Summary: MethodHandle invoke call sites should not be fixed-up by SharedRuntime::fixup_callers_callsite as c2i/i2c adapters are used to implement MethodHandle actions.
Reviewed-by: kvn, never

Summary: We need to introduce a new MH deopt handler so we can easily determine if the deopt happened at a MH call site or not.
Reviewed-by: never, jrose

Reviewed-by: kvn, twisti

Summary: Speculatively unload the oldest nmethods when code cache gets full.
Reviewed-by: never, kvn
Contributed-by: eric.caspole@amd.com

Reviewed-by: mr

Summary: We need to introduce a new MH deopt handler so we can easily determine if the deopt happened at a MH call site or not.
Reviewed-by: never, jrose

Reviewed-by: kvn

Reviewed-by: kvn

Summary: Two recent commits broke the build on Zero.
Reviewed-by: twisti
Contributed-by: NGary Benson <gbenson@redhat.com>

Summary: Add safepoint after CompileTheWorldSafepointInterval (100) compilations and do full sweep of CodeCache each time.
Reviewed-by: never
Contributed-by: eric.caspole@amd.com

Reviewed-by: kvn, jrose

Summary: Recent changes call os::is_allocatable which was not implemented in Zero.
Reviewed-by: twisti
Contributed-by: NEdward Nevill <ed@camswl.com>

Reviewed-by: kvn, cfang

Reviewed-by: kvn, twisti

Reviewed-by: twisti, kvn

Summary: When enqueuing a completed PtrQueue buffer, cache a local pointer to the buffer and clear the field in the PtrQueue prior to unlocking the mutex referenced by the _lock field and pass the cached local value to the enqueuing routine. This will prevent the same completed buffer being enqueued multiple times, which causes the hang.
Reviewed-by: ysr

Summary: Deferred card marks are now flushed during the gc prologue. Parallel[Scavege,OldGC] and SerialGC no longer defer card marks generated by COMPILER2 as a result of ReduceInitialCardMarks. For these cases, introduced a diagnostic option to defer the card marks, only for the purposes of testing and diagnostics. CMS and G1 continue to defer card marks. Potential performance concern related to single-threaded flushing of deferred card marks in the gc prologue will be addressed in the future.
Reviewed-by: never, johnc

Summary: What the title says.
Reviewed-by: ysr, jmasa

6580131: 3/4 CompiledMethodLoad events don't produce the expected extra notifications to describe inlining
Summary: Add support for additional implementation specific info to the JVM/TI CompiledMethodLoad event via the compile_info parameter.
Reviewed-by: never, ohair, tbell, tdeneau
Contributed-by: NVasanth Venkatachalam <vasanth.venkatachalam@amd.com>

6902115: G1:assert(ignore_max_completed||thread->is_Java_thread()||SafepointSynchronize::is_at_safepoint())
Summary: Remove invalid assert and mangle filler objects in TLABs that are being retired.
Reviewed-by: ysr, jmasa

Summary: Loop predication implementation
Reviewed-by: never, kvn

Reviewed-by: kvn, jrose

Summary: Put all inline-related switches into product mode, to allow tuning by dynamic language implementors.
Reviewed-by: twisti, kvn

Summary: More informative disassembly in product mode.  Also, a more consistent CompileCommand syntax.
Reviewed-by: never

Summary: Remove AND operation only if mask is equal to shift.
Reviewed-by: never

Summary: Check RootNode before check Loop in IfNode::up_one_dom().
Reviewed-by: never
Contributed-by: kevin.brown@sun.com

Summary: Put generated MH adapter in InvokeDynamic/MethodHandle classes to be able to indentify them easily in the compiler.
Reviewed-by: kvn, never, jrose

Summary: Add missing check that value is used in memory expression in instructions with embedded load.
Reviewed-by: never, jrose

Summary: Change the flag -XX:+PrintFlagsFinal to product and add new product flag -XX:+PrintFlagsInitial.
Reviewed-by: phh, ysr
Contributed-by: gbenson@redhat.com

Summary: Block too small to split was not correctly putback to free lists.
Reviewed-by: ysr

Reviewed-by: kvn, twisti

Reviewed-by: kvn, twisti

Reviewed-by: never
Contributed-by: NGary Benson <gbenson@redhat.com>

Summary: C2 needs some additional optimizations to be able to handle MethodHandle invokes and invokedynamic instructions at the best performance.
Reviewed-by: kvn, never

Summary: C2 implementation for invokedynamic support.
Reviewed-by: kvn, never

Summary: EA incorrectly identifies escape state of an allocation passed as call argument.
Reviewed-by: never

6637203: Classunloading messages go to stdout rather than Xloggc file, causing hangs when stdout is closed
Summary: Decoupled TraceClassUnloading from verbose:gc, JVMTI_VERBOSE_GC and PrintGC[Details], making it settable in a manner identical to TraceClassLoading. Reverted an inadvertent change of TraceClassUnloading output in a previous changeset from gclog back to tty.
Reviewed-by: coleenp, dholmes, jmasa, poonam

Summary: During the work for 6829187 we have fixed a number of basic bugs which are logically grouped with 6815692 and 6858164 but which must be reviewed and pushed separately.
Reviewed-by: kvn, never

Summary: We need a way to walk chained method handles in the JVM to call the right methods and to generate required bytecode adapters for the compilers.
Reviewed-by: kvn

Summary: Zero currently won't build on zSeries or PowerPC machines with assertions turned on.
Reviewed-by: twisti
Contributed-by: NGary Benson <gbenson@redhat.com>