diff --git a/src/main/java/jsr166e/CompletableFuture.java b/src/main/java/jsr166e/CompletableFuture.java
index d8a944f004020..2a9e0bb04920f 100644
--- a/src/main/java/jsr166e/CompletableFuture.java
+++ b/src/main/java/jsr166e/CompletableFuture.java
@@ -1392,6 +1392,7 @@ public CompletableFuture() {
      *
      * @param supplier a function returning the value to be used
      * to complete the returned CompletableFuture
+     * @param <U> the function's return type
      * @return the new CompletableFuture
      */
     public static <U> CompletableFuture<U> supplyAsync(Generator<U> supplier) {
@@ -1410,6 +1411,7 @@ public static <U> CompletableFuture<U> supplyAsync(Generator<U> supplier) {
      * @param supplier a function returning the value to be used
      * to complete the returned CompletableFuture
      * @param executor the executor to use for asynchronous execution
+     * @param <U> the function's return type
      * @return the new CompletableFuture
      */
     public static <U> CompletableFuture<U> supplyAsync(Generator<U> supplier,
@@ -1462,6 +1464,7 @@ public static CompletableFuture<Void> runAsync(Runnable runnable,
      * the given value.
      *
      * @param value the value
+     * @param <U> the type of the value
      * @return the completed CompletableFuture
      */
     public static <U> CompletableFuture<U> completedFuture(U value) {
@@ -2829,7 +2832,7 @@ else if (UNSAFE.compareAndSwapObject
             }
             if (dst == null)
                 dst = new CompletableFuture<U>();
-            if (e == null || ex != null)
+            if (ex != null)
                 dst.internalComplete(null, ex);
         }
         helpPostComplete();
diff --git a/src/main/java/jsr166e/ConcurrentHashMapV8.java b/src/main/java/jsr166e/ConcurrentHashMapV8.java
index 5706cd04d769f..b4d041086d2f1 100644
--- a/src/main/java/jsr166e/ConcurrentHashMapV8.java
+++ b/src/main/java/jsr166e/ConcurrentHashMapV8.java
@@ -12,6 +12,7 @@
 import java.io.Serializable;
 import java.lang.reflect.ParameterizedType;
 import java.lang.reflect.Type;
+import java.util.AbstractMap;
 import java.util.Arrays;
 import java.util.Collection;
 import java.util.Comparator;
@@ -218,7 +219,7 @@
  * @param <K> the type of keys maintained by this map
  * @param <V> the type of mapped values
  */
-public class ConcurrentHashMapV8<K,V>
+public class ConcurrentHashMapV8<K,V> extends AbstractMap<K,V>
     implements ConcurrentMap<K,V>, Serializable {
     private static final long serialVersionUID = 7249069246763182397L;
 
@@ -275,6 +276,7 @@ public interface LongByLongToLong { long apply(long a, long b); }
     /** Interface describing a function mapping two ints to an int */
     public interface IntByIntToInt { int apply(int a, int b); }
 
+
     /*
      * Overview:
      *
@@ -380,14 +382,15 @@ public interface IntByIntToInt { int apply(int a, int b); }
      * The table is resized when occupancy exceeds a percentage
      * threshold (nominally, 0.75, but see below).  Any thread
      * noticing an overfull bin may assist in resizing after the
-     * initiating thread allocates and sets up the replacement
-     * array. However, rather than stalling, these other threads may
-     * proceed with insertions etc.  The use of TreeBins shields us
-     * from the worst case effects of overfilling while resizes are in
+     * initiating thread allocates and sets up the replacement array.
+     * However, rather than stalling, these other threads may proceed
+     * with insertions etc.  The use of TreeBins shields us from the
+     * worst case effects of overfilling while resizes are in
      * progress.  Resizing proceeds by transferring bins, one by one,
-     * from the table to the next table. To enable concurrency, the
-     * next table must be (incrementally) prefilled with place-holders
-     * serving as reverse forwarders to the old table.  Because we are
+     * from the table to the next table. However, threads claim small
+     * blocks of indices to transfer (via field transferIndex) before
+     * doing so, reducing contention.  A generation stamp in field
+     * sizeCtl ensures that resizings do not overlap. Because we are
      * using power-of-two expansion, the elements from each bin must
      * either stay at same index, or move with a power of two
      * offset. We eliminate unnecessary node creation by catching
@@ -408,13 +411,19 @@ public interface IntByIntToInt { int apply(int a, int b); }
      * locks, average aggregate waits become shorter as resizing
      * progresses.  The transfer operation must also ensure that all
      * accessible bins in both the old and new table are usable by any
-     * traversal.  This is arranged by proceeding from the last bin
-     * (table.length - 1) up towards the first.  Upon seeing a
-     * forwarding node, traversals (see class Traverser) arrange to
-     * move to the new table without revisiting nodes.  However, to
-     * ensure that no intervening nodes are skipped, bin splitting can
-     * only begin after the associated reverse-forwarders are in
-     * place.
+     * traversal.  This is arranged in part by proceeding from the
+     * last bin (table.length - 1) up towards the first.  Upon seeing
+     * a forwarding node, traversals (see class Traverser) arrange to
+     * move to the new table without revisiting nodes.  To ensure that
+     * no intervening nodes are skipped even when moved out of order,
+     * a stack (see class TableStack) is created on first encounter of
+     * a forwarding node during a traversal, to maintain its place if
+     * later processing the current table. The need for these
+     * save/restore mechanics is relatively rare, but when one
+     * forwarding node is encountered, typically many more will be.
+     * So Traversers use a simple caching scheme to avoid creating so
+     * many new TableStack nodes. (Thanks to Peter Levart for
+     * suggesting use of a stack here.)
      *
      * The traversal scheme also applies to partial traversals of
      * ranges of bins (via an alternate Traverser constructor)
@@ -446,16 +455,18 @@ public interface IntByIntToInt { int apply(int a, int b); }
      * related operations (which is the main reason we cannot use
      * existing collections such as TreeMaps). TreeBins contain
      * Comparable elements, but may contain others, as well as
-     * elements that are Comparable but not necessarily Comparable
-     * for the same T, so we cannot invoke compareTo among them. To
-     * handle this, the tree is ordered primarily by hash value, then
-     * by Comparable.compareTo order if applicable.  On lookup at a
-     * node, if elements are not comparable or compare as 0 then both
-     * left and right children may need to be searched in the case of
-     * tied hash values. (This corresponds to the full list search
-     * that would be necessary if all elements were non-Comparable and
-     * had tied hashes.)  The red-black balancing code is updated from
-     * pre-jdk-collections
+     * elements that are Comparable but not necessarily Comparable for
+     * the same T, so we cannot invoke compareTo among them. To handle
+     * this, the tree is ordered primarily by hash value, then by
+     * Comparable.compareTo order if applicable.  On lookup at a node,
+     * if elements are not comparable or compare as 0 then both left
+     * and right children may need to be searched in the case of tied
+     * hash values. (This corresponds to the full list search that
+     * would be necessary if all elements were non-Comparable and had
+     * tied hashes.) On insertion, to keep a total ordering (or as
+     * close as is required here) across rebalancings, we compare
+     * classes and identityHashCodes as tie-breakers. The red-black
+     * balancing code is updated from pre-jdk-collections
      * (http://gee.cs.oswego.edu/dl/classes/collections/RBCell.java)
      * based in turn on Cormen, Leiserson, and Rivest "Introduction to
      * Algorithms" (CLR).
@@ -485,6 +496,10 @@ public interface IntByIntToInt { int apply(int a, int b); }
      * unused "Segment" class that is instantiated in minimal form
      * only when serializing.
      *
+     * Also, solely for compatibility with previous versions of this
+     * class, it extends AbstractMap, even though all of its methods
+     * are overridden, so it is just useless baggage.
+     *
      * This file is organized to make things a little easier to follow
      * while reading than they might otherwise: First the main static
      * declarations and utilities, then fields, then main public
@@ -565,6 +580,23 @@ public interface IntByIntToInt { int apply(int a, int b); }
      */
     private static final int MIN_TRANSFER_STRIDE = 16;
 
