCKRT		0x0020
+#define FLAGS_HAS_TIMEOUT	0x0040
+#define FLAGS_NUMA		0x0080
+#define FLAGS_STRICT		0x0100
+#define FLAGS_MPOL		0x0200
+#define FLAGS_ROBUST_UNLOCK	0x0400
+#define FLAGS_ROBUST_LIST32	0x0800
+
+/* FUTEX_ to FLAGS_ */
+static inline unsigned int futex_to_flags(unsigned int op)
+{
+	unsigned int flags = FLAGS_SIZE_32;
+
+	if (!(op & FUTEX_PRIVATE_FLAG))
+		flags |= FLAGS_SHARED;
+
+	if (op & FUTEX_CLOCK_REALTIME)
+		flags |= FLAGS_CLOCKRT;
+
+	if (op & FUTEX_ROBUST_UNLOCK)
+		flags |= FLAGS_ROBUST_UNLOCK;
+
+	if (op & FUTEX_ROBUST_LIST32)
+		flags |= FLAGS_ROBUST_LIST32;
+
+	return flags;
+}
+
+#define FUTEX2_VALID_MASK (FUTEX2_SIZE_MASK | FUTEX2_NUMA | FUTEX2_MPOL | FUTEX2_PRIVATE)
+
+/* FUTEX2_ to FLAGS_ */
+static inline unsigned int futex2_to_flags(unsigned int flags2)
+{
+	unsigned int flags = flags2 & FUTEX2_SIZE_MASK;
+
+	if (!(flags2 & FUTEX2_PRIVATE))
+		flags |= FLAGS_SHARED;
+
+	if (flags2 & FUTEX2_NUMA)
+		flags |= FLAGS_NUMA;
+
+	if (flags2 & FUTEX2_MPOL)
+		flags |= FLAGS_MPOL;
+
+	return flags;
+}
+
+static inline unsigned int futex_size(unsigned int flags)
+{
+	return 1 << (flags & FLAGS_SIZE_MASK);
+}
+
+static inline bool futex_flags_valid(unsigned int flags)
+{
+	/* Only 64bit futexes for 64bit code */
+	if (!IS_ENABLED(CONFIG_64BIT) || in_compat_syscall()) {
+		if ((flags & FLAGS_SIZE_MASK) == FLAGS_SIZE_64)
+			return false;
+	}
+
+	/* Only 32bit futexes are implemented -- for now */
+	if ((flags & FLAGS_SIZE_MASK) != FLAGS_SIZE_32)
+		return false;
+
+	/*
+	 * Must be able to represent both FUTEX_NO_NODE and every valid nodeid
+	 * in a futex word.
+	 */
+	if (flags & FLAGS_NUMA) {
+		int bits = 8 * futex_size(flags);
+		u64 max = ~0ULL;
+
+		max >>= 64 - bits;
+		if (nr_node_ids >= max)
+			return false;
+	}
+
+	return true;
+}
+
+static inline bool futex_validate_input(unsigned int flags, u64 val)
+{
+	int bits = 8 * futex_size(flags);
+
+	if (bits < 64 && (val >> bits))
+		return false;
+
+	return true;
+}
+
+#ifdef CONFIG_FAIL_FUTEX
+extern bool should_fail_futex(bool fshared);
+#else
+static inline bool should_fail_futex(bool fshared)
+{
+	return false;
+}
+#endif
+
+static inline bool futex_key_is_private(union futex_key *key)
+{
+	/*
+	 * Relies on get_futex_key() to set either bit for shared
+	 * futexes -- see comment with union futex_key.
+	 */
+	return !(key->both.offset & (FUT_OFF_INODE | FUT_OFF_MMSHARED));
+}
+
+/*
+ * Hash buckets are shared by all the futex_keys that hash to the same
+ * location.  Each key may have multiple futex_q structures, one for each task
+ * waiting on a futex.
+ */
+struct futex_hash_bucket {
+	atomic_t waiters;
+	spinlock_t lock;
+	struct plist_head chain;
+} ____cacheline_aligned_in_smp;
+
+/*
+ * Priority Inheritance state:
+ */
+struct futex_pi_state {
+	/*
+	 * list of 'owned' pi_state instances - these have to be
+	 * cleaned up in do_exit() if the task exits prematurely:
+	 */
+	struct list_head list;
+
+	/*
+	 * The PI object:
+	 */
+	struct rt_mutex_base pi_mutex;
+
+	struct task_struct *owner;
+	refcount_t refcount;
+
+	union futex_key key;
+} __randomize_layout;
+
+struct futex_q;
+typedef void (futex_wake_fn)(struct wake_q_head *wake_q, struct futex_q *q);
+
+/**
+ * struct futex_q - The hashed futex queue entry, one per waiting task
+ * @list:		priority-sorted list of tasks waiting on this futex
+ * @task:		the task waiting on the futex
+ * @lock_ptr:		the hash bucket lock
+ * @wake:		the wake handler for this queue
+ * @wake_data:		data associated with the wake handler
+ * @key:		the key the futex is hashed on
+ * @pi_state:		optional priority inheritance state
+ * @rt_waiter:		rt_waiter storage for use with requeue_pi
+ * @requeue_pi_key:	the requeue_pi target futex key
+ * @bitset:		bitset for the optional bitmasked wakeup
+ * @requeue_state:	State field for futex_requeue_pi()
+ * @drop_fph:		Waiter should drop the extra private hash reference when set
+ * @requeue_wait:	RCU wait for futex_requeue_pi() (RT only)
+ *
+ * We use this hashed waitqueue, instead of a normal wait_queue_entry_t, so
+ * we can wake only the relevant ones (hashed queues may be shared).
+ *
+ * A futex_q has a woken state, just like tasks have TASK_RUNNING.
+ * It is considered woken when plist_node_empty(&q->list) || q->lock_ptr == 0.
+ * The order of wakeup is always to make the first condition true, then
+ * the second.
+ *
+ * PI futexes are typically woken before they are removed from the hash list via
+ * the rt_mutex code. See futex_unqueue_pi().
+ */
+struct futex_q {
+	struct plist_node list;
+
+	struct task_struct *task;
+	spinlock_t *lock_ptr;
+	futex_wake_fn *wake;
+	void *wake_data;
+	union futex_key key;
+	struct futex_pi_state *pi_state;
+	struct rt_mutex_waiter *rt_waiter;
+	union futex_key *requeue_pi_key;
+	u32 bitset;
+	atomic_t requeue_state;
+	struct futex_private_hash *drop_fph;
+#ifdef CONFIG_PREEMPT_RT
+	struct rcuwait requeue_wait;
+#endif
+} __randomize_layout;
+
+extern const struct futex_q futex_q_init;
+
+enum futex_access {
+	FUTEX_READ,
+	FUTEX_WRITE
+};
+
+extern int get_futex_key(u32 __user *uaddr, unsigned int flags, union futex_key *key,
+			 enum futex_access rw);
+extern void futex_q_lockptr_lock(struct futex_q *q) __acquires(q->lock_ptr);
+extern struct hrtimer_sleeper *
+futex_setup_timer(ktime_t *time, struct hrtimer_sleeper *timeout,
+		  int flags, u64 range_ns);
+
+struct futex_bucket_ref {
+	struct futex_hash_bucket *hb;
+	struct futex_private_hash *fph;
+};
+
+#ifdef CONFIG_FUTEX_PRIVATE_HASH
+extern struct futex_private_hash *futex_private_hash(struct mm_struct *mm);
+extern void futex_private_hash_put(struct futex_private_hash *fph);
+
+#else /* !CONFIG_FUTEX_PRIVATE_HASH */
+static inline struct futex_private_hash *futex_private_hash(struct mm_struct *mm) { return NULL; }
+static inline void futex_private_hash_put(struct futex_private_hash *fph) { }
+#endif
+
+extern struct futex_bucket_ref futex_hash(union futex_key *key);
+
+DEFINE_CLASS(hbr, struct futex_bucket_ref,
+	     if (_T.fph) futex_private_hash_put(_T.fph),
+	     futex_hash(key), union futex_key *key);
+
+DEFINE_CLASS(private_hash, struct futex_private_hash *,
+	     if (_T) futex_private_hash_put(_T),
+	     futex_private_hash(mm), struct mm_struct *mm);
+
+/**
+ * futex_match - Check whether two futex keys are equal
+ * @key1:	Pointer to key1
+ * @key2:	Pointer to key2
+ *
+ * Return 1 if two futex_keys are equal, 0 otherwise.
+ */
+static inline int futex_match(union futex_key *key1, union futex_key *key2)
+{
+	return (key1 && key2
+		&& key1->both.word == key2->both.word
+		&& key1->both.ptr == key2->both.ptr
+		&& key1->both.offset == key2->both.offset);
+}
+
+extern int futex_wait_setup(u32 __user *uaddr, u32 val, unsigned int flags,
+			    struct futex_q *q, union futex_key *key2,
+			    struct task_struct *task);
+extern void futex_do_wait(struct futex_q *q, struct hrtimer_sleeper *timeout);
+extern bool __futex_wake_mark(struct futex_q *q);
+extern void futex_wake_mark(struct wake_q_head *wake_q, struct futex_q *q);
+
+extern int fault_in_user_writeable(u32 __user *uaddr);
+extern struct futex_q *futex_top_waiter(struct futex_hash_bucket *hb, union futex_key *key);
+
+static inline int futex_cmpxchg_value_locked(u32 *curval, u32 __user *uaddr, u32 uval, u32 newval)
+{
+	int ret;
+
+	pagefault_disable();
+	ret = futex_atomic_cmpxchg_inatomic(curval, uaddr, uval, newval);
+	pagefault_enable();
+
+	return ret;
+}
+
+/* Read from user memory with pagefaults disabled */
+static inline int futex_get_value_locked(u32 *dest, u32 __user *from)
+{
+	guard(pagefault)();
+	return get_user_inline(*dest, from);
+}
+
+extern void __futex_unqueue(struct futex_q *q);
+extern void __futex_queue(struct futex_q *q, struct futex_hash_bucket *hb,
+				struct task_struct *task);
+extern int futex_unqueue(struct futex_q *q);
+
+/**
+ * futex_queue() - Enqueue the futex_q on the futex_hash_bucket
+ * @q:	The futex_q to enqueue
+ * @hb:	The destination hash bucket
+ * @task: Task queueing this futex
+ *
+ * The hb->lock must be held by the caller, and is released here. A call to
+ * futex_queue() is typically paired with exactly one call to futex_unqueue().  The
+ * exceptions involve the PI related operations, which may use futex_unqueue_pi()
+ * or nothing if the unqueue is done as part of the wake process and the unqueue
+ * state is implicit in the state of woken task (see futex_wait_requeue_pi() for
+ * an example).
+ *
+ * Note that @task may be NULL, for async usage of futexes.
+ */
+static inline void futex_queue(struct futex_q *q, struct futex_hash_bucket *hb,
+			       struct task_struct *task)
+	__releases(&hb->lock)
+	__releases(q->lock_ptr)
+{
+	__futex_queue(q, hb, task);
+	spin_unlock(&hb->lock);
+	__release(q->lock_ptr);
+}
+
+extern void futex_unqueue_pi(struct futex_q *q);
+
+extern void wait_for_owner_exiting(int ret, struct task_struct *exiting);
+
+/*
+ * Reflects a new waiter being added to the waitqueue.
+ */
+static inline void futex_hb_waiters_inc(struct futex_hash_bucket *hb)
+{
+#ifdef CONFIG_SMP
+	atomic_inc(&hb->waiters);
+	/*
+	 * Full barrier (A), see the ordering comment above.
+	 */
+	smp_mb__after_atomic();
+#endif
+}
+
+/*
+ * Reflects a waiter being removed from the waitqueue by wakeup
+ * paths.
+ */
+static inline void futex_hb_waiters_dec(struct futex_hash_bucket *hb)
+{
+#ifdef CONFIG_SMP
+	atomic_dec(&hb->waiters);
+#endif
+}
+
+static inline int futex_hb_waiters_pending(struct futex_hash_bucket *hb)
+{
+#ifdef CONFIG_SMP
+	/*
+	 * Full barrier (B), see the ordering comment above.
