/*

 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.

 *

 * This code is free software; you can redistribute it and/or modify it

 * under the terms of the GNU General Public License version 2 only, as

 * published by the Free Software Foundation.  Oracle designates this

 * particular file as subject to the "Classpath" exception as provided

 * by Oracle in the LICENSE file that accompanied this code.

 *

 * This code is distributed in the hope that it will be useful, but WITHOUT

 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or

 * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License

 * version 2 for more details (a copy is included in the LICENSE file that

 * accompanied this code).

 *

 * You should have received a copy of the GNU General Public License version

 * 2 along with this work; if not, write to the Free Software Foundation,

 * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.

 *

 * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA

 * or visit www.oracle.com if you need additional information or have any

 * questions.

 */

/*

 * This file is available under and governed by the GNU General Public

 * License version 2 only, as published by the Free Software Foundation.

 * However, the following notice accompanied the original version of this

 * file:

 *

 * Written by Doug Lea, Bill Scherer, and Michael Scott with

 * assistance from members of JCP JSR-166 Expert Group and released to

 * the public domain, as explained at

 * http://creativecommons.org/publicdomain/zero/1.0/

 */

package java.util.concurrent;

import java.util.AbstractQueue;

import java.util.Collection;

import java.util.Collections;

import java.util.Iterator;

import java.util.Spliterator;

import java.util.Spliterators;

import java.util.concurrent.locks.LockSupport;

import java.util.concurrent.locks.ReentrantLock;

/**

 * A {@linkplain BlockingQueue blocking queue} in which each insert

 * operation must wait for a corresponding remove operation by another

 * thread, and vice versa.  A synchronous queue does not have any

 * internal capacity, not even a capacity of one.  You cannot

 * {@code peek} at a synchronous queue because an element is only

 * present when you try to remove it; you cannot insert an element

 * (using any method) unless another thread is trying to remove it;

 * you cannot iterate as there is nothing to iterate.  The

 * <em>head</em> of the queue is the element that the first queued

 * inserting thread is trying to add to the queue; if there is no such

 * queued thread then no element is available for removal and

 * {@code poll()} will return {@code null}.  For purposes of other

 * {@code Collection} methods (for example {@code contains}), a

 * {@code SynchronousQueue} acts as an empty collection.  This queue

 * does not permit {@code null} elements.

 *

 * <p>Synchronous queues are similar to rendezvous channels used in

 * CSP and Ada. They are well suited for handoff designs, in which an

 * object running in one thread must sync up with an object running

 * in another thread in order to hand it some information, event, or

 * task.

 *

 * <p>This class supports an optional fairness policy for ordering

 * waiting producer and consumer threads.  By default, this ordering

 * is not guaranteed. However, a queue constructed with fairness set

 * to {@code true} grants threads access in FIFO order.

 *

 * <p>This class and its iterator implement all of the

 * <em>optional</em> methods of the {@link Collection} and {@link

 * Iterator} interfaces.

 *

 * <p>This class is a member of the

 * <a href="{@docRoot}/../technotes/guides/collections/index.html">

 * Java Collections Framework</a>.

 *

 * @since 1.5

 * @author Doug Lea and Bill Scherer and Michael Scott

 * @param <E> the type of elements held in this queue

 */

public class SynchronousQueue<E> extends AbstractQueue<E>

    implements BlockingQueue<E>, java.io.Serializable {

    private static final long serialVersionUID = -3223113410248163686L;

    /*

     * This class implements extensions of the dual stack and dual

     * queue algorithms described in "Nonblocking Concurrent Objects

     * with Condition Synchronization", by W. N. Scherer III and

     * M. L. Scott.  18th Annual Conf. on Distributed Computing,

     * Oct. 2004 (see also

     * http://www.cs.rochester.edu/u/scott/synchronization/pseudocode/duals.html).

     * The (Lifo) stack is used for non-fair mode, and the (Fifo)

     * queue for fair mode. The performance of the two is generally

     * similar. Fifo usually supports higher throughput under

     * contention but Lifo maintains higher thread locality in common

     * applications.

     *

     * A dual queue (and similarly stack) is one that at any given

     * time either holds "data" -- items provided by put operations,

     * or "requests" -- slots representing take operations, or is

     * empty. A call to "fulfill" (i.e., a call requesting an item

     * from a queue holding data or vice versa) dequeues a

     * complementary node.  The most interesting feature of these

     * queues is that any operation can figure out which mode the

     * queue is in, and act accordingly without needing locks.