+    /**
+     * The number of bits used for generation stamp in sizeCtl.
+     * Must be at least 6 for 32bit arrays.
+     */
+    private static int RESIZE_STAMP_BITS = 16;
+
+    /**
+     * The maximum number of threads that can help resize.
+     * Must fit in 32 - RESIZE_STAMP_BITS bits.
+     */
+    private static final int MAX_RESIZERS = (1 << (32 - RESIZE_STAMP_BITS)) - 1;
+
+    /**
+     * The bit shift for recording size stamp in sizeCtl.
+     */
+    private static final int RESIZE_STAMP_SHIFT = 32 - RESIZE_STAMP_BITS;
+
     /*
      * Encodings for Node hash fields. See above for explanation.
      */
@@ -722,7 +754,7 @@ static int compareComparables(Class<?> kc, Object k, Object x) {
      * errors by users, these checks must operate on local variables,
      * which accounts for some odd-looking inline assignments below.
      * Note that calls to setTabAt always occur within locked regions,
-     * and so in principle require only release ordering, not need
+     * and so in principle require only release ordering, not
      * full volatile semantics, but are currently coded as volatile
      * writes to be conservative.
      */
@@ -776,11 +808,6 @@ static final <K,V> void setTabAt(Node<K,V>[] tab, int i, Node<K,V> v) {
      */
     private transient volatile int transferIndex;
 
-    /**
-     * The least available table index to split while resizing.
-     */
-    private transient volatile int transferOrigin;
-
     /**
      * Spinlock (locked via CAS) used when resizing and/or creating CounterCells.
      */
@@ -1359,6 +1386,7 @@ static class Segment<K,V> extends ReentrantLock implements Serializable {
      * Saves the state of the {@code ConcurrentHashMapV8} instance to a
      * stream (i.e., serializes it).
      * @param s the stream
+     * @throws java.io.IOException if an I/O error occurs
      * @serialData
      * the key (Object) and value (Object)
      * for each key-value mapping, followed by a null pair.
@@ -1401,6 +1429,9 @@ private void writeObject(java.io.ObjectOutputStream s)
     /**
      * Reconstitutes the instance from a stream (that is, deserializes it).
      * @param s the stream
+     * @throws ClassNotFoundException if the class of a serialized object
+     *         could not be found
+     * @throws java.io.IOException if an I/O error occurs
      */
     private void readObject(java.io.ObjectInputStream s)
         throws java.io.IOException, ClassNotFoundException {
@@ -1435,8 +1466,8 @@ private void readObject(java.io.ObjectInputStream s)
                 int sz = (int)size;
                 n = tableSizeFor(sz + (sz >>> 1) + 1);
             }
-            @SuppressWarnings({"rawtypes","unchecked"})
-                Node<K,V>[] tab = (Node<K,V>[])new Node[n];
+            @SuppressWarnings("unchecked")
+                Node<K,V>[] tab = (Node<K,V>[])new Node<?,?>[n];
             int mask = n - 1;
             long added = 0L;
             while (p != null) {
@@ -2101,9 +2132,9 @@ public static <K> KeySetView<K,Boolean> newKeySet() {
      *
      * @param initialCapacity The implementation performs internal
      * sizing to accommodate this many elements.
+     * @return the new set
      * @throws IllegalArgumentException if the initial capacity of
      * elements is negative
-     * @return the new set
      * @since 1.8
      */
     public static <K> KeySetView<K,Boolean> newKeySet(int initialCapacity) {
@@ -2182,6 +2213,14 @@ Node<K,V> find(int h, Object k) {
 
     /* ---------------- Table Initialization and Resizing -------------- */
 
+    /**
+     * Returns the stamp bits for resizing a table of size n.
+     * Must be negative when shifted left by RESIZE_STAMP_SHIFT.
+     */
+    static final int resizeStamp(int n) {
+        return Integer.numberOfLeadingZeros(n) | (1 << (RESIZE_STAMP_BITS - 1));
+    }
+
     /**
      * Initializes table, using the size recorded in sizeCtl.
      */
@@ -2194,8 +2233,8 @@ else if (U.compareAndSwapInt(this, SIZECTL, sc, -1)) {
                 try {
                     if ((tab = table) == null || tab.length == 0) {
                         int n = (sc > 0) ? sc : DEFAULT_CAPACITY;
-                        @SuppressWarnings({"rawtypes","unchecked"})
-                            Node<K,V>[] nt = (Node<K,V>[])new Node[n];
+                        @SuppressWarnings("unchecked")
+                        Node<K,V>[] nt = (Node<K,V>[])new Node<?,?>[n];
                         table = tab = nt;
                         sc = n - (n >>> 2);
                     }
@@ -2237,17 +2276,20 @@ private final void addCount(long x, int check) {
             s = sumCount();
         }
         if (check >= 0) {
-            Node<K,V>[] tab, nt; int sc;
+            Node<K,V>[] tab, nt; int n, sc;
             while (s >= (long)(sc = sizeCtl) && (tab = table) != null &&
-                   tab.length < MAXIMUM_CAPACITY) {
+                   (n = tab.length) < MAXIMUM_CAPACITY) {
+                int rs = resizeStamp(n);
                 if (sc < 0) {
-                    if (sc == -1 || transferIndex <= transferOrigin ||
-                        (nt = nextTable) == null)
+                    if ((sc >>> RESIZE_STAMP_SHIFT) != rs || sc == rs + 1 ||
+                        sc == rs + MAX_RESIZERS || (nt = nextTable) == null ||
+                        transferIndex <= 0)
                         break;
-                    if (U.compareAndSwapInt(this, SIZECTL, sc, sc - 1))
+                    if (U.compareAndSwapInt(this, SIZECTL, sc, sc + 1))
                         transfer(tab, nt);
                 }
-                else if (U.compareAndSwapInt(this, SIZECTL, sc, -2))
+                else if (U.compareAndSwapInt(this, SIZECTL, sc,
+                                             (rs << RESIZE_STAMP_SHIFT) + 2))
                     transfer(tab, null);
                 s = sumCount();
             }
@@ -2259,12 +2301,19 @@ else if (U.compareAndSwapInt(this, SIZECTL, sc, -2))
      */
     final Node<K,V>[] helpTransfer(Node<K,V>[] tab, Node<K,V> f) {
         Node<K,V>[] nextTab; int sc;
-        if ((f instanceof ForwardingNode) &&
+        if (tab != null && (f instanceof ForwardingNode) &&
             (nextTab = ((ForwardingNode<K,V>)f).nextTable) != null) {
-            if (nextTab == nextTable && tab == table &&
-                transferIndex > transferOrigin && (sc = sizeCtl) < -1 &&
-                U.compareAndSwapInt(this, SIZECTL, sc, sc - 1))
-                transfer(tab, nextTab);
+            int rs = resizeStamp(tab.length);
+            while (nextTab == nextTable && table == tab &&
+                   (sc = sizeCtl) < 0) {
+                if ((sc >>> RESIZE_STAMP_SHIFT) != rs || sc == rs + 1 ||
+                    sc == rs + MAX_RESIZERS || transferIndex <= 0)
+                    break;
+                if (U.compareAndSwapInt(this, SIZECTL, sc, sc + 1)) {
+                    transfer(tab, nextTab);
+                    break;
+                }
+            }
             return nextTab;
         }
         return table;
@@ -2286,8 +2335,8 @@ private final void tryPresize(int size) {
                 if (U.compareAndSwapInt(this, SIZECTL, sc, -1)) {
                     try {
                         if (table == tab) {
-                            @SuppressWarnings({"rawtypes","unchecked"})
-                                Node<K,V>[] nt = (Node<K,V>[])new Node[n];
+                            @SuppressWarnings("unchecked")
+                            Node<K,V>[] nt = (Node<K,V>[])new Node<?,?>[n];
                             table = nt;
                             sc = n - (n >>> 2);
                         }
@@ -2298,9 +2347,21 @@ private final void tryPresize(int size) {
             }
             else if (c <= sc || n >= MAXIMUM_CAPACITY)
                 break;
-            else if (tab == table &&
-                     U.compareAndSwapInt(this, SIZECTL, sc, -2))
-                transfer(tab, null);
+            else if (tab == table) {
+                int rs = resizeStamp(n);
+                if (sc < 0) {
+                    Node<K,V>[] nt;
+                    if ((sc >>> RESIZE_STAMP_SHIFT) != rs || sc == rs + 1 ||
+                        sc == rs + MAX_RESIZERS || (nt = nextTable) == null ||
+                        transferIndex <= 0)
+                        break;
+                    if (U.compareAndSwapInt(this, SIZECTL, sc, sc + 1))
+                        transfer(tab, nt);
+                }
+                else if (U.compareAndSwapInt(this, SIZECTL, sc,
+                                             (rs << RESIZE_STAMP_SHIFT) + 2))
+                    transfer(tab, null);
+            }
         }
     }
 
