| ed2876e520bbdf295f894c5fb7c5a58bf90bf60f |
|
29-Mar-2013 |
Udayan Banerji <udayan.banerji@intel.com> |
[x86] Fix errors with WITH_JIT_TUNING defined
This patch makes the necessary changes to pass on correct information to
dvmBumpNoChain, so that WITH_JIT_TUNING flag can be enabled for x86 codegen
Signed-off-by: Udayan Banerji <udayan.banerji@intel.com>
(cherry picked from commit 19eb287ac848f10e03ca2614bf53bd9d1ddd3724)
Change-Id: I6871dd0839b3656beed4633e3a0f3df780af98a0
|
| 3599cdd1b4e72f4cb047fc31bf7c579764fa93d2 |
|
14-Feb-2013 |
Elliott Hughes <enh@google.com> |
Remove stray references to non-existent opcodes.
Change-Id: I83ca6ea12344a8df7ef14d600baf5060b76870f5
|
| 22cf4ac092fa952fc2ebf04cb63736fe7b7f744b |
|
02-Feb-2013 |
Jeff Hao <jeffhao@google.com> |
Remove dead instruction in common_exceptionThrown.
Addresses bug: https://code.google.com/p/android/issues/detail?id=43920
Change-Id: Ie735222db17b883416543ca5617b4f02fd8a8d76
|
| 0c2dc522d0e120f346cf0a40c8cf0c93346131c2 |
|
03-Jul-2012 |
Dong-Yuan Chen <dong-yuan.chen@intel.com> |
[X86] X86 trace JIT compiler support
This patch provides a fully functional x86 trace JIT compiler for Dalvik
VM. It is built on top of the existing x86 fast interpreter
with bug fixes and needed extension to support trace JIT interface. The
x86 trace JIT code generator was developed independent of the existing
template-based code generator and thus does not share exactly the same
infrastructure. Included in this patch are:
* Deprecated and removed the x86-atom fast interpreter that is no
longer functional since ICS.
* Augmented x86 fast interpreter to provide interfaces for x86 trace JIT
compiler.
* Added x86 trace JIT code generator with full JDWP debugging support.
* Method JIT and self-verification mode are not supported.
The x86 code generator uses the x86 instruction encoder/decoder library
from the Apache Harmony project. Additional wrapper extension and bug
fixes were added to support the x86 trace JIT code generator. The x86
instruction encoder/decoder is embedded inside the x86 code generator
under the libenc subdirectory.
Change-Id: I241113681963a16c13a3562390813cbaaa6eedf0
Signed-off-by: Dong-Yuan Chen <dong-yuan.chen@intel.com>
Signed-off-by: Yixin Shou <yixin.shou@intel.com>
Signed-off-by: Johnnie Birch <johnnie.l.birch.jr@intel.com>
Signed-off-by: Udayan <udayan.banerji@intel.com>
Signed-off-by: Sushma Kyasaralli Thimmappa <sushma.kyasaralli.thimmappa@intel.com>
Signed-off-by: Bijoy Jose <bijoy.a.jose@intel.com>
Signed-off-by: Razvan A Lupusoru <razvan.a.lupusoru@intel.com>
Signed-off-by: Tim Hartley <timothy.d.hartley@intel.com>
|
| 3185a41fe8b3223003a07685c1acdf44bfe148d0 |
|
30-Jan-2012 |
buzbee <buzbee@google.com> |
x86 mterp debug/profile fix (issue 5938080)
When profiling or debugging is active, the Dalvik vm calls out to
a helper function to handle any pending debug/profile activities
before and after native invokes. The assembly code in footer.s
was passing arguments to these routines in the wrong oder.
Issue 5938080
Change-Id: I425eb2bfbee504a70eda8b382f4cf7340e458241
|
| ab35b50311951feea3782151dd5422ee944685c2 |
|
05-Jan-2012 |
Elliott Hughes <enh@google.com> |
Remove unsupported experimental opcodes.
External developers were starting to try to get themselves into trouble with
this stuff...
Change-Id: I2b03bfeaa8c98b6a994bc7924fc8dcf4e4d4f6cb
|
| 97b22b8d41742fa84812f46d1125e9735420782a |
|
23-May-2011 |
buzbee <buzbee@google.com> |
Fix alt handling for Jumbo ops
The mterp alt mechanism allows us to break out of the fast
interpreter loop to handle debugging, JIT trace selection and
other non-standard behavior. It does this by replacing the
base pointer to the instruction handlers with an alternate
base that references a set of dummy handlers that first call
out the dvmCheckBefore() to handle special actions before
routing control to the real handlers.
This mechanism was slightly broken for the Jumbo ops - which
have a first opcode byte of 0xFF (Dispatch), followed by the
Jumbo opcode byte. In short, when the altHandlerBase was active
dvmCheckBefore() was getting called for both the dispatch opcode
byte and the Jumbo byte.
This change adds special ALT_OP_DISPATCH_FF handlers which skip
the dvmCheckBefore() call.
Change-Id: If57c298a33404cdaca7456bc8fe1159c70240bea
|
| 2ec9f7802034144383261b2fd915bdf1eb396ea4 |
|
03-May-2011 |
buzbee <buzbee@google.com> |
x86 interpreter fix
Correct the ordering of FP save prior to special subMode handling.
Also added a stress test mode to help catch this sort of problem in
the future.
Change-Id: I5bcd325858fa63023498bfd47e910aaf1530d6bb
|
| 389e258a5b9b2afb7bfaee3344c615d3310fae4e |
|
23-Apr-2011 |
buzbee <buzbee@google.com> |
InterpBreak cleanup (part 1)
Moved the suspend count variables from the interpBreak structure. These
are already protected by a mutex, and we need the space in interpBreak
for additional subMode flags. This CL just does the move and expands
the width of subMode to 16-bits.