+	 */
+	smp_mb();
+	return atomic_read(&hb->waiters);
+#else
+	return 1;
+#endif
+}
+
+extern void futex_q_lock(struct futex_q *q, struct futex_hash_bucket *hb)
+	__acquires(&hb->lock)
+	__acquires(q->lock_ptr);
+
+extern void futex_q_unlock(struct futex_hash_bucket *hb)
+	__releases(&hb->lock);
+
+extern int futex_lock_pi_atomic(u32 __user *uaddr, struct futex_hash_bucket *hb,
+				union futex_key *key,
+				struct futex_pi_state **ps,
+				struct task_struct *task,
+				struct task_struct **exiting,
+				int set_waiters);
+
+extern int refill_pi_state_cache(void);
+extern void get_pi_state(struct futex_pi_state *pi_state);
+extern void put_pi_state(struct futex_pi_state *pi_state);
+extern int fixup_pi_owner(u32 __user *uaddr, struct futex_q *q, int locked);
+
+/*
+ * Express the locking dependencies for lockdep:
+ */
+static inline void
+double_lock_hb(struct futex_hash_bucket *hb1, struct futex_hash_bucket *hb2)
+	__acquires(&hb1->lock)
+	__acquires(&hb2->lock)
+	__no_context_analysis
+{
+	if (hb1 > hb2)
+		swap(hb1, hb2);
+
+	spin_lock(&hb1->lock);
+	if (hb1 != hb2)
+		spin_lock_nested(&hb2->lock, SINGLE_DEPTH_NESTING);
+}
+
+static inline void
+double_unlock_hb(struct futex_hash_bucket *hb1, struct futex_hash_bucket *hb2)
+	__releases(&hb1->lock)
+	__releases(&hb2->lock)
+	__no_context_analysis
+{
+	spin_unlock(&hb1->lock);
+	if (hb1 != hb2)
+		spin_unlock(&hb2->lock);
+}
+
+/* syscalls */
+
+extern int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, u32
+				 val, ktime_t *abs_time, u32 bitset, u32 __user
+				 *uaddr2);
+
+extern int futex_requeue(u32 __user *uaddr1, unsigned int flags1,
+			 u32 __user *uaddr2, unsigned int flags2,
+			 int nr_wake, int nr_requeue,
+			 u32 *cmpval, int requeue_pi);
+
+extern int __futex_wait(u32 __user *uaddr, unsigned int flags, u32 val,
+			struct hrtimer_sleeper *to, u32 bitset);
+
+extern int futex_wait(u32 __user *uaddr, unsigned int flags, u32 val,
+		      ktime_t *abs_time, u32 bitset);
+
+/**
+ * struct futex_vector - Auxiliary struct for futex_waitv()
+ * @w: Userspace provided data
+ * @q: Kernel side data
+ *
+ * Struct used to build an array with all data need for futex_waitv()
+ */
+struct futex_vector {
+	struct futex_waitv w;
+	struct futex_q q;
+};
+
+extern int futex_parse_waitv(struct futex_vector *futexv,
+			     struct futex_waitv __user *uwaitv,
+			     unsigned int nr_futexes, futex_wake_fn *wake,
+			     void *wake_data);
+
+extern int futex_wait_multiple_setup(struct futex_vector *vs, int count,
+				     int *woken);
+
+extern int futex_unqueue_multiple(struct futex_vector *v, int count);
+
+extern int futex_wait_multiple(struct futex_vector *vs, unsigned int count,
+			       struct hrtimer_sleeper *to);
+
+extern int futex_wake(u32 __user *uaddr, unsigned int flags, void __user *pop,
+		      int nr_wake, u32 bitset);
+
+extern int futex_wake_op(u32 __user *uaddr1, unsigned int flags,
+			 u32 __user *uaddr2, int nr_wake, int nr_wake2, int op);
+
+extern int futex_unlock_pi(u32 __user *uaddr, unsigned int flags, void __user *pop);
+
+extern int futex_lock_pi(u32 __user *uaddr, unsigned int flags, ktime_t *time, int trylock);
+
+bool futex_robust_list_clear_pending(void __user *pop, unsigned int flags);
+
+#endif /* _FUTEX_H */

linux-7.2.3/kernel/futex/requeue.c

@@ -0,0 +1,918 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/plist.h>
+#include <linux/sched/signal.h>
+
+#include "futex.h"
+#include "../locking/rtmutex_common.h"
+
+/*
+ * On PREEMPT_RT, the hash bucket lock is a 'sleeping' spinlock with an
+ * underlying rtmutex. The task which is about to be requeued could have
+ * just woken up (timeout, signal). After the wake up the task has to
+ * acquire hash bucket lock, which is held by the requeue code.  As a task
+ * can only be blocked on _ONE_ rtmutex at a time, the proxy lock blocking
+ * and the hash bucket lock blocking would collide and corrupt state.
+ *
+ * On !PREEMPT_RT this is not a problem and everything could be serialized
+ * on hash bucket lock, but aside of having the benefit of common code,
+ * this allows to avoid doing the requeue when the task is already on the
+ * way out and taking the hash bucket lock of the original uaddr1 when the
+ * requeue has been completed.
+ *
+ * The following state transitions are valid:
+ *
+ * On the waiter side:
+ *   Q_REQUEUE_PI_NONE		-> Q_REQUEUE_PI_IGNORE
+ *   Q_REQUEUE_PI_IN_PROGRESS	-> Q_REQUEUE_PI_WAIT
+ *
+ * On the requeue side:
+ *   Q_REQUEUE_PI_NONE		-> Q_REQUEUE_PI_INPROGRESS
+ *   Q_REQUEUE_PI_IN_PROGRESS	-> Q_REQUEUE_PI_DONE/LOCKED
+ *   Q_REQUEUE_PI_IN_PROGRESS	-> Q_REQUEUE_PI_NONE (requeue failed)
+ *   Q_REQUEUE_PI_WAIT		-> Q_REQUEUE_PI_DONE/LOCKED
+ *   Q_REQUEUE_PI_WAIT		-> Q_REQUEUE_PI_IGNORE (requeue failed)
+ *
+ * The requeue side ignores a waiter with state Q_REQUEUE_PI_IGNORE as this
+ * signals that the waiter is already on the way out. It also means that
+ * the waiter is still on the 'wait' futex, i.e. uaddr1.
+ *
+ * The waiter side signals early wakeup to the requeue side either through
+ * setting state to Q_REQUEUE_PI_IGNORE or to Q_REQUEUE_PI_WAIT depending
+ * on the current state. In case of Q_REQUEUE_PI_IGNORE it can immediately
+ * proceed to take the hash bucket lock of uaddr1. If it set state to WAIT,
+ * which means the wakeup is interleaving with a requeue in progress it has
+ * to wait for the requeue side to change the state. Either to DONE/LOCKED
+ * or to IGNORE. DONE/LOCKED means the waiter q is now on the uaddr2 futex
+ * and either blocked (DONE) or has acquired it (LOCKED). IGNORE is set by
+ * the requeue side when the requeue attempt failed via deadlock detection
+ * and therefore the waiter q is still on the uaddr1 futex.
+ */
+enum {
+	Q_REQUEUE_PI_NONE		=  0,
+	Q_REQUEUE_PI_IGNORE,
+	Q_REQUEUE_PI_IN_PROGRESS,
+	Q_REQUEUE_PI_WAIT,
+	Q_REQUEUE_PI_DONE,
+	Q_REQUEUE_PI_LOCKED,
+};
+
+const struct futex_q futex_q_init = {
+	/* list gets initialized in futex_queue()*/
+	.wake		= futex_wake_mark,
+	.key		= FUTEX_KEY_INIT,
+	.bitset		= FUTEX_BITSET_MATCH_ANY,
+	.requeue_state	= ATOMIC_INIT(Q_REQUEUE_PI_NONE),
+};
+
+/**
+ * requeue_futex() - Requeue a futex_q from one hb to another
+ * @q:		the futex_q to requeue
+ * @hb1:	the source hash_bucket
+ * @hb2:	the target hash_bucket
+ * @key2:	the new key for the requeued futex_q
+ */
+static inline
+void requeue_futex(struct futex_q *q, struct futex_hash_bucket *hb1,
+		   struct futex_hash_bucket *hb2, union futex_key *key2)
+{
+
+	/*
+	 * If key1 and key2 hash to the same bucket, no need to
+	 * requeue.
+	 */
+	if (likely(&hb1->chain != &hb2->chain)) {
+		plist_del(&q->list, &hb1->chain);
+		futex_hb_waiters_dec(hb1);
+		futex_hb_waiters_inc(hb2);
+		plist_add(&q->list, &hb2->chain);
+		q->lock_ptr = &hb2->lock;
+		/*
+		 * hb1 and hb2 belong to the same futex_hash_bucket_private
+		 * because if we managed get a reference on hb1 then it can't be
+		 * replaced. Therefore we avoid put(hb1)+get(hb2) here.
+		 */
+	}
+	q->key = *key2;
+}
+
+static inline bool futex_requeue_pi_prepare(struct futex_q *q,
+					    struct futex_pi_state *pi_state)
+{
+	int old, new;
+
+	/*
+	 * Set state to Q_REQUEUE_PI_IN_PROGRESS unless an early wakeup has
+	 * already set Q_REQUEUE_PI_IGNORE to signal that requeue should
+	 * ignore the waiter.
+	 */
+	old = atomic_read_acquire(&q->requeue_state);
+	do {
+		if (old == Q_REQUEUE_PI_IGNORE)
+			return false;
+
+		/*
+		 * futex_proxy_trylock_atomic() might have set it to
+		 * IN_PROGRESS and a interleaved early wake to WAIT.
+		 *
+		 * It was considered to have an extra state for that
+		 * trylock, but that would just add more conditionals
+		 * all over the place for a dubious value.
+		 */
+		if (old != Q_REQUEUE_PI_NONE)
+			break;
+
+		new = Q_REQUEUE_PI_IN_PROGRESS;
+	} while (!atomic_try_cmpxchg(&q->requeue_state, &old, new));
+
+	q->pi_state = pi_state;
+	return true;
+}
+
+static inline void futex_requeue_pi_complete(struct futex_q *q, int locked)
+{
+	int old, new;
+
+	old = atomic_read_acquire(&q->requeue_state);
+	do {
+		if (old == Q_REQUEUE_PI_IGNORE)
+			return;
+
+		if (locked >= 0) {
+			/* Requeue succeeded. Set DONE or LOCKED */
+			WARN_ON_ONCE(old != Q_REQUEUE_PI_IN_PROGRESS &&
+				     old != Q_REQUEUE_PI_WAIT);
+			new = Q_REQUEUE_PI_DONE + locked;
+		} else if (old == Q_REQUEUE_PI_IN_PROGRESS) {
+			/* Deadlock, no early wakeup interleave */
+			new = Q_REQUEUE_PI_NONE;
+		} else {
+			/* Deadlock, early wakeup interleave. */
+			WARN_ON_ONCE(old != Q_REQUEUE_PI_WAIT);
+			new = Q_REQUEUE_PI_IGNORE;
+		}
+	} while (!atomic_try_cmpxchg(&q->requeue_state, &old, new));
+
+#ifdef CONFIG_PREEMPT_RT
+	/* If the waiter interleaved with the requeue let it know */
+	if (unlikely(old == Q_REQUEUE_PI_WAIT))
+		rcuwait_wake_up(&q->requeue_wait);
+#endif
+}
+
+static inline int futex_requeue_pi_wakeup_sync(struct futex_q *q)
+{
+	int old, new;
+
+	old = atomic_read_acquire(&q->requeue_state);
+	do {
+		/* Is requeue done already? */
+		if (old >= Q_REQUEUE_PI_DONE)
+			return old;
+
+		/*
+		 * If not done, then tell the requeue code to either ignore
+		 * the waiter or to wake it up once the requeue is done.