@@ -2314,36 +2375,27 @@ private final void transfer(Node<K,V>[] tab, Node<K,V>[] nextTab) {
             stride = MIN_TRANSFER_STRIDE; // subdivide range
         if (nextTab == null) {            // initiating
             try {
-                @SuppressWarnings({"rawtypes","unchecked"})
-                    Node<K,V>[] nt = (Node<K,V>[])new Node[n << 1];
+                @SuppressWarnings("unchecked")
+                Node<K,V>[] nt = (Node<K,V>[])new Node<?,?>[n << 1];
                 nextTab = nt;
             } catch (Throwable ex) {      // try to cope with OOME
                 sizeCtl = Integer.MAX_VALUE;
                 return;
             }
             nextTable = nextTab;
-            transferOrigin = n;
             transferIndex = n;
-            ForwardingNode<K,V> rev = new ForwardingNode<K,V>(tab);
-            for (int k = n; k > 0;) {    // progressively reveal ready slots
-                int nextk = (k > stride) ? k - stride : 0;
-                for (int m = nextk; m < k; ++m)
-                    nextTab[m] = rev;
-                for (int m = n + nextk; m < n + k; ++m)
-                    nextTab[m] = rev;
-                U.putOrderedInt(this, TRANSFERORIGIN, k = nextk);
-            }
         }
         int nextn = nextTab.length;
         ForwardingNode<K,V> fwd = new ForwardingNode<K,V>(nextTab);
         boolean advance = true;
         boolean finishing = false; // to ensure sweep before committing nextTab
         for (int i = 0, bound = 0;;) {
-            int nextIndex, nextBound, fh; Node<K,V> f;
+            Node<K,V> f; int fh;
             while (advance) {
+                int nextIndex, nextBound;
                 if (--i >= bound || finishing)
                     advance = false;
-                else if ((nextIndex = transferIndex) <= transferOrigin) {
+                else if ((nextIndex = transferIndex) <= 0) {
                     i = -1;
                     advance = false;
                 }
@@ -2357,29 +2409,22 @@ else if (U.compareAndSwapInt
                 }
             }
             if (i < 0 || i >= n || i + n >= nextn) {
+                int sc;
                 if (finishing) {
                     nextTable = null;
                     table = nextTab;
                     sizeCtl = (n << 1) - (n >>> 1);
                     return;
                 }
-                for (int sc;;) {
-                    if (U.compareAndSwapInt(this, SIZECTL, sc = sizeCtl, ++sc)) {
-                        if (sc != -1)
-                            return;
-                        finishing = advance = true;
-                        i = n; // recheck before commit
-                        break;
-                    }
-                }
-            }
-            else if ((f = tabAt(tab, i)) == null) {
-                if (casTabAt(tab, i, null, fwd)) {
-                    setTabAt(nextTab, i, null);
-                    setTabAt(nextTab, i + n, null);
-                    advance = true;
+                if (U.compareAndSwapInt(this, SIZECTL, sc = sizeCtl, sc - 1)) {
+                    if ((sc - 2) != resizeStamp(n) << RESIZE_STAMP_SHIFT)
+                        return;
+                    finishing = advance = true;
+                    i = n; // recheck before commit
                 }
             }
+            else if ((f = tabAt(tab, i)) == null)
+                advance = casTabAt(tab, i, null, fwd);
             else if ((fh = f.hash) == MOVED)
                 advance = true; // already processed
             else {
@@ -2466,11 +2511,8 @@ else if (f instanceof TreeBin) {
     private final void treeifyBin(Node<K,V>[] tab, int index) {
         Node<K,V> b; int n, sc;
         if (tab != null) {
-            if ((n = tab.length) < MIN_TREEIFY_CAPACITY) {
-                if (tab == table && (sc = sizeCtl) >= 0 &&
-                    U.compareAndSwapInt(this, SIZECTL, sc, -2))
-                    transfer(tab, null);
-            }
+            if ((n = tab.length) < MIN_TREEIFY_CAPACITY)
+                tryPresize(n << 1);
             else if ((b = tabAt(tab, index)) != null && b.hash >= 0) {
                 synchronized (b) {
                     if (tabAt(tab, index) == b) {
@@ -2546,19 +2588,18 @@ else if (ph < h)
                         p = pr;
                     else if ((pk = p.key) == k || (pk != null && k.equals(pk)))
                         return p;
-                    else if (pl == null && pr == null)
-                        break;
+                    else if (pl == null)
+                        p = pr;
+                    else if (pr == null)
+                        p = pl;
                     else if ((kc != null ||
                               (kc = comparableClassFor(k)) != null) &&
                              (dir = compareComparables(kc, k, pk)) != 0)
                         p = (dir < 0) ? pl : pr;
-                    else if (pl == null)
-                        p = pr;
-                    else if (pr == null ||
-                             (q = pr.findTreeNode(h, k, kc)) == null)
-                        p = pl;
-                    else
+                    else if ((q = pr.findTreeNode(h, k, kc)) != null)
                         return q;
+                    else
+                        p = pl;
                 } while (p != null);
             }
             return null;
@@ -2584,6 +2625,23 @@ static final class TreeBin<K,V> extends Node<K,V> {
         static final int WAITER = 2; // set when waiting for write lock
         static final int READER = 4; // increment value for setting read lock
 
+        /**
+         * Tie-breaking utility for ordering insertions when equal
+         * hashCodes and non-comparable. We don't require a total
+         * order, just a consistent insertion rule to maintain
+         * equivalence across rebalancings. Tie-breaking further than
+         * necessary simplifies testing a bit.
+         */
+        static int tieBreakOrder(Object a, Object b) {
+            int d;
+            if (a == null || b == null ||
+                (d = a.getClass().getName().
+                 compareTo(b.getClass().getName())) == 0)
+                d = (System.identityHashCode(a) <= System.identityHashCode(b) ?
+                     -1 : 1);
+            return d;
+        }
+
         /**
          * Creates bin with initial set of nodes headed by b.
          */
@@ -2600,21 +2658,21 @@ static final class TreeBin<K,V> extends Node<K,V> {
                     r = x;
                 }
                 else {
-                    Object key = x.key;
-                    int hash = x.hash;
+                    K k = x.key;
+                    int h = x.hash;
                     Class<?> kc = null;
                     for (TreeNode<K,V> p = r;;) {
                         int dir, ph;
-                        if ((ph = p.hash) > hash)
+                        K pk = p.key;
+                        if ((ph = p.hash) > h)
                             dir = -1;
-                        else if (ph < hash)
+                        else if (ph < h)
                             dir = 1;
-                        else if ((kc != null ||
-                                  (kc = comparableClassFor(key)) != null))
-                            dir = compareComparables(kc, key, p.key);
-                        else
-                            dir = 0;
-                        TreeNode<K,V> xp = p;
+                        else if ((kc == null &&
+                                  (kc = comparableClassFor(k)) == null) ||
+                                 (dir = compareComparables(kc, k, pk)) == 0)
+                            dir = tieBreakOrder(k, pk);
+                            TreeNode<K,V> xp = p;
                         if ((p = (dir <= 0) ? p.left : p.right) == null) {
                             x.parent = xp;
                             if (dir <= 0)
@@ -2628,6 +2686,7 @@ else if ((kc != null ||
                 }
             }
             this.root = r;
+            assert checkInvariants(root);
         }
 
