2011-02-25  Sheriff Bot  <webkit.review.bot@gmail.com>

        Unreviewed, rolling out r79627.
        http://trac.webkit.org/changeset/79627
        https://bugs.webkit.org/show_bug.cgi?id=55274

        broke worker tests (Requested by olliej on #webkit).

        * JavaScriptCore.exp:
        * JavaScriptCore.vcproj/JavaScriptCore/JavaScriptCore.def:
        * runtime/Heap.cpp:
        (JSC::Heap::allocate):
        * runtime/Heap.h:
        * runtime/JSCell.h:
        (JSC::JSCell::JSCell::operator new):
        (JSC::JSCell::MarkedSpace::sizeClassFor):
        (JSC::JSCell::MarkedSpace::allocate):
        * runtime/MarkedBlock.h:
        * runtime/MarkedSpace.cpp:
        (JSC::MarkedSpace::MarkedSpace):
        (JSC::MarkedSpace::allocateBlock):
        (JSC::MarkedSpace::reset):
        * runtime/MarkedSpace.h:
        (JSC::MarkedSpace::SizeClass::SizeClass):

2011-02-25  Michael Saboff  <msaboff@apple.com>

        Reviewed by Darin Adler.

        Leak in JSParser::Scope of ScopeLabelInfo Vector
        https://bugs.webkit.org/show_bug.cgi?id=55249

        Changed m_labels to be an OwnPtr<>.  Added VectorTraits
        and Scope copy constructor to support this change.

        * parser/JSParser.cpp:
        (JSC::JSParser::Scope::~Scope):

2011-02-25  Fumitoshi Ukai  <ukai@chromium.org>

        Reviewed by Adam Barth.

        WebSocket uses insecure random numbers
        https://bugs.webkit.org/show_bug.cgi?id=54714

        * JavaScriptCore.exp: Export WTF::cryptographicallyRandomNumber()

2011-02-25  Patrick Gansterer  <paroga@webkit.org>

        Reviewed by Adam Roben.

        Move timeBeginPeriod into OS(WINDOWS) section
        https://bugs.webkit.org/show_bug.cgi?id=55247

        * jsc.cpp:
        (main): timeBeginPeriod is available on all Windows versions and not compiler specific.

2011-02-25  Patrick Gansterer  <paroga@webkit.org>

        Unreviewed WinCE build fix for r79695.

        * jsc.cpp:
        (main): SetErrorMode isn't available on WinCE.

2011-02-25  Adam Roben  <aroben@apple.com>

        Work around Cygwin's crash-suppression behavior

        Cygwin calls ::SetErrorMode(SEM_FAILCRITICALERRORS), which any processes it launches will
        inherit. This is bad for testing/debugging, as it causes the post-mortem debugger not to be
        invoked. (Cygwin does this because it makes crashes more UNIX-y.) We reset the error mode
        when our test apps launch to work around Cygwin's behavior.

        Fixes <http://webkit.org/b/55222> Test apps crash silently (without invoking post-mortem
        debugger) when launched from Cygwin 1.7

        Reviewed by Darin Adler.

        * API/tests/testapi.c: Added a now-needed #include.
        (main):
        * jsc.cpp:
        (main):
        Call ::SetErrorMode(0) to undo Cygwin's folly.

        * JavaScriptCore.vcproj/testapi/testapiCommon.vsprops: Define NOMINMAX like many of our
        other projects do so that windows.h won't define min/max macros that interfere with
        std::numeric_limits<T>::min/max.

2011-02-24  Adam Barth  <abarth@webkit.org>

        Reviewed by Eric Seidel.

        Add GYP project for JavaScriptCore
        https://bugs.webkit.org/show_bug.cgi?id=55027

        Again, this GYP files is very rough, but it succeeds in building
        JavaScriptCore.  There's a lot more work to do here, especially in the
        area of sharing with JavaScriptGlue.gyp.  This patch is more of a
        checkpoint so that other folks can help out if they wish.

        * gyp: Added.
        * gyp/JavaScriptCore.gyp: Added.
        * gyp/generate-derived-sources.sh: Added.

2011-02-24  Adam Barth  <abarth@webkit.org>

        Reviewed by Eric Seidel.

        Add missing files to JavaScriptCore.gypi
        https://bugs.webkit.org/show_bug.cgi?id=55193

        I forgot to add mm files in my previous patch.

        * JavaScriptCore.gyp/JavaScriptCore.gyp:
        * JavaScriptCore.gypi:

2011-02-24  Adam Barth  <abarth@webkit.org>

        Reviewed by Eric Seidel.

        Remove unused parameter name in GCActivityCallback.cpp
        https://bugs.webkit.org/show_bug.cgi?id=55194

        This change is not strictly required for the GYP-based build system,
        but I noticed this error when working on the new build system.

        * runtime/GCActivityCallback.cpp:
        (JSC::DefaultGCActivityCallback::DefaultGCActivityCallback):

2011-02-24  James Robinson  <jamesr@chromium.org>

        Reviewed by Darin Fisher.

        Add a USE() macro to control use of the built-in UTF8 codec
        https://bugs.webkit.org/show_bug.cgi?id=55189

        Defaults USE(BUILTIN_UTF8_CODEC) to true for all platforms except chromium, which controls the flag via features.gypi.

        * wtf/Platform.h:

2011-02-24  Geoffrey Garen  <ggaren@apple.com>

        Reviewed by Darin Adler.

        Variable-sized allocation (but still capped at 64 bytes)
        https://bugs.webkit.org/show_bug.cgi?id=55159
        
        SunSpider reports no change.

        * JavaScriptCore.exp: Some day, I hope not to have to edit this file.

        * runtime/Heap.cpp:
        (JSC::Heap::allocateSlowCase): Split allocation into a fast and slow
        case, so the fast case can inline size class selection and turn it into
        a compile-time constant.
        
        Changed the collect-on-every allocation debugging switch to collect only
        on every slow allocation, so you can still flip the switch without
        recompiling the world. This may also be preferable for debugging purposes,
        since collecting after every single allocation can be unusably slow,
        and can mask problems by running destructors early.

        * runtime/Heap.h: Ditto.

        * runtime/JSCell.h:
        (JSC::JSCell::MarkedSpace::sizeClassFor):
        (JSC::JSCell::Heap::allocate):
        (JSC::JSCell::JSCell::operator new): The inlining mentioned above.

        * runtime/MarkedBlock.h: Dropped the block size from 256KB to 16KB. With
        multiple size classes, allocating a full 256KB for the first allocation
        in a given class can be pathologically wasteful. (8KB, or 4KB Mac and
        8KB Windows, would be even better, but that seems to be a peformance
        regression for now.)
        
        * runtime/MarkedSpace.cpp:
        (JSC::MarkedSpace::MarkedSpace):
        (JSC::MarkedSpace::allocateBlock):
        (JSC::MarkedSpace::reset): There's more than one size class now, and its
        cell size is not constant.

        * runtime/MarkedSpace.h:
        (JSC::MarkedSpace::SizeClass::SizeClass): Ditto.

2011-02-23  Oliver Hunt  <oliver@apple.com>

        Reviewed by Geoffrey Garen.

        Make WeakGCMap use new handle infrastructure
        https://bugs.webkit.org/show_bug.cgi?id=55100

        Remove old WeakGCMap implementation and move over to new handle
        based logic.

        This has a number of benefits, most notably it makes a WeakGCMap
        always reflect the true state of the world by as all entries are
        removed at the first gc cycle that makes them dead.  This allows
        us to get rid of code in a wide variety of objects where the only
        purpose was to remove themselves from maps.

        It also means that we no longer need to have special "unchecked"
        versions of any functions on WeakGCMap.  Alas in order to maintain
        compatibility with the JSWeakObjectMapClear API it is still
        necessary to have an api that resembles uncheckedRemove, this is
        now deprecatedRemove and will be dealt with in a later patch.

        In order to get correct semantics in WeakGCMap we need more
        contextual information in the finalizer, so we've added an
        abstract class based finaliser and a context parameter to the
        calls.

        The new an improved WeakGCMap also results in sigificantly more
        churn in the weak handle lists so exposed some potential problems
        during the post mark phase which have been rectified as well.