+		 */
+		new = Q_REQUEUE_PI_WAIT;
+		if (old == Q_REQUEUE_PI_NONE)
+			new = Q_REQUEUE_PI_IGNORE;
+	} while (!atomic_try_cmpxchg(&q->requeue_state, &old, new));
+
+	/* If the requeue was in progress, wait for it to complete */
+	if (old == Q_REQUEUE_PI_IN_PROGRESS) {
+#ifdef CONFIG_PREEMPT_RT
+		rcuwait_wait_event(&q->requeue_wait,
+				   atomic_read(&q->requeue_state) != Q_REQUEUE_PI_WAIT,
+				   TASK_UNINTERRUPTIBLE);
+#else
+		(void)atomic_cond_read_relaxed(&q->requeue_state, VAL != Q_REQUEUE_PI_WAIT);
+#endif
+	}
+
+	/*
+	 * Requeue is now either prohibited or complete. Reread state
+	 * because during the wait above it might have changed. Nothing
+	 * will modify q->requeue_state after this point.
+	 */
+	return atomic_read(&q->requeue_state);
+}
+
+/**
+ * requeue_pi_wake_futex() - Wake a task that acquired the lock during requeue
+ * @q:		the futex_q
+ * @key:	the key of the requeue target futex
+ * @hb:		the hash_bucket of the requeue target futex
+ *
+ * During futex_requeue, with requeue_pi=1, it is possible to acquire the
+ * target futex if it is uncontended or via a lock steal.
+ *
+ * 1) Set @q::key to the requeue target futex key so the waiter can detect
+ *    the wakeup on the right futex.
+ *
+ * 2) Dequeue @q from the hash bucket.
+ *
+ * 3) Set @q::rt_waiter to NULL so the woken up task can detect atomic lock
+ *    acquisition.
+ *
+ * 4) Set the q->lock_ptr to the requeue target hb->lock for the case that
+ *    the waiter has to fixup the pi state.
+ *
+ * 5) Complete the requeue state so the waiter can make progress. After
+ *    this point the waiter task can return from the syscall immediately in
+ *    case that the pi state does not have to be fixed up.
+ *
+ * 6) Wake the waiter task.
+ *
+ * Must be called with both q->lock_ptr and hb->lock held.
+ */
+static inline
+void requeue_pi_wake_futex(struct futex_q *q, union futex_key *key,
+			   struct futex_hash_bucket *hb)
+{
+	struct task_struct *task;
+
+	q->key = *key;
+	__futex_unqueue(q);
+
+	WARN_ON(!q->rt_waiter);
+	q->rt_waiter = NULL;
+	/*
+	 * Acquire a reference for the waiter to ensure valid
+	 * futex_q::lock_ptr.
+	 */
+	if (futex_key_is_private(key))
+		q->drop_fph = futex_private_hash(key->private.mm);
+	q->lock_ptr = &hb->lock;
+	task = READ_ONCE(q->task);
+
+	/* Signal locked state to the waiter */
+	futex_requeue_pi_complete(q, 1);
+	wake_up_state(task, TASK_NORMAL);
+}
+
+/**
+ * futex_proxy_trylock_atomic() - Attempt an atomic lock for the top waiter
+ * @pifutex:		the user address of the to futex
+ * @hb1:		the from futex hash bucket, must be locked by the caller
+ * @hb2:		the to futex hash bucket, must be locked by the caller
+ * @key1:		the from futex key
+ * @key2:		the to futex key
+ * @ps:			address to store the pi_state pointer
+ * @exiting:		Pointer to store the task pointer of the owner task
+ *			which is in the middle of exiting
+ * @set_waiters:	force setting the FUTEX_WAITERS bit (1) or not (0)
+ *
+ * Try and get the lock on behalf of the top waiter if we can do it atomically.
+ * Wake the top waiter if we succeed.  If the caller specified set_waiters,
+ * then direct futex_lock_pi_atomic() to force setting the FUTEX_WAITERS bit.
+ * hb1 and hb2 must be held by the caller.
+ *
+ * @exiting is only set when the return value is -EBUSY. If so, this holds
+ * a refcount on the exiting task on return and the caller needs to drop it
+ * after waiting for the exit to complete.
+ *
+ * Return:
+ *  -  0 - failed to acquire the lock atomically;
+ *  - >0 - acquired the lock, return value is vpid of the top_waiter
+ *  - <0 - error
+ */
+static int
+futex_proxy_trylock_atomic(u32 __user *pifutex, struct futex_hash_bucket *hb1,
+			   struct futex_hash_bucket *hb2, union futex_key *key1,
+			   union futex_key *key2, struct futex_pi_state **ps,
+			   struct task_struct **exiting, int set_waiters)
+{
+	struct futex_q *top_waiter;
+	u32 curval;
+	int ret;
+
+	if (futex_get_value_locked(&curval, pifutex))
+		return -EFAULT;
+
+	if (unlikely(should_fail_futex(true)))
+		return -EFAULT;
+
+	/*
+	 * Find the top_waiter and determine if there are additional waiters.
+	 * If the caller intends to requeue more than 1 waiter to pifutex,
+	 * force futex_lock_pi_atomic() to set the FUTEX_WAITERS bit now,
+	 * as we have means to handle the possible fault.  If not, don't set
+	 * the bit unnecessarily as it will force the subsequent unlock to enter
+	 * the kernel.
+	 */
+	top_waiter = futex_top_waiter(hb1, key1);
+
+	/* There are no waiters, nothing for us to do. */
+	if (!top_waiter)
+		return 0;
+
+	/*
+	 * Ensure that this is a waiter sitting in futex_wait_requeue_pi()
+	 * and waiting on the 'waitqueue' futex which is always !PI.
+	 */
+	if (!top_waiter->rt_waiter || top_waiter->pi_state)
+		return -EINVAL;
+
+	/* Ensure we requeue to the expected futex. */
+	if (!futex_match(top_waiter->requeue_pi_key, key2))
+		return -EINVAL;
+
+	/* Ensure that this does not race against an early wakeup */
+	if (!futex_requeue_pi_prepare(top_waiter, NULL)) {
+		plist_del(&top_waiter->list, &hb1->chain);
+		futex_hb_waiters_dec(hb1);
+		return -EAGAIN;
+	}
+
+	/*
+	 * Try to take the lock for top_waiter and set the FUTEX_WAITERS bit
+	 * in the contended case or if @set_waiters is true.
+	 *
+	 * In the contended case PI state is attached to the lock owner. If
+	 * the user space lock can be acquired then PI state is attached to
+	 * the new owner (@top_waiter->task) when @set_waiters is true.
+	 */
+	ret = futex_lock_pi_atomic(pifutex, hb2, key2, ps, top_waiter->task,
+				   exiting, set_waiters);
+	if (ret == 1) {
+		/*
+		 * Lock was acquired in user space and PI state was
+		 * attached to @top_waiter->task. That means state is fully
+		 * consistent and the waiter can return to user space
+		 * immediately after the wakeup.
+		 */
+		requeue_pi_wake_futex(top_waiter, key2, hb2);
+	} else if (ret < 0) {
+		/* Rewind top_waiter::requeue_state */
+		futex_requeue_pi_complete(top_waiter, ret);
+	} else {
+		/*
+		 * futex_lock_pi_atomic() did not acquire the user space
+		 * futex, but managed to establish the proxy lock and pi
+		 * state. top_waiter::requeue_state cannot be fixed up here
+		 * because the waiter is not enqueued on the rtmutex
+		 * yet. This is handled at the callsite depending on the
+		 * result of rt_mutex_start_proxy_lock() which is
+		 * guaranteed to be reached with this function returning 0.
+		 */
+	}
+	return ret;
+}
+
+/**
+ * futex_requeue() - Requeue waiters from uaddr1 to uaddr2
+ * @uaddr1:	source futex user address
+ * @flags1:	futex flags (FLAGS_SHARED, etc.)
+ * @uaddr2:	target futex user address
+ * @flags2:	futex flags (FLAGS_SHARED, etc.)
+ * @nr_wake:	number of waiters to wake (must be 1 for requeue_pi)
+ * @nr_requeue:	number of waiters to requeue (0-INT_MAX)
+ * @cmpval:	@uaddr1 expected value (or %NULL)
+ * @requeue_pi:	if we are attempting to requeue from a non-pi futex to a
+ *		pi futex (pi to pi requeue is not supported)
+ *
+ * Requeue waiters on uaddr1 to uaddr2. In the requeue_pi case, try to acquire
+ * uaddr2 atomically on behalf of the top waiter.
+ *
+ * Return:
+ *  - >=0 - on success, the number of tasks requeued or woken;
+ *  -  <0 - on error
+ */
+int futex_requeue(u32 __user *uaddr1, unsigned int flags1,
+		  u32 __user *uaddr2, unsigned int flags2,
+		  int nr_wake, int nr_requeue, u32 *cmpval, int requeue_pi)
+{
+	union futex_key key1 = FUTEX_KEY_INIT, key2 = FUTEX_KEY_INIT;
+	int task_count = 0, ret;
+	struct futex_pi_state *pi_state = NULL;
+	struct futex_q *this, *next;
+	DEFINE_WAKE_Q(wake_q);
+
+	if (nr_wake < 0 || nr_requeue < 0)
+		return -EINVAL;
+
+	/*
+	 * When PI not supported: return -ENOSYS if requeue_pi is true,
+	 * consequently the compiler knows requeue_pi is always false past
+	 * this point which will optimize away all the conditional code
+	 * further down.
+	 */
+	if (!IS_ENABLED(CONFIG_FUTEX_PI) && requeue_pi)
+		return -ENOSYS;
+
+	if (requeue_pi) {
+		/*
+		 * Requeue PI only works on two distinct uaddrs. This
+		 * check is only valid for private futexes. See below.
+		 */
+		if (uaddr1 == uaddr2)
+			return -EINVAL;
+
+		/*
+		 * futex_requeue() allows the caller to define the number
+		 * of waiters to wake up via the @nr_wake argument. With
+		 * REQUEUE_PI, waking up more than one waiter is creating
+		 * more problems than it solves. Waking up a waiter makes
+		 * only sense if the PI futex @uaddr2 is uncontended as
+		 * this allows the requeue code to acquire the futex
+		 * @uaddr2 before waking the waiter. The waiter can then
+		 * return to user space without further action. A secondary
+		 * wakeup would just make the futex_wait_requeue_pi()
+		 * handling more complex, because that code would have to
+		 * look up pi_state and do more or less all the handling
+		 * which the requeue code has to do for the to be requeued
+		 * waiters. So restrict the number of waiters to wake to
+		 * one, and only wake it up when the PI futex is
+		 * uncontended. Otherwise requeue it and let the unlock of
+		 * the PI futex handle the wakeup.
+		 *
+		 * All REQUEUE_PI users, e.g. pthread_cond_signal() and
+		 * pthread_cond_broadcast() must use nr_wake=1.
+		 */
+		if (nr_wake != 1)
+			return -EINVAL;
+
+		/*
+		 * requeue_pi requires a pi_state, try to allocate it now
+		 * without any locks in case it fails.
+		 */
+		if (refill_pi_state_cache())
+			return -ENOMEM;
+	}
+
+retry:
+	ret = get_futex_key(uaddr1, flags1, &key1, FUTEX_READ);
+	if (unlikely(ret != 0))
+		return ret;
+	ret = get_futex_key(uaddr2, flags2, &key2,
+			    requeue_pi ? FUTEX_WRITE : FUTEX_READ);
+	if (unlikely(ret != 0))
+		return ret;
+
+	/*
+	 * The check above which compares uaddrs is not sufficient for
+	 * shared futexes. We need to compare the keys:
+	 */
+	if (requeue_pi && futex_match(&key1, &key2))
+		return -EINVAL;
+
+retry_private:
+	if (1) {
+		CLASS(hbr, hbr1)(&key1);
+		CLASS(hbr, hbr2)(&key2);
+		auto hb1 = hbr1.hb;
+		auto hb2 = hbr2.hb;
+
+		futex_hb_waiters_inc(hb2);
+		double_lock_hb(hb1, hb2);
+
+		if (likely(cmpval != NULL)) {
+			u32 curval;
+
+			ret = futex_get_value_locked(&curval, uaddr1);
+
+			if (unlikely(ret)) {
+				futex_hb_waiters_dec(hb2);
+				double_unlock_hb(hb1, hb2);
+
+				ret = get_user(curval, uaddr1);
+				if (ret)
+					return ret;
+
+				if (!(flags1 & FLAGS_SHARED))
+					goto retry_private;
+
+				goto retry;
+			}
+			if (curval != *cmpval) {
+				ret = -EAGAIN;
+				goto out_unlock;
+			}
+		}
+
+		if (requeue_pi) {
+			struct task_struct *exiting = NULL;
+
+			/*
+			 * Attempt to acquire uaddr2 and wake the top waiter. If we
+			 * intend to requeue waiters, force setting the FUTEX_WAITERS
+			 * bit.  We force this here where we are able to easily handle
+			 * faults rather in the requeue loop below.