         /**
@@ -2651,14 +2710,14 @@ private final void unlockRoot() {
         private final void contendedLock() {
             boolean waiting = false;
             for (int s;;) {
-                if (((s = lockState) & WRITER) == 0) {
+                if (((s = lockState) & ~WAITER) == 0) {
                     if (U.compareAndSwapInt(this, LOCKSTATE, s, WRITER)) {
                         if (waiting)
                             waiter = null;
                         return;
                     }
                 }
-                else if ((s | WAITER) == 0) {
+                else if ((s & WAITER) == 0) {
                     if (U.compareAndSwapInt(this, LOCKSTATE, s, s | WAITER)) {
                         waiting = true;
                         waiter = Thread.currentThread();
@@ -2676,12 +2735,13 @@ else if (waiting)
          */
         final Node<K,V> find(int h, Object k) {
             if (k != null) {
-                for (Node<K,V> e = first; e != null; e = e.next) {
+                for (Node<K,V> e = first; e != null; ) {
                     int s; K ek;
                     if (((s = lockState) & (WAITER|WRITER)) != 0) {
                         if (e.hash == h &&
                             ((ek = e.key) == k || (ek != null && k.equals(ek))))
                             return e;
+                        e = e.next;
                     }
                     else if (U.compareAndSwapInt(this, LOCKSTATE, s,
                                                  s + READER)) {
@@ -2711,8 +2771,9 @@ else if (U.compareAndSwapInt(this, LOCKSTATE, s,
          */
         final TreeNode<K,V> putTreeVal(int h, K k, V v) {
             Class<?> kc = null;
+            boolean searched = false;
             for (TreeNode<K,V> p = root;;) {
-                int dir, ph; K pk; TreeNode<K,V> q, pr;
+                int dir, ph; K pk;
                 if (p == null) {
                     first = root = new TreeNode<K,V>(h, k, v, null, null);
                     break;
@@ -2726,21 +2787,25 @@ else if ((pk = p.key) == k || (pk != null && k.equals(pk)))
                 else if ((kc == null &&
                           (kc = comparableClassFor(k)) == null) ||
                          (dir = compareComparables(kc, k, pk)) == 0) {
-                    if (p.left == null)
-                        dir = 1;
-                    else if ((pr = p.right) == null ||
-                             (q = pr.findTreeNode(h, k, kc)) == null)
-                        dir = -1;
-                    else
-                        return q;
+                    if (!searched) {
+                        TreeNode<K,V> q, ch;
+                        searched = true;
+                        if (((ch = p.left) != null &&
+                             (q = ch.findTreeNode(h, k, kc)) != null) ||
+                            ((ch = p.right) != null &&
+                             (q = ch.findTreeNode(h, k, kc)) != null))
+                            return q;
+                    }
+                    dir = tieBreakOrder(k, pk);
                 }
+
                 TreeNode<K,V> xp = p;
-                if ((p = (dir < 0) ? p.left : p.right) == null) {
+                if ((p = (dir <= 0) ? p.left : p.right) == null) {
                     TreeNode<K,V> x, f = first;
                     first = x = new TreeNode<K,V>(h, k, v, f, xp);
                     if (f != null)
                         f.prev = x;
-                    if (dir < 0)
+                    if (dir <= 0)
                         xp.left = x;
                     else
                         xp.right = x;
@@ -3094,6 +3159,18 @@ static <K,V> boolean checkInvariants(TreeNode<K,V> t) {
 
     /* ----------------Table Traversal -------------- */
 
+    /**
+     * Records the table, its length, and current traversal index for a
+     * traverser that must process a region of a forwarded table before
+     * proceeding with current table.
+     */
+    static final class TableStack<K,V> {
+        int length;
+        int index;
+        Node<K,V>[] tab;
+        TableStack<K,V> next;
+    }
+
     /**
      * Encapsulates traversal for methods such as containsValue; also
      * serves as a base class for other iterators and spliterators.
@@ -3118,6 +3195,7 @@ static <K,V> boolean checkInvariants(TreeNode<K,V> t) {
     static class Traverser<K,V> {
         Node<K,V>[] tab;        // current table; updated if resized
         Node<K,V> next;         // the next entry to use
+        TableStack<K,V> stack, spare; // to save/restore on ForwardingNodes
         int index;              // index of bin to use next
         int baseIndex;          // current index of initial table
         int baseLimit;          // index bound for initial table
@@ -3139,16 +3217,17 @@ final Node<K,V> advance() {
             if ((e = next) != null)
                 e = e.next;
             for (;;) {
-                Node<K,V>[] t; int i, n; K ek;  // must use locals in checks
+                Node<K,V>[] t; int i, n;  // must use locals in checks
                 if (e != null)
                     return next = e;
                 if (baseIndex >= baseLimit || (t = tab) == null ||
                     (n = t.length) <= (i = index) || i < 0)
                     return next = null;
-                if ((e = tabAt(t, index)) != null && e.hash < 0) {
+                if ((e = tabAt(t, i)) != null && e.hash < 0) {
                     if (e instanceof ForwardingNode) {
                         tab = ((ForwardingNode<K,V>)e).nextTable;
                         e = null;
+                        pushState(t, i, n);
                         continue;
                     }
                     else if (e instanceof TreeBin)
@@ -3156,9 +3235,48 @@ else if (e instanceof TreeBin)
                     else
                         e = null;
                 }
-                if ((index += baseSize) >= n)
-                    index = ++baseIndex;    // visit upper slots if present
+                if (stack != null)
+                    recoverState(n);
+                else if ((index = i + baseSize) >= n)
+                    index = ++baseIndex; // visit upper slots if present
+            }
+        }
+
+        /**
+         * Saves traversal state upon encountering a forwarding node.
+         */
+        private void pushState(Node<K,V>[] t, int i, int n) {
+            TableStack<K,V> s = spare;  // reuse if possible
+            if (s != null)
+                spare = s.next;
+            else
+                s = new TableStack<K,V>();
+            s.tab = t;
+            s.length = n;
+            s.index = i;
+            s.next = stack;
+            stack = s;
+        }
+
+        /**
+         * Possibly pops traversal state.
+         *
+         * @param n length of current table
+         */
+        private void recoverState(int n) {
+            TableStack<K,V> s; int len;
+            while ((s = stack) != null && (index += (len = s.length)) >= n) {
+                n = len;
+                index = s.index;
+                tab = s.tab;
+                s.tab = null;
+                TableStack<K,V> next = s.next;
+                s.next = spare; // save for reuse
+                stack = next;
+                spare = s;
             }
+            if (s == null && (index += baseSize) >= n)
+                index = ++baseIndex;
         }
     }
 
@@ -6126,7 +6244,6 @@ else if (U.compareAndSwapLong(this, BASECOUNT, v = baseCount, v + x))
     private static final sun.misc.Unsafe U;
     private static final long SIZECTL;
     private static final long TRANSFERINDEX;
-    private static final long TRANSFERORIGIN;
     private static final long BASECOUNT;
     private static final long CELLSBUSY;
     private static final long CELLVALUE;
@@ -6141,8 +6258,6 @@ else if (U.compareAndSwapLong(this, BASECOUNT, v = baseCount, v + x))
                 (k.getDeclaredField("sizeCtl"));
             TRANSFERINDEX = U.objectFieldOffset
                 (k.getDeclaredField("transferIndex"));
-            TRANSFERORIGIN = U.objectFieldOffset
-                (k.getDeclaredField("transferOrigin"));
             BASECOUNT = U.objectFieldOffset
                 (k.getDeclaredField("baseCount"));
             CELLSBUSY = U.objectFieldOffset
diff --git a/src/main/java/jsr166e/CountedCompleter.java b/src/main/java/jsr166e/CountedCompleter.java
index d9d1d48132e96..c7717ee9032e8 100644
--- a/src/main/java/jsr166e/CountedCompleter.java
+++ b/src/main/java/jsr166e/CountedCompleter.java
@@ -686,7 +686,7 @@ protected final boolean exec() {
     }
 
