Summary: This changeset introduces filtering of SATB buffers at the point when they are about to be enqueued. If this filtering clears enough entries on each buffer, the buffer can then be re-used and not enqueued. This cuts down the number of SATB buffers that need to be processed by the concurrent marking threads.
Reviewed-by: johnc, ysr

Summary: Revert a (relaxed version of the) bounds-check that was incorrectly removed in the fix for 7008136.
Reviewed-by: jmasa, johnc

Summary: Pass the value of UseLargePages instead of false as the "large" parameter when reserving the G1 heap.
Reviewed-by: tonyp, johnc, phh

Summary: Change get_temp_directory() back to /tmp and %TEMP% like it always was and where the tools expect it to be.
Reviewed-by: phh, dcubed, kamg, alanb

Summary: First attempt to allocate out the current alloc region using a CAS instead of taking the Heap_lock (first level of G1's slow allocation path). Only if that fails and it's necessary to replace the current alloc region take the Heap_lock (that's the second level of G1's slow allocation path).
Reviewed-by: johnc, brutisso, ysr

Summary: During evacuation failure handling we refine the BOT to reflect the location of all the objects in the regions we scan. The changeset includes some minor cleanup: a) non-product print_on() method on the G1 BOT class, b) added more complete BOT verification during heap / region verification, c) slight modification to the BOT set up for humongous regions to be more consistent with the BOT set up during evac failure handling, and d) removed a couple of unused methods.
Reviewed-by: johnc, ysr

Reviewed-by: mchung, acorn

Summary: Move _lower_dimension field initialization before _higher_dimension and add storestore barrier.
Reviewed-by: dholmes, iveresov, never

Summary: Mark field volatile, use membars, and change access order to close race
Reviewed-by: dcubed, dholmes

Summary: Reuse set_method_data_for_bcp() to setup mdp after MDO creation.
Reviewed-by: kvn, never

Summary: Make JvmtiGCMark safe to run non-safepoint and instrument CMS
Reviewed-by: ysr, dcubed

Reviewed-by: kvn, never

Reviewed-by: never

Summary: Modify membars to match regular volatile variable handling
Reviewed-by: iveresov, kvn, never

6876037: CTW fails jdk7/hotspot/src/share/vm/opto/type.cpp:2055. assert(bits,"Use TypePtr for NULL")
Summary: Add missing 0 value check in TypeRawPtr::add_offset().
Reviewed-by: never

Summary: Use Atomic::load() and Atomic::store() to access a volatile long.
Reviewed-by: iveresov, jrose, dholmes, never

Summary: Codebuffer can overflow on test with large number of calls
Reviewed-by: dholmes, collins

Summary: Track allocated bytes in Thread's, update on TLAB retirement and direct allocation in Eden and tenured, add JNI methods for ThreadMXBean.
Reviewed-by: coleenp, kvn, dholmes, ysr

Summary: The recorded _sweep_limit may not necessarily remain a block boundary as the old generation expands during a concurrent cycle. Terminal actions inside the sweep closure need to be aware of this as they cross over the limit.
Reviewed-by: johnc, minqi

6583275: Hotspot crash in vm_perform_shutdown_actions due to uninitialized TLS during out of memory handling
Summary: Call get_thread_slow() in vm_perform_shutdown actions and add null check.
Reviewed-by: kvn, dholmes, jcoomes

Summary: enhance the error reporting mechanism to help user to fix the problem rather than making it look like a VM error.
Reviewed-by: kvn, kamg

Summary: Fix frame size computation
Reviewed-by: phh, kvn

Summary: reset NoHandleMark before going into VM.
Reviewed-by: iveresov

Summary: remove clear_scratch_buffer_blob and let init_scratch_buffer_blob free and allocate a new blob if required.
Reviewed-by: twisti

7009359: HS with -XX:+AggressiveOpts optimize new StringBuffer(null) so it does not throw NPE as expected
Summary: Bailout StringConcat optimization if null is passed to StringBuffer constructor.
Reviewed-by: iveresov

Summary: Fix CAS of longs on SPARC 32bit and cmove on SPARC 64bit.
Reviewed-by: kvn

Reviewed-by: kvn, jrose

Summary: bump CG_BUILD_ITER_LIMIT to 20
Reviewed-by: iveresov

Summary: When bootstrap_method_ref in BootstrapMethods attribute points to a wrong CP entry (non-MethodHandle), JVM throws ClassFormatError with a message, where method index and class file name is garbage.
Reviewed-by: iveresov

Summary: Fire the gc-begin and gc-end probes for G1.
Reviewed-by: kamg, ysr, jcoomes

Reviewed-by: never

Summary: Age bits need not enter the mark-word preservation calculus; also affected, in addition to CMS, per CR synopsis above, were ParNew (but not DefNew), ParallelScavenge and G1, albeit to a lesser degree than CMS.
Reviewed-by: tonyp, johnc

6579789: Internal error "c1_LinearScan.cpp:1429 Error: assert(false,"")" in debuggee with fastdebug VM
Reviewed-by: kvn, iveresov

Summary: Initialize the _is_alive_non_header field of G1's reference processor with an instance of the G1CMIsAliveClosure. This will stop adding reference objects with live referents to the discovered reference lists unnecessarily.
Reviewed-by: tonyp, ysr, jwilhelm, brutisso

Summary: read Solaris kstat data to get more precise CPU information
Reviewed-by: iveresov, never, twisti, dholmes

Reviewed-by: kvn, iveresov

Summary: An interference between a fix for 6993125 and disabled optimization in compressedStream.cpp produces a warning with VS2010. Disable the warning for the code fragment for which the optimizations are disabled.
Reviewed-by: kvn

Reviewed-by: kvn, iveresov

7000559: G1: assertion failure !outer || (full_collections_started == _full_collections_completed + 1)
Summary: The concurrent marking thread can complete its operation and increment the full GC counter during a Full GC. This causes the nesting of increments to the start and end of Full GCs that we are expecting to be wrong. the fix is for the marking thread to join the suspendible thread set before incrementing the counter so that it's blocked until the Full GC (or any other safepoint) is finished. The change also includes some minor code cleanup (I renamed a parameter).
Reviewed-by: brutisso, ysr

Summary: missing null check in owns_pending_list_lock() because this can be called before pending_list_lock is initialized.
Reviewed-by: never, kvn