        * API/JSWeakObjectMapRefPrivate.cpp:
        * API/JSWeakObjectMapRefPrivate.h:
        * runtime/Heap.cpp:
        (JSC::Heap::globalObjectCount):
        (JSC::Heap::protectedGlobalObjectCount):
        * runtime/JSGlobalData.cpp:
        (JSC::JSGlobalData::JSGlobalData):
        * runtime/JSGlobalData.h:
        * runtime/JSGlobalObject.cpp:
        (JSC::JSGlobalObject::~JSGlobalObject):
        (JSC::JSGlobalObject::init):
        * runtime/WeakGCMap.h:
        (JSC::WeakGCMap::iterator::iterator):
        (JSC::WeakGCMap::iterator::get):
        (JSC::WeakGCMap::iterator::getSlot):
        (JSC::WeakGCMap::iterator::operator++):
        (JSC::WeakGCMap::iterator::operator==):
        (JSC::WeakGCMap::iterator::operator!=):
        (JSC::WeakGCMap::WeakGCMap):
        (JSC::WeakGCMap::isEmpty):
        (JSC::WeakGCMap::clear):
        (JSC::WeakGCMap::get):
        (JSC::WeakGCMap::getSlot):
        (JSC::WeakGCMap::set):
        (JSC::WeakGCMap::take):
        (JSC::WeakGCMap::size):
        (JSC::WeakGCMap::deprecatedRemove):
        (JSC::WeakGCMap::begin):
        (JSC::WeakGCMap::end):
        (JSC::WeakGCMap::~WeakGCMap):
        (JSC::WeakGCMap::finalize):
        * runtime/WeakGCPtr.h:
        (JSC::WeakGCPtr::WeakGCPtr):
        (JSC::WeakGCPtr::set):

2011-02-24  Oliver Hunt  <oliver@apple.com>

        Reviewed by Gavin Barraclough.

        Make weaklist processing deal with weak handles being removed during the iteration
        https://bugs.webkit.org/show_bug.cgi?id=55105

        It is possible for the handle heap to end up in a broken state if
        a handle's finalizer removes either the current or next handle
        to be visited during the post-gc cleanup.  This patch removes that
        problem by allowing the deallocate(Node*) routine to update the
        iterator if it is called during finalization.

        * collector/handles/HandleHeap.cpp:
        (JSC::HandleHeap::HandleHeap):
        (JSC::HandleHeap::updateAfterMark):
        (JSC::HandleHeap::clearWeakPointers):
        (JSC::HandleHeap::writeBarrier):
        (JSC::HandleHeap::protectedGlobalObjectCount):
        * collector/handles/HandleHeap.h:
        (JSC::Finalizer::~Finalizer):
        (JSC::HandleHeap::getFinalizer):
        (JSC::HandleHeap::deallocate):
        (JSC::HandleHeap::makeWeak):
        (JSC::HandleHeap::makeSelfDestroying):
        (JSC::HandleHeap::Node::Node):
        (JSC::HandleHeap::Node::setFinalizer):
        (JSC::HandleHeap::Node::finalizer):
        (JSC::HandleHeap::Node::finalizerContext):
        * interpreter/RegisterFile.cpp:
        (JSC::RegisterFile::setGlobalObject):
        (JSC::GlobalObjectNotifier::finalize):
        (JSC::RegisterFile::globalObjectCollectedNotifier):
        * interpreter/RegisterFile.h:
        (JSC::RegisterFile::RegisterFile):
        * runtime/Heap.cpp:
        (JSC::Heap::destroy):
        * runtime/WeakGCPtr.h:
        (JSC::WeakGCPtr::WeakGCPtr):
        (JSC::WeakGCPtr::set):

2011-02-24  Michael Saboff  <msaboff@apple.com>

        Reviewed by Oliver Hunt.

        PatternAlternative leaked in YarrPatternConstructor::atomParenthesesEnd()
        https://bugs.webkit.org/show_bug.cgi?id=55156

        Added code to delete unneeded PatternAlternative after it is removed
        from m_alternatives Vector.

        * yarr/YarrPattern.cpp:
        (JSC::Yarr::YarrPatternConstructor::atomParenthesesEnd):

2011-02-24  Eric Seidel  <eric@webkit.org>

        Reviewed by Anders Carlsson.

        VectorBuffer should not call malloc(0)
        https://bugs.webkit.org/show_bug.cgi?id=55091

        Turns out the malloc() call which was so hot in:
        https://bugs.webkit.org/show_bug.cgi?id=55005
        was actually just malloc(0).

        We shouldn't be calling malloc(0) anyway, since there is no need to
        and it might actually do work on some systems.
        I believe on Mac it ends up taking the standard spinlocks (expensive)
        and the code on Brew actually does a malloc(1) instead.  Neither is desirable.

        * wtf/Vector.h:
        (WTF::VectorBufferBase::allocateBuffer):
        (WTF::VectorBufferBase::tryAllocateBuffer):

2011-02-24  Patrick Gansterer  <paroga@webkit.org>

        Reviewed by Darin Adler.

        Remove obsolete PLATFORM(CI)
        https://bugs.webkit.org/show_bug.cgi?id=55082

        * wtf/Platform.h:

2011-02-24  Martin Robinson  <mrobinson@igalia.com>

        Reviewed by Xan Lopez.

        [GTK] Remove the GFile GOwnPtr specialization
        https://bugs.webkit.org/show_bug.cgi?id=55154

        Remove the GFile specialization of GOwnPtr. It's sufficient to use GRefPtr
        to track GFiles since they are just regular reference-counted GObjects.

        * wtf/gobject/GOwnPtr.cpp: Remove GFile specialization.
        * wtf/gobject/GOwnPtr.h: Ditto.

2011-02-24  Patrick Gansterer  <paroga@webkit.org>

        Reviewed by Eric Seidel.

        Rename PLATFORM(SKIA) to USE(SKIA)
        https://bugs.webkit.org/show_bug.cgi?id=55090

        * wtf/Platform.h:

2011-02-24  Patrick Gansterer  <paroga@webkit.org>

        Reviewed by Alexey Proskuryakov.

        Remove pthreads dependecy for JSLock
        https://bugs.webkit.org/show_bug.cgi?id=54832

        JSLock is only needed to support an obsolete execution model where JavaScriptCore
        automatically protected against concurrent access from multiple threads.
        So it's safe to disable it on non-mac platforms where we don't have native pthreads.

        * runtime/JSLock.cpp:

2011-02-24  Chao-ying Fu  <fu@mips.com>

        Reviewed by Eric Seidel.

        Fix MIPS build with new patchOffsetPut/GetByIdPropertyMapOffset1/2 values
        https://bugs.webkit.org/show_bug.cgi?id=54997

        * jit/JIT.h:
        * jit/JITStubs.cpp:
        (JSC::JITThunks::JITThunks):

2011-02-24  Andras Becsi  <abecsi@webkit.org>

        Reviewed by Laszlo Gombos.

        [Qt] MinGW build fails to link
        https://bugs.webkit.org/show_bug.cgi?id=55050

        Prepend the libraries of subcomponents instead of appending them
        to fix the library order according to the dependency of the libraries

        * JavaScriptCore.pri: rename addJavaScriptCore to prependJavaScriptCore
        * jsc.pro: ditto

2011-02-24  Eric Seidel  <eric@webkit.org>

        Reviewed by Adam Barth.

        Deque<T> should support inline capacity
        https://bugs.webkit.org/show_bug.cgi?id=55032

        The title says it all.  There are currently no places
        which use this code yet, however it's been tested in conjunction
        with code for bug 55005.

        This also adds an ASSERT that capacity is never 1.  If you were able
        to set the capacity equal to 1, the Deque would just get confused
        and happily append your item but still think it had size 0.

        * wtf/Deque.h:
        (WTF::DequeIterator::DequeIterator):
        (WTF::DequeConstIterator::DequeConstIterator):
        (WTF::DequeReverseIterator::DequeReverseIterator):
        (WTF::DequeConstReverseIterator::DequeConstReverseIterator):
        (WTF::::checkValidity):
        (WTF::::checkIndexValidity):
        (WTF::::invalidateIterators):
        (WTF::::Deque):
        (WTF::deleteAllValues):
        (WTF::::operator):
        (WTF::::destroyAll):
        (WTF::::~Deque):
        (WTF::::swap):
        (WTF::::clear):
        (WTF::::findIf):
        (WTF::::expandCapacityIfNeeded):
        (WTF::::expandCapacity):
        (WTF::::takeFirst):
        (WTF::::append):
        (WTF::::prepend):
        (WTF::::removeFirst):
        (WTF::::remove):
        (WTF::::addToIteratorsList):
        (WTF::::removeFromIteratorsList):
        (WTF::::DequeIteratorBase):
        (WTF::::~DequeIteratorBase):
        (WTF::::isEqual):
        (WTF::::increment):
        (WTF::::decrement):
        (WTF::::after):
        (WTF::::before):
        * wtf/Vector.h:

2011-02-22  Adam Barth  <abarth@webkit.org>

        Reviewed by Ojan Vafai. 