     /**
-     * Returns the result of the computation. By default
+     * Returns the result of the computation.  By default,
      * returns {@code null}, which is appropriate for {@code Void}
      * actions, but in other cases should be overridden, almost
      * always to return a field or function of a field that
diff --git a/src/main/java/jsr166e/ForkJoinPool.java b/src/main/java/jsr166e/ForkJoinPool.java
index e814f23d52961..8a0497371c2ff 100644
--- a/src/main/java/jsr166e/ForkJoinPool.java
+++ b/src/main/java/jsr166e/ForkJoinPool.java
@@ -532,8 +532,8 @@ public static interface ForkJoinWorkerThreadFactory {
          * Returns a new worker thread operating in the given pool.
          *
          * @param pool the pool this thread works in
-         * @throws NullPointerException if the pool is null
          * @return the new worker thread
+         * @throws NullPointerException if the pool is null
          */
         public ForkJoinWorkerThread newThread(ForkJoinPool pool);
     }
@@ -2098,7 +2098,7 @@ final void helpQuiescePool(WorkQueue w) {
                     w.currentSteal = ps;
                 }
             }
-            else if (active) {       // decrement active count without queuing
+            else if (active) {      // decrement active count without queuing
                 long nc = ((c = ctl) & ~AC_MASK) | ((c & AC_MASK) - AC_UNIT);
                 if ((int)(nc >> AC_SHIFT) + parallelism == 0)
                     break;          // bypass decrement-then-increment
@@ -2497,6 +2497,7 @@ public static ForkJoinPool commonPool() {
      * minimally only the latter.
      *
      * @param task the task
+     * @param <T> the type of the task's result
      * @return the task's result
      * @throws NullPointerException if the task is null
      * @throws RejectedExecutionException if the task cannot be
@@ -2545,6 +2546,7 @@ public void execute(Runnable task) {
      * Submits a ForkJoinTask for execution.
      *
      * @param task the task to submit
+     * @param <T> the type of the task's result
      * @return the task
      * @throws NullPointerException if the task is null
      * @throws RejectedExecutionException if the task cannot be
diff --git a/src/main/java/jsr166e/ForkJoinTask.java b/src/main/java/jsr166e/ForkJoinTask.java
index e23dfbe3f796a..99ac374ec79b5 100644
--- a/src/main/java/jsr166e/ForkJoinTask.java
+++ b/src/main/java/jsr166e/ForkJoinTask.java
@@ -134,7 +134,7 @@
  * (DAG). Otherwise, executions may encounter a form of deadlock as
  * tasks cyclically wait for each other.  However, this framework
  * supports other methods and techniques (for example the use of
- * {@link Phaser}, {@link #helpQuiesce}, and {@link #complete}) that
+ * {@link java.util.concurrent.Phaser Phaser}, {@link #helpQuiesce}, and {@link #complete}) that
  * may be of use in constructing custom subclasses for problems that
  * are not statically structured as DAGs. To support such usages, a
  * ForkJoinTask may be atomically <em>tagged</em> with a {@code short}
@@ -411,11 +411,13 @@ static final class ExceptionNode extends WeakReference<ForkJoinTask<?>> {
         final Throwable ex;
         ExceptionNode next;
         final long thrower;  // use id not ref to avoid weak cycles
+        final int hashCode;  // store task hashCode before weak ref disappears
         ExceptionNode(ForkJoinTask<?> task, Throwable ex, ExceptionNode next) {
             super(task, exceptionTableRefQueue);
             this.ex = ex;
             this.next = next;
             this.thrower = Thread.currentThread().getId();
+            this.hashCode = System.identityHashCode(task);
         }
     }
 
@@ -571,15 +573,18 @@ else if (ps.length == 1 && ps[0] == Throwable.class)
         return ex;
     }
 
+    /**
+     * Poll stale refs and remove them. Call only while holding lock.
+     */
     /**
      * Poll stale refs and remove them. Call only while holding lock.
      */
     private static void expungeStaleExceptions() {
         for (Object x; (x = exceptionTableRefQueue.poll()) != null;) {
             if (x instanceof ExceptionNode) {
-                ForkJoinTask<?> key = ((ExceptionNode)x).get();
+                int hashCode = ((ExceptionNode)x).hashCode;
                 ExceptionNode[] t = exceptionTable;
-                int i = System.identityHashCode(key) & (t.length - 1);
+                int i = hashCode & (t.length - 1);
                 ExceptionNode e = t[i];
                 ExceptionNode pred = null;
                 while (e != null) {
@@ -782,6 +787,7 @@ else if (t.doJoin() < NORMAL)
      * unprocessed.
      *
      * @param tasks the collection of tasks
+     * @param <T> the type of the values returned from the tasks
      * @return the tasks argument, to simplify usage
      * @throws NullPointerException if tasks or any element are null
      */
@@ -1444,6 +1450,7 @@ public static ForkJoinTask<?> adapt(Runnable runnable) {
      *
      * @param runnable the runnable action
      * @param result the result upon completion
+     * @param <T> the type of the result
      * @return the task
      */
     public static <T> ForkJoinTask<T> adapt(Runnable runnable, T result) {
@@ -1457,6 +1464,7 @@ public static <T> ForkJoinTask<T> adapt(Runnable runnable, T result) {
      * encountered into {@code RuntimeException}.
      *
      * @param callable the callable action
+     * @param <T> the type of the callable's result
      * @return the task
      */
     public static <T> ForkJoinTask<T> adapt(Callable<? extends T> callable) {
@@ -1470,6 +1478,8 @@ public static <T> ForkJoinTask<T> adapt(Callable<? extends T> callable) {
     /**
      * Saves this task to a stream (that is, serializes it).
      *
+     * @param s the stream
+     * @throws java.io.IOException if an I/O error occurs
      * @serialData the current run status and the exception thrown
      * during execution, or {@code null} if none
      */
@@ -1481,6 +1491,10 @@ private void writeObject(java.io.ObjectOutputStream s)
 
     /**
      * Reconstitutes this task from a stream (that is, deserializes it).
+     * @param s the stream
+     * @throws ClassNotFoundException if the class of a serialized object
+     *         could not be found
+     * @throws java.io.IOException if an I/O error occurs
      */
     private void readObject(java.io.ObjectInputStream s)
         throws java.io.IOException, ClassNotFoundException {
diff --git a/src/main/java/jsr166e/RecursiveTask.java b/src/main/java/jsr166e/RecursiveTask.java
index a31bd0cfff81c..263364af1a255 100644
--- a/src/main/java/jsr166e/RecursiveTask.java
+++ b/src/main/java/jsr166e/RecursiveTask.java
@@ -15,7 +15,7 @@
  * class Fibonacci extends RecursiveTask<Integer> {
  *   final int n;
  *   Fibonacci(int n) { this.n = n; }
- *   Integer compute() {
+ *   protected Integer compute() {
  *     if (n <= 1)
  *       return n;
  *     Fibonacci f1 = new Fibonacci(n - 1);
@@ -46,6 +46,7 @@ public abstract class RecursiveTask<V> extends ForkJoinTask<V> {
 
     /**
      * The main computation performed by this task.
+     * @return the result of the computation
      */
     protected abstract V compute();
 
diff --git a/src/main/java/jsr166e/StampedLock.java b/src/main/java/jsr166e/StampedLock.java
index d8fe6f8af795e..45d873a1c0a01 100644
--- a/src/main/java/jsr166e/StampedLock.java
+++ b/src/main/java/jsr166e/StampedLock.java
@@ -198,7 +198,11 @@ public class StampedLock implements java.io.Serializable {
      * incoming reader arrives while read lock is held but there is a
      * queued writer, this incoming reader is queued.  (This rule is
      * responsible for some of the complexity of method acquireRead,
-     * but without it, the lock becomes highly unfair.)
+     * but without it, the lock becomes highly unfair.) Method release
+     * does not (and sometimes cannot) itself wake up cowaiters. This
+     * is done by the primary thread, but helped by any other threads
+     * with nothing better to do in methods acquireRead and
+     * acquireWrite.
      *
      * These rules apply to threads actually queued. All tryLock forms
      * opportunistically try to acquire locks regardless of preference
@@ -242,11 +246,14 @@ public class StampedLock implements java.io.Serializable {
     /** Number of processors, for spin control */
     private static final int NCPU = Runtime.getRuntime().availableProcessors();
 
-    /** Maximum number of retries before blocking on acquisition */
+    /** Maximum number of retries before enqueuing on acquisition */
     private static final int SPINS = (NCPU > 1) ? 1 << 6 : 0;
 
+    /** Maximum number of retries before blocking at head on acquisition */
+    private static final int HEAD_SPINS = (NCPU > 1) ? 1 << 10 : 0;
+
     /** Maximum number of retries before re-blocking */
-    private static final int MAX_HEAD_SPINS = (NCPU > 1) ? 1 << 12 : 0;
+    private static final int MAX_HEAD_SPINS = (NCPU > 1) ? 1 << 16 : 0;
 
     /** The period for yielding when waiting for overflow spinlock */
     private static final int OVERFLOW_YIELD_RATE = 7; // must be power 2 - 1
@@ -390,8 +397,8 @@ public long writeLockInterruptibly() throws InterruptedException {
      * @return a stamp that can be used to unlock or convert mode
      */
     public long readLock() {
-        long s, next;  // bypass acquireRead on fully unlocked case only
-        return ((((s = state) & ABITS) == 0L &&
+        long s = state, next;  // bypass acquireRead on common uncontended case
+        return ((whead == wtail && (s & ABITS) < RFULL &&
                  U.compareAndSwapLong(this, STATE, s, next = s + RUNIT)) ?
                 next : acquireRead(false, 0L));
     }
@@ -668,7 +675,7 @@ public long tryConvertToOptimisticRead(long stamp) {
         long a = stamp & ABITS, m, s, next; WNode h;
         for (;;) {
             s = U.getLongVolatile(this, STATE); // see above
-            if ((s & SBITS) != (stamp & SBITS))
+            if (((s = state) & SBITS) != (stamp & SBITS))
                 break;
             if ((m = s & ABITS) == 0L) {
                 if (a != 0L)
@@ -987,17 +994,8 @@ private void release(WNode h) {
                     if (t.status <= 0)
                         q = t;
             }
-            if (q != null) {
-                for (WNode r = q;;) {  // release co-waiters too
-                    if ((w = r.thread) != null) {
-                        r.thread = null;
-                        U.unpark(w);
-                    }
-                    if ((r = q.cowait) == null)
-                        break;
-                    U.compareAndSwapObject(q, WCOWAIT, r, r.cowait);
-                }
-            }
+            if (q != null && (w = q.thread) != null)
+                U.unpark(w);
         }
     }
 
