Now, rb_call_info contains how to call the method with tuple of
(mid, orig_argc, flags, kwarg). Most of cases, kwarg == NULL and
mid+argc+flags only requires 64bits. So this patch packed
rb_call_info to VALUE (1 word) on such cases. If we can not
represent it in VALUE, then use imemo_callinfo which contains
conventional callinfo (rb_callinfo, renamed from rb_call_info).
iseq->body->ci_kw_size is removed because all of callinfo is VALUE
size (packed ci or a pointer to imemo_callinfo).
To access ci information, we need to use these functions:
vm_ci_mid(ci), _flag(ci), _argc(ci), _kwarg(ci).
struct rb_call_info_kw_arg is renamed to rb_callinfo_kwarg.
rb_funcallv_with_cc() and rb_method_basic_definition_p_with_cc()
is temporary removed because cd->ci should be marked.
This removes the warnings added in 2.7, and changes the behavior
so that a final positional hash is not treated as keywords or
vice-versa.
To handle the arg_setup_block splat case correctly with keyword
arguments, we need to check if we are taking a keyword hash.
That case didn't have a test, but it affects real-world code,
so add a test for it.
This removes rb_empty_keyword_given_p() and related code, as
that is not needed in Ruby 3. The empty keyword case is the
same as the no keyword case in Ruby 3.
This changes rb_scan_args to implement keyword argument
separation for C functions when the : character is used.
For backwards compatibility, it returns a duped hash.
This is a bad idea for performance, but not duping the hash
breaks at least Enumerator::ArithmeticSequence#inspect.
Instead of having RB_PASS_CALLED_KEYWORDS be a number,
simplify the code by just making it be rb_keyword_given_p().
Saves comitters' daily life by avoid #include-ing everything from
internal.h to make each file do so instead. This would significantly
speed up incremental builds.
We take the following inclusion order in this changeset:
1. "ruby/config.h", where _GNU_SOURCE is defined (must be the very
first thing among everything).
2. RUBY_EXTCONF_H if any.
3. Standard C headers, sorted alphabetically.
4. Other system headers, maybe guarded by #ifdef
5. Everything else, sorted alphabetically.
Exceptions are those win32-related headers, which tend not be self-
containing (headers have inclusion order dependencies).
Before this commit, Kernel#lambda can't tell the difference between a
directly passed literal block and one passed with an ampersand.
A block passed with an ampersand is semantically speaking already a
non-lambda proc. When Kernel#lambda receives a non-lambda proc, it
should simply return it.
Implementation wise, when the VM calls a method with a literal block, it
places the code for the block on the calling control frame and passes a
pointer (block handler) to the callee. Before this commit, the VM
forwards block arguments by simply forwarding the block handler, which
leaves the slot for block code unused when a control frame forwards its
block argument. I use the vacant space to indicate that a frame has
forwarded its block argument and inspect that in Kernel#lambda to detect
forwarded blocks.
This is a very ad-hoc solution and relies *heavily* on the way block
passing works in the VM. However, it's the most self-contained solution
I have.
[Bug #15620]
(This is the second try of 036bc1da6c6c9b0fa9b7f5968d897a9554dd770e.)
If iseq is GC'ed, the pointer of iseq may be reused, which may hide a
deprecation warning of keyword argument change.
http://ci.rvm.jp/results/trunk-test1@phosphorus-docker/2474221
```
1) Failure:
TestKeywordArguments#test_explicit_super_kwsplat [/tmp/ruby/v2/src/trunk-test1/test/ruby/test_keyword.rb:549]:
--- expected
+++ actual
@@ -1 +1 @@
-/The keyword argument is passed as the last hash parameter.* for `m'/m
+""
```
This change ad-hocly adds iseq_unique_id for each iseq, and use it
instead of iseq pointer. This covers the case where caller is GC'ed.
Still, the case where callee is GC'ed, is not covered.
But anyway, it is very rare that iseq is GC'ed. Even when it occurs, it
just hides some warnings. It's no big deal.
If iseq is GC'ed, the pointer of iseq may be reused, which may hide a
deprecation warning of keyword argument change.
http://ci.rvm.jp/results/trunk-test1@phosphorus-docker/2474221
```
1) Failure:
TestKeywordArguments#test_explicit_super_kwsplat [/tmp/ruby/v2/src/trunk-test1/test/ruby/test_keyword.rb:549]:
--- expected
+++ actual
@@ -1 +1 @@
-/The keyword argument is passed as the last hash parameter.* for `m'/m
+""
```
This change ad-hocly adds iseq_unique_id for each iseq, and use it
instead of iseq pointer. This covers the case where caller is GC'ed.
Still, the case where callee is GC'ed, is not covered.
But anyway, it is very rare that iseq is GC'ed. Even when it occurs, it
just hides some warnings. It's no big deal.