     *

     * Both the queue and stack extend abstract class Transferer

     * defining the single method transfer that does a put or a

     * take. These are unified into a single method because in dual

     * data structures, the put and take operations are symmetrical,

     * so nearly all code can be combined. The resulting transfer

     * methods are on the long side, but are easier to follow than

     * they would be if broken up into nearly-duplicated parts.

     *

     * The queue and stack data structures share many conceptual

     * similarities but very few concrete details. For simplicity,

     * they are kept distinct so that they can later evolve

     * separately.

     *

     * The algorithms here differ from the versions in the above paper

     * in extending them for use in synchronous queues, as well as

     * dealing with cancellation. The main differences include:

     *

     *  1. The original algorithms used bit-marked pointers, but

     *     the ones here use mode bits in nodes, leading to a number

     *     of further adaptations.

     *  2. SynchronousQueues must block threads waiting to become

     *     fulfilled.

     *  3. Support for cancellation via timeout and interrupts,

     *     including cleaning out cancelled nodes/threads

     *     from lists to avoid garbage retention and memory depletion.

     *

     * Blocking is mainly accomplished using LockSupport park/unpark,

     * except that nodes that appear to be the next ones to become

     * fulfilled first spin a bit (on multiprocessors only). On very

     * busy synchronous queues, spinning can dramatically improve

     * throughput. And on less busy ones, the amount of spinning is

     * small enough not to be noticeable.

     *

     * Cleaning is done in different ways in queues vs stacks.  For

     * queues, we can almost always remove a node immediately in O(1)

     * time (modulo retries for consistency checks) when it is

     * cancelled. But if it may be pinned as the current tail, it must

     * wait until some subsequent cancellation. For stacks, we need a

     * potentially O(n) traversal to be sure that we can remove the

     * node, but this can run concurrently with other threads

     * accessing the stack.

     *

     * While garbage collection takes care of most node reclamation

     * issues that otherwise complicate nonblocking algorithms, care

     * is taken to "forget" references to data, other nodes, and

     * threads that might be held on to long-term by blocked

     * threads. In cases where setting to null would otherwise

     * conflict with main algorithms, this is done by changing a

     * node's link to now point to the node itself. This doesn't arise

     * much for Stack nodes (because blocked threads do not hang on to

     * old head pointers), but references in Queue nodes must be

     * aggressively forgotten to avoid reachability of everything any

     * node has ever referred to since arrival.

     */

    /**

     * Shared internal API for dual stacks and queues.

     */

    abstract static class Transferer<E> {

        /**

         * Performs a put or take.

         *

         * @param e if non-null, the item to be handed to a consumer;

         *          if null, requests that transfer return an item

         *          offered by producer.

         * @param timed if this operation should timeout

         * @param nanos the timeout, in nanoseconds

         * @return if non-null, the item provided or received; if null,

         *         the operation failed due to timeout or interrupt --

         *         the caller can distinguish which of these occurred

         *         by checking Thread.interrupted.

         */

        abstract E transfer(E e, boolean timed, long nanos);

    }

    /**

     * The number of times to spin before blocking in timed waits.

     * The value is empirically derived -- it works well across a

     * variety of processors and OSes. Empirically, the best value

     * seems not to vary with number of CPUs (beyond 2) so is just

     * a constant.

     */

    static final int MAX_TIMED_SPINS =

        (Runtime.getRuntime().availableProcessors() < 2) ? 0 : 32;

    /**

     * The number of times to spin before blocking in untimed waits.

     * This is greater than timed value because untimed waits spin

     * faster since they don't need to check times on each spin.

     */

    static final int MAX_UNTIMED_SPINS = MAX_TIMED_SPINS * 16;

    /**

     * The number of nanoseconds for which it is faster to spin

     * rather than to use timed park. A rough estimate suffices.

     */

    static final long SPIN_FOR_TIMEOUT_THRESHOLD = 1000L;

    /** Dual stack */

    static final class TransferStack<E> extends Transferer<E> {

        /*

         * This extends Scherer-Scott dual stack algorithm, differing,

         * among other ways, by using "covering" nodes rather than

         * bit-marked pointers: Fulfilling operations push on marker

         * nodes (with FULFILLING bit set in mode) to reserve a spot

         * to match a waiting node.