+			 *
+			 * Updates topwaiter::requeue_state if a top waiter exists.
+			 */
+			ret = futex_proxy_trylock_atomic(uaddr2, hb1, hb2, &key1,
+							 &key2, &pi_state,
+							 &exiting, nr_requeue);
+
+			/*
+			 * At this point the top_waiter has either taken uaddr2 or
+			 * is waiting on it. In both cases pi_state has been
+			 * established and an initial refcount on it. In case of an
+			 * error there's nothing.
+			 *
+			 * The top waiter's requeue_state is up to date:
+			 *
+			 *  - If the lock was acquired atomically (ret == 1), then
+			 *    the state is Q_REQUEUE_PI_LOCKED.
+			 *
+			 *    The top waiter has been dequeued and woken up and can
+			 *    return to user space immediately. The kernel/user
+			 *    space state is consistent. In case that there must be
+			 *    more waiters requeued the WAITERS bit in the user
+			 *    space futex is set so the top waiter task has to go
+			 *    into the syscall slowpath to unlock the futex. This
+			 *    will block until this requeue operation has been
+			 *    completed and the hash bucket locks have been
+			 *    dropped.
+			 *
+			 *  - If the trylock failed with an error (ret < 0) then
+			 *    the state is either Q_REQUEUE_PI_NONE, i.e. "nothing
+			 *    happened", or Q_REQUEUE_PI_IGNORE when there was an
+			 *    interleaved early wakeup.
+			 *
+			 *  - If the trylock did not succeed (ret == 0) then the
+			 *    state is either Q_REQUEUE_PI_IN_PROGRESS or
+			 *    Q_REQUEUE_PI_WAIT if an early wakeup interleaved.
+			 *    This will be cleaned up in the loop below, which
+			 *    cannot fail because futex_proxy_trylock_atomic() did
+			 *    the same sanity checks for requeue_pi as the loop
+			 *    below does.
+			 */
+			switch (ret) {
+			case 0:
+				/* We hold a reference on the pi state. */
+				break;
+
+			case 1:
+				/*
+				 * futex_proxy_trylock_atomic() acquired the user space
+				 * futex. Adjust task_count.
+				 */
+				task_count++;
+				ret = 0;
+				break;
+
+				/*
+				 * If the above failed, then pi_state is NULL and
+				 * waiter::requeue_state is correct.
+				 */
+			case -EFAULT:
+				futex_hb_waiters_dec(hb2);
+				double_unlock_hb(hb1, hb2);
+				ret = fault_in_user_writeable(uaddr2);
+				if (!ret)
+					goto retry;
+				return ret;
+			case -EBUSY:
+			case -EAGAIN:
+				/*
+				 * Two reasons for this:
+				 * - EBUSY: Owner is exiting and we just wait for the
+				 *   exit to complete.
+				 * - EAGAIN: The user space value changed.
+				 */
+				futex_hb_waiters_dec(hb2);
+				double_unlock_hb(hb1, hb2);
+				/*
+				 * Handle the case where the owner is in the middle of
+				 * exiting. Wait for the exit to complete otherwise
+				 * this task might loop forever, aka. live lock.
+				 */
+				wait_for_owner_exiting(ret, exiting);
+				cond_resched();
+				goto retry;
+			default:
+				goto out_unlock;
+			}
+		}
+
+		plist_for_each_entry_safe(this, next, &hb1->chain, list) {
+			if (task_count - nr_wake >= nr_requeue)
+				break;
+
+			if (!futex_match(&this->key, &key1))
+				continue;
+
+			/*
+			 * FUTEX_WAIT_REQUEUE_PI and FUTEX_CMP_REQUEUE_PI should always
+			 * be paired with each other and no other futex ops.
+			 *
+			 * We should never be requeueing a futex_q with a pi_state,
+			 * which is awaiting a futex_unlock_pi().
+			 */
+			if ((requeue_pi && !this->rt_waiter) ||
+			    (!requeue_pi && this->rt_waiter) ||
+			    this->pi_state) {
+				ret = -EINVAL;
+				break;
+			}
+
+			/* Plain futexes just wake or requeue and are done */
+			if (!requeue_pi) {
+				if (++task_count <= nr_wake)
+					this->wake(&wake_q, this);
+				else
+					requeue_futex(this, hb1, hb2, &key2);
+				continue;
+			}
+
+			/* Ensure we requeue to the expected futex for requeue_pi. */
+			if (!futex_match(this->requeue_pi_key, &key2)) {
+				ret = -EINVAL;
+				break;
+			}
+
+			/*
+			 * Requeue nr_requeue waiters and possibly one more in the case
+			 * of requeue_pi if we couldn't acquire the lock atomically.
+			 *
+			 * Prepare the waiter to take the rt_mutex. Take a refcount
+			 * on the pi_state and store the pointer in the futex_q
+			 * object of the waiter.
+			 */
+			get_pi_state(pi_state);
+
+			/* Don't requeue when the waiter is already on the way out. */
+			if (!futex_requeue_pi_prepare(this, pi_state)) {
+				/*
+				 * Early woken waiter signaled that it is on the
+				 * way out. Drop the pi_state reference and try the
+				 * next waiter. @this->pi_state is still NULL.
+				 */
+				put_pi_state(pi_state);
+				continue;
+			}
+
+			ret = rt_mutex_start_proxy_lock(&pi_state->pi_mutex,
+							this->rt_waiter,
+							this->task);
+
+			if (ret == 1) {
+				/*
+				 * We got the lock. We do neither drop the refcount
+				 * on pi_state nor clear this->pi_state because the
+				 * waiter needs the pi_state for cleaning up the
+				 * user space value. It will drop the refcount
+				 * after doing so. this::requeue_state is updated
+				 * in the wakeup as well.
+				 */
+				requeue_pi_wake_futex(this, &key2, hb2);
+				task_count++;
+			} else if (!ret) {
+				/* Waiter is queued, move it to hb2 */
+				requeue_futex(this, hb1, hb2, &key2);
+				futex_requeue_pi_complete(this, 0);
+				task_count++;
+			} else {
+				/*
+				 * rt_mutex_start_proxy_lock() detected a potential
+				 * deadlock when we tried to queue that waiter.
+				 * Drop the pi_state reference which we took above
+				 * and remove the pointer to the state from the
+				 * waiters futex_q object.
+				 */
+				this->pi_state = NULL;
+				put_pi_state(pi_state);
+				futex_requeue_pi_complete(this, ret);
+				/*
+				 * We stop queueing more waiters and let user space
+				 * deal with the mess.
+				 */
+				break;
+			}
+		}
+
+		/*
+		 * We took an extra initial reference to the pi_state in
+		 * futex_proxy_trylock_atomic(). We need to drop it here again.
+		 */
+		put_pi_state(pi_state);
+
+out_unlock:
+		futex_hb_waiters_dec(hb2);
+		double_unlock_hb(hb1, hb2);
+	}
+	wake_up_q(&wake_q);
+	return ret ? ret : task_count;
+}
+
+/**
+ * handle_early_requeue_pi_wakeup() - Handle early wakeup on the initial futex
+ * @hb:		the hash_bucket futex_q was original enqueued on
+ * @q:		the futex_q woken while waiting to be requeued
+ * @timeout:	the timeout associated with the wait (NULL if none)
+ *
+ * Determine the cause for the early wakeup.
+ *
+ * Return:
+ *  -EWOULDBLOCK or -ETIMEDOUT or -ERESTARTNOINTR
+ */
+static inline
+int handle_early_requeue_pi_wakeup(struct futex_hash_bucket *hb,
+				   struct futex_q *q,
+				   struct hrtimer_sleeper *timeout)
+{
+	int ret;
+
+	/*
+	 * With the hb lock held, we avoid races while we process the wakeup.
+	 * We only need to hold hb (and not hb2) to ensure atomicity as the
+	 * wakeup code can't change q.key from uaddr to uaddr2 if we hold hb.
+	 * It can't be requeued from uaddr2 to something else since we don't
+	 * support a PI aware source futex for requeue.
+	 */
+	WARN_ON_ONCE(&hb->lock != q->lock_ptr);
+
+	/*
+	 * We were woken prior to requeue by a timeout or a signal.
+	 * Conditionally unqueue the futex_q and determine which it was.
+	 */
+	if (!plist_node_empty(&q->list)) {
+		plist_del(&q->list, &hb->chain);
+		futex_hb_waiters_dec(hb);
+	}
+
+	/* Handle spurious wakeups gracefully */
+	ret = -EWOULDBLOCK;
+	if (timeout && !timeout->task)
+		ret = -ETIMEDOUT;
+	else if (signal_pending(current))
+		ret = -ERESTARTNOINTR;
+	return ret;
+}
+
+/**
+ * futex_wait_requeue_pi() - Wait on uaddr and take uaddr2
+ * @uaddr:	the futex we initially wait on (non-pi)
+ * @flags:	futex flags (FLAGS_SHARED, FLAGS_CLOCKRT, etc.), they must be
+ *		the same type, no requeueing from private to shared, etc.
+ * @val:	the expected value of uaddr
+ * @abs_time:	absolute timeout
+ * @bitset:	32 bit wakeup bitset set by userspace, defaults to all
+ * @uaddr2:	the pi futex we will take prior to returning to user-space
+ *
+ * The caller will wait on uaddr and will be requeued by futex_requeue() to
+ * uaddr2 which must be PI aware and unique from uaddr.  Normal wakeup will wake
+ * on uaddr2 and complete the acquisition of the rt_mutex prior to returning to
+ * userspace.  This ensures the rt_mutex maintains an owner when it has waiters;
+ * without one, the pi logic would not know which task to boost/deboost, if
+ * there was a need to.
+ *
+ * We call schedule in futex_wait_queue() when we enqueue and return there
+ * via the following--
+ * 1) wakeup on uaddr2 after an atomic lock acquisition by futex_requeue()
+ * 2) wakeup on uaddr2 after a requeue
+ * 3) signal
+ * 4) timeout
+ *
+ * If 3, cleanup and return -ERESTARTNOINTR.
+ *
+ * If 2, we may then block on trying to take the rt_mutex and return via:
+ * 5) successful lock
+ * 6) signal
+ * 7) timeout
+ * 8) other lock acquisition failure
+ *
+ * If 6, return -EWOULDBLOCK (restarting the syscall would do the same).
+ *
+ * If 4 or 7, we cleanup and return with -ETIMEDOUT.
+ *
+ * Return:
+ *  -  0 - On success;
+ *  - <0 - On error
+ */
+int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
+			  u32 val, ktime_t *abs_time, u32 bitset,
+			  u32 __user *uaddr2)
+{
+	struct hrtimer_sleeper timeout, *to;
+	struct rt_mutex_waiter rt_waiter;
+	union futex_key key2 = FUTEX_KEY_INIT;
+	struct futex_q q = futex_q_init;
+	struct rt_mutex_base *pi_mutex;
+	int res, ret;
+
+	if (!IS_ENABLED(CONFIG_FUTEX_PI))
+		return -ENOSYS;
+
+	if (uaddr == uaddr2)
+		return -EINVAL;
+
+	if (!bitset)
+		return -EINVAL;
+
+	to = futex_setup_timer(abs_time, &timeout, flags,
+			       current->timer_slack_ns);
+
+	/*
+	 * The waiter is allocated on our stack, manipulated by the requeue
+	 * code while we sleep on uaddr.
+	 */
+	rt_mutex_init_waiter(&rt_waiter);
+
+	ret = get_futex_key(uaddr2, flags, &key2, FUTEX_WRITE);
+	if (unlikely(ret != 0))
+		goto out;
+
+	q.bitset = bitset;
+	q.rt_waiter = &rt_waiter;
+	q.requeue_pi_key = &key2;
+
+	/*
+	 * Prepare to wait on uaddr. On success, it holds hb->lock and q
+	 * is initialized.