        Add missing files to JavaScriptCore.gypi 
        https://bugs.webkit.org/show_bug.cgi?id=55020 

        gypi files are supposed to list every file under the sun.  This patch 
        adds some missing files and sorts the rest. 

        * JavaScriptCore.gypi: 

2011-02-23  Geoffrey Garen  <ggaren@apple.com>

        Reviewed by Darin Adler.

        Refactored MarkedSpace to operate in terms of size classes
        https://bugs.webkit.org/show_bug.cgi?id=55106
        
        SunSpider reports no change.

        * runtime/JSCell.h:
        (JSC::JSCell::MarkedSpace::sizeClassFor):
        (JSC::JSCell::MarkedSpace::allocate): Delegate allocation based on size
        class. Since these functions are inline, the compiler can constant fold
        them.

        * runtime/MarkedBlock.h:
        (JSC::MarkedBlock::cellSize):
        (JSC::MarkedBlock::size): Factored out a cellSize() helper.

        * runtime/MarkedSpace.cpp:
        (JSC::MarkedSpace::allocateBlock):
        (JSC::MarkedSpace::allocateFromSizeClass):
        (JSC::MarkedSpace::shrink):
        (JSC::MarkedSpace::reset):
        * runtime/MarkedSpace.h:
        (JSC::MarkedSpace::SizeClass::SizeClass):
        (JSC::MarkedSpace::SizeClass::reset): Changed to operate in terms of
        abstract SizeClass objects, which are independent linked lists of blocks
        of a certain size class, instead of a single m_heap object.

2011-02-23  Adam Barth  <abarth@webkit.org>

        Reviewed by James Robinson.

        [Chromium] Use WebKitClient for OSRandomSource instead of trying to talk to the file system in the sandbox
        https://bugs.webkit.org/show_bug.cgi?id=55093

        Exclude OSRandomSource.cpp from the Chromium build.  This function is
        implemented in WebKit/chromium/src instead.

        * JavaScriptCore.gyp/JavaScriptCore.gyp:

2011-02-23  Oliver Hunt  <oliver@apple.com>

        Roll out r64156 as it introduces incorrect behaviour.

        * runtime/JSByteArray.h:
        (JSC::JSByteArray::setIndex):

2011-02-23  Geoffrey Garen  <ggaren@apple.com>

        Reviewed by Oliver Hunt.

        Moved the "nextAtom" allocation pointer into MarkedBlock for better encapsulation
        https://bugs.webkit.org/show_bug.cgi?id=55079
        
        SunSpider reports no change.

        * runtime/Heap.cpp:
        (JSC::Heap::reset): Moved Zombie sweeping here, up from MarkedSpace,
        since we want Heap to logically control MarkedSpace. MarkedSpace should
        never choose to sweep itself.

        * runtime/JSCell.h:
        (JSC::JSCell::MarkedBlock::allocate): Updated for nextAtom becoming a
        member of MarkedBlock. No need to reset nextAtom to firstAtom() when
        we reach the end of a block, since there's now an explicit reset pass
        during GC.

        * runtime/MarkedBlock.cpp:
        (JSC::MarkedBlock::MarkedBlock):
        * runtime/MarkedBlock.h:
        (JSC::MarkedBlock::reset): Added the nextAtom data member, and reordered
        some data members to improve cache locality.

        * runtime/MarkedSpace.cpp:
        (JSC::MarkedSpace::MarkedSpace):
        (JSC::MarkedSpace::allocate):
        (JSC::MarkedSpace::reset):
        * runtime/MarkedSpace.h:
        (JSC::CollectorHeap::CollectorHeap): Removed nextAtom, and added an
        explicit reset pass.

2011-02-23  James Robinson  <jamesr@chromium.org>

        Unreviewed, rolling out r79428.
        http://trac.webkit.org/changeset/79428
        https://bugs.webkit.org/show_bug.cgi?id=54714

        Does not work in the Chromium sandbox

        * JavaScriptCore.exp:

2011-02-23  Adam Roben  <aroben@apple.com>

        Fix an off-by-one error in JSC::appendSourceToError

        Looks like this bug has been around since the code was first added in r35245.

        Fixes <http://webkit.org/b/55052> <rdar://problem/9043512> Crash in JSC::appendSourceToError
        when running fast/dom/objc-big-method-name.html on Windows with full page heap enabled

        Reviewed by Darin Adler.

        * interpreter/Interpreter.cpp:
        (JSC::appendSourceToError): When trimming whitespace off the end of the string, examine the
        character at stop-1 rather than at stop. At this point in the code, stop represents the
        index just past the end of the characters we care about, and can even be just past the end
        of the entire data buffer.

2011-02-23  Geoffrey Garen  <ggaren@apple.com>

        Reviewed by Darin Adler.
        
        Rolled back in r79367 with SnowLeopard Release bot crash fixed.
        https://bugs.webkit.org/show_bug.cgi?id=54999
        
        The crash was caused by failure to update the "nextBlock" pointer when
        removing a block from the list while shrinking. The fix is to update the
        "nextBlock" pointer.
        
        This crash was very rare because it only happened in cases where the very
        first block in the heap contained no marked cells.

2011-02-23  Dan Bernstein  <mitz@apple.com>

        Reviewed by Gavin Barraclough.

        Include frame numbers in backtraces.
        https://bugs.webkit.org/show_bug.cgi?id=55060

        * wtf/Assertions.cpp:

2011-02-23  Xan Lopez  <xlopez@igalia.com>

        Reviewed by Gavin Barraclough.

        latest jsc for armv7 crashes in sunspider tests
        https://bugs.webkit.org/show_bug.cgi?id=54667

        Update JIT offset values in ARMv7 after r78732. Fixes crashes in
        SunSpider and JavaScript tests.

        * jit/JIT.h: update values.

2011-02-23  Sheriff Bot  <webkit.review.bot@gmail.com>

        Unreviewed, rolling out r79418.
        http://trac.webkit.org/changeset/79418
        https://bugs.webkit.org/show_bug.cgi?id=55043

        "breaks shlib linux build" (Requested by morrita on #webkit).

        * JavaScriptCore.gyp/JavaScriptCore.gyp:
        * JavaScriptCore.gypi:

2011-02-23  Patrick Gansterer  <paroga@webkit.org>

        Reviewed by Alexey Proskuryakov.

        Use DEFINE_STATIC_LOCAL for ignoreSetMutex in Structure.cpp
        https://bugs.webkit.org/show_bug.cgi?id=54831

        * runtime/InitializeThreading.cpp:
        (JSC::initializeThreadingOnce):
        * runtime/Structure.cpp:
        (JSC::ignoreSetMutex):
        (JSC::Structure::Structure):
        (JSC::Structure::~Structure):
        (JSC::Structure::initializeThreading):
        * runtime/Structure.h:

2011-02-23  Patrick Gansterer  <paroga@webkit.org>

        Reviewed by Darin Adler.

        Rename PLATFORM(CF) to USE(CF)
        https://bugs.webkit.org/show_bug.cgi?id=53540

        * runtime/DatePrototype.cpp:
        * runtime/GCActivityCallbackCF.cpp:
        * runtime/JSGlobalData.cpp:
        (JSC::JSGlobalData::JSGlobalData):
        * wtf/CurrentTime.cpp:
        * wtf/Platform.h:
        * wtf/text/AtomicString.h:
        * wtf/text/StringImpl.h:
        (WTF::StringImpl::computeHash):
        * wtf/text/WTFString.h:
        * wtf/unicode/icu/CollatorICU.cpp:
        (WTF::Collator::userDefault):

2011-02-23  Fumitoshi Ukai  <ukai@chromium.org>

        Unreviewed build fix for Windows.

        WebSocket uses insecure random numbers
        https://bugs.webkit.org/show_bug.cgi?id=54714

        * JavaScriptCore.vcproj/JavaScriptCore/JavaScriptCore.def: Export WTF::cryptographicallyRandomNumber()

2011-02-23  Fumitoshi Ukai  <ukai@chromium.org>

        Reviewed by Adam Barth.

        WebSocket uses insecure random numbers
        https://bugs.webkit.org/show_bug.cgi?id=54714

        * JavaScriptCore.exp: Export WTF::cryptographicallyRandomNumber()

2011-02-22  Adam Barth  <abarth@webkit.org>

        Reviewed by Ojan Vafai.