@@ -1013,22 +1011,22 @@ private void release(WNode h) {
     private long acquireWrite(boolean interruptible, long deadline) {
         WNode node = null, p;
         for (int spins = -1;;) { // spin while enqueuing
-            long s, ns;
-            if (((s = state) & ABITS) == 0L) {
+            long m, s, ns;
+            if ((m = (s = state) & ABITS) == 0L) {
                 if (U.compareAndSwapLong(this, STATE, s, ns = s + WBIT))
                     return ns;
             }
+            else if (spins < 0)
+                spins = (m == WBIT && wtail == whead) ? SPINS : 0;
             else if (spins > 0) {
                 if (ThreadLocalRandom.current().nextInt() >= 0)
                     --spins;
             }
             else if ((p = wtail) == null) { // initialize queue
-                WNode h = new WNode(WMODE, null);
-                if (U.compareAndSwapObject(this, WHEAD, null, h))
-                    wtail = h;
+                WNode hd = new WNode(WMODE, null);
+                if (U.compareAndSwapObject(this, WHEAD, null, hd))
+                    wtail = hd;
             }
-            else if (spins < 0)
-                spins = (p == whead) ? SPINS : 0;
             else if (node == null)
                 node = new WNode(WMODE, p);
             else if (node.prev != p)
@@ -1039,14 +1037,18 @@ else if (U.compareAndSwapObject(this, WTAIL, p, node)) {
             }
         }
 
-        for (int spins = SPINS;;) {
-            WNode np, pp; int ps; long s, ns; Thread w;
-            while ((np = node.prev) != p && np != null)
-                (p = np).next = node;   // stale
-            if (whead == p) {
+        for (int spins = -1;;) {
+            WNode h, np, pp; int ps;
+            if ((h = whead) == p) {
+                if (spins < 0)
+                    spins = HEAD_SPINS;
+                else if (spins < MAX_HEAD_SPINS)
+                    spins <<= 1;
                 for (int k = spins;;) { // spin at head
+                    long s, ns;
                     if (((s = state) & ABITS) == 0L) {
-                        if (U.compareAndSwapLong(this, STATE, s, ns = s+WBIT)) {
+                        if (U.compareAndSwapLong(this, STATE, s,
+                                                 ns = s + WBIT)) {
                             whead = node;
                             node.prev = null;
                             return ns;
@@ -1056,33 +1058,45 @@ else if (ThreadLocalRandom.current().nextInt() >= 0 &&
                              --k <= 0)
                         break;
                 }
-                if (spins < MAX_HEAD_SPINS)
-                    spins <<= 1;
             }
-            if ((ps = p.status) == 0)
-                U.compareAndSwapInt(p, WSTATUS, 0, WAITING);
-            else if (ps == CANCELLED) {
-                if ((pp = p.prev) != null) {
-                    node.prev = pp;
-                    pp.next = node;
+            else if (h != null) { // help release stale waiters
+                WNode c; Thread w;
+                while ((c = h.cowait) != null) {
+                    if (U.compareAndSwapObject(h, WCOWAIT, c, c.cowait) &&
+                        (w = c.thread) != null)
+                        U.unpark(w);
                 }
             }
-            else {
-                long time; // 0 argument to park means no timeout
-                if (deadline == 0L)
-                    time = 0L;
-                else if ((time = deadline - System.nanoTime()) <= 0L)
-                    return cancelWaiter(node, node, false);
-                Thread wt = Thread.currentThread();
-                U.putObject(wt, PARKBLOCKER, this); // emulate LockSupport.park
-                node.thread = wt;
-                if (node.prev == p && p.status == WAITING && // recheck
-                    (p != whead || (state & ABITS) != 0L))
-                    U.park(false, time);
-                node.thread = null;
-                U.putObject(wt, PARKBLOCKER, null);
-                if (interruptible && Thread.interrupted())
-                    return cancelWaiter(node, node, true);
+            if (whead == h) {
+                if ((np = node.prev) != p) {
+                    if (np != null)
+                        (p = np).next = node;   // stale
+                }
+                else if ((ps = p.status) == 0)
+                    U.compareAndSwapInt(p, WSTATUS, 0, WAITING);
+                else if (ps == CANCELLED) {
+                    if ((pp = p.prev) != null) {
+                        node.prev = pp;
+                        pp.next = node;
+                    }
+                }
+                else {
+                    long time; // 0 argument to park means no timeout
+                    if (deadline == 0L)
+                        time = 0L;
+                    else if ((time = deadline - System.nanoTime()) <= 0L)
+                        return cancelWaiter(node, node, false);
+                    Thread wt = Thread.currentThread();
+                    U.putObject(wt, PARKBLOCKER, this);
+                    node.thread = wt;
+                    if (p.status < 0 && (p != h || (state & ABITS) != 0L) &&
+                        whead == h && node.prev == p)
+                        U.park(false, time);  // emulate LockSupport.park
+                    node.thread = null;
+                    U.putObject(wt, PARKBLOCKER, null);
+                    if (interruptible && Thread.interrupted())
+                        return cancelWaiter(node, node, true);
+                }
             }
         }
     }
@@ -1097,138 +1111,159 @@ else if ((time = deadline - System.nanoTime()) <= 0L)
      * @return next state, or INTERRUPTED
      */
     private long acquireRead(boolean interruptible, long deadline) {
-        WNode node = null, group = null, p;
+        WNode node = null, p;
         for (int spins = -1;;) {
-            for (;;) {
-                long s, m, ns; WNode h, q; Thread w; // anti-barging guard
-                if (group == null && (h = whead) != null &&
-                    (q = h.next) != null && q.mode != RMODE)
-                    break;
-                if ((m = (s = state) & ABITS) < RFULL ?
-                    U.compareAndSwapLong(this, STATE, s, ns = s + RUNIT) :
-                    (m < WBIT && (ns = tryIncReaderOverflow(s)) != 0L)) {
-                    if (group != null) {  // help release others
-                        for (WNode r = group;;) {
-                            if ((w = r.thread) != null) {
-                                r.thread = null;
-                                U.unpark(w);
+            WNode h;
+            if ((h = whead) == (p = wtail)) {
+                for (long m, s, ns;;) {
+                    if ((m = (s = state) & ABITS) < RFULL ?
+                        U.compareAndSwapLong(this, STATE, s, ns = s + RUNIT) :
+                        (m < WBIT && (ns = tryIncReaderOverflow(s)) != 0L))
+                        return ns;
+                    else if (m >= WBIT) {
+                        if (spins > 0) {
+                            if (ThreadLocalRandom.current().nextInt() >= 0)
+                                --spins;
+                        }
+                        else {
+                            if (spins == 0) {
+                                WNode nh = whead, np = wtail;
+                                if ((nh == h && np == p) || (h = nh) != (p = np))
+                                    break;
                             }
-                            if ((r = group.cowait) == null)
-                                break;
-                            U.compareAndSwapObject(group, WCOWAIT, r, r.cowait);
+                            spins = SPINS;
                         }
                     }
-                    return ns;
                 }
-                if (m >= WBIT)
-                    break;
-            }
-            if (spins > 0) {
-                if (ThreadLocalRandom.current().nextInt() >= 0)
-                    --spins;
             }
-            else if ((p = wtail) == null) {
-                WNode h = new WNode(WMODE, null);
-                if (U.compareAndSwapObject(this, WHEAD, null, h))
-                    wtail = h;
+            if (p == null) { // initialize queue
+                WNode hd = new WNode(WMODE, null);
+                if (U.compareAndSwapObject(this, WHEAD, null, hd))
+                    wtail = hd;
             }
-            else if (spins < 0)
-                spins = (p == whead) ? SPINS : 0;
             else if (node == null)
-                node = new WNode(WMODE, p);
-            else if (node.prev != p)
-                node.prev = p;
-            else if (p.mode == RMODE && p != whead) {
-                WNode pp = p.prev;  // become co-waiter with group p
-                if (pp != null && p == wtail &&
-                    U.compareAndSwapObject(p, WCOWAIT,
-                                           node.cowait = p.cowait, node)) {
-                    node.thread = Thread.currentThread();
-                    for (long time;;) {
+                node = new WNode(RMODE, p);
+            else if (h == p || p.mode != RMODE) {
+                if (node.prev != p)
+                    node.prev = p;
+                else if (U.compareAndSwapObject(this, WTAIL, p, node)) {
+                    p.next = node;
+                    break;
+                }
+            }
+            else if (!U.compareAndSwapObject(p, WCOWAIT,
+                                             node.cowait = p.cowait, node))
+                node.cowait = null;
+            else {
+                for (;;) {
+                    WNode pp, c; Thread w;
+                    if ((h = whead) != null && (c = h.cowait) != null &&
+                        U.compareAndSwapObject(h, WCOWAIT, c, c.cowait) &&
+                        (w = c.thread) != null) // help release
+                        U.unpark(w);
+                    if (h == (pp = p.prev) || h == p || pp == null) {
+                        long m, s, ns;
+                        do {
+                            if ((m = (s = state) & ABITS) < RFULL ?
+                                U.compareAndSwapLong(this, STATE, s,
+                                                     ns = s + RUNIT) :
+                                (m < WBIT &&
+                                 (ns = tryIncReaderOverflow(s)) != 0L))
+                                return ns;
+                        } while (m < WBIT);
+                    }
+                    if (whead == h && p.prev == pp) {
+                        long time;
+                        if (pp == null || h == p || p.status > 0) {
+                            node = null; // throw away
+                            break;
+                        }
                         if (deadline == 0L)
                             time = 0L;
                         else if ((time = deadline - System.nanoTime()) <= 0L)
                             return cancelWaiter(node, p, false);
-                        if (node.thread == null)
-                            break;
-                        if (p.prev != pp || p.status == CANCELLED ||
-                            p == whead || p.prev != pp) {
-                            node.thread = null;
-                            break;
-                        }
                         Thread wt = Thread.currentThread();
                         U.putObject(wt, PARKBLOCKER, this);
-                        if (node.thread == null) // must recheck
-                            break;
-                        U.park(false, time);
+                        node.thread = wt;
+                        if ((h != pp || (state & ABITS) == WBIT) &&
+                            whead == h && p.prev == pp)
+                            U.park(false, time);
+                        node.thread = null;
                         U.putObject(wt, PARKBLOCKER, null);
                         if (interruptible && Thread.interrupted())
                             return cancelWaiter(node, p, true);
                     }
-                    group = p;
                 }
-                node = null; // throw away
-            }
-            else if (U.compareAndSwapObject(this, WTAIL, p, node)) {
-                p.next = node;
-                break;
             }
         }
 