         */

        /* Modes for SNodes, ORed together in node fields */

        /** Node represents an unfulfilled consumer */

        static final int REQUEST    = 0;

        /** Node represents an unfulfilled producer */

        static final int DATA       = 1;

        /** Node is fulfilling another unfulfilled DATA or REQUEST */

        static final int FULFILLING = 2;

        /** Returns true if m has fulfilling bit set. */

        static boolean isFulfilling(int m) { return (m & FULFILLING) != 0; }

        /** Node class for TransferStacks. */

        static final class SNode {

            volatile SNode next;        // next node in stack

            volatile SNode match;       // the node matched to this

            volatile Thread waiter;     // to control park/unpark

            Object item;                // data; or null for REQUESTs

            int mode;

            // Note: item and mode fields don't need to be volatile

            // since they are always written before, and read after,

            // other volatile/atomic operations.

            SNode(Object item) {

                this.item = item;

            }

            boolean casNext(SNode cmp, SNode val) {

                return cmp == next &&

                    U.compareAndSwapObject(this, NEXT, cmp, val);

            }

            /**

             * Tries to match node s to this node, if so, waking up thread.

             * Fulfillers call tryMatch to identify their waiters.

             * Waiters block until they have been matched.

             *

             * @param s the node to match

             * @return true if successfully matched to s

             */

            boolean tryMatch(SNode s) {

                if (match == null &&

                    U.compareAndSwapObject(this, MATCH, null, s)) {

                    Thread w = waiter;

                    if (w != null) {    // waiters need at most one unpark

                        waiter = null;

                        LockSupport.unpark(w);

                    }

                    return true;

                }

                return match == s;

            }

            /**

             * Tries to cancel a wait by matching node to itself.

             */

            void tryCancel() {

                U.compareAndSwapObject(this, MATCH, null, this);

            }

            boolean isCancelled() {

                return match == this;

            }

            // Unsafe mechanics

            private static final long MATCH;

            private static final long NEXT;

            static {

                try {

                    MATCH = U.objectFieldOffset

                        (SNode.class.getDeclaredField("match"));

                    NEXT = U.objectFieldOffset

                        (SNode.class.getDeclaredField("next"));

                } catch (ReflectiveOperationException e) {

                    throw new Error(e);

                }

            }

        }

        /** The head (top) of the stack */

        volatile SNode head;

        boolean casHead(SNode h, SNode nh) {

            return h == head &&

                U.compareAndSwapObject(this, HEAD, h, nh);

        }

        /**

         * Creates or resets fields of a node. Called only from transfer

         * where the node to push on stack is lazily created and

         * reused when possible to help reduce intervals between reads

         * and CASes of head and to avoid surges of garbage when CASes

         * to push nodes fail due to contention.

         */

        static SNode snode(SNode s, Object e, SNode next, int mode) {

            if (s == null) s = new SNode(e);

            s.mode = mode;

            s.next = next;

            return s;

        }

        /**

         * Puts or takes an item.

         */

        @SuppressWarnings("unchecked")

        E transfer(E e, boolean timed, long nanos) {

            /*

             * Basic algorithm is to loop trying one of three actions:

             *

             * 1. If apparently empty or already containing nodes of same

             *    mode, try to push node on stack and wait for a match,

             *    returning it, or null if cancelled.

             *

             * 2. If apparently containing node of complementary mode,

             *    try to push a fulfilling node on to stack, match

             *    with corresponding waiting node, pop both from

             *    stack, and return matched item. The matching or

             *    unlinking might not actually be necessary because of

             *    other threads performing action 3:

             *

             * 3. If top of stack already holds another fulfilling node,

             *    help it out by doing its match and/or pop

             *    operations, and then continue. The code for helping

             *    is essentially the same as for fulfilling, except

             *    that it doesn't return the item.

             */

            SNode s = null; // constructed/reused as needed

            int mode = (e == null) ? REQUEST : DATA;

            for (;;) {

                SNode h = head;

                if (h == null || h.mode == mode) {  // empty or same-mode

                    if (timed && nanos <= 0L) {     // can't wait

                        if (h != null && h.isCancelled())

                            casHead(h, h.next);     // pop cancelled node

                        else

                            return null;

                    } else if (casHead(h, s = snode(s, e, h, mode))) {

                        SNode m = awaitFulfill(s, timed, nanos);

                        if (m == s) {               // wait was cancelled

                            clean(s);

                            return null;

                        }

                        if ((h = head) != null && h.next == s)

                            casHead(h, s.next);     // help s's fulfiller

                        return (E) ((mode == REQUEST) ? m.item : s.item);