        Add missing files to JavaScriptCore.gypi
        https://bugs.webkit.org/show_bug.cgi?id=55020

        gypi files are supposed to list every file under the sun.  This patch
        adds some missing files and sorts the rest.

        * JavaScriptCore.gypi:

2011-02-22  Sheriff Bot  <webkit.review.bot@gmail.com>

        Unreviewed, rolling out r79367.
        http://trac.webkit.org/changeset/79367
        https://bugs.webkit.org/show_bug.cgi?id=55012

        all layout tests are crashing on Snow Leopard (Requested by
        rniwa on #webkit).

        * GNUmakefile.am:
        * JavaScriptCore.gypi:
        * JavaScriptCore.vcproj/WTF/WTF.vcproj:
        * JavaScriptCore.xcodeproj/project.pbxproj:
        * runtime/MarkedBlock.cpp:
        (JSC::MarkedBlock::MarkedBlock):
        * runtime/MarkedBlock.h:
        * runtime/MarkedSpace.cpp:
        (JSC::MarkedSpace::destroy):
        (JSC::MarkedSpace::allocateBlock):
        (JSC::MarkedSpace::freeBlock):
        (JSC::MarkedSpace::allocate):
        (JSC::MarkedSpace::shrink):
        (JSC::MarkedSpace::reset):
        * runtime/MarkedSpace.h:
        (JSC::CollectorHeap::collectorBlock):
        * wtf/CMakeLists.txt:
        * wtf/DoublyLinkedList.h: Removed.

2011-02-22  Geoffrey Garen  <ggaren@apple.com>

        Reviewed by Oliver Hunt.

        Manage MarkedBlocks in a linked list instead of a vector, so arbitrary removal is O(1)
        https://bugs.webkit.org/show_bug.cgi?id=54999
        
        SunSpider reports no change.

        * GNUmakefile.am:
        * JavaScriptCore.gypi:
        * JavaScriptCore.vcproj/WTF/WTF.vcproj:
        * JavaScriptCore.xcodeproj/project.pbxproj: So many build systems, so little time.
        * wtf/CMakeLists.txt:

        * runtime/MarkedBlock.cpp:
        (JSC::MarkedBlock::MarkedBlock):
        * runtime/MarkedBlock.h:
        (JSC::MarkedBlock::setPrev):
        (JSC::MarkedBlock::setNext):
        (JSC::MarkedBlock::prev):
        (JSC::MarkedBlock::next): Added linked list data members and accessors.

        * runtime/MarkedSpace.cpp:
        (JSC::MarkedSpace::destroy):
        (JSC::MarkedSpace::allocateBlock): Stop using vector, since it doesn't exist anymore.

        (JSC::MarkedSpace::freeBlocks): New helper function for updating relevant
        data structures when freeing blocks.

        (JSC::MarkedSpace::allocate): Updated for nextBlock being a pointer and
        not a vector index.

        (JSC::MarkedSpace::shrink): Construct a temporary list of empties and
        then free them, to avoid modifying our hash table while iterating it.
        This wasn't a concern before because we were using indirect array
        indexing, not direct pointer indexing.

        (JSC::MarkedSpace::reset): Updated for nextBlock being a pointer and
        not a vector index.

        * runtime/MarkedSpace.h:
        (JSC::CollectorHeap::CollectorHeap): Changed data type from vector to linked list.

        * wtf/DoublyLinkedList.h: Added. New linked list class.
        (WTF::::DoublyLinkedList):
        (WTF::::isEmpty):
        (WTF::::head):
        (WTF::::append):
        (WTF::::remove):

2011-02-22  Gavin Barraclough  <barraclough@apple.com>

        Windows build fix.

        * JavaScriptCore.vcproj/JavaScriptCore/JavaScriptCore.def:

2011-02-22  Gavin Barraclough  <barraclough@apple.com>

        Reviewed by Sam Weinig.

        Bug 54988 - Re-create StructureTransitionTable class, encapsulate transition table

        The Structure class keeps a table of transitions to derived Structure types. Since
        this table commonly contains a single entry we employ an optimization where instead
        of holding a map, we may hold a pointer directly to a single instance of the mapped
        type. We use an additional bit of data to flag whether the pointer is currently
        pointing to a table of transitions, or a singleton transition. Previously we had
        commonly used a pattern of storing data in the low bits of pointers, but had moved
        away from this since it causes false leaks to be reported by the leaks tool. However
        in this case, the entries in the map are weak links - this pointer will never be
        responsible for keeping an object alive.  As such we can use this approach provided
        that the bit is set when a table is not in use (otherwise the table would appear to
        be leaked).

        Additionally, the transition table currently allows two entries to exist for a given
        key - one specialized to a particular value, and one not specialized. This is
        unnecessary, wasteful, and a little inconsistent. (If you create an entry for a
        specialized value, then a non-specialized entry, both will exist.  If you create an
        entry for a non-specialized value, then try to create a specialized entry, only a
        non-specialized form will be allowed.)

        This shows a small progression on v8.

        * JavaScriptCore.exp:
        * runtime/JSObject.h:
        (JSC::JSObject::putDirectInternal):
        * runtime/Structure.cpp:
        (JSC::StructureTransitionTable::contains):
        (JSC::StructureTransitionTable::get):
        (JSC::StructureTransitionTable::remove):
        (JSC::StructureTransitionTable::add):
        (JSC::Structure::dumpStatistics):
        (JSC::Structure::Structure):
        (JSC::Structure::~Structure):
        (JSC::Structure::addPropertyTransitionToExistingStructure):
        (JSC::Structure::addPropertyTransition):
        * runtime/Structure.h:
        (JSC::Structure::get):
        * runtime/StructureTransitionTable.h:
        (JSC::StructureTransitionTable::Hash::hash):
        (JSC::StructureTransitionTable::Hash::equal):
        (JSC::StructureTransitionTable::HashTraits::emptyValue):
        (JSC::StructureTransitionTable::HashTraits::constructDeletedValue):
        (JSC::StructureTransitionTable::HashTraits::isDeletedValue):
        (JSC::StructureTransitionTable::StructureTransitionTable):
        (JSC::StructureTransitionTable::~StructureTransitionTable):
        (JSC::StructureTransitionTable::isUsingSingleSlot):
        (JSC::StructureTransitionTable::map):
        (JSC::StructureTransitionTable::setMap):
        (JSC::StructureTransitionTable::singleTransition):
        (JSC::StructureTransitionTable::setSingleTransition):

2011-02-22  Andras Becsi  <abecsi@webkit.org>

        Reviewed by Laszlo Gombos.

        [Qt] Redesign the build system
        https://bugs.webkit.org/show_bug.cgi?id=51339

        Part 2.

        Build WebCore as a static library, compile the WebKit API and WebKit2 API
        in a final step and link to WebKit2, WebCore and JSC libraries to fix
        linking issues resulting from stripped away symbols.

        * JavaScriptCore.pri: Remove the workaround.

2011-02-21  Adam Roben  <aroben@apple.com>

        Fix linker warning on Windows

        r79135 tried to export JSObject::s_info by adding it to JavaScriptCore.def. This is the
        obvious way (since it's how we export functions), but unfortunately it doesn't work correct.
        r79222 made us export it the right way (using the JS_EXPORTDATA macro), but forgot to remove
        it from JavaScriptCore.def. This caused us to get linker warnings about exporting the symbol
        multiple times.

        Rubber-stamped by Anders Carlsson.

        * JavaScriptCore.vcproj/JavaScriptCore/JavaScriptCore.def: Removed JSObject::s_info.

2011-02-21  Brian Weinstein  <bweinstein@apple.com>

        Reviewed by Adam Roben.

        WebResourceCacheManager should be responsible for managing the CFURLCache as well
        as the WebCore memory cache.
        https://bugs.webkit.org/show_bug.cgi?id=54886
        Part of <rdar://problem/8971738>

        Add a new use flag for using the CFURLCache.

        * wtf/Platform.h:

2011-02-21  Xan Lopez  <xlopez@igalia.com>

        Reviewed by Gavin Barraclough.