Change-Id: I4a6070b1ba4fb08a0f6e0aba6f150b30f9159eed
|
| 30bc0d46ae730d78c42c39cfa56a59ba3025380b |
|
22-Apr-2011 |
buzbee <buzbee@google.com> |
Consolidate curFrame fields in thread storage
We ended up with two locations in the Thread structure for saved
Dalvik frame pointer. This change consolidates them.
Change-Id: I78f288e4e57e232f29663be930101e775bfe370f
|
| a4a19037f75e0e3c85fb5f3c7fa31732f8475719 |
|
05-Apr-2011 |
buzbee <buzbee@google.com> |
Fix x86 fast interpreter
Was passing wrong value to dvmResolveField() in OP_IGET_WIDE_JUMBO
Change-Id: I7773fd0932d7d032fce30dc57b33ef6a8fbc7afb
|
| 99e3e6e72e3471eb85fc2e405866392b01c080fe |
|
29-Mar-2011 |
buzbee <buzbee@google.com> |
Fix interpreter debug attach
Fix a few miscellaneous bugs from the interpreter restructuring that were
causing a segfault on debugger attach.
Added a sanity checking routine for debugging.
Fixed a problem in which the JIT's threshold and on/off switch
wouldn't get initialized properly on thread creation.
Renamed dvmCompilerStateRefresh() to dvmCompilerUpdateGlobalState() to
better reflect its function.
Change-Id: I5b8af1ce2175e3c6f53cda19dd8e052a5f355587
|
| 9a3147c7412f4794434b4c2604aa2ba784867774 |
|
03-Mar-2011 |
buzbee <buzbee@google.com> |
Interpreter restructuring
This is a restructuring of the Dalvik ARM and x86 interpreters:
o Combine the old portstd and portdbg interpreters into a single
portable interpreter.
o Add debug/profiling support to the fast (mterp) interpreters.
o Delete old mechansim of switching between interpreters. Now, once
you choose an interpreter at startup, you stick with it.
o Allow JIT to co-exist with profiling & debugging (necessary for
first-class support of debugging with the JIT active).
o Adds single-step capability to the fast assembly interpreters without
slowing them down (and, in fact, measurably improves their performance).
o Remove old "polling for safe point" mechanism. Breakouts now achieved
via modifying base of interpreter handler table.
o Simplify interpeter control mechanism.
o Allow thread-granularity control for profiling & debugging
The primary motivation behind this change was to improve the responsiveness
of debugging and profiling and to make it easier to add new debugging and
profiling capabilities in the future. Instead of always bailing out to the
slow debug portable interpreter, we can now stay in the fast interpreter.
A nice side effect of the change is that the fast interpreters
got a healthy speed boost because we were able to replace the
polling safepoint check that involved a dozen or so instructions
with a single table-base reload. When combined with the two earlier CLs
related to this restructuring, we show a 5.6% performance improvement
using libdvm_interp.so on the Checkers benchmark relative to Honeycomb.
Change-Id: I8d37e866b3618def4e582fc73f1cf69ffe428f3c
|
| 61f4c7e40b885ccb0a55d9553f07a888469621dc |
|
16-Mar-2011 |
Dan Bornstein <danfuzz@android.com> |
Clean up ArrayStoreException some more.
Each of the four variants thrown by the VM now has a
descriptively-named function defined in Exception.c, and the messages
uniformly use human-oriented class names instead of the internal
"[[Lfoo/bar/Baz;" forms.
Bug: 3500987
Change-Id: I747315e36005c6d352116ce6a8af9d49c622f59a
|
| 24bd4c50bb3ea13be4f049710967961f0546fb2c |
|
10-Mar-2011 |
Andy McFadden <fadden@android.com> |
Add volatile/jumbo opcodes
This adds 12 dexopt-generated "volatile/jumbo" instructions, to
be used for replacing appropriate get/put ops, plus a jumbo
replacement for invoke-object-init/range.
The new instructions are defined but not yet used. For x86 and
x86-atom, C stubs are selected.
Also, guarded macro args used in arithmetic expressions in header.S.
Bug 3403118
Change-Id: I283cea053d1cee1d70c3715df3e71177e8b8d3b2
|
| 4570ad0a7706d3338d58bd0204e102719e4d68fb |
|
09-Mar-2011 |
Eugene Surovegin <surovegin@google.com> |
x86: restore standard stack frame layout and fix stack alignment.
Native x86 can contain SSE instructions, this requires 16-byte aligned stack
which is what GCC expects these days. Enforce this in dvmPlatformInvoke and
in mterp.
Also fix stack frame layout, so debuggers can produce backtraces across
dvmMterpStdRun invocations.
Change-Id: I43d00a6bf8210b7d3aa9276edabc08978084e4f2
|
| 47f58250c5177adba475b0b11a36151ac0ce9ab9 |
|
07-Mar-2011 |
Dan Bornstein <danfuzz@android.com> |
Consistency in exception throws.
Make the messages that consist of a series of values consistently use
semicolons between the values, and make the call order for exception
throws that take both "info about a thing" as well as "info about a
use of that thing" take the "info about a thing" argument first.
Practical upshot: Adding a second semicolon in the message for
StringIndexOutOfBoundsException being thrown for a region, and
switching the order of arguments of
dvmThrowArrayIndexOutOfBoundsException().