This commit introduces an "inline ivar cache" struct. The reason we
need this is so compaction can differentiate from an ivar cache and a
regular inline cache. Regular inline caches contain references to
`VALUE` and ivar caches just contain references to the ivar index. With
this new struct we can easily update references for inline caches (but
not inline var caches as they just contain an int)
These functions are used from within a compilation unit so we can
make them static, for better binary size. This changeset reduces
the size of generated ruby binary from 26,590,128 bytes to
26,584,472 bytes on my macihne.
This removes the security features added by $SAFE = 1, and warns for access
or modification of $SAFE from Ruby-level, as well as warning when calling
all public C functions related to $SAFE.
This modifies some internal functions that took a safe level argument
to no longer take the argument.
rb_require_safe now warns, rb_require_string has been added as a
version that takes a VALUE and does not warn.
One public C function that still takes a safe level argument and that
this doesn't warn for is rb_eval_cmd. We may want to consider
adding an alternative method that does not take a safe level argument,
and warn for rb_eval_cmd.
Looking at the list of symbols inside of libruby-static.a, I found
hundreds of functions that are defined, but used from nowhere.
There can be reasons for each of them (e.g. some functions are
specific to some platform, some are useful when debugging, etc).
However it seems the functions deleted here exist for no reason.
This changeset reduces the size of ruby binary from 26,671,456
bytes to 26,592,864 bytes on my machine.
Add an experimental `__builtin_inline!(c_expression)` special intrinsic
which run a C code snippet.
In `c_expression`, you can access the following variables:
* ec (rb_execution_context_t *)
* self (const VALUE)
* local variables (const VALUE)
Not that you can read these variables, but you can not write them.
You need to return from this expression and return value will be a
result of __builtin_inline!().
Examples:
`def foo(x) __builtin_inline!('return rb_p(x);'); end` calls `p(x)`.
`def double(x) __builtin_inline!('return INT2NUM(NUM2INT(x) * 2);')`
returns x*2.
Support loading builtin features written in Ruby, which implement
with C builtin functions.
[Feature #16254]
Several features:
(1) Load .rb file at boottime with native binary.
Now, prelude.rb is loaded at boottime. However, this file is contained
into the interpreter as a text format and we need to compile it.
This patch contains a feature to load from binary format.
(2) __builtin_func() in Ruby call func() written in C.
In Ruby file, we can write `__builtin_func()` like method call.
However this is not a method call, but special syntax to call
a function `func()` written in C. C functions should be defined
in a file (same compile unit) which load this .rb file.
Functions (`func` in above example) should be defined with
(a) 1st parameter: rb_execution_context_t *ec
(b) rest parameters (0 to 15).
(c) VALUE return type.
This is very similar requirements for functions used by
rb_define_method(), however `rb_execution_context_t *ec`
is new requirement.
(3) automatic C code generation from .rb files.
tool/mk_builtin_loader.rb creates a C code to load .rb files
needed by miniruby and ruby command. This script is run by
BASERUBY, so *.rb should be written in BASERUBY compatbile
syntax. This script load a .rb file and find all of __builtin_
prefix method calls, and generate a part of C code to export
functions.
tool/mk_builtin_binary.rb creates a C code which contains
binary compiled Ruby files needed by ruby command.
To perform a regular method call, the VM needs two structs,
`rb_call_info` and `rb_call_cache`. At the moment, we allocate these two
structures in separate buffers. In the worst case, the CPU needs to read
4 cache lines to complete a method call. Putting the two structures
together reduces the maximum number of cache line reads to 2.
Combining the structures also saves 8 bytes per call site as the current
layout uses separate two pointers for the call info and the call cache.
This saves about 2 MiB on Discourse.
This change improves the Optcarrot benchmark at least 3%. For more
details, see attached bugs.ruby-lang.org ticket.
Complications:
- A new instruction attribute `comptime_sp_inc` is introduced to
calculate SP increase at compile time without using call caches. At
compile time, a `TS_CALLDATA` operand points to a call info struct, but
at runtime, the same operand points to a call data struct. Instruction
that explicitly define `sp_inc` also need to define `comptime_sp_inc`.
- MJIT code for copying call cache becomes slightly more complicated.
- This changes the bytecode format, which might break existing tools.
[Misc #16258]
On Android, a signal handler that is not SIG_DFL is set by default for
SIGSEGV. Ruby's install_sighandler inserts Ruby's handler only when the
signal has no handler, so it does not insert Ruby's SEGV report handler,
which caused some test failures.
This changeset forces to install Ruby's handler for some fatal signals
(sigbus, sigsegv, and sigill). They keep the original handlers, and
call them when the interpreter receives the signals.
Just refactoring.
The name "rb_bug_context" is completely unclear for me.
(Can you see that "context" means "machine register context"?)
The context is available only when a fatal signal (sigbus, sigsegv, or
sigill) is received; in fact, the function is used only for fatal
signals. So, I think the name should be changed.
ko1 cannot remember why he introduced the function. And it is not used.
After it is removed, the argument "base_block" of
rb_iseq_compile_with_option is always zero.