-        for (int spins = SPINS;;) {
-            WNode np, pp, r; int ps; long m, s, ns; Thread w;
-            while ((np = node.prev) != p && np != null)
-                (p = np).next = node;
-            if (whead == p) {
-                for (int k = spins;;) {
-                    if ((m = (s = state) & ABITS) != WBIT) {
-                        if (m < RFULL ?
-                            U.compareAndSwapLong(this, STATE, s, ns = s + RUNIT):
-                            (ns = tryIncReaderOverflow(s)) != 0L) {
-                            whead = node;
-                            node.prev = null;
-                            while ((r = node.cowait) != null) {
-                                if (U.compareAndSwapObject(node, WCOWAIT,
-                                                           r, r.cowait) &&
-                                    (w = r.thread) != null) {
-                                    r.thread = null;
-                                    U.unpark(w); // release co-waiter
-                                }
-                            }
-                            return ns;
+        for (int spins = -1;;) {
+            WNode h, np, pp; int ps;
+            if ((h = whead) == p) {
+                if (spins < 0)
+                    spins = HEAD_SPINS;
+                else if (spins < MAX_HEAD_SPINS)
+                    spins <<= 1;
+                for (int k = spins;;) { // spin at head
+                    long m, s, ns;
+                    if ((m = (s = state) & ABITS) < RFULL ?
+                        U.compareAndSwapLong(this, STATE, s, ns = s + RUNIT) :
+                        (m < WBIT && (ns = tryIncReaderOverflow(s)) != 0L)) {
+                        WNode c; Thread w;
+                        whead = node;
+                        node.prev = null;
+                        while ((c = node.cowait) != null) {
+                            if (U.compareAndSwapObject(node, WCOWAIT,
+                                                       c, c.cowait) &&
+                                (w = c.thread) != null)
+                                U.unpark(w);
                         }
+                        return ns;
                     }
-                    else if (ThreadLocalRandom.current().nextInt() >= 0 &&
-                             --k <= 0)
+                    else if (m >= WBIT &&
+                             ThreadLocalRandom.current().nextInt() >= 0 && --k <= 0)
                         break;
                 }
-                if (spins < MAX_HEAD_SPINS)
-                    spins <<= 1;
             }
-            if ((ps = p.status) == 0)
-                U.compareAndSwapInt(p, WSTATUS, 0, WAITING);
-            else if (ps == CANCELLED) {
-                if ((pp = p.prev) != null) {
-                    node.prev = pp;
-                    pp.next = node;
+            else if (h != null) {
+                WNode c; Thread w;
+                while ((c = h.cowait) != null) {
+                    if (U.compareAndSwapObject(h, WCOWAIT, c, c.cowait) &&
+                        (w = c.thread) != null)
+                        U.unpark(w);
                 }
             }
-            else {
-                long time;
-                if (deadline == 0L)
-                    time = 0L;
-                else if ((time = deadline - System.nanoTime()) <= 0L)
-                    return cancelWaiter(node, node, false);
-                Thread wt = Thread.currentThread();
-                U.putObject(wt, PARKBLOCKER, this);
-                node.thread = wt;
-                if (node.prev == p && p.status == WAITING &&
-                    (p != whead || (state & ABITS) != WBIT))
-                    U.park(false, time);
-                node.thread = null;
-                U.putObject(wt, PARKBLOCKER, null);
-                if (interruptible && Thread.interrupted())
-                    return cancelWaiter(node, node, true);
+            if (whead == h) {
+                if ((np = node.prev) != p) {
+                    if (np != null)
+                        (p = np).next = node;   // stale
+                }
+                else if ((ps = p.status) == 0)
+                    U.compareAndSwapInt(p, WSTATUS, 0, WAITING);
+                else if (ps == CANCELLED) {
+                    if ((pp = p.prev) != null) {
+                        node.prev = pp;
+                        pp.next = node;
+                    }
+                }
+                else {
+                    long time;
+                    if (deadline == 0L)
+                        time = 0L;
+                    else if ((time = deadline - System.nanoTime()) <= 0L)
+                        return cancelWaiter(node, node, false);
+                    Thread wt = Thread.currentThread();
+                    U.putObject(wt, PARKBLOCKER, this);
+                    node.thread = wt;
+                    if (p.status < 0 &&
+                        (p != h || (state & ABITS) == WBIT) &&
+                        whead == h && node.prev == p)
+                        U.park(false, time);
+                    node.thread = null;
+                    U.putObject(wt, PARKBLOCKER, null);
+                    if (interruptible && Thread.interrupted())
+                        return cancelWaiter(node, node, true);
+                }
             }
         }
     }
@@ -1253,22 +1288,19 @@ private long cancelWaiter(WNode node, WNode group, boolean interrupted) {
         if (node != null && group != null) {
             Thread w;
             node.status = CANCELLED;
-            node.thread = null;
             // unsplice cancelled nodes from group
             for (WNode p = group, q; (q = p.cowait) != null;) {
-                if (q.status == CANCELLED)
-                    U.compareAndSwapObject(p, WNEXT, q, q.next);
+                if (q.status == CANCELLED) {
+                    U.compareAndSwapObject(p, WCOWAIT, q, q.cowait);
+                    p = group; // restart
+                }
                 else
                     p = q;
             }
             if (group == node) {
-                WNode r; // detach and wake up uncancelled co-waiters
-                while ((r = node.cowait) != null) {
-                    if (U.compareAndSwapObject(node, WCOWAIT, r, r.cowait) &&
-                        (w = r.thread) != null) {
-                        r.thread = null;
-                        U.unpark(w);
-                    }
+                for (WNode r = group.cowait; r != null; r = r.cowait) {
+                    if ((w = r.thread) != null)
+                        U.unpark(w);       // wake up uncancelled co-waiters
                 }
                 for (WNode pred = node.prev; pred != null; ) { // unsplice
                     WNode succ, pp;        // find valid successor
diff --git a/src/main/java/jsr166e/extra/AtomicDouble.java b/src/main/java/jsr166e/extra/AtomicDouble.java
index 4a17613567191..b3976589ff958 100644
--- a/src/main/java/jsr166e/extra/AtomicDouble.java
+++ b/src/main/java/jsr166e/extra/AtomicDouble.java
@@ -212,6 +212,8 @@ public double doubleValue() {
     /**
      * Saves the state to a stream (that is, serializes it).
      *
+     * @param s the stream
+     * @throws java.io.IOException if an I/O error occurs
      * @serialData The current value is emitted (a {@code double}).
      */
     private void writeObject(java.io.ObjectOutputStream s)
@@ -223,6 +225,10 @@ private void writeObject(java.io.ObjectOutputStream s)
 