Bug: 3500987
Change-Id: I97eb0046ab8997a68e2d6dfde5dbf3d02290c1f7
|
| 6a52d1d4061950c5358b67e180e25e8c55cbdda7 |
|
06-Mar-2011 |
buzbee <buzbee@google.com> |
Fix JUMBO failures
Fix some failures w/ the new Dalvik JUMBO opcodes on the x86 and portable
interpreters. These showed up on dalvik/test/089-jumbo-opcodes when
running with:
run-test --host 089 # x86 host-mode
run-test --portable --host 089 # portable host-mode
run-test --portable 089 # on device, portable
Change-Id: I520c8d2e001db95aa7525e4ffde7a81e2e786d38
|
| 0346e9dcddccd449c731e42ef83708ff6d8f0976 |
|
02-Mar-2011 |
Andy McFadden <fadden@android.com> |
Change invoke-object-init to /range form
The invoke-object-init instruction pretends to be a regular invoke
that only knows how to call Object.<init>. As such it always takes
one argument, and if we use the /range version we can specify the
"this" register with 16 bits instead of only 4.
Bug 3486699
Change-Id: I9ee4700c6935beee1dcbaa583b57befd33641414
|
| 3d054be0780e2bee9553711d409608495cc2c19e |
|
02-Mar-2011 |
buzbee <buzbee@google.com> |
mterp generation cleanup
Change I3a22048a introduced a new interpreter breakout mechanism, and
with it a bit of hackish ugliness in the mechanism to automatically
generate interpreter source files.
This CL applies some Lipo and Botox:
o New alt-op-start, alt-op-end commands removed - will just use
existing op-start & op-end.
o New command "handler-style" to explicitly declare interpreter
style (computed-goto, jump-table or all-c). Previous trigger
on "handler-size==0" removed.
o Alternate handler stub no longer using fixed file name, but
intead is named by command asm-alt-stub (which is modelled on
existing alt-stub command).
o Previous CL stated requirement for explicitly called-out handler
for the Dalvik dispatch opcode. Turns out this was not necessary.
Requirement removed.
Change-Id: I20f7411820715476533c2073d28f357e28c1ae52
|
| 98f3eb12bf2a33c49712e093d5cc2aa713a93aa5 |
|
01-Mar-2011 |
buzbee <buzbee@google.com> |
Exception cleanup in the assembly interpreters
Removed the last of the "exception as strings" calls from the
assembly interpreters, replacing them with the helper functions.
Change-Id: I4c44cde348ed7d2ea99f908bc22166afeb5e3d37
|
| a7d59bbafea5430fe81fc21ba94ddf6f6a63b0b3 |
|
24-Feb-2011 |
buzbee <buzbee@google.com> |
New interpreter breakout mechanism
Introduce parallel handler entry points for mterp interpreters as a step
towards fully supporting debug, profile and JIT within mterp (instead of
bailing out to the portable debug interpreter).
This CL contains most of the structural changes that need to happen,
but does not yet enable the new switch mode. In short, within the
mterp assembly interpreter register rIBASE points to an array of handlers
for Dalvik opcodes. Instead of periodically checking for suspend,
debug, profiling and JIT trace selection breakouts, rIBASE may simply
be altered to point to the parallel breakout handlers when control needs
to be rerouted. This will enable us to eliminate the separate portable
debug interpreter and the entire mechanism of switching between the fast
and portable interpreters.
The x86 implementation required a large number of changes because of the
need to dedicate a register to holding the table base. It will now use %edx
(which was previously scratch).
Changes include:
o Support for two styles of mterp assembly code generation: computed goto
and jump table (ARM uses computed goto, x86 uses jump table)
o New mterp config operators to trigger generation of alternate entry points.
o Alternate entries route execution through new dvmCheckInst(). That's
where the checking code will go.
o For x86, reserved register edx as dedicated rIBASE.
o For jump-table mterps, ignore "%break" operator and allow variable-sized
handlers with no "sister" region.
Note that the x86-atom implementation will need substantial changes
to function in this new model.
Change-Id: I3a22048adb7dcfdeba4f94fbb977b26c3ab2fcb3
|
| 8cb0d098d79af61546e275f633325794f4587602 |
|
28-Feb-2011 |
buzbee <buzbee@google.com> |
Use new negative array size exception reporting
Follow-up to change 98624 to enhance assembly interpreters to use
the new dvmThrowNegativeArraySizeException.
Change-Id: I9c8b425b3255d42afa1dc466024c03eeeb4eec23
|
| 74501e600dcb5634aa26aee0a3f57f2b45b213f2 |
|
24-Feb-2011 |
Dan Bornstein <danfuzz@android.com> |
Round three of exception cleanup.
I expanded AIOOBE since it was the odd one out, migrated the wrappers
in Exception.h to the end of the file where they're less disruptive,
and tweaked a couple other throws in the main vm code.
Change-Id: Iae11fda2c47989ce7579483df226124ffeb2ac84
|
| 9f601a917c8878204482c37aec7005054b6776fa |
|
12-Feb-2011 |
buzbee <buzbee@google.com> |
Interpreter restructuring: eliminate InterpState
The key datastructure for the interpreter is InterpState.
This change eliminates it, merging its data with the Thread structure.
Here's why:
In principio creavit Fadden Thread et InterpState. And it was good.
Thread holds thread-private state, while InterpState captures data
associated with a Dalvik interpreter activation. Because JNI calls
can result in nested interpreter invocations, we can have more than one
InterpState for each actual thread. InterpState was relatively small,
and it all worked well. It was used enough that in the Arm version
a register (rGLUE) was dedicated to it.
Then, along came the JIT guys, who saw InterpState as a convenient place
to dump all sorts of useful data that they wanted quick access to through
that dedicated register. InterpState grew and grew. In terms of
space, this wasn't a big problem - but it did mean that the initialization
cost of each interpreter activation grew as well. For applications
that do a lot of callbacks from native code into Dalvik, this is
measurable. It's also mostly useless cost because much of the JIT-related
InterpState initialization was setting up useful constants - things that
don't need to be saved and restored all the time.