        Use ASSERT_JIT_OFFSET in JITPropertyAccess32_64.cpp
        https://bugs.webkit.org/show_bug.cgi?id=54901

        * jit/JIT.h: swap actual and expected values in message, they were
        reversed.
        * jit/JITCall32_64.cpp:
        (JSC::JIT::compileOpCall): use ASSERT_JIT_OFFSET instead of
        a simple ASSERT.
        * jit/JITPropertyAccess32_64.cpp:
        (JSC::JIT::emit_op_method_check): ditto.
        (JSC::JIT::compileGetByIdHotPath): ditto.
        (JSC::JIT::compileGetByIdSlowCase): ditto.
        (JSC::JIT::emit_op_put_by_id): ditto.

2011-02-21  Gavin Barraclough  <barraclough@apple.com>

        Ruber stamped by Sam Weinig

        Bug 54899 - Math.LOG10E should be 0.4342944819032518
        This value is quoted in section 15.8.1.5 of the spec.

        * runtime/MathObject.cpp:
        (JSC::MathObject::MathObject):

2011-02-21  Gavin Barraclough  <barraclough@apple.com>

        Reviewed by Sam Weinig.

        Bug 54894 - Make inheritance structure described by ClassInfo match C++ class hierarchy.

        The ClassInfo objects describe an inheritance hierarchy, with each ClassInfo instance
        containing a pointer to its parent class. These links should reflect the inheritance
        hierarchy of C++ classes below JSObject. For the large part it does, but in some cases
        entries in the C++ hierarchy are skipped over. This presently likely doesn't matter,
        since intervening C++ classes may not have ClassInfo - but would be a potential bug
        were ClassInfo were to be added.

        * API/JSCallbackConstructor.cpp:
        * API/JSCallbackFunction.cpp:
        * API/JSCallbackObjectFunctions.h:
        * runtime/Arguments.h:
        * runtime/ArrayPrototype.cpp:
        * runtime/BooleanObject.cpp:
        * runtime/DateInstance.cpp:
        * runtime/DatePrototype.cpp:
        * runtime/ErrorInstance.cpp:
        * runtime/InternalFunction.cpp:
        * runtime/JSActivation.cpp:
        * runtime/JSArray.cpp:
        * runtime/JSFunction.cpp:
        * runtime/JSONObject.cpp:
        * runtime/JSObject.h:
        * runtime/JSZombie.h:
        * runtime/MathObject.cpp:
        * runtime/NativeErrorConstructor.cpp:
        * runtime/NumberConstructor.cpp:
        * runtime/NumberObject.cpp:
        * runtime/RegExpConstructor.cpp:
        * runtime/RegExpObject.cpp:
        * runtime/StringObject.cpp:
        * runtime/StringPrototype.cpp:

2011-02-21  Adam Roben  <aroben@apple.com>

        Export JSObject::s_info from JavaScriptCore.dll

        This matches what we do for all other ClassInfo objects that WebCore needs access to.

        Fixes <http://webkit.org/b/54881> REGRESSION (r79132): Lots of tests crashing in
        JSCell::inherits on Windows

        Reviewed by Sam Weinig.

        * runtime/JSObject.h: Added JS_EXPORTDATA to s_info.

2011-02-21  Kristian Amlie  <kristian.amlie@nokia.com>

        Reviewed by Andreas Kling.

        Switched to compiler based detection, where the error actually is.

        It is not the platform that needs the workaround, it is the compiler.

        QtWebKit fails to compile on Windows XP with msvc-2008
        https://bugs.webkit.org/show_bug.cgi?id=54746

        * bytecode/CodeBlock.h:
        * runtime/RegExpObject.h:

2011-02-20  Gavin Barraclough  <barraclough@apple.com>

        Reviewed by Oliver Hunt.

        https://bugs.webkit.org/show_bug.cgi?id=54839
        Remove PrototypeFunction, NativeFunctionWrapper, and GlobalEvalFunction.

        Historically, Native functions used to be represented by PrototypeFunctions, however
        since introducing call optimizations to the JIT this has used JSFunctions for host
        calls too. At the point this change was made, the interpreter continued to use
        PrototypeFunctions, however since fallback from the JIT to interpreter was introduced
        the interpreter has had to be able to run using host functions represented using
        JSFunctions - leading to an unnecessary and redundant divergence in behaviour between 
        interpreter only builds, and situations where the JIT has fallen back to interpreting.

        NativeFunctionWrapper only existed to select between PrototypeFunction and JSFunction
        for wrappers for host functions, and as such can also be removed.

        GlobalEvalFunction is a redundant wrapper that happens to be derived from
        PrototypeFunction. It existed to hold a reference to the global object - but since all
        functions how derive from JSObjectWithGlobalObject, this no longer requires an
        additional class to provide this functionality.

        * JavaScriptCore.JSVALUE32_64only.exp:
        * JavaScriptCore.JSVALUE64only.exp:
        * JavaScriptCore.xcodeproj/project.pbxproj:
            Removed symbols / references to files.

        * runtime/GlobalEvalFunction.cpp: Removed.
        * runtime/GlobalEvalFunction.h: Removed.
        * runtime/NativeFunctionWrapper.h: Removed.
        * runtime/PrototypeFunction.cpp: Removed.
        * runtime/PrototypeFunction.h: Removed.
            Removed.

        * runtime/Executable.cpp:
        (JSC::NativeExecutable::~NativeExecutable):
        * runtime/Executable.h:
        (JSC::NativeExecutable::create):
        (JSC::NativeExecutable::NativeExecutable):
        (JSC::JSFunction::nativeFunction):
        * runtime/JSFunction.cpp:
        (JSC::callHostFunctionAsConstructor):
        (JSC::JSFunction::JSFunction):
        (JSC::JSFunction::getCallData):
        * runtime/JSFunction.h:
        * runtime/JSGlobalData.cpp:
        (JSC::JSGlobalData::getHostFunction):
        * runtime/JSGlobalData.h:
        (JSC::JSGlobalData::getCTIStub):
            Added interpreter-friendly constructors for NativeExecutables.

        * bytecompiler/BytecodeGenerator.cpp:
        * interpreter/Interpreter.cpp:
        * jit/JITStubs.cpp:
        * jsc.cpp:
        * runtime/ArrayConstructor.cpp:
        * runtime/BooleanPrototype.cpp:
        * runtime/BooleanPrototype.h:
        * runtime/CallData.h:
        * runtime/DateConstructor.cpp:
        * runtime/DateConstructor.h:
        * runtime/ErrorPrototype.cpp:
        * runtime/ErrorPrototype.h:
        * runtime/FunctionPrototype.cpp:
        * runtime/FunctionPrototype.h:
        * runtime/JSGlobalObject.cpp:
        * runtime/JSGlobalObject.h:
        * runtime/JSGlobalObjectFunctions.cpp:
        * runtime/Lookup.cpp:
        * runtime/NumberPrototype.cpp:
        * runtime/NumberPrototype.h:
        * runtime/ObjectConstructor.cpp:
        * runtime/ObjectConstructor.h:
        * runtime/ObjectPrototype.cpp:
        * runtime/ObjectPrototype.h:
        * runtime/RegExpPrototype.cpp:
        * runtime/RegExpPrototype.h:
        * runtime/SmallStrings.h:
        * runtime/StringConstructor.cpp:
        * runtime/StringConstructor.h:
            Removed use of redundant classes.

2011-02-19  Laszlo Gombos  <laszlo.1.gombos@nokia.com>

        Unreviewed build fix for Symbian.

        [Symbian] Revert the removal of linking 
        against hal after r79126.

        Dependency on the hal library can not be removed 
        as it is still used (e.g. in MarkStackSymbian.cpp).

        * JavaScriptCore.pri:

2011-02-19  Gavin Barraclough  <barraclough@apple.com>

        Interpreter build fix.

        * runtime/ArrayConstructor.cpp:
        * runtime/BooleanPrototype.cpp:
        * runtime/DateConstructor.cpp:
        * runtime/ErrorPrototype.cpp:
        * runtime/FunctionPrototype.cpp:
        * runtime/Lookup.cpp:
        * runtime/NumberPrototype.cpp:
        * runtime/ObjectConstructor.cpp:
        * runtime/ObjectPrototype.cpp:
        * runtime/RegExpPrototype.cpp:
        * runtime/StringConstructor.cpp:

2011-02-19  Gavin Barraclough  <barraclough@apple.com>

        Build fix!!

        * JavaScriptCore.exp:

2011-02-19  Gavin Barraclough  <barraclough@apple.com>

        Windows build fix!!

        * JavaScriptCore.vcproj/JavaScriptCore/JavaScriptCore.def:

2011-02-19  Gavin Barraclough  <barraclough@apple.com>

        Windows build fix!

        * JavaScriptCore.vcproj/JavaScriptCore/JavaScriptCore.def:

2011-02-19  Gavin Barraclough  <barraclough@apple.com>

        Build fix!