+	 */
+	ret = futex_wait_setup(uaddr, val, flags, &q, &key2, current);
+	if (ret)
+		goto out;
+
+	/* Queue the futex_q, drop the hb lock, wait for wakeup. */
+	futex_do_wait(&q, to);
+
+	switch (futex_requeue_pi_wakeup_sync(&q)) {
+	case Q_REQUEUE_PI_IGNORE:
+		{
+			CLASS(hbr, hbr)(&q.key);
+			auto hb = hbr.hb;
+			/* The waiter is still on uaddr1 */
+			spin_lock(&hb->lock);
+			ret = handle_early_requeue_pi_wakeup(hb, &q, to);
+			spin_unlock(&hb->lock);
+		}
+		break;
+
+	case Q_REQUEUE_PI_LOCKED:
+		/* The requeue acquired the lock */
+		if (q.pi_state && (q.pi_state->owner != current)) {
+			futex_q_lockptr_lock(&q);
+			ret = fixup_pi_owner(uaddr2, &q, true);
+			/*
+			 * Drop the reference to the pi state which the
+			 * requeue_pi() code acquired for us.
+			 */
+			put_pi_state(q.pi_state);
+			spin_unlock(q.lock_ptr);
+			/*
+			 * Adjust the return value. It's either -EFAULT or
+			 * success (1) but the caller expects 0 for success.
+			 */
+			ret = ret < 0 ? ret : 0;
+		}
+		break;
+
+	case Q_REQUEUE_PI_DONE:
+		/* Requeue completed. Current is 'pi_blocked_on' the rtmutex */
+		pi_mutex = &q.pi_state->pi_mutex;
+		ret = rt_mutex_wait_proxy_lock(pi_mutex, to, &rt_waiter);
+
+		/*
+		 * See futex_unlock_pi()'s cleanup: comment.
+		 */
+		if (ret && !rt_mutex_cleanup_proxy_lock(pi_mutex, &rt_waiter))
+			ret = 0;
+
+		futex_q_lockptr_lock(&q);
+		debug_rt_mutex_free_waiter(&rt_waiter);
+		/*
+		 * Fixup the pi_state owner and possibly acquire the lock if we
+		 * haven't already.
+		 */
+		res = fixup_pi_owner(uaddr2, &q, !ret);
+		/*
+		 * If fixup_pi_owner() returned an error, propagate that.  If it
+		 * acquired the lock, clear -ETIMEDOUT or -EINTR.
+		 */
+		if (res)
+			ret = (res < 0) ? res : 0;
+
+		futex_unqueue_pi(&q);
+		spin_unlock(q.lock_ptr);
+
+		if (ret == -EINTR) {
+			/*
+			 * We've already been requeued, but cannot restart
+			 * by calling futex_lock_pi() directly. We could
+			 * restart this syscall, but it would detect that
+			 * the user space "val" changed and return
+			 * -EWOULDBLOCK.  Save the overhead of the restart
+			 * and return -EWOULDBLOCK directly.
+			 */
+			ret = -EWOULDBLOCK;
+		}
+		break;
+	default:
+		BUG();
+	}
+	/* Additional reference from requeue_pi_wake_futex() */
+	futex_private_hash_put(q.drop_fph);
+
+out:
+	if (to) {
+		hrtimer_cancel(&to->timer);
+		destroy_hrtimer_on_stack(&to->timer);
+	}
+	return ret;
+}
+

linux-7.2.3/kernel/futex/syscalls.c

@@ -0,0 +1,526 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/syscalls.h>
+#include <linux/time_namespace.h>
+
+#include "futex.h"
+
+/*
+ * Support for robust futexes: the kernel cleans up held futexes at
+ * thread exit time.
+ *
+ * Implementation: user-space maintains a per-thread list of locks it
+ * is holding. Upon do_exit(), the kernel carefully walks this list,
+ * and marks all locks that are owned by this thread with the
+ * FUTEX_OWNER_DIED bit, and wakes up a waiter (if any). The list is
+ * always manipulated with the lock held, so the list is private and
+ * per-thread. Userspace also maintains a per-thread 'list_op_pending'
+ * field, to allow the kernel to clean up if the thread dies after
+ * acquiring the lock, but just before it could have added itself to
+ * the list. There can only be one such pending lock.
+ */
+
+/**
+ * sys_set_robust_list() - Set the robust-futex list head of a task
+ * @head:	pointer to the list-head
+ * @len:	length of the list-head, as userspace expects
+ */
+SYSCALL_DEFINE2(set_robust_list, struct robust_list_head __user *, head, size_t, len)
+{
+	/* The kernel knows only one size for now. */
+	if (unlikely(len != sizeof(*head)))
+		return -EINVAL;
+
+	current->futex.robust_list = head;
+	return 0;
+}
+
+static inline void __user *futex_task_robust_list(struct task_struct *p, bool compat)
+{
+#ifdef CONFIG_COMPAT
+	if (compat)
+		return p->futex.compat_robust_list;
+#endif
+	return p->futex.robust_list;
+}
+
+static void __user *futex_get_robust_list_common(int pid, bool compat)
+{
+	struct task_struct *p = current;
+	void __user *head;
+	int ret;
+
+	scoped_guard(rcu) {
+		if (pid) {
+			p = find_task_by_vpid(pid);
+			if (!p)
+				return (void __user *)ERR_PTR(-ESRCH);
+		}
+		get_task_struct(p);
+	}
+
+	/*
+	 * Hold exec_update_lock to serialize with concurrent exec()
+	 * so ptrace_may_access() is checked against stable credentials
+	 */
+	ret = down_read_killable(&p->signal->exec_update_lock);
+	if (ret)
+		goto err_put;
+
+	ret = -EPERM;
+	if (!ptrace_may_access(p, PTRACE_MODE_READ_REALCREDS))
+		goto err_unlock;
+
+	head = futex_task_robust_list(p, compat);
+
+	up_read(&p->signal->exec_update_lock);
+	put_task_struct(p);
+
+	return head;
+
+err_unlock:
+	up_read(&p->signal->exec_update_lock);
+err_put:
+	put_task_struct(p);
+	return (void __user *)ERR_PTR(ret);
+}
+
+/**
+ * sys_get_robust_list() - Get the robust-futex list head of a task
+ * @pid:	pid of the process [zero for current task]
+ * @head_ptr:	pointer to a list-head pointer, the kernel fills it in
+ * @len_ptr:	pointer to a length field, the kernel fills in the header size
+ */
+SYSCALL_DEFINE3(get_robust_list, int, pid,
+		struct robust_list_head __user * __user *, head_ptr,
+		size_t __user *, len_ptr)
+{
+	struct robust_list_head __user *head = futex_get_robust_list_common(pid, false);
+
+	if (IS_ERR(head))
+		return PTR_ERR(head);
+
+	if (put_user(sizeof(*head), len_ptr))
+		return -EFAULT;
+	return put_user(head, head_ptr);
+}
+
+long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout,
+		u32 __user *uaddr2, u32 val2, u32 val3)
+{
+	unsigned int flags = futex_to_flags(op);
+	int cmd = op & FUTEX_CMD_MASK;
+
+	if (flags & FLAGS_CLOCKRT) {
+		if (cmd != FUTEX_WAIT_BITSET &&
+		    cmd != FUTEX_WAIT_REQUEUE_PI &&
+		    cmd != FUTEX_LOCK_PI2)
+			return -ENOSYS;
+	}
+
+	if (flags & FLAGS_ROBUST_UNLOCK) {
+		if (cmd != FUTEX_WAKE &&
+		    cmd != FUTEX_WAKE_BITSET &&
+		    cmd != FUTEX_UNLOCK_PI)
+			return -ENOSYS;
+	}
+
+	switch (cmd) {
+	case FUTEX_WAIT:
+		val3 = FUTEX_BITSET_MATCH_ANY;
+		fallthrough;
+	case FUTEX_WAIT_BITSET:
+		return futex_wait(uaddr, flags, val, timeout, val3);
+	case FUTEX_WAKE:
+		val3 = FUTEX_BITSET_MATCH_ANY;
+		fallthrough;
+	case FUTEX_WAKE_BITSET:
+		return futex_wake(uaddr, flags, uaddr2, val, val3);
+	case FUTEX_REQUEUE:
+		return futex_requeue(uaddr, flags, uaddr2, flags, val, val2, NULL, 0);
+	case FUTEX_CMP_REQUEUE:
+		return futex_requeue(uaddr, flags, uaddr2, flags, val, val2, &val3, 0);
+	case FUTEX_WAKE_OP:
+		return futex_wake_op(uaddr, flags, uaddr2, val, val2, val3);
+	case FUTEX_LOCK_PI:
+		flags |= FLAGS_CLOCKRT;
+		fallthrough;
+	case FUTEX_LOCK_PI2:
+		return futex_lock_pi(uaddr, flags, timeout, 0);
+	case FUTEX_UNLOCK_PI:
+		return futex_unlock_pi(uaddr, flags, uaddr2);
+	case FUTEX_TRYLOCK_PI:
+		return futex_lock_pi(uaddr, flags, NULL, 1);
+	case FUTEX_WAIT_REQUEUE_PI:
+		val3 = FUTEX_BITSET_MATCH_ANY;
+		return futex_wait_requeue_pi(uaddr, flags, val, timeout, val3,
+					     uaddr2);
+	case FUTEX_CMP_REQUEUE_PI:
+		return futex_requeue(uaddr, flags, uaddr2, flags, val, val2, &val3, 1);
+	}
+	return -ENOSYS;
+}
+
+static __always_inline bool futex_cmd_has_timeout(u32 cmd)
+{
+	switch (cmd) {
+	case FUTEX_WAIT:
+	case FUTEX_LOCK_PI:
+	case FUTEX_LOCK_PI2:
+	case FUTEX_WAIT_BITSET:
+	case FUTEX_WAIT_REQUEUE_PI:
+		return true;
+	}
+	return false;
+}
+
+static __always_inline int
+futex_init_timeout(u32 cmd, u32 op, struct timespec64 *ts, ktime_t *t)
+{
+	if (!timespec64_valid(ts))
+		return -EINVAL;
+
+	*t = timespec64_to_ktime(*ts);
+	if (cmd == FUTEX_WAIT)
+		*t = ktime_add_safe(ktime_get(), *t);
+	else if (cmd != FUTEX_LOCK_PI && !(op & FUTEX_CLOCK_REALTIME))
+		*t = timens_ktime_to_host(CLOCK_MONOTONIC, *t);
+	return 0;
+}
+
+SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val,
+		const struct __kernel_timespec __user *, utime,
+		u32 __user *, uaddr2, u32, val3)
+{
+	int ret, cmd = op & FUTEX_CMD_MASK;
+	ktime_t t, *tp = NULL;
+	struct timespec64 ts;
+
+	if (utime && futex_cmd_has_timeout(cmd)) {
+		if (unlikely(should_fail_futex(!(op & FUTEX_PRIVATE_FLAG))))
+			return -EFAULT;
+		if (get_timespec64(&ts, utime))
+			return -EFAULT;
+		ret = futex_init_timeout(cmd, op, &ts, &t);
+		if (ret)
+			return ret;
+		tp = &t;
+	}
+
+	return do_futex(uaddr, op, val, tp, uaddr2, (unsigned long)utime, val3);
+}
+
+/**
+ * futex_parse_waitv - Parse a waitv array from userspace
+ * @futexv:	Kernel side list of waiters to be filled
+ * @uwaitv:     Userspace list to be parsed
+ * @nr_futexes: Length of futexv
+ * @wake:	Wake to call when futex is woken
+ * @wake_data:	Data for the wake handler
+ *
+ * Return: Error code on failure, 0 on success
+ */
+int futex_parse_waitv(struct futex_vector *futexv,
+		      struct futex_waitv __user *uwaitv,
+		      unsigned int nr_futexes, futex_wake_fn *wake,
+		      void *wake_data)
+{
+	struct futex_waitv aux;
+	unsigned int i;
+
+	for (i = 0; i < nr_futexes; i++) {
+		unsigned int flags;
+
+		if (copy_from_user(&aux, &uwaitv[i], sizeof(aux)))
+			return -EFAULT;
+
+		if ((aux.flags & ~FUTEX2_VALID_MASK) || aux.__reserved)
+			return -EINVAL;
+
+		flags = futex2_to_flags(aux.flags);
+		if (!futex_flags_valid(flags))
+			return -EINVAL;
+
+		if (!futex_validate_input(flags, aux.val))
+			return -EINVAL;
+
+		futexv[i].w.flags = flags;
+		futexv[i].w.val = aux.val;
+		futexv[i].w.uaddr = aux.uaddr;
+		futexv[i].q = futex_q_init;
+		futexv[i].q.wake = wake;
+		futexv[i].q.wake_data = wake_data;
+	}
+
+	return 0;
+}
+
+static int futex2_setup_timeout(struct __kernel_timespec __user *timeout,
+				clockid_t clockid, struct hrtimer_sleeper *to)
+{
+	int flag_clkid = 0, flag_init = 0;
+	struct timespec64 ts;
+	ktime_t time;
+	int ret;
+
+	if (!timeout)
+		return 0;
+
+	if (clockid == CLOCK_REALTIME) {
+		flag_clkid = FLAGS_CLOCKRT;
+		flag_init = FUTEX_CLOCK_REALTIME;
+	}
+
+	if (clockid != CLOCK_REALTIME && clockid != CLOCK_MONOTONIC)
+		return -EINVAL;
+
+	if (get_timespec64(&ts, timeout))
+		return -EFAULT;
+
+	/*
+	 * Since there's no opcode for futex_waitv, use
+	 * FUTEX_WAIT_BITSET that uses absolute timeout as well
+	 */
+	ret = futex_init_timeout(FUTEX_WAIT_BITSET, flag_init, &ts, &time);
+	if (ret)
+		return ret;
+
+	futex_setup_timer(&time, to, flag_clkid, 0);
+	return 0;
+}
+
+static inline void futex2_destroy_timeout(struct hrtimer_sleeper *to)
+{
+	hrtimer_cancel(&to->timer);
+	destroy_hrtimer_on_stack(&to->timer);
+}
+
+/**
+ * sys_futex_waitv - Wait on a list of futexes
+ * @waiters:    List of futexes to wait on
+ * @nr_futexes: Length of futexv
+ * @flags:      Flag for timeout (monotonic/realtime)
+ * @timeout:	Optional absolute timeout.