The biggest problem, though, deals with thread control. When something
interesting is happening that needs all threads to be stopped (such as
GC and debugger attach), we have access to all of the Thread structures,
but we don't have access to all of the InterpState structures (which
may be buried/nested on the native stack). As a result, polling for
thread suspension is done via a one-indirection pointer chase. InterpState
itself can't hold the stop bits because we can't always find it, so
instead it holds a pointer to the global or thread-specific stop control.
Yuck.
With this change, we eliminate InterpState and merge all needed data
into Thread. Further, we replace the decidated rGLUE register with a
pointer to the Thread structure (rSELF). The small subset of state
data that needs to be saved and restored across nested interpreter
activations is collected into a record that is saved to the interpreter
frame, and restored on exit. Further, these small records are linked
together to allow tracebacks to show nested activations. Old InterpState
variables that simply contain useful constants are initialized once at
thread creation time.
This CL is large enough by itself that the new ability to streamline
suspend checks is not done here - that will happen in a future CL. Here
we just focus on consolidation.
Change-Id: Ide6b2fb85716fea454ac113f5611263a96687356
|
| 6af2ddd107842c3737c04c37343cac9be17f4209 |
|
17-Feb-2011 |
Andy McFadden <fadden@android.com> |
Defer marking of objects as finalizable
This shifts responsibility for marking an object as "finalizable" from
object creation to object initialization. We want to make the object
finalizable when Object.<init> completes. For performance reasons we
skip the call to the Object constructor (which doesn't do anything)
and just take the opportunity to check the class flag.
Handling of clone()d object isn't quite right yet.
Also, fixed a minor glitch in stubdefs.
Bug 3342343
Change-Id: I5b7b819079e5862dc9cbd1830bb445a852dc63bf
|
| b387fe1b970a216c09d2abc98c893ff1fff3e512 |
|
16-Feb-2011 |
Andy McFadden <fadden@android.com> |
Fix some asm .size directives
We were missing a .size directive for dvmPlatformInvoke, and the
directive for the mterp handlers wasn't being handled right. Threw
in a bonus directive for the entry point and the "assist debugger"
stuff that wraps method calls.
Bug 3456786
Change-Id: Ideee64a496e54eb09008410e9e9eba652b59f403
|
| 750d110b62cef538e193b6f91f5239b0c4b63ef1 |
|
12-Feb-2011 |
Andy McFadden <fadden@android.com> |
Rename invoke-direct-empty to invoke-object-init
The invoke-direct-empty instruction was introduced to remove the
overhead of calling the empty Object constructor. We now need it
to do some extra work on behalf of object construction, so it's
appropriate to change the instruction name to match the role it
fills rather than the more general role it was hoped to fill.
No functional changes.
Bug 3342343
Change-Id: I65dd6a2c00c99581c9a19b16fe193b70642c8fbb
|
| 01605d2b668e8e1701cfdfa302dde847b9171fc9 |
|
01-Feb-2011 |
Carl Shapiro <cshapiro@google.com> |
Remove the unused monitor tracking and deadlock prediction code.
This feature has been in the code base for several releases but has never
been enabled.
Change-Id: Ia770b03ebc90a3dc7851c0cd8ef301f9762f50db
|
| cfdeca37fcaa27c37bad5077223e4d1e87f1182e |
|
14-Jan-2011 |
Ben Cheng <bccheng@android.com> |
Add runtime support for method based compilation.
Enhanced code cache management to accommodate both trace and method
compilations. Also implemented a hacky dispatch routine for virtual
leaf methods.
Microbenchmark showed 3x speedup in leaf method invocation.
Change-Id: I79d95b7300ba993667b3aa221c1df9c7b0583521
|
| cb3081f675109049e63380170b60871e8275f9a8 |
|
14-Jan-2011 |
buzbee <buzbee@google.com> |
Consolidate mterp's debug/profile/suspend control
This is a step towards full debug & profiling support in JIT'd code.
Previously, the interpreter made multiple distinct checks for pending
suspend requests, debugger and profiler checks at each safe point.
This CL moves the individual controls into a single control word,
significantly speeding up the safe-point check code path in the common
fast case.
In short, any time some VM component wants control to break at a safe
point it will set a bit in gDvm.interpBreak, which will be examined
at the safe point check in footer.S. In the old code, the safe point
check consisted of 11 instructions (including 6 loads). The new sequence
is 6 instructions (4 loads - two of which are needed and two are
speculative to fill otherwise stalling slots).
This code path is hot enough in the interpreter that we actually see
some measureable speedups in benchmarks. The old sieve benchmark
improves from 252 to 256 (~1.5%).
As part of the change, global debuggerActive and activeProfilers variables
have been eliminated as redundant. Note also that there is a subtle
change in thread suspension. Thread suspend request counts are kept on
a per-thread basis, and previously each thread would only examine its own
suspend count. With this change, a bit has been allocated in interpBreak
to signify that at least one suspend request is active across all
threads. This bit is treated as "some thread is supposed to
suspend, check to see if it's me".
Change-Id: I527dc918f58d1486ef3324136080ef541a775ba8
|
| 71eee1f0c2eb514585fdbee16730c9c2209e8f68 |
|
04-Jan-2011 |
jeffhao <jeffhao@google.com> |
Added vm support for new jumbo opcodes.
This enables jumbo opcodes by default, and they will get used by the
current build without modification. Support has been added for arm, x86,
and the portable interpreter. x86-atom support is on the TODO list. This
commit also includes a test for the new jumbo opcodes.
Change-Id: Ic3f1b41b51645861c5196f76aaf0e96e727ea537
|
| dfd1bbf07d98c82a6072182f705f64a30ebf480b |
|
23-Sep-2010 |
buzbee <buzbee@google.com> |
Experimental x86 Jit trace selection
Experimental support for trace selection for x86 host mode operation.
Not enabled by default. Turned on by setting WITH_HOST_DALVIK true
and WITH_JIT true. When enabled, profiles during x86 fast interpreter
operation, selects hot traces and "compiles" traces consisting of jumps
back to the interpreter.