        * JavaScriptCore.exp:

2011-02-18  Gavin Barraclough  <barraclough@apple.com>

        Reviewed by Sam Weinig.

        Bug 54786 - Devirtualize JSCell::classInfo()

        Instead of making a virtual function call, add a pointer to the ClassInfo
        onto Structure.

        This removes a virtual function call, and paves the way towards removing all
        the createStructure methods, and StructureFlags/AnonymousSlotCount properties
        (these should be able to move onto ClassInfo).

        Calls to Structure::create must now pass a pointer to the ClassInfo for the
        structure. All objects now have a ClassInfo pointer, non-object cell types
        still do not.

        Changes are most mechanical, involving three steps:
            * Remove virtual classInfo() methods.
            * Add &s_info parameter to calls to Structure::create.
            * Rename ClassInfo static members on classes from 'info' to 's_info',
              for consistency.

        * API/JSCallbackConstructor.cpp:
        * API/JSCallbackConstructor.h:
        * API/JSCallbackFunction.cpp:
        * API/JSCallbackFunction.h:
        * API/JSCallbackObject.cpp:
        * API/JSCallbackObject.h:
        * API/JSCallbackObjectFunctions.h:
        * API/JSObjectRef.cpp:
        * API/JSValueRef.cpp:
        * API/JSWeakObjectMapRefPrivate.cpp:
        * JavaScriptCore.exp:
        * debugger/Debugger.cpp:
        * debugger/DebuggerActivation.h:
        * debugger/DebuggerCallFrame.cpp:
        * interpreter/Interpreter.cpp:
        * jit/JITCall32_64.cpp:
        * jit/JITOpcodes.cpp:
        * jit/JITStubs.cpp:
        * profiler/Profiler.cpp:
        * runtime/Arguments.cpp:
        * runtime/Arguments.h:
        * runtime/ArrayConstructor.cpp:
        * runtime/ArrayPrototype.cpp:
        * runtime/ArrayPrototype.h:
        * runtime/BooleanObject.cpp:
        * runtime/BooleanObject.h:
        * runtime/BooleanPrototype.cpp:
        * runtime/DateConstructor.cpp:
        * runtime/DateInstance.cpp:
        * runtime/DateInstance.h:
        * runtime/DatePrototype.cpp:
        * runtime/DatePrototype.h:
        * runtime/ErrorInstance.cpp:
        * runtime/ErrorInstance.h:
        * runtime/ErrorPrototype.cpp:
        * runtime/FunctionPrototype.cpp:
        * runtime/FunctionPrototype.h:
        * runtime/GetterSetter.h:
        * runtime/GlobalEvalFunction.h:
        * runtime/InternalFunction.cpp:
        * runtime/InternalFunction.h:
        * runtime/JSAPIValueWrapper.h:
        * runtime/JSActivation.cpp:
        * runtime/JSActivation.h:
        * runtime/JSArray.cpp:
        * runtime/JSArray.h:
        * runtime/JSByteArray.cpp:
        * runtime/JSByteArray.h:
        * runtime/JSCell.cpp:
        * runtime/JSCell.h:
        * runtime/JSFunction.cpp:
        * runtime/JSFunction.h:
        * runtime/JSGlobalData.cpp:
        * runtime/JSGlobalObject.cpp:
        * runtime/JSGlobalObject.h:
        * runtime/JSNotAnObject.h:
        * runtime/JSONObject.cpp:
        * runtime/JSONObject.h:
        * runtime/JSObject.cpp:
        * runtime/JSObject.h:
        * runtime/JSObjectWithGlobalObject.h:
        * runtime/JSPropertyNameIterator.h:
        * runtime/JSStaticScopeObject.h:
        * runtime/JSString.h:
        * runtime/JSVariableObject.h:
        * runtime/JSWrapperObject.h:
        * runtime/JSZombie.cpp:
        * runtime/JSZombie.h:
        * runtime/Lookup.cpp:
        * runtime/MathObject.cpp:
        * runtime/MathObject.h:
        * runtime/NativeErrorConstructor.cpp:
        * runtime/NativeErrorConstructor.h:
        * runtime/NumberConstructor.cpp:
        * runtime/NumberConstructor.h:
        * runtime/NumberObject.cpp:
        * runtime/NumberObject.h:
        * runtime/NumberPrototype.cpp:
        * runtime/ObjectConstructor.cpp:
        * runtime/ObjectPrototype.cpp:
        * runtime/RegExpConstructor.cpp:
        * runtime/RegExpConstructor.h:
        * runtime/RegExpObject.cpp:
        * runtime/RegExpObject.h:
        * runtime/RegExpPrototype.cpp:
        * runtime/ScopeChain.cpp:
        * runtime/StringConstructor.cpp:
        * runtime/StringObject.cpp:
        * runtime/StringObject.h:
        * runtime/StringObjectThatMasqueradesAsUndefined.h:
        * runtime/StringPrototype.cpp:
        * runtime/StringPrototype.h:
        * runtime/Structure.cpp:
        * runtime/Structure.h:

2011-02-19  David Kilzer  <ddkilzer@apple.com>

        <http://webkit.org/b/54808> Change jsc target to build directly into JavaScriptCore.framework/Resources/jsc

        Reviewed by Dan Bernstein.

        * Configurations/Base.xcconfig: Added
        JAVASCRIPTCORE_FRAMEWORKS_DIR variable.
        * Configurations/JavaScriptCore.xcconfig: Used
        JAVASCRIPTCORE_FRAMEWORKS_DIR to define INSTALL_PATH.
        * JavaScriptCore.xcodeproj/project.pbxproj: Set the INSTALL_PATH
        for Production configuration of jsc target.
        (Copy Into Framework): Removed old build phase.
        (Fix Framework Reference): Renamed build phase to "Copy Into
        Framework".  Added "set -x" call to make the script print the
        commands it is running.  Added code to exit early for Production
        builds since this was never intended for them.  Added code to
        copy jsc into the JavaScriptCore.framework/Resources directory.

2011-02-19  Siddharth Mathur  <siddharth.mathur@nokia.com>

        Reviewed by Laszlo Gombos.

        [Symbian] OSAllocator implementation for Symbian OS. 
        Manages both data and code region requests. V8 and Sunspider tested
        OK with interpreter. Not tested with JSC JIT yet as it has unrelated
        failures. Also no thread safety yet.
        https://bugs.webkit.org/show_bug.cgi?id=51128

        * JavaScriptCore.pri: removed HAL linkage
        * wtf/Bitmap.h:
        (WTF::::findRunOfZeros): find run of zeros in a bitmap. quick n dirty
        * wtf/OSAllocator.h:
        (WTF::OSAllocator::decommitAndRelease): decommit explicitly 
        * wtf/OSAllocatorSymbian.cpp: Impl. of OSAllocator interface 
        (WTF::allocateCodeChunk): utility for code chunks
        (WTF::deallocateCodeChunk): utility for code chunks
        (WTF::dataAllocatorInstance): getter for data allocator instance
        (WTF::OSAllocator::reserveUncommitted):
        (WTF::OSAllocator::releaseDecommitted):
        (WTF::OSAllocator::commit):
        (WTF::OSAllocator::decommit):
        (WTF::OSAllocator::reserveAndCommit):
        (WTF::PageAllocatorSymbian::PageAllocatorSymbian): maps requests 
        to one underlying Symbian chunk
        (WTF::PageAllocatorSymbian::~PageAllocatorSymbian):
        (WTF::PageAllocatorSymbian::reserve):
        (WTF::PageAllocatorSymbian::release):
        (WTF::PageAllocatorSymbian::commit):
        (WTF::PageAllocatorSymbian::decommit):
        (WTF::PageAllocatorSymbian::contains):
        * wtf/PageAllocatorSymbian.h: Added.
        (WTF::SymbianChunk::SymbianChunk): wrapper around RChunk  
        (WTF::SymbianChunk::~SymbianChunk):
        (WTF::SymbianChunk::contains):
        
2011-02-19  Yong Li  <yoli@rim.com>

        Reviewed by Eric Seidel.

        https://bugs.webkit.org/show_bug.cgi?id=54687
        When being built with armcc, "int" bit fields are treated as
        unsigned integers, which will fail the comparisons like "m_offset == -1".
        Using "signed" fixes the problem.

        * assembler/ARMAssembler.h:
        * assembler/ARMv7Assembler.h:

2011-02-18  Geoffrey Garen  <ggaren@apple.com>

        Reviewed by Sam Weinig.