+ * @clockid:	Clock to be used for the timeout, realtime or monotonic.
+ *
+ * Given an array of `struct futex_waitv`, wait on each uaddr. The thread wakes
+ * if a futex_wake() is performed at any uaddr. The syscall returns immediately
+ * if any waiter has *uaddr != val. *timeout is an optional timeout value for
+ * the operation. Each waiter has individual flags. The `flags` argument for
+ * the syscall should be used solely for specifying the timeout as realtime, if
+ * needed. Flags for private futexes, sizes, etc. should be used on the
+ * individual flags of each waiter.
+ *
+ * Returns the array index of one of the woken futexes. No further information
+ * is provided: any number of other futexes may also have been woken by the
+ * same event, and if more than one futex was woken, the retrned index may
+ * refer to any one of them. (It is not necessaryily the futex with the
+ * smallest index, nor the one most recently woken, nor...)
+ */
+
+SYSCALL_DEFINE5(futex_waitv, struct futex_waitv __user *, waiters,
+		unsigned int, nr_futexes, unsigned int, flags,
+		struct __kernel_timespec __user *, timeout, clockid_t, clockid)
+{
+	struct hrtimer_sleeper to;
+	struct futex_vector *futexv;
+	int ret;
+
+	/* This syscall supports no flags for now */
+	if (flags)
+		return -EINVAL;
+
+	if (!nr_futexes || nr_futexes > FUTEX_WAITV_MAX || !waiters)
+		return -EINVAL;
+
+	if (timeout && (ret = futex2_setup_timeout(timeout, clockid, &to)))
+		return ret;
+
+	futexv = kzalloc_objs(*futexv, nr_futexes);
+	if (!futexv) {
+		ret = -ENOMEM;
+		goto destroy_timer;
+	}
+
+	ret = futex_parse_waitv(futexv, waiters, nr_futexes, futex_wake_mark,
+				NULL);
+	if (!ret)
+		ret = futex_wait_multiple(futexv, nr_futexes, timeout ? &to : NULL);
+
+	kfree(futexv);
+
+destroy_timer:
+	if (timeout)
+		futex2_destroy_timeout(&to);
+	return ret;
+}
+
+/*
+ * sys_futex_wake - Wake a number of futexes
+ * @uaddr:	Address of the futex(es) to wake
+ * @mask:	bitmask
+ * @nr:		Number of the futexes to wake
+ * @flags:	FUTEX2 flags
+ *
+ * Identical to the traditional FUTEX_WAKE_BITSET op, except it is part of the
+ * futex2 family of calls.
+ */
+
+SYSCALL_DEFINE4(futex_wake,
+		void __user *, uaddr,
+		unsigned long, mask,
+		int, nr,
+		unsigned int, flags)
+{
+	if (flags & ~FUTEX2_VALID_MASK)
+		return -EINVAL;
+
+	flags = futex2_to_flags(flags);
+	if (!futex_flags_valid(flags))
+		return -EINVAL;
+
+	if (!futex_validate_input(flags, mask))
+		return -EINVAL;
+
+	return futex_wake(uaddr, FLAGS_STRICT | flags, NULL, nr, mask);
+}
+
+/*
+ * sys_futex_wait - Wait on a futex
+ * @uaddr:	Address of the futex to wait on
+ * @val:	Value of @uaddr
+ * @mask:	bitmask
+ * @flags:	FUTEX2 flags
+ * @timeout:	Optional absolute timeout
+ * @clockid:	Clock to be used for the timeout, realtime or monotonic
+ *
+ * Identical to the traditional FUTEX_WAIT_BITSET op, except it is part of the
+ * futex2 familiy of calls.
+ */
+
+SYSCALL_DEFINE6(futex_wait,
+		void __user *, uaddr,
+		unsigned long, val,
+		unsigned long, mask,
+		unsigned int, flags,
+		struct __kernel_timespec __user *, timeout,
+		clockid_t, clockid)
+{
+	struct hrtimer_sleeper to;
+	int ret;
+
+	if (flags & ~FUTEX2_VALID_MASK)
+		return -EINVAL;
+
+	flags = futex2_to_flags(flags);
+	if (!futex_flags_valid(flags))
+		return -EINVAL;
+
+	if (!futex_validate_input(flags, val) ||
+	    !futex_validate_input(flags, mask))
+		return -EINVAL;
+
+	if (timeout && (ret = futex2_setup_timeout(timeout, clockid, &to)))
+		return ret;
+
+	ret = __futex_wait(uaddr, flags, val, timeout ? &to : NULL, mask);
+
+	if (timeout)
+		futex2_destroy_timeout(&to);
+
+	return ret;
+}
+
+/*
+ * sys_futex_requeue - Requeue a waiter from one futex to another
+ * @waiters:	array describing the source and destination futex
+ * @flags:	unused
+ * @nr_wake:	number of futexes to wake
+ * @nr_requeue:	number of futexes to requeue
+ *
+ * Identical to the traditional FUTEX_CMP_REQUEUE op, except it is part of the
+ * futex2 family of calls.
+ */
+
+SYSCALL_DEFINE4(futex_requeue,
+		struct futex_waitv __user *, waiters,
+		unsigned int, flags,
+		int, nr_wake,
+		int, nr_requeue)
+{
+	struct futex_vector futexes[2];
+	u32 cmpval;
+	int ret;
+
+	if (flags)
+		return -EINVAL;
+
+	if (!waiters)
+		return -EINVAL;
+
+	ret = futex_parse_waitv(futexes, waiters, 2, futex_wake_mark, NULL);
+	if (ret)
+		return ret;
+
+	/*
+	 * For now mandate both flags are identical, like the sys_futex()
+	 * interface has. If/when we merge the variable sized futex support,
+	 * that patch can modify this test to allow a difference in size.
+	 */
+	if (futexes[0].w.flags != futexes[1].w.flags)
+		return -EINVAL;
+
+	cmpval = futexes[0].w.val;
+
+	return futex_requeue(u64_to_user_ptr(futexes[0].w.uaddr), futexes[0].w.flags,
+			     u64_to_user_ptr(futexes[1].w.uaddr), futexes[1].w.flags,
+			     nr_wake, nr_requeue, &cmpval, 0);
+}
+
+#ifdef CONFIG_COMPAT
+COMPAT_SYSCALL_DEFINE2(set_robust_list, struct compat_robust_list_head __user *, head,
+		       compat_size_t, len)
+{
+	if (unlikely(len != sizeof(*head)))
+		return -EINVAL;
+
+	current->futex.compat_robust_list = head;
+	return 0;
+}
+
+COMPAT_SYSCALL_DEFINE3(get_robust_list, int, pid,
+			compat_uptr_t __user *, head_ptr,
+			compat_size_t __user *, len_ptr)
+{
+	struct compat_robust_list_head __user *head = futex_get_robust_list_common(pid, true);
+
+	if (IS_ERR(head))
+		return PTR_ERR(head);
+
+	if (put_user(sizeof(*head), len_ptr))
+		return -EFAULT;
+	return put_user(ptr_to_compat(head), head_ptr);
+}
+#endif /* CONFIG_COMPAT */
+
+#ifdef CONFIG_COMPAT_32BIT_TIME
+SYSCALL_DEFINE6(futex_time32, u32 __user *, uaddr, int, op, u32, val,
+		const struct old_timespec32 __user *, utime, u32 __user *, uaddr2,
+		u32, val3)
+{
+	int ret, cmd = op & FUTEX_CMD_MASK;
+	ktime_t t, *tp = NULL;
+	struct timespec64 ts;
+
+	if (utime && futex_cmd_has_timeout(cmd)) {
+		if (get_old_timespec32(&ts, utime))
+			return -EFAULT;
+		ret = futex_init_timeout(cmd, op, &ts, &t);
+		if (ret)
+			return ret;
+		tp = &t;
+	}
+
+	return do_futex(uaddr, op, val, tp, uaddr2, (unsigned long)utime, val3);
+}
+#endif /* CONFIG_COMPAT_32BIT_TIME */

linux-7.2.3/kernel/futex/waitwake.c

@@ -0,0 +1,786 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/plist.h>
+#include <linux/sched/task.h>
+#include <linux/sched/signal.h>
+#include <linux/freezer.h>
+
+#include "futex.h"
+
+/*
+ * READ this before attempting to hack on futexes!
+ *
+ * Basic futex operation and ordering guarantees
+ * =============================================
+ *
+ * The waiter reads the futex value in user space and calls
+ * futex_wait(). This function computes the hash bucket and acquires
+ * the hash bucket lock. After that it reads the futex user space value
+ * again and verifies that the data has not changed. If it has not changed
+ * it enqueues itself into the hash bucket, releases the hash bucket lock
+ * and schedules.
+ *
+ * The waker side modifies the user space value of the futex and calls
+ * futex_wake(). This function computes the hash bucket and acquires the
+ * hash bucket lock. Then it looks for waiters on that futex in the hash
+ * bucket and wakes them.
+ *
+ * In futex wake up scenarios where no tasks are blocked on a futex, taking
+ * the hb spinlock can be avoided and simply return. In order for this
+ * optimization to work, ordering guarantees must exist so that the waiter
+ * being added to the list is acknowledged when the list is concurrently being
+ * checked by the waker, avoiding scenarios like the following:
+ *
+ * CPU 0                               CPU 1
+ * val = *futex;
+ * sys_futex(WAIT, futex, val);
+ *   futex_wait(futex, val);
+ *   uval = *futex;
+ *                                     *futex = newval;
+ *                                     sys_futex(WAKE, futex);
+ *                                       futex_wake(futex);
+ *                                       if (queue_empty())
+ *                                         return;
+ *   if (uval == val)
+ *      lock(hash_bucket(futex));
+ *      queue();
+ *     unlock(hash_bucket(futex));
+ *     schedule();
+ *
+ * This would cause the waiter on CPU 0 to wait forever because it
+ * missed the transition of the user space value from val to newval
+ * and the waker did not find the waiter in the hash bucket queue.