First in a series of experimental x86 support checkins.
Change-Id: I0e423ec58a7bf01f226cb486f55de2841fab1002
|
| 90f15431b24a4004fab2db70f273155fcd1c42a4 |
|
03-Dec-2010 |
Dan Bornstein <danfuzz@android.com> |
Make opcode 00ff be called "dispatch-ff".
With this change, it's still implemented as an unused opcode, but
it's now ready for its new life!
Change-Id: Ic70d311704925067e47d87b657d133a792144e65
|
| 7dc44a1c9a37d528f080eb51739da80696bb1f05 |
|
02-Dec-2010 |
buzbee <buzbee@google.com> |
x86-mterp bug fix; support host mode in tests
A recent x86 housecleaning change introduced a bug in OP_FILLED_ARRAY.
Fixed that, plus hacked up dalvik test scripts to support host
mode operation (with --host)
Change-Id: Iaf8b1ab753f93fa344e64f984a3c4696433ec9aa
|
| 63644657f74e0a5d05f2c5fb56a18872e7ac7427 |
|
20-Nov-2010 |
Elliott Hughes <enh@google.com> |
Better ArrayStoreException detail messages.
This fixes the portable interpreter, ARM, and x86. System.arraycopy was already
doing the right thing.
Bug: 3216051
Change-Id: I8a675eb62d6e7fd53a009f53ce8e34f93799b18c
|
| bb08b668b174d6babcc3866201aaf1d3b7293ada |
|
19-Nov-2010 |
Elliott Hughes <enh@google.com> |
Better ClassCastException detail messages for x86.
Bug: 3210374
Change-Id: I5b6ff68b611f56276ef6e519511ed4dee22b0136
|
| 3e1bbffab14075a340ad0165c6ada6a43875a01f |
|
27-Oct-2010 |
buzbee <buzbee@google.com> |
x86: Improve ArrayIndexOutOfBoundsException detail messages
issue 3122084
Changes the x86 interpreter to use the new dvmThrowAIOOBE call
for out of bounds exception w/ more useful info.
Change-Id: Ic196cc99c561bf31953993a6928f574e5c5bf831
|
| ef1ed3c5cbde4de64e1991de2dbea57efd964841 |
|
14-Oct-2010 |
buzbee <buzbee@google.com> |
x86 mterp: fix cherry-pick/merge, issue 3095771
Bug http://b/issue?id=3095771
Change
https://android-git.corp.google.com/g/#change,70700
was a cherry-pick/merge of
https://android-git.corp.google.com/g/#change,70388
It was not properly merged, and resulting in the register holding
the object head to be trashed (and subsequently broke GC).
Change-Id: Ic480104e3a643a5b744d36eb0aefaedd3e4f925c
|
| e09a766f3a964fb98296939ce1f92b8c95bf8c25 |
|
14-Oct-2010 |
buzbee <buzbee@google.com> |
x86 mterp: fix cherry-pick/merge, issue 3095771
Bug http://b/issue?id=3095771
Change
https://android-git.corp.google.com/g/#change,70700
was a cherry-pick/merge of
https://android-git.corp.google.com/g/#change,70388
It was not properly merged, and resulting in the register holding
the object head to be trashed (and subsequently broke GC).
Change-Id: Ic480104e3a643a5b744d36eb0aefaedd3e4f925c
|
| b78c76f88ea42e7a3b295c210ca9ee86e7290043 |
|
01-Oct-2010 |
buzbee <buzbee@google.com> |
GC Card marking fix for SPUT_OBJECT - use correct object head
Change-Id: I8b84a4f1e1690f5b62de7404ea6ede00317848bb
|
| d82097f6b409c5cd48568e54eb701604c3cceb18 |
|
27-Sep-2010 |
buzbee <buzbee@google.com> |
Change GC card making to use object head, bug fix for volatile sput obj
This CL changes the way we mark GC card to consistently use the object
head (previously, we marked somewhere in the object - often the head, but
not always). Also, previously a coding error caused us to skip the card
mark for OP_APUT_OBJECT_VOLATILES. Fixed here.
Change-Id: I133ef6395c51a0466c9708209b08e79c3083aff2
|
| d3b0a4bf6b2e38e6e9e80e203ca753e941084103 |
|
27-Sep-2010 |
buzbee <buzbee@google.com> |
Change GC card making to use object head, bug fix for volatile sput obj
This CL changes the way we mark GC card to consistently use the object
head (previously, we marked somewhere in the object - often the head, but
not always). Also, previously a coding error caused us to skip the card
mark for OP_APUT_OBJECT_VOLATILES. Fixed here.
Change-Id: I53eb333b9bd0b770201af0dc617d9a8f38afa699
|
| b703ba2fbbf626a087903b5ee890989d18fd0c2b |
|
26-Sep-2010 |
buzbee <buzbee@google.com> |
Fix OP_USHR_LONG in x86 mterp (Issue 3038137)
Change https://android-git.corp.google.com/g/#change,67744 introduced
bad hand-scheduling in 64-bit unsigned 3-operand right shifts which
clobbered the result before storing it.
Change-Id: Ic862fa683092d09476510d78e5edd1735f09f8c2
|
| c11e0e14df2c0c4264e5cc6c3e96d14832cbecad |
|
22-Sep-2010 |
buzbee <buzbee@google.com> |
Fix x86 mterp "longjmp"
The recent x86 mterp update failed to properly restore callee save
registers when returning from the call to dvmMterpStdRun.
Change-Id: Ied73cc5fb380a6375d1f71ce679003fbc293d08d
|
| 3b8a9072510222067b7c48fe2d59d1e58436be24 |
|
21-Sep-2010 |
buzbee <buzbee@google.com> |
Fix 64-bit 3-operand multiplication in x86 mterp.
rPC was being unspilled a bit late.