        Made MarkedSpace block iteration size-class agnostic
        https://bugs.webkit.org/show_bug.cgi?id=54792
        
        SunSpider reports no change.

        * runtime/MarkedSpace.cpp:
        (JSC::MarkedSpace::clearMarks):
        (JSC::MarkedSpace::sweep):
        (JSC::MarkedSpace::objectCount):
        (JSC::MarkedSpace::size):
        (JSC::MarkedSpace::capacity):
        * runtime/MarkedSpace.h:
        (JSC::MarkedSpace::forEach): Iterate blocks in hashing order instead of
        size class list order. This is a much simpler convention in a world
        of many different size classes.

2011-02-18  Kristian Amlie  <kristian.amlie@nokia.com>

        Reviewed by Andreas Kling.

        Added friend exception to Qt platform, which also compiles Windows.

        QtWebKit fails to compile on Windows XP with msvc-2008
        https://bugs.webkit.org/show_bug.cgi?id=54746

        * bytecode/CodeBlock.h:
        * runtime/RegExpObject.h:

2011-02-18  Geoffrey Garen  <ggaren@apple.com>

        (Rolled back in r79022 with crash fixed.)

        Reviewed by Sam Weinig.

        Use hashing instead of linear search in the conservative pointer test
        https://bugs.webkit.org/show_bug.cgi?id=54767
        
        SunSpider reports no change.

        * runtime/MarkedSpace.cpp:
        (JSC::MarkedSpace::destroy): No need to explicitly clear the blocks array,
        since freeBlock removes items for us.

        (JSC::MarkedSpace::freeBlock): Fixed a typo that always removed the last
        block from the block set instead of the block being freed. Changed to
        remove a block from our data structures before deallocating it, since
        this is slightly cleaner.

        * runtime/MarkedSpace.h:
        (JSC::MarkedSpace::contains): Variable-sized objects will use more,
        smaller blocks, so it's important for the contains check not to be O(n)
        in the number of blocks.

2011-02-18  chris reiss  <christopher.reiss@nokia.com>

        Reviewed by Andreas Kling.

        REGRESSION: Date.parse("Tue Nov 23 20:40:05 2010 GMT") returns NaN
        https://bugs.webkit.org/show_bug.cgi?id=49989

        updated test fast/js/script-tests/date-parse-test.js

        * wtf/DateMath.cpp:
        (WTF::parseDateFromNullTerminatedCharacters):

2011-02-18  Sheriff Bot  <webkit.review.bot@gmail.com>

        Unreviewed, rolling out r79022.
        http://trac.webkit.org/changeset/79022
        https://bugs.webkit.org/show_bug.cgi?id=54775

        It broke the whole world (Requested by Ossy on #webkit).

        * runtime/MarkedSpace.h:
        (JSC::MarkedSpace::contains):

2011-02-18  Yael Aharon  <yael.aharon@nokia.com>

        Reviewed by Dave Hyatt.

        Add support for dir=auto
        https://bugs.webkit.org/show_bug.cgi?id=50916

        Change defaultWritingDirection() to return if the writing direction
        was determined from a letter with strong directionality or not.

        * JavaScriptCore.exp:
        * JavaScriptCore.order:
        * wtf/text/StringImpl.cpp:
        (WTF::StringImpl::defaultWritingDirection):
        * wtf/text/StringImpl.h:
        * wtf/text/WTFString.h:
        (WTF::String::defaultWritingDirection):

2011-02-18  Geoffrey Garen  <ggaren@apple.com>

        Reviewed by Sam Weinig.

        Use hashing instead of linear search in the conservative pointer test
        https://bugs.webkit.org/show_bug.cgi?id=54767
        
        SunSpider reports no change.

        * runtime/MarkedSpace.h:
        (JSC::MarkedSpace::contains): Variable-sized objects will use more,
        smaller blocks, so it's important for the contains check not to be O(n)
        in the number of blocks.

2011-02-18  Geoffrey Garen  <ggaren@apple.com>

        Reviewed by Sam Weinig.

        Tightened some usage accounting code in MarkedSpace
        https://bugs.webkit.org/show_bug.cgi?id=54761
        
        SunSpider reports no change.

        * runtime/Heap.cpp:
        (JSC::Heap::Heap): Initialize the marked space high water mark on
        construction, instead of relying on some implicit subtleties to make
        not initializing it work out OK.

        * runtime/Heap.h: Fixed up includes.

        * runtime/MarkedBlock.h: Made firstAtom() static so clients can call it
        even without having allocated a block.

        * runtime/MarkedSpace.cpp:
        (JSC::MarkedSpace::MarkedSpace): Don't pre-allocate a block, since this
        would be prohibitively expensive with multiple size classes.

        (JSC::MarkedSpace::allocateBlock):
        (JSC::MarkedSpace::freeBlock): Track allocated blocks in a hash set,
        since linear search in the contains check will be prohibitively
        expensive once we're using lots of smaller blocks.

        (JSC::MarkedSpace::allocate): Don't assume that we always have a block
        allocated, since we don't anymore. (See above.)

        (JSC::MarkedSpace::reset):
        * runtime/MarkedSpace.h: Updated for changes mentioned above.

2011-02-17  Geoffrey Garen  <ggaren@apple.com>

        Reviewed by Sam Weinig.

        Made object allocation secretly variable-sized (Shhhh!)
        https://bugs.webkit.org/show_bug.cgi?id=54721
        
        SunSpider reports no change.
        
        Internally, MarkedBlock now makes variable-sized allocations, even
        though MarkedSpace doesn't take advantage of this yet.

        * runtime/MarkedBlock.cpp:
        (JSC::MarkedBlock::MarkedBlock): No need to ASSERT that allocations are
        fixed-sized.

        * runtime/MarkedBlock.h: Shrunk the atom size so we can allocate things
        that are not multiples of 64 bytes.

2011-02-17  Geoffrey Garen  <ggaren@apple.com>

        Reviewed by Sam Weinig.

        Fixed some math errors when when using variable-sized cells
        https://bugs.webkit.org/show_bug.cgi?id=54717
        
        SunSpider reports no change.
        
        Computer Science Barbie says, "Math is not so hard afterall!"

        * runtime/JSCell.h:
        (JSC::JSCell::MarkedBlock::allocate): Round up when calculating the
        minimum number of atoms required for a cell, since rounding down
        will get you splinched.

        * runtime/MarkedBlock.cpp:
        (JSC::MarkedBlock::MarkedBlock):
        (JSC::MarkedBlock::sweep):
        * runtime/MarkedBlock.h:
        (JSC::MarkedBlock::forEach): Changed a bunch of != tests to < tests
        because m_endAtom is actually a fuzzy end -- iterating from firstAtom()
        may not hit m_endAtom exactly.

2011-02-17  Geoffrey Garen  <ggaren@apple.com>

        Reviewed by Sam Weinig.

        A little more abstraction for MarkedSpace::contains
        https://bugs.webkit.org/show_bug.cgi?id=54715

        * runtime/MarkedBlock.h:
        (JSC::MarkedBlock::contains): Added a contains function, so MarkedSpace
        doesn't have to know how MarkedBlock tracks containment internally.

        * runtime/MarkedSpace.h:
        (JSC::MarkedSpace::contains): Call through to MarkedBlock to figure out
        if a cell that seems to be in a block is valid.

2011-02-17  Geoffrey Garen  <ggaren@apple.com>

        Reviewed by Sam Weinig.

        Removed the invariant that the last cell in a block is always marked
        https://bugs.webkit.org/show_bug.cgi?id=54713
        
        SunSpider reports no change.
        
        This adds one branch to allocation, but simplifies the mark invariant,
        especially in a world of variable-sized cells. Now, it really is true
        that any cell whose mark bit is set is a valid, live cell whose
        constructor has run and whose destructor has not run.

        * runtime/JSCell.h: 
        (JSC::JSCell::MarkedBlock::allocate): Changed this do-while into a while
        since we can no longer rely on a set mark bit to break out of this loop
        before it reaches the end of the block.

        * runtime/MarkedBlock.cpp:
        (JSC::MarkedBlock::MarkedBlock):
        (JSC::MarkedBlock::sweep): 
        * runtime/MarkedBlock.h:
        (JSC::MarkedBlock::isEmpty):
        (JSC::MarkedBlock::clearMarks):
        (JSC::MarkedBlock::markCount):
        (JSC::MarkedBlock::forEach): No need to set a special last mark bit.