+ *
+ * The correct serialization ensures that a waiter either observes
+ * the changed user space value before blocking or is woken by a
+ * concurrent waker:
+ *
+ * CPU 0                                 CPU 1
+ * val = *futex;
+ * sys_futex(WAIT, futex, val);
+ *   futex_wait(futex, val);
+ *
+ *   waiters++; (a)
+ *   smp_mb(); (A) <-- paired with -.
+ *                                  |
+ *   lock(hash_bucket(futex));      |
+ *                                  |
+ *   uval = *futex;                 |
+ *                                  |        *futex = newval;
+ *                                  |        sys_futex(WAKE, futex);
+ *                                  |          futex_wake(futex);
+ *                                  |
+ *                                  `--------> smp_mb(); (B)
+ *   if (uval == val)
+ *     queue();
+ *     unlock(hash_bucket(futex));
+ *     schedule();                         if (waiters)
+ *                                           lock(hash_bucket(futex));
+ *   else                                    wake_waiters(futex);
+ *     waiters--; (b)                        unlock(hash_bucket(futex));
+ *
+ * Where (A) orders the waiters increment and the futex value read through
+ * atomic operations (see futex_hb_waiters_inc) and where (B) orders the write
+ * to futex and the waiters read (see futex_hb_waiters_pending()).
+ *
+ * This yields the following case (where X:=waiters, Y:=futex):
+ *
+ *	X = Y = 0
+ *
+ *	w[X]=1		w[Y]=1
+ *	MB		MB
+ *	r[Y]=y		r[X]=x
+ *
+ * Which guarantees that x==0 && y==0 is impossible; which translates back into
+ * the guarantee that we cannot both miss the futex variable change and the
+ * enqueue.
+ *
+ * Note that a new waiter is accounted for in (a) even when it is possible that
+ * the wait call can return error, in which case we backtrack from it in (b).
+ * Refer to the comment in futex_q_lock().
+ *
+ * Similarly, in order to account for waiters being requeued on another
+ * address we always increment the waiters for the destination bucket before
+ * acquiring the lock. It then decrements them again  after releasing it -
+ * the code that actually moves the futex(es) between hash buckets (requeue_futex)
+ * will do the additional required waiter count housekeeping. This is done for
+ * double_lock_hb() and double_unlock_hb(), respectively.
+ */
+
+bool __futex_wake_mark(struct futex_q *q)
+{
+	if (WARN(q->pi_state || q->rt_waiter, "refusing to wake PI futex\n"))
+		return false;
+
+	__futex_unqueue(q);
+	/*
+	 * The waiting task can free the futex_q as soon as q->lock_ptr = NULL
+	 * is written, without taking any locks. This is possible in the event
+	 * of a spurious wakeup, for example. A memory barrier is required here
+	 * to prevent the following store to lock_ptr from getting ahead of the
+	 * plist_del in __futex_unqueue().
+	 */
+	smp_store_release(&q->lock_ptr, NULL);
+
+	return true;
+}
+
+/*
+ * The hash bucket lock must be held when this is called.
+ * Afterwards, the futex_q must not be accessed. Callers
+ * must ensure to later call wake_up_q() for the actual
+ * wakeups to occur.
+ */
+void futex_wake_mark(struct wake_q_head *wake_q, struct futex_q *q)
+{
+	struct task_struct *p = q->task;
+
+	get_task_struct(p);
+
+	if (!__futex_wake_mark(q)) {
+		put_task_struct(p);
+		return;
+	}
+
+	/*
+	 * Queue the task for later wakeup for after we've released
+	 * the hb->lock.
+	 */
+	wake_q_add_safe(wake_q, p);
+}
+
+/*
+ * If requested, clear the robust list pending op and unlock the futex
+ */
+static bool futex_robust_unlock(u32 __user *uaddr, unsigned int flags, void __user *pop)
+{
+	if (!(flags & FLAGS_ROBUST_UNLOCK))
+		return true;
+
+	/* First unlock the futex, which requires release semantics. */
+	scoped_user_write_access(uaddr, efault)
+		unsafe_atomic_store_release_user(0, uaddr, efault);
+
+	/*
+	 * Clear the pending list op now. If that fails, then the task is in
+	 * deeper trouble as the robust list head is usually part of the TLS.
+	 * The chance of survival is close to zero.
+	 */
+	return futex_robust_list_clear_pending(pop, flags);
+
+efault:
+	return false;
+}
+
+/*
+ * Wake up waiters matching bitset queued on this futex (uaddr).
+ */
+int futex_wake(u32 __user *uaddr, unsigned int flags, void __user *pop, int nr_wake, u32 bitset)
+{
+	union futex_key key = FUTEX_KEY_INIT;
+	struct futex_q *this, *next;
+	DEFINE_WAKE_Q(wake_q);
+	int ret;
+
+	if (!bitset)
+		return -EINVAL;
+
+	ret = get_futex_key(uaddr, flags, &key, FUTEX_READ);
+	if (unlikely(ret != 0))
+		return ret;
+
+	if (!futex_robust_unlock(uaddr, flags, pop))
+		return -EFAULT;
+
+	if ((flags & FLAGS_STRICT) && !nr_wake)
+		return 0;
+
+	CLASS(hbr, hbr)(&key);
+	auto hb = hbr.hb;
+
+	/* Make sure we really have tasks to wakeup */
+	if (!futex_hb_waiters_pending(hb))
+		return ret;
+
+	spin_lock(&hb->lock);
+
+	plist_for_each_entry_safe(this, next, &hb->chain, list) {
+		if (futex_match (&this->key, &key)) {
+			if (this->pi_state || this->rt_waiter) {
+				ret = -EINVAL;
+				break;
+			}
+
+			/* Check if one of the bits is set in both bitsets */
+			if (!(this->bitset & bitset))
+				continue;
+
+			this->wake(&wake_q, this);
+			if (++ret >= nr_wake)
+				break;
+		}
+	}
+
+	spin_unlock(&hb->lock);
+	wake_up_q(&wake_q);
+	return ret;
+}
+
+static int futex_atomic_op_inuser(unsigned int encoded_op, u32 __user *uaddr)
+{
+	unsigned int op =	  (encoded_op & 0x70000000) >> 28;
+	unsigned int cmp =	  (encoded_op & 0x0f000000) >> 24;
+	int oparg = sign_extend32((encoded_op & 0x00fff000) >> 12, 11);
+	int cmparg = sign_extend32(encoded_op & 0x00000fff, 11);
+	int oldval, ret;
+
+	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) {
+		if (oparg < 0 || oparg > 31) {
+			/*
+			 * kill this print and return -EINVAL when userspace
+			 * is sane again
+			 */
+			pr_info_ratelimited("futex_wake_op: %s tries to shift op by %d; fix this program\n",
+					    current->comm, oparg);
+			oparg &= 31;
+		}
+		oparg = 1 << oparg;
+	}
+
+	pagefault_disable();
+	ret = arch_futex_atomic_op_inuser(op, oparg, &oldval, uaddr);
+	pagefault_enable();
+	if (ret)
+		return ret;
+
+	switch (cmp) {
+	case FUTEX_OP_CMP_EQ:
+		return oldval == cmparg;
+	case FUTEX_OP_CMP_NE:
+		return oldval != cmparg;
+	case FUTEX_OP_CMP_LT:
+		return oldval < cmparg;
+	case FUTEX_OP_CMP_GE:
+		return oldval >= cmparg;
+	case FUTEX_OP_CMP_LE:
+		return oldval <= cmparg;
+	case FUTEX_OP_CMP_GT:
+		return oldval > cmparg;
+	default:
+		return -ENOSYS;
+	}
+}
+
+/*
+ * Wake up all waiters hashed on the physical page that is mapped
+ * to this virtual address:
+ */
+int futex_wake_op(u32 __user *uaddr1, unsigned int flags, u32 __user *uaddr2,
+		  int nr_wake, int nr_wake2, int op)
+{
+	union futex_key key1 = FUTEX_KEY_INIT, key2 = FUTEX_KEY_INIT;
+	struct futex_q *this, *next;
+	int ret, op_ret;
+	DEFINE_WAKE_Q(wake_q);
+
+retry:
+	ret = get_futex_key(uaddr1, flags, &key1, FUTEX_READ);
+	if (unlikely(ret != 0))
+		return ret;
+	ret = get_futex_key(uaddr2, flags, &key2, FUTEX_WRITE);
+	if (unlikely(ret != 0))
+		return ret;
+
+retry_private:
+	if (1) {
+		CLASS(hbr, hbr1)(&key1);
+		CLASS(hbr, hbr2)(&key2);
+		auto hb1 = hbr1.hb;
+		auto hb2 = hbr2.hb;
+
+		double_lock_hb(hb1, hb2);
+		op_ret = futex_atomic_op_inuser(op, uaddr2);
+		if (unlikely(op_ret < 0)) {
+			double_unlock_hb(hb1, hb2);
+
+			if (!IS_ENABLED(CONFIG_MMU) ||
+			    unlikely(op_ret != -EFAULT && op_ret != -EAGAIN)) {
+				/*
+				 * we don't get EFAULT from MMU faults if we don't have
+				 * an MMU, but we might get them from range checking
+				 */
+				ret = op_ret;
+				return ret;
+			}
+
+			if (op_ret == -EFAULT) {
+				ret = fault_in_user_writeable(uaddr2);
+				if (ret)
+					return ret;
+			}
+
+			cond_resched();
+			if (!(flags & FLAGS_SHARED))
+				goto retry_private;
+			goto retry;
+		}
+
+		plist_for_each_entry_safe(this, next, &hb1->chain, list) {
+			if (futex_match(&this->key, &key1)) {
+				if (this->pi_state || this->rt_waiter) {
+					ret = -EINVAL;
+					goto out_unlock;
+				}
+				this->wake(&wake_q, this);
+				if (++ret >= nr_wake)
+					break;
+			}
+		}
+
+		if (op_ret > 0) {
+			op_ret = 0;
+			plist_for_each_entry_safe(this, next, &hb2->chain, list) {
+				if (futex_match(&this->key, &key2)) {
+					if (this->pi_state || this->rt_waiter) {
+						ret = -EINVAL;
+						goto out_unlock;
+					}
+					this->wake(&wake_q, this);
+					if (++op_ret >= nr_wake2)
+						break;
+				}
+			}
+			ret += op_ret;
+		}
+
+out_unlock:
+		double_unlock_hb(hb1, hb2);
+	}
+	wake_up_q(&wake_q);
+	return ret;
+}
+
+static long futex_wait_restart(struct restart_block *restart);
+
+/**
+ * futex_do_wait() - wait for wakeup, timeout, or signal
+ * @q:		the futex_q to queue up on
+ * @timeout:	the prepared hrtimer_sleeper, or null for no timeout
+ */
+void futex_do_wait(struct futex_q *q, struct hrtimer_sleeper *timeout)
+{
+	/* Arm the timer */
+	if (timeout)
+		hrtimer_sleeper_start_expires(timeout, HRTIMER_MODE_ABS);
+
+	/*
+	 * If we have been removed from the hash list, then another task
+	 * has tried to wake us, and we can skip the call to schedule().
+	 */
+	if (likely(!plist_node_empty(&q->list))) {
+		/*
+		 * If the timer has already expired, current will already be
+		 * flagged for rescheduling. Only call schedule if there
+		 * is no timeout, or if it has yet to expire.
+		 */
+		if (!timeout || timeout->task)
+			schedule();
+	}
+	__set_current_state(TASK_RUNNING);
+}
+
+/**
+ * futex_unqueue_multiple - Remove various futexes from their hash bucket
+ * @v:	   The list of futexes to unqueue
+ * @count: Number of futexes in the list
+ *
+ * Helper to unqueue a list of futexes. This can't fail.