Change-Id: Idf73b9eeeb972f3fb1861224397d0592c6d3bb2f
|
| f3e177289ac078f18401cfd8eebafe584dd0d01f |
|
12-Sep-2010 |
buzbee <buzbee@google.com> |
x86 mterp: reduce x86/x86-atom differences
To ease future x86 development, elminate unnecessary differences
between x86 and x86-atom targets.
1. Macros instead of defines (cosmetic change)
2. Register naming convention (cosmetic change)
3. Register usage convention
- Drop rIBASE, freeing %edx for general usage
- use %edi for rPC (callee-save) & eliminate spills
4. Spill & temp frame layout
5. rGLUE usage 0(%ebp) instead of -24(%ebp)
6. Jump table transition between instruction interpretations
instead of computed goto.
7. Change entry convention for instruction handlers:
Previously:
%bl contains 8-bit Dalvik opcode
%bh contains 2nd half of 16-bit Dalvik insn (usually AA or BA)
upper 16 bits of %ebx are zero
Now:
%bl contains 2nd half of 16-bit Dalvik insn (usually AA or BA)
upper 24 bits of %ebx are zero
8. Include copies of x86-atom macros and defines into x86 build. This
allows the x86 build to mix-and-match x86 and x86-atom handlers
via the normal config mechanism. [Note - only for non-control-flow
instructions. There are still some conflicts in the footer.S
main loop re-entry points].
Change-Id: Ib9d549b56f7ffd7420f9dbf97b2169f65603ee83
|
| 7520ee7ff226e12e06818561b15741d2575072e3 |
|
18-Sep-2010 |
buzbee <buzbee@google.com> |
Add source code skeletons for x86 work. No actual JIT'ng yet.
Change-Id: Ic94a916e777e9bc5163cf205899daf9c18dcafe1
|
| 291758c5c4902900c6f86794ba8ab9cad9b26197 |
|
10-Sep-2010 |
Andy McFadden <fadden@android.com> |
Add return-void-barrier instruction.
This introduces the return-void-barrier instruction, which is identical
to return-void on UP systems, but provides an additional store/store
barrier on SMP. This is intended for use in constructors of objects
with final fields.
The assembler doesn't like "dmb st", and we don't have an
ANDROID_MEMBAR_STORE barrier defined, so this currently uses full
fences.
This just defines the new instruction. It's not actually used yet.
Also, removed some stale "unused" files from the x86 and x86-atom
directories.
Bug 2965743.
Change-Id: I072e372fd2d57f2617a8d4fff5fd4b38bdda75d1
|
| 0d615c3ce5bf97ae65b9347ee77968f38620d5e8 |
|
18-Aug-2010 |
Andy McFadden <fadden@android.com> |
Always support debugging and profiling.
This eliminates the use of the WITH_DEBUGGER and WITH_PROFILER
conditional compilation flags. We've never shipped a device without
these features, and it's unlikely we ever will. They're not worth
the code clutter they cause.
As usual, since I can't test the x86-atom code I left that alone and
added an item to the TODO list.
Bug 2923442.
Change-Id: I335ebd5193bc86f7641513b1b41c0378839be1fe
|
| f079e1d5c51fc33ab537bbdfc79cbac8e771d7e9 |
|
05-Aug-2010 |
buzbee <buzbee@google.com> |
Tweaks to x86 mterp periodic checks [issue 2634642]
Update the x86 mterp main interpetation loop to match Arm and the portable
interpreter by checking for debugger/profiler after suspends. Also,
enable ability to skip a load when checking for active debugger (both
Arm and x86).
Related cl: https://android-git.corp.google.com/g/#change,50229
Change-Id: Ic5d0f102b2250393eaf4405e4cafb7678b1a563e
|
| 3d95064ad1d8e6da4f9a523b2c2f11cf1f1ea952 |
|
16-Jul-2010 |
buzbee <buzbee@google.com> |
x86 interpreter write barrier support
Fix for 2837703. Also added support for new Dalvik volatile ops.
Change-Id: Ic2b8d31afc8806077c5bf27ec90c643f7e47591e
|
| c35a2ef53d0cccd6f924eeba36633220ec67c32e |
|
17-Jun-2010 |
Andy McFadden <fadden@android.com> |
Add opcodes for volatile field accesses
This adds instructions for {i,s}{get,put}{,-object}-volatile, for a
total of eight new instructions.
On SMP systems, these instructions will be substituted in for existing
field access instructions, either by dexopt or during just-in-time
verification. Unlike the wide-volatile instructions, these will not be
used at all when the VM is not built for SMP.
(Ideally we'd omit the volatile instruction implementations entirely on
non-SMP builds, but that requires a little work in gen-mterp.py.)
The change defines and implements the opcodes and support methods, but
does not cause them to be used.
Also, changed dvmQuasiAtomicRead64's argument to be const.
Change-Id: I9e44fe881e87f27aa41f6c6e898ec4402cb5493e
|
| 7365493ad8d360c1dcf9cd8b6eee62747af01cae |
|
09-Jun-2010 |
Carl Shapiro <cshapiro@google.com> |
Remove repeated newlines at the end of files.
Change-Id: I1e3d103a7b932ef21acedb6438c0f26b315df28f
|
| de75089fb7216d19e9c22cce4dc62a49513477d3 |
|
09-Jun-2010 |
Carl Shapiro <cshapiro@google.com> |
Remove trailing whitespace.
Change-Id: I95534bb2b88eaf48f2329282041118cd034c812b
|
| 8ba2708ea118381f2df5ca55b9bad2ae4c050504 |
|
21-May-2010 |
Andy McFadden <fadden@android.com> |
Added EXPORT_PC to "throw" instruction.
For bug 2700761.