                    }

                } else if (!isFulfilling(h.mode)) { // try to fulfill

                    if (h.isCancelled())            // already cancelled

                        casHead(h, h.next);         // pop and retry

                    else if (casHead(h, s=snode(s, e, h, FULFILLING|mode))) {

                        for (;;) { // loop until matched or waiters disappear

                            SNode m = s.next;       // m is s's match

                            if (m == null) {        // all waiters are gone

                                casHead(s, null);   // pop fulfill node

                                s = null;           // use new node next time

                                break;              // restart main loop

                            }

                            SNode mn = m.next;

                            if (m.tryMatch(s)) {

                                casHead(s, mn);     // pop both s and m

                                return (E) ((mode == REQUEST) ? m.item : s.item);

                            } else                  // lost match

                                s.casNext(m, mn);   // help unlink

                        }

                    }

                } else {                            // help a fulfiller

                    SNode m = h.next;               // m is h's match

                    if (m == null)                  // waiter is gone

                        casHead(h, null);           // pop fulfilling node

                    else {

                        SNode mn = m.next;

                        if (m.tryMatch(h))          // help match

                            casHead(h, mn);         // pop both h and m

                        else                        // lost match

                            h.casNext(m, mn);       // help unlink

                    }

                }

            }

        }

        /**

         * Spins/blocks until node s is matched by a fulfill operation.

         *

         * @param s the waiting node

         * @param timed true if timed wait

         * @param nanos timeout value

         * @return matched node, or s if cancelled

         */

        SNode awaitFulfill(SNode s, boolean timed, long nanos) {

            /*

             * When a node/thread is about to block, it sets its waiter

             * field and then rechecks state at least one more time

             * before actually parking, thus covering race vs

             * fulfiller noticing that waiter is non-null so should be

             * woken.

             *

             * When invoked by nodes that appear at the point of call

             * to be at the head of the stack, calls to park are

             * preceded by spins to avoid blocking when producers and

             * consumers are arriving very close in time.  This can

             * happen enough to bother only on multiprocessors.

             *

             * The order of checks for returning out of main loop

             * reflects fact that interrupts have precedence over

             * normal returns, which have precedence over

             * timeouts. (So, on timeout, one last check for match is

             * done before giving up.) Except that calls from untimed

             * SynchronousQueue.{poll/offer} don't check interrupts

             * and don't wait at all, so are trapped in transfer

             * method rather than calling awaitFulfill.

             */

            final long deadline = timed ? System.nanoTime() + nanos : 0L;

            Thread w = Thread.currentThread();

            int spins = shouldSpin(s)

                ? (timed ? MAX_TIMED_SPINS : MAX_UNTIMED_SPINS)

                : 0;

            for (;;) {

                if (w.isInterrupted())

                    s.tryCancel();

                SNode m = s.match;

                if (m != null)

                    return m;

                if (timed) {

                    nanos = deadline - System.nanoTime();

                    if (nanos <= 0L) {

                        s.tryCancel();

                        continue;

                    }

                }

                if (spins > 0)

                    spins = shouldSpin(s) ? (spins - 1) : 0;

                else if (s.waiter == null)

                    s.waiter = w; // establish waiter so can park next iter

                else if (!timed)

                    LockSupport.park(this);

                else if (nanos > SPIN_FOR_TIMEOUT_THRESHOLD)

                    LockSupport.parkNanos(this, nanos);

            }

        }

        /**

         * Returns true if node s is at head or there is an active

         * fulfiller.

         */

        boolean shouldSpin(SNode s) {

            SNode h = head;

            return (h == s || h == null || isFulfilling(h.mode));

        }

        /**

         * Unlinks s from the stack.

         */

        void clean(SNode s) {

            s.item = null;   // forget item

            s.waiter = null; // forget thread

            /*

             * At worst we may need to traverse entire stack to unlink

             * s. If there are multiple concurrent calls to clean, we

             * might not see s if another thread has already removed

             * it. But we can stop when we see any node known to

             * follow s. We use s.next unless it too is cancelled, in

             * which case we try the node one past. We don't check any

             * further because we don't want to doubly traverse just to

             * find sentinel.

             */

            SNode past = s.next;

            if (past != null && past.isCancelled())

                past = past.next;

            // Absorb cancelled nodes at head

            SNode p;

            while ((p = head) != null && p != past && p.isCancelled())

                casHead(p, p.next);

            // Unsplice embedded nodes

            while (p != null && p != past) {

                SNode n = p.next;

                if (n != null && n.isCancelled())

                    p.casNext(n, n.next);

                else

                    p = n;

            }

        }

        // Unsafe mechanics

        private static final long HEAD;

        static {

            try {

                HEAD = U.objectFieldOffset

                    (TransferStack.class.getDeclaredField("head"));

            } catch (ReflectiveOperationException e) {