path: root/kernel/futex/requeue.c

// SPDX-License-Identifier: GPL-2.0-or-later

#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()*/
	.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;
	}
	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)
{
	q->key = *key;

	__futex_unqueue(q);

	WARN_ON(!q->rt_waiter);
	q->rt_waiter = NULL;

	q->lock_ptr = &hb->lock;

	/* Signal locked state to the waiter */
	futex_requeue_pi_complete(q, 1);
	wake_up_state(q->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 = NULL;
	u32 curval;
	int ret;

	if (futex_get_value_locked(&curval,