     /**
      * Reconstitutes the instance from a stream (that is, deserializes it).
+     * @param s the stream
+     * @throws ClassNotFoundException if the class of a serialized object
+     *         could not be found
+     * @throws java.io.IOException if an I/O error occurs
      */
     private void readObject(java.io.ObjectInputStream s)
         throws java.io.IOException, ClassNotFoundException {
diff --git a/src/main/java/jsr166e/extra/AtomicDoubleArray.java b/src/main/java/jsr166e/extra/AtomicDoubleArray.java
index 8d56c51f031a5..33b10f825650f 100644
--- a/src/main/java/jsr166e/extra/AtomicDoubleArray.java
+++ b/src/main/java/jsr166e/extra/AtomicDoubleArray.java
@@ -237,6 +237,8 @@ public String toString() {
     /**
      * Saves the state to a stream (that is, serializes it).
      *
+     * @param s the stream
+     * @throws java.io.IOException if an I/O error occurs
      * @serialData The length of the array is emitted (int), followed by all
      *             of its elements (each a {@code double}) in the proper order.
      */
@@ -255,6 +257,10 @@ private void writeObject(java.io.ObjectOutputStream s)
 
     /**
      * Reconstitutes the instance from a stream (that is, deserializes it).
+     * @param s the stream
+     * @throws ClassNotFoundException if the class of a serialized object
+     *         could not be found
+     * @throws java.io.IOException if an I/O error occurs
      */
     private void readObject(java.io.ObjectInputStream s)
         throws java.io.IOException, ClassNotFoundException {
diff --git a/src/main/java/jsr166e/extra/SequenceLock.java b/src/main/java/jsr166e/extra/SequenceLock.java
index cc997b6d9d7bb..ed2a8c80a4aa6 100644
--- a/src/main/java/jsr166e/extra/SequenceLock.java
+++ b/src/main/java/jsr166e/extra/SequenceLock.java
@@ -257,8 +257,10 @@ private void readObject(ObjectInputStream s)
 
     /**
      * Creates an instance of {@code SequenceLock} that will retry
-     * attempts to acquire the lock at least the given number times
+     * attempts to acquire the lock at least the given number of times
      * before blocking.
+     *
+     * @param spins the number of times before blocking
      */
     public SequenceLock(int spins) { sync = new Sync(spins); }
 
@@ -508,7 +510,7 @@ public boolean tryLock(long timeout, TimeUnit unit)
      * Throws UnsupportedOperationException. SequenceLocks
      * do not support Condition objects.
      *
-     * @throws UnsupportedOperationException
+     * @throws UnsupportedOperationException always
      */
     public Condition newCondition() {
         throw new UnsupportedOperationException();
diff --git a/src/main/java/jsr166y/CountedCompleter.java b/src/main/java/jsr166y/CountedCompleter.java
index b23db5311ddca..7e742409a36d2 100644
--- a/src/main/java/jsr166y/CountedCompleter.java
+++ b/src/main/java/jsr166y/CountedCompleter.java
@@ -680,7 +680,7 @@ protected final boolean exec() {
     }
 
     /**
-     * Returns the result of the computation. By default
+     * Returns the result of the computation.  By default,
      * returns {@code null}, which is appropriate for {@code Void}
      * actions, but in other cases should be overridden, almost
      * always to return a field or function of a field that
diff --git a/src/main/java/jsr166y/ForkJoinPool.java b/src/main/java/jsr166y/ForkJoinPool.java
index 5ebd02761857f..211722d45487b 100644
--- a/src/main/java/jsr166y/ForkJoinPool.java
+++ b/src/main/java/jsr166y/ForkJoinPool.java
@@ -2127,10 +2127,10 @@ final void helpQuiescePool(WorkQueue w) {
                     w.runSubtask(t);
                 }
             }
-            else if (active) {       // decrement active count without queuing
+            else if (active) {      // decrement active count without queuing
                 long nc = (c = ctl) - AC_UNIT;
                 if ((int)(nc >> AC_SHIFT) + (config & SMASK) == 0)
-                    return;          // bypass decrement-then-increment
+                    return;         // bypass decrement-then-increment
                 if (U.compareAndSwapLong(this, CTL, c, nc))
                     active = false;
             }
diff --git a/src/main/java/jsr166y/ForkJoinTask.java b/src/main/java/jsr166y/ForkJoinTask.java
index df5739ee12a6b..ab56eca152ed0 100644
--- a/src/main/java/jsr166y/ForkJoinTask.java
+++ b/src/main/java/jsr166y/ForkJoinTask.java
@@ -395,11 +395,13 @@ static final class ExceptionNode extends WeakReference<ForkJoinTask<?>> {
         final Throwable ex;
         ExceptionNode next;
         final long thrower;  // use id not ref to avoid weak cycles
+        final int hashCode;  // store task hashCode before weak ref disappears
         ExceptionNode(ForkJoinTask<?> task, Throwable ex, ExceptionNode next) {
             super(task, exceptionTableRefQueue);
             this.ex = ex;
             this.next = next;
             this.thrower = Thread.currentThread().getId();
+            this.hashCode = System.identityHashCode(task);
         }
     }
 
@@ -561,9 +563,9 @@ else if (ps.length == 1 && ps[0] == Throwable.class)
     private static void expungeStaleExceptions() {
         for (Object x; (x = exceptionTableRefQueue.poll()) != null;) {
             if (x instanceof ExceptionNode) {
-                ForkJoinTask<?> key = ((ExceptionNode)x).get();
+                int hashCode = ((ExceptionNode)x).hashCode;
                 ExceptionNode[] t = exceptionTable;
-                int i = System.identityHashCode(key) & (t.length - 1);
+                int i = hashCode & (t.length - 1);
                 ExceptionNode e = t[i];
                 ExceptionNode pred = null;
                 while (e != null) {
diff --git a/src/main/java/jsr166y/RecursiveTask.java b/src/main/java/jsr166y/RecursiveTask.java
index eba46631dc527..0192966418907 100644
--- a/src/main/java/jsr166y/RecursiveTask.java
+++ b/src/main/java/jsr166y/RecursiveTask.java
@@ -15,7 +15,7 @@
  * class Fibonacci extends RecursiveTask<Integer> {
  *   final int n;
  *   Fibonacci(int n) { this.n = n; }
- *   Integer compute() {
+ *   protected Integer compute() {
  *     if (n <= 1)
  *       return n;
  *     Fibonacci f1 = new Fibonacci(n - 1);
diff --git a/src/main/java/jsr166y/ThreadLocalRandom.java b/src/main/java/jsr166y/ThreadLocalRandom.java
index 032f77a04bc59..fe6fc8ed65413 100644
--- a/src/main/java/jsr166y/ThreadLocalRandom.java
+++ b/src/main/java/jsr166y/ThreadLocalRandom.java
@@ -107,9 +107,9 @@ protected int next(int bits) {
      *
      * @param least the least value returned
      * @param bound the upper bound (exclusive)
+     * @return the next value
      * @throws IllegalArgumentException if least greater than or equal
      * to bound
-     * @return the next value
      */
     public int nextInt(int least, int bound) {
         if (least >= bound)
diff --git a/src/main/java/jsr166y/package-info.java b/src/main/java/jsr166y/package-info.java
index b6e19b97965f1..980280390a3f4 100644
--- a/src/main/java/jsr166y/package-info.java
+++ b/src/main/java/jsr166y/package-info.java
@@ -25,6 +25,4 @@
  * complete the tasks.  In general, the most efficient ForkJoinTasks
  * are those that directly implement this algorithmic design pattern.
  */
-
-// Built on 2013-07-10
 package jsr166y;