2011-02-17  Sheriff Bot  <webkit.review.bot@gmail.com>

        Unreviewed, rolling out r78856 and r78907.
        http://trac.webkit.org/changeset/78856
        http://trac.webkit.org/changeset/78907
        https://bugs.webkit.org/show_bug.cgi?id=54705

        These seem to break tests on 32-bit builds. (Requested by
        aroben on #webkit).

        * JavaScriptCore.xcodeproj/project.pbxproj:
        * collector/handles/Global.h:
        (JSC::Global::internalSet):
        * collector/handles/Handle.h:
        (JSC::HandleTypes::getFromSlot):
        (JSC::HandleTypes::toJSValue):
        (JSC::HandleTypes::validateUpcast):
        (JSC::HandleConverter::operator->):
        (JSC::HandleConverter::operator*):
        (JSC::Handle::Handle):
        (JSC::Handle::get):
        * runtime/JSArray.cpp:
        (JSC::JSArray::sortNumeric):
        * runtime/JSObject.h:
        (JSC::JSObject::inlineGetOwnPropertySlot):
        * runtime/SlotAccessor.h: Removed.
        * runtime/WeakGCPtr.h:
        (JSC::WeakGCPtr::get):
        (JSC::WeakGCPtr::internalSet):
        * runtime/WriteBarrier.h:
        (JSC::DeprecatedPtr::DeprecatedPtr):
        (JSC::DeprecatedPtr::get):
        (JSC::DeprecatedPtr::operator*):
        (JSC::DeprecatedPtr::operator->):
        (JSC::DeprecatedPtr::slot):
        (JSC::DeprecatedPtr::operator UnspecifiedBoolType*):
        (JSC::DeprecatedPtr::operator!):
        (JSC::WriteBarrierBase::set):
        (JSC::WriteBarrierBase::get):
        (JSC::WriteBarrierBase::operator*):
        (JSC::WriteBarrierBase::operator->):
        (JSC::WriteBarrierBase::clear):
        (JSC::WriteBarrierBase::slot):
        (JSC::WriteBarrierBase::operator UnspecifiedBoolType*):
        (JSC::WriteBarrierBase::operator!):
        (JSC::WriteBarrierBase::setWithoutWriteBarrier):
        (JSC::WriteBarrier::WriteBarrier):

2011-02-17  Csaba Osztrogonác  <ossy@webkit.org>

        Unreviewed.

        [Qt] Buildfix.

        * wtf/RetainPtr.h: Add missing PLATFORM(CF) guard.

2011-02-17  Geoffrey Garen  <ggaren@apple.com>

        Reviewed by Oliver Hunt.

        Made MarkedBlock variable-sized
        https://bugs.webkit.org/show_bug.cgi?id=54692
        
        SunSpider reports no change.
        
        Each MarkedBlock is now composed of a set of fixed-sized atoms, with one
        mark bit per atom. A given cell may be composed of one or more atoms.
        
        * runtime/Heap.cpp:
        (JSC::Heap::allocate): Made fixed-sizedness a property of MarkedSpace,
        bubbling it up from MarkedBlock, since MarkedBlock now supports variable-
        sizedness.

        * runtime/JSCell.h:
        (JSC::JSCell::MarkedBlock::allocate): Removed use of CELLS_PER_BLOCK and
        (implicit) one constants -- these quantities are not constant anymore.
        Updated for switch from cell to atom.

        * runtime/MarkedBlock.cpp:
        (JSC::MarkedBlock::create):
        (JSC::MarkedBlock::destroy):
        (JSC::MarkedBlock::MarkedBlock):
        (JSC::MarkedBlock::sweep):
        * runtime/MarkedBlock.h:
        (JSC::MarkedBlock::firstAtom):
        (JSC::MarkedBlock::atoms):
        (JSC::MarkedBlock::isAtomAligned):
        (JSC::MarkedBlock::blockFor):
        (JSC::MarkedBlock::isEmpty):
        (JSC::MarkedBlock::clearMarks):
        (JSC::MarkedBlock::size):
        (JSC::MarkedBlock::capacity):
        (JSC::MarkedBlock::atomNumber):
        (JSC::MarkedBlock::isMarked):
        (JSC::MarkedBlock::testAndSetMarked):
        (JSC::MarkedBlock::setMarked):
        (JSC::MarkedBlock::forEach): Same as above. Also removed use of CELL_SIZE
        and BLOCK_SIZE, and switched away from calling arbitrary pointers cells.

        * runtime/MarkedSpace.cpp:
        (JSC::MarkedSpace::MarkedSpace):
        (JSC::MarkedSpace::allocateBlock):
        (JSC::MarkedSpace::allocate):
        (JSC::MarkedSpace::reset):
        * runtime/MarkedSpace.h:
        (JSC::CollectorHeap::CollectorHeap):
        (JSC::MarkedSpace::contains): Updated for renames. Made fixed-sizedness
        a property of MarkedSpace.

2011-02-17  Oliver Hunt  <oliver@apple.com>

        Attempt to fix windows build

        * runtime/WriteBarrier.h:

2011-02-17  Oliver Hunt  <oliver@apple.com>

        Reviewed by Geoffrey Garen.

        Refactor WriteBarrier and DeprecatedPtr to have less code duplication.
        https://bugs.webkit.org/show_bug.cgi?id=54608

        Make use of the tricks used for Handle, et al to avoid duplicating all
        of the logic for DeprecatedPtr and WriteBarrier simply to support known
        vs. unknown types.

        * JavaScriptCore.xcodeproj/project.pbxproj:
        * collector/handles/Global.h:
        (JSC::Global::internalSet):
        * collector/handles/Handle.h:
        (JSC::Handle::Handle):
        (JSC::Handle::get):
        * runtime/JSArray.cpp:
        (JSC::JSArray::sortNumeric):
        * runtime/JSObject.h:
        (JSC::JSObject::inlineGetOwnPropertySlot):
        * runtime/SlotAccessor.h: Added.
        (JSC::SlotTypes::getFromBaseType):
        (JSC::SlotTypes::convertToBaseType):
        (JSC::SlotTypes::getFromSlot):
        (JSC::SlotTypes::toJSValue):
        (JSC::SlotTypes::validateUpcast):
        (JSC::SlotAccessor::operator->):
        (JSC::SlotAccessor::operator*):
        * runtime/WeakGCPtr.h:
        (JSC::WeakGCPtr::get):
        (JSC::WeakGCPtr::internalSet):
        * runtime/WriteBarrier.h:
        (JSC::DeprecatedPtr::DeprecatedPtr):
        (JSC::DeprecatedPtr::get):
        (JSC::DeprecatedPtr::slot):
        (JSC::DeprecatedPtr::operator=):
        (JSC::WriteBarrierTranslator::convertToStorage):
        (JSC::WriteBarrierTranslator::convertFromStorage):
        (JSC::WriteBarrierBase::set):
        (JSC::WriteBarrierBase::get):
        (JSC::WriteBarrierBase::clear):
        (JSC::WriteBarrierBase::slot):
        (JSC::WriteBarrierBase::operator UnspecifiedBoolType*):
        (JSC::WriteBarrierBase::operator!):
        (JSC::WriteBarrierBase::setWithoutWriteBarrier):
        (JSC::WriteBarrier::WriteBarrier):

2011-02-17  Kevin Ollivier  <kevino@theolliviers.com>

        [wx] Revert incorrect blind fix and restore previous working code.

        * wtf/wx/StringWx.cpp:
        (WTF::String::String):

2011-02-16  Geoffrey Garen  <ggaren@apple.com>

        Reviewed by Maciej Stachowiak.

        Intermittent crashes beneath MarkStack::drain
        https://bugs.webkit.org/show_bug.cgi?id=54614
        <rdar://problem/8971070>
        
        The crashes were caused by a GC happening after the global object's
        property table had grown (due to compilation), but before the properties
        had been fully initialized by program execution.

        * bytecompiler/BytecodeGenerator.cpp:
        (JSC::BytecodeGenerator::BytecodeGenerator): Explicitly resize the global
        object's register storage immediately, without waiting for program
        execution to do it for us. This ensures that the global object's count
        of global variables is consistent with the size of its global variable
        storage at all times, and it ensures that all global variables are
        properly initialized from the get-go.

        * runtime/JSGlobalObject.cpp:
        (JSC::JSGlobalObject::resizeRegisters):
        * runtime/JSGlobalObject.h: Added a helper function for growing the
        global object's register storage, and initializing new registers.

== Rolled over to ChangeLog-2011-02-16 ==