+ *
+ * Return:
+ *  - >=0 - Index of the last futex that was awoken;
+ *  - -1  - No futex was awoken
+ */
+int futex_unqueue_multiple(struct futex_vector *v, int count)
+{
+	int ret = -1, i;
+
+	for (i = 0; i < count; i++) {
+		if (!futex_unqueue(&v[i].q))
+			ret = i;
+	}
+
+	return ret;
+}
+
+/**
+ * futex_wait_multiple_setup - Prepare to wait and enqueue multiple futexes
+ * @vs:		The futex list to wait on
+ * @count:	The size of the list
+ * @woken:	Index of the last woken futex, if any. Used to notify the
+ *		caller that it can return this index to userspace (return parameter)
+ *
+ * Prepare multiple futexes in a single step and enqueue them. This may fail if
+ * the futex list is invalid or if any futex was already awoken. On success the
+ * task is ready to interruptible sleep.
+ *
+ * Return:
+ *  -  1 - One of the futexes was woken by another thread
+ *  -  0 - Success
+ *  - <0 - -EFAULT, -EWOULDBLOCK or -EINVAL
+ */
+int futex_wait_multiple_setup(struct futex_vector *vs, int count, int *woken)
+{
+	bool retry = false;
+	int ret, i;
+	u32 uval;
+
+	/*
+	 * Make sure to have a reference on the private_hash such that we
+	 * don't block on rehash after changing the task state below.
+	 */
+	guard(private_hash)(current->mm);
+
+	/*
+	 * Enqueuing multiple futexes is tricky, because we need to enqueue
+	 * each futex on the list before dealing with the next one to avoid
+	 * deadlocking on the hash bucket. But, before enqueuing, we need to
+	 * make sure that current->state is TASK_INTERRUPTIBLE, so we don't
+	 * lose any wake events, which cannot be done before the get_futex_key
+	 * of the next key, because it calls get_user_pages, which can sleep.
+	 * Thus, we fetch the list of futexes keys in two steps, by first
+	 * pinning all the memory keys in the futex key, and only then we read
+	 * each key and queue the corresponding futex.
+	 *
+	 * Private futexes doesn't need to recalculate hash in retry, so skip
+	 * get_futex_key() when retrying.
+	 */
+retry:
+	for (i = 0; i < count; i++) {
+		if (!(vs[i].w.flags & FLAGS_SHARED) && retry)
+			continue;
+
+		ret = get_futex_key(u64_to_user_ptr(vs[i].w.uaddr),
+				    vs[i].w.flags,
+				    &vs[i].q.key, FUTEX_READ);
+
+		if (unlikely(ret))
+			return ret;
+	}
+
+	set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE);
+
+	for (i = 0; i < count; i++) {
+		u32 __user *uaddr = (u32 __user *)(unsigned long)vs[i].w.uaddr;
+		struct futex_q *q = &vs[i].q;
+		u32 val = vs[i].w.val;
+
+		if (1) {
+			CLASS(hbr, hbr)(&q->key);
+			auto hb = hbr.hb;
+
+			futex_q_lock(q, hb);
+			ret = futex_get_value_locked(&uval, uaddr);
+
+			if (!ret && uval == val) {
+				/*
+				 * The bucket lock can't be held while dealing with the
+				 * next futex. Queue each futex at this moment so hb can
+				 * be unlocked.
+				 */
+				futex_queue(q, hb, current);
+				continue;
+			}
+
+			futex_q_unlock(hb);
+			__release(q->lock_ptr);
+		}
+		__set_current_state(TASK_RUNNING);
+
+		/*
+		 * Even if something went wrong, if we find out that a futex
+		 * was woken, we don't return error and return this index to
+		 * userspace
+		 */
+		*woken = futex_unqueue_multiple(vs, i);
+		if (*woken >= 0)
+			return 1;
+
+		if (ret) {
+			/*
+			 * If we need to handle a page fault, we need to do so
+			 * without any lock and any enqueued futex (otherwise
+			 * we could lose some wakeup). So we do it here, after
+			 * undoing all the work done so far. In success, we
+			 * retry all the work.
+			 */
+			if (get_user(uval, uaddr))
+				return -EFAULT;
+
+			retry = true;
+			goto retry;
+		}
+
+		if (uval != val)
+			return -EWOULDBLOCK;
+	}
+
+	return 0;
+}
+
+/**
+ * futex_sleep_multiple - Check sleeping conditions and sleep
+ * @vs:    List of futexes to wait for
+ * @count: Length of vs
+ * @to:    Timeout
+ *
+ * Sleep if and only if the timeout hasn't expired and no futex on the list has
+ * been woken up.
+ */
+static void futex_sleep_multiple(struct futex_vector *vs, unsigned int count,
+				 struct hrtimer_sleeper *to)
+{
+	if (to && !to->task)
+		return;
+
+	for (; count; count--, vs++) {
+		if (!READ_ONCE(vs->q.lock_ptr))
+			return;
+	}
+
+	schedule();
+}
+
+/**
+ * futex_wait_multiple - Prepare to wait on and enqueue several futexes
+ * @vs:		The list of futexes to wait on
+ * @count:	The number of objects
+ * @to:		Timeout before giving up and returning to userspace
+ *
+ * Entry point for the FUTEX_WAIT_MULTIPLE futex operation, this function
+ * sleeps on a group of futexes and returns on the first futex that is
+ * wake, or after the timeout has elapsed.
+ *
+ * Return:
+ *  - >=0 - Hint to the futex that was awoken
+ *  - <0  - On error
+ */
+int futex_wait_multiple(struct futex_vector *vs, unsigned int count,
+			struct hrtimer_sleeper *to)
+{
+	int ret, hint = 0;
+
+	if (to)
+		hrtimer_sleeper_start_expires(to, HRTIMER_MODE_ABS);
+
+	while (1) {
+		ret = futex_wait_multiple_setup(vs, count, &hint);
+		if (ret) {
+			if (ret > 0) {
+				/* A futex was woken during setup */
+				ret = hint;
+			}
+			return ret;
+		}
+
+		futex_sleep_multiple(vs, count, to);
+
+		__set_current_state(TASK_RUNNING);
+
+		ret = futex_unqueue_multiple(vs, count);
+		if (ret >= 0)
+			return ret;
+
+		if (to && !to->task)
+			return -ETIMEDOUT;
+		else if (signal_pending(current))
+			return -ERESTARTSYS;
+		/*
+		 * The final case is a spurious wakeup, for
+		 * which just retry.
+		 */
+	}
+}
+
+/**
+ * futex_wait_setup() - Prepare to wait on a futex
+ * @uaddr:	the futex userspace address
+ * @val:	the expected value
+ * @flags:	futex flags (FLAGS_SHARED, etc.)
+ * @q:		the associated futex_q
+ * @key2:	the second futex_key if used for requeue PI
+ * @task:	Task queueing this futex
+ *
+ * Setup the futex_q and locate the hash_bucket.  Get the futex value and
+ * compare it with the expected value.  Handle atomic faults internally.
+ * Return with the hb lock held on success, and unlocked on failure.
+ *
+ * Return:
+ *  -  0 - uaddr contains val and hb has been locked;
+ *  - <0 - On error and the hb is unlocked. A possible reason: the uaddr can not
+ *	   be read, does not contain the expected value or is not properly aligned.
+ */
+int futex_wait_setup(u32 __user *uaddr, u32 val, unsigned int flags,
+		     struct futex_q *q, union futex_key *key2,
+		     struct task_struct *task)
+{
+	u32 uval;
+	int ret;
+
+	/*
+	 * Access the page AFTER the hash-bucket is locked.
+	 * Order is important:
+	 *
+	 *   Userspace waiter: val = var; if (cond(val)) futex_wait(&var, val);
+	 *   Userspace waker:  if (cond(var)) { var = new; futex_wake(&var); }
+	 *
+	 * The basic logical guarantee of a futex is that it blocks ONLY
+	 * if cond(var) is known to be true at the time of blocking, for
+	 * any cond.  If we locked the hash-bucket after testing *uaddr, that
+	 * would open a race condition where we could block indefinitely with
+	 * cond(var) false, which would violate the guarantee.
+	 *
+	 * On the other hand, we insert q and release the hash-bucket only
+	 * after testing *uaddr.  This guarantees that futex_wait() will NOT
+	 * absorb a wakeup if *uaddr does not match the desired values
+	 * while the syscall executes.
+	 */
+retry:
+	ret = get_futex_key(uaddr, flags, &q->key, FUTEX_READ);
+	if (unlikely(ret != 0))
+		return ret;
+
+retry_private:
+	if (1) {
+		CLASS(hbr, hbr)(&q->key);
+		auto hb = hbr.hb;
+
+		futex_q_lock(q, hb);
+
+		ret = futex_get_value_locked(&uval, uaddr);
+
+		if (ret) {
+			futex_q_unlock(hb);
+			__release(q->lock_ptr);
+
+			ret = get_user(uval, uaddr);
+			if (ret)
+				return ret;
+
+			if (!(flags & FLAGS_SHARED))
+				goto retry_private;
+
+			goto retry;
+		}
+
+		if (uval != val) {
+			futex_q_unlock(hb);
+			__release(q->lock_ptr);
+			return -EWOULDBLOCK;
+		}
+
+		if (key2 && futex_match(&q->key, key2)) {
+			futex_q_unlock(hb);
+			__release(q->lock_ptr);
+			return -EINVAL;
+		}
+
+		/*
+		 * The task state is guaranteed to be set before another task can
+		 * wake it. set_current_state() is implemented using smp_store_mb() and
+		 * futex_queue() calls spin_unlock() upon completion, both serializing
+		 * access to the hash list and forcing another memory barrier.
+		 */
+		if (task == current)
+			set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE);
+		futex_queue(q, hb, task);
+	}
+
+	return ret;
+}
+
+int __futex_wait(u32 __user *uaddr, unsigned int flags, u32 val,
+		 struct hrtimer_sleeper *to, u32 bitset)
+{
+	struct futex_q q = futex_q_init;
+	int ret;
+
+	if (!bitset)
+		return -EINVAL;
+
+	q.bitset = bitset;
+
+retry:
+	/*
+	 * Prepare to wait on uaddr. On success, it holds hb->lock and q
+	 * is initialized.
+	 */
+	ret = futex_wait_setup(uaddr, val, flags, &q, NULL, current);
+	if (ret)
+		return ret;
+
+	/* futex_queue and wait for wakeup, timeout, or a signal. */
+	futex_do_wait(&q, to);
+
+	/* If we were woken (and unqueued), we succeeded, whatever. */
+	if (!futex_unqueue(&q))
+		return 0;
+
+	if (to && !to->task)
+		return -ETIMEDOUT;
+
+	/*
+	 * We expect signal_pending(current), but we might be the
+	 * victim of a spurious wakeup as well.
+	 */
+	if (!signal_pending(current))
+		goto retry;
+
+	return -ERESTARTSYS;
+}
+
+int futex_wait(u32 __user *uaddr, unsigned int flags, u32 val, ktime_t *abs_time, u32 bitset)
+{
+	struct hrtimer_sleeper timeout, *to;
+	struct restart_block *restart;
+	int ret;
+
+	to = futex_setup_timer(abs_time, &timeout, flags,
+			       current->timer_slack_ns);
+
+	ret = __futex_wait(uaddr, flags, val, to, bitset);
+
+	/* No timeout, nothing to clean up. */
+	if (!to)
+		return ret;
+
+	hrtimer_cancel(&to->timer);
+	destroy_hrtimer_on_stack(&to->timer);
+
+	if (ret == -ERESTARTSYS) {
+		restart = &current->restart_block;
+		restart->futex.uaddr = uaddr;
+		restart->futex.val = val;
+		restart->futex.time = *abs_time;
+		restart->futex.bitset = bitset;
+		restart->futex.flags = flags | FLAGS_HAS_TIMEOUT;
+
+		return set_restart_fn(restart, futex_wait_restart);
+	}
+
+	return ret;
+}
+
+static long futex_wait_restart(struct restart_block *restart)
+{
+	u32 __user *uaddr = restart->futex.uaddr;
+	ktime_t *tp = NULL;
+
+	if (restart->futex.flags & FLAGS_HAS_TIMEOUT)
+		tp = &restart->futex.time;
+
+	restart->fn = do_no_restart_syscall;
+
+	return (long)futex_wait(uaddr, restart->futex.flags,
+				restart->futex.val, tp, restart->futex.bitset);
+}
+