Change-Id: I889e59ea35d9cadd99fc884e5b1301a4cf103f93
|
| fbdcfb9ea9e2a78f295834424c3f24986ea45dac |
|
29-May-2010 |
Brian Carlstrom <bdc@google.com> |
Merge remote branch 'goog/dalvik-dev' into dalvik-dev-to-master
Change-Id: I0c0edb3ebf0d5e040d6bbbf60269fab0deb70ef9
|
| c95e0fbce4f77b2b08eb48205e405793de0d4248 |
|
29-Apr-2010 |
Andy McFadden <fadden@android.com> |
Rework common_periodicChecks.
The function was rewritten to optimize the common path. The control flow
now matches the C version, which tests for debugger/profiler even if the
previous test for suspension came up true.
This also adds a minor optimization on the test for debugger attachment,
allowing us to skip a load from memory if the process is simply not
debuggable. (The optimization isn't yet enabled because a similar change
must be made to the x86 asm code.)
The VM apparently hadn't been built without debugging/profiling support
for a while, so this fixes those places (necessary to be able to test
all forms of the new code).
Bug 2634642.
Change-Id: I096b58c961bb73ee0d128ba776d68dbf29bba924
|
| 5387824f19033ed51a945fbc8c2b574998404b3d |
|
05-Mar-2010 |
Andy McFadden <fadden@android.com> |
Add instructions for volatile wide fields.
This adds four new instructions for accessing volatile wide fields (long
and double). The JLS requires that such accesses are atomic, but the
VM doesn't otherwise make guarantees about the atomicity of reads and
writes on 64-bit fields.
There are no behavioral changes. This just adds definitions for the new
instructions and a couple of tests. The current implementation is just
the non-volatile form of the instructions or a C stub, but since we're
not generating them it doesn't really matter yet.
Also:
- bumped Dalvik version to 1.3.0
- added a note to the x86-atom TODO list
For bug 1633591.
|
| 668628abe05cb30f86bd02c824f7219a7e20b82c |
|
16-Feb-2010 |
Bill Buzbee <buzbee@google.com> |
Jit: Monitor exit, possible fix for Issue 2396073
Two problems with monitor-exit:
1. The Jit code wasn't checking for exception thrown following
unlocks of fat locks using dvmUnlockObject().
2. The mterp interpreter unlock code branched to handle exceptions
thrown during dvmUnlockObject() with the wrong dalvik PC (the
dPC of the unlock, rather than the instruction following the unlock).
Similar issue with the x86 interpreter fixed. Also, deleted armv7-a
MONITOR_ENTER template, which turned out to be identical to the armv5te
one.
|
| 6bbdd6b005ec5cb567ec9576190a7cd784248c5c |
|
16-Feb-2010 |
Bill Buzbee <buzbee@google.com> |
Jit: Monitor exit, possible fix for Issue 2396073
Two problems with monitor-exit:
1. The Jit code wasn't checking for exception thrown following
unlocks of fat locks using dvmUnlockObject().
2. The mterp interpreter unlock code branched to handle exceptions
thrown during dvmUnlockObject() with the wrong dalvik PC (the
dPC of the unlock, rather than the instruction following the unlock).
Similar issue with the x86 interpreter fixed. Also, deleted armv7-a
MONITOR_ENTER template, which turned out to be identical to the armv5te
one.
|
| b0a0541b59d1126ff77c88de742b4a74579fe296 |
|
19-Nov-2009 |
Andy McFadden <fadden@android.com> |
Add execute-inline/range instruction.
Like "execute-inline", this is an instruction generated by dexopt that
replaces a method invoke instruction. It's useful for small, frequently
called methods in the core libs.
As with execute-inline, we allow at most 4 arguments, but with /range
we're no longer limited to the low 16 registers.
Also: marked execute-inline as being able to throw an exception.
Needed: native x86 implementation; support in JIT.
For bug 2268232.
|
| 96516932f1557d8f48a8b2dbbb885af01a11ef6e |
|
29-Oct-2009 |
Andy McFadden <fadden@android.com> |
Change the way breakpoints work.
This replaces the breakpoint mechanism with a more efficient approach.
We now insert breakpoint instructions into the bytecode stream instead of
maintaining a table. This requires mapping DEX files as private instead
of shared, which allows copy-on-write to work. mprotect() is used to
guard the pages against inadvertent writes.
Unused opcode EC is now OP_BREAKPOINT. It's not recognized by dexdump or
any interpreter except portdbg, but it can be encountered by the bytecode
verifier (the debugger can request breakpoints in unverified code).
Breakpoint changes are blocked while the verifier runs to avoid races.
This eliminates method->debugBreakpointCount, which is no longer needed.
(Also, it clashed with LinearAlloc's read-only mode.)
The deferred verification error mechanism was using a code-copying
approach to modify the bytecode stream. That has been changed to use
the same copy-on-write modification mechanism.
Also, normalized all PAGE_SIZE/PAGESIZE references to a single
SYSTEM_PAGE_SIZE define.
Simple Fibonacci computation test times (opal-eng):
JIT, no debugger: 10.6ms
Fast interp, no debugger: 36ms
Portable interp, no debugger: 43.8ms
ORIG debug interp, no breakpoints set: 458ms
ORIG debug interp, breakpoint set nearby: 697ms
NEW debug interp, no breakpoints set: 341ms
NEW debug interp, breakpoints set nearby: 341ms
Where "nearby" means there's a breakpoint in the method doing the
computation that isn't actually hit -- the VM had an optimization where
it flagged methods with breakpoints and skipped some of the processing
when possible.
The bottom line is that code should run noticeably faster while a
debugger is attached.
|
| 72e93344b4d1ffc71e9c832ec23de0657e5b04a5 |
|
13-Nov-2009 |
Jean-Baptiste Queru <jbq@google.com> |
eclair snapshot
|
| 6ed1a0f396a1857c31b486d3e93ee2dbeb49a6cd |
|
11-Sep-2009 |
Andy McFadden <fadden@android.com> |
Display additional information on stack overflow.