This reverts commits: 10d6a3aca78ba48c1b85fba8627dc1dd883de5ba6c6a25feca167e6b48f17cb96d41a53207979278595b3c4fdd1521f7cf89c11c5e69accf336082033632a812c0f56506be0d86427a3219 .
The reason for the revert is that we observe ABA problem around
inline method cache. When a cache misshits, we search for a
method entry. And if the entry is identical to what was cached
before, we reuse the cache. But the commits we are reverting here
introduced situations where a method entry is freed, then the
identical memory region is used for another method entry. An
inline method cache cannot detect that ABA.
Here is a code that reproduce such situation:
```ruby
require 'prime'
class << Integer
alias org_sqrt sqrt
def sqrt(n)
raise
end
GC.stress = true
Prime.each(7*37){} rescue nil # <- Here we populate CC
class << Object.new; end
# These adjacent remove-then-alias maneuver
# frees a method entry, then immediately
# reuses it for another.
remove_method :sqrt
alias sqrt org_sqrt
end
Prime.each(7*37).to_a # <- SEGV
```
Most (if not all) of the fields of rb_method_definition_t are never
meant to be modified once after they are stored. Marking them const
makes it possible for compilers to warn on unintended modifications.
This approach uses a flag bit on the final hash object in the regular splat,
as opposed to a previous approach that used a VM frame flag. The hash flag
approach is less invasive, and handles some cases that the VM frame flag
approach does not, such as saving the argument splat array and splatting it
later:
ruby2_keywords def foo(*args)
@args = args
bar
end
def bar
baz(*@args)
end
def baz(*args, **kw)
[args, kw]
end
foo(a:1) #=> [[], {a: 1}]
foo({a: 1}, **{}) #=> [[{a: 1}], {}]
foo({a: 1}) #=> 2.7: [[], {a: 1}] # and warning
foo({a: 1}) #=> 3.0: [[{a: 1}], {}]
It doesn't handle some cases that the VM frame flag handles, such as when
the final hash object is replaced using Hash#merge, but those cases are
probably less common and are unlikely to properly support keyword
argument separation.
Use ruby2_keywords to handle argument delegation in the delegate library.
The built-in version operates on a buffer of 5 words, much smaller than
the size of jmp_buf defined in libc.
Note, powerpc requires 5 words, while arm and x86_64 just require 3.
Also add keyword argument separation warnings for Class#new and Method#call.
To allow for keyword argument to required positional hash converstion in
cfuncs, add a vm frame flag indicating the cfunc was called with an empty
keyword hash (which was removed before calling the cfunc). The cfunc can
check this frame flag and add back an empty hash if it is passing its
arguments to another Ruby method. Add rb_empty_keyword_given_p function
for checking if called with an empty keyword hash, and
rb_add_empty_keyword for adding back an empty hash to argv.
All of this empty keyword argument support is only for 2.7. It will be
removed in 3.0 as Ruby 3 will not convert empty keyword arguments to
required positional hash arguments. Comment all of the relevent code
to make it obvious this is expected to be removed.
Add rb_funcallv_kw as an public C-API function, just like rb_funcallv
but with a keyword flag. This is used by rb_obj_call_init (internals
of Class#new). This also required expected call_type enum with
CALL_FCALL_KW, similar to the recent addition of CALL_PUBLIC_KW.
Add rb_vm_call_kw as a internal function, used by call_method_data
(internals of Method#call and UnboundMethod#bind_call). Add tests
for UnboundMethod#bind_call keyword handling.
The kw_splat flag is whether the original call passes keyword or not.
Some types of methods (e.g., bmethod and sym_proc) drops the
information. This change tries to propagate the flag to the final
callee, as far as I can.
This syntax means the method should be treated as a method that
uses keyword arguments, but no specific keyword arguments are
supported, and therefore calling the method with keyword arguments
will raise an ArgumentError. It is still allowed to double splat
an empty hash when calling the method, as that does not pass
any keyword arguments.
After 5e86b005c0, I now think ANYARGS is
dangerous and should be extinct. This commit deletes ANYARGS from
rb_thread_create, which seems very safe to do.
After 5e86b005c0, I now think ANYARGS is
dangerous and should be extinct. This commit deletes ANYARGS from
rb_ensure, which also revealed many arity / type mismatches.
After 5e86b005c0, I now think ANYARGS is
dangerous and should be extinct. This commit deletes ANYARGS from
struct vm_ifunc, but in doing so we also have to decouple the usage
of this struct in compile.c, which (I think) is an abuse of ANYARGS.
If `vm_stack` is left dangling in a forked process, the gc attempts to scan
it, but it is invalid and will cause a segfault. Therefore, we clear it
before forking.
In order to simplify this, `rb_ec_clear_vm_stack` was introduced.
Before this commit, classes and modules would be registered with the
VM's `defined_module_hash`. The key was the ID of the class, but that
meant that it was possible for hash collisions to occur. The compactor
doesn't allow classes in the `defined_module_hash` to move, but if there
is a conflict, then it's possible a class would be removed from the hash
and not get pined.
This commit changes the key