This required passing an additional argument into dvmHandleStackOverflow,
which is called directly from mterp. Fortunately the method being
called is sitting in a register for both ARM and x86, so this is a
fairly simple change.
For internal bug 2110533.
|
| d5ab726b65d7271be261864c7e224fb90bfe06e0 |
|
25-Aug-2009 |
Andy McFadden <fadden@android.com> |
Another round of scary indirect ref changes.
This change adds a not-really-working implementation to Jni.c, with
various changes #ifdefed throughout the code. The ifdef is currently
disabled, so the old behavior should continue. Eventually the old
version will be stripped out and the ifdefs removed.
This renames the stack's "localRefTop" field, which nudged a bunch of
code. The name wasn't really right before (it's the *bottom* of the
local references), and it's even less right now. This and one other
mterp-visible constant were changed, which caused some ripples through
mterp and the JIT, but the ifdeffing was limited to one in
asm-constants.h (and the constant is the same both ways, so toggling the
ifdef won't require rebuilding asm sources).
Some comments and arg names in ReferenceTable were updated for the
correct orientation of bottom vs. top.
Some adjustments were made to the JNI code, e.g. dvmCallMethod now needs
to understand if it needs to convert reference arguments from
local/global refs to pointers (it's called from various places
throughout the VM).
|
| be74aeb457df67355ce7c16721ecc436c8fd770a |
|
29-Jul-2009 |
Bill Buzbee <buzbee@google.com> |
Fix for 1857865: Need x86 implementation for OP_THROW_VERIFICATION_ERROR
|
| b51ea11c70602918c42764bfafe92a997d3b1803 |
|
09-May-2009 |
Andy McFadden <fadden@android.com> |
Defer reporting of certain verifier failures.
The verifier currently reports all failures immediately. Certain failures,
such as the failure to resolve a method, or the determination that access
to a field is not allowed, are supposed to deferred until the first time
that executing code does something that could cause the resolution.
With this change, several kinds of verification failures are deferred.
This is done by making a writable copy of the bytecode and replacing the
failing instruction with an "always throw" opcode.
Gory details:
- Added throw-verification-error instruction. Implemented in "portable"
and ARM interpreters. x86 uses portable form through stub.
- Added a function that creates a copy of a DexCode area and makes the
bytecodes writable.
- Added code that replaces a single instruction with an "always throw".
- Replaced runtime check for abstract/interface in new-instance with a
check at verification time.
- Added a test to exercise the deferred error mechanism.
- Minor cleanups (replaced tab, bad valgrind command, ...).
|
| 3a1aedbc9777eab6275a360b93b81b079464238e |
|
07-May-2009 |
Andy McFadden <fadden@android.com> |
Added throw-verification-error instruction.
This is for the deferred verifier error reporting. It replaces OP_UNUSED_ED.
The instructions aren't actually used yet, which is good since the x86
version hasn't been written yet.
The mterp regen also pushed out some recent-ish changes that hadn't
propagated to the armv4t sources.
|
| 99409883d9c4c0ffb49b070ce307bb33a9dfe9f1 |
|
19-Mar-2009 |
The Android Open Source Project <initial-contribution@android.com> |
auto import //branches/master/...@140412
|
| f6c387128427e121477c1b32ad35cdcaa5101ba3 |
|
04-Mar-2009 |
The Android Open Source Project <initial-contribution@android.com> |
auto import from //depot/cupcake/@135843
|
| f72d5de56a522ac3be03873bdde26f23a5eeeb3c |
|
04-Mar-2009 |
The Android Open Source Project <initial-contribution@android.com> |
auto import from //depot/cupcake/@135843
|
| 31e30105703263782efd450d356cd67ea01af3b7 |
|
03-Mar-2009 |
The Android Open Source Project <initial-contribution@android.com> |
auto import from //depot/cupcake/@132589
|
| 6dcac3deb3c19dc634470eb30b2daedf2b201bd4 |
|
03-Mar-2009 |
The Android Open Source Project <initial-contribution@android.com> |
auto import from //depot/cupcake/@137055
|
| 5d709784bbf5001012d7f25172927d46f6c1abe1 |
|
11-Feb-2009 |
The Android Open Source Project <initial-contribution@android.com> |
auto import from //branches/cupcake/...@130745
|
| c4080f6bdeda19901a508cc75f96ac7e07903918 |
|
11-Feb-2009 |
Johnnie Birch <johnnie.l.birch.jr@intel.com> |
This patch rewrites common_invokeOld for the x86 fast interpreter. The implementation is similar to what is done for the armv5 code.
Testing shows the patch provides a performance boost to benchmarks such as Caffeine Mark. When testing the simulator build on an Intel(R) Core(TM)2 Quad CPU Q9550 @ 2.83GHz, the string score for Caffeine Mark improved by 6%, the Method score improved by 12% and the overall score improved by 3%.
This patch is one of our incremental efforts to merge some Intel's x86 fast interpreter features in http://review.source.android.com/Gerrit#change,6041 to the mterp/x86 directory.
|
| 4c1a2915e40eceeb68dbc323d28b8bf8763af83b |
|
20-Jan-2009 |
The Android Open Source Project <initial-contribution@android.com> |
auto import from //branches/cupcake/...@127101
|
| cc05ad238516f1303687aba4a978e24e57c0c07a |
|
10-Jan-2009 |
The Android Open Source Project <initial-contribution@android.com> |
auto import from //branches/cupcake/...@125939
|
| 89c1feb0a69a7707b271086e749975b3f7acacf7 |
|
18-Dec-2008 |
The Android Open Source Project <initial-contribution@android.com> |
Code drop from //branches/cupcake/...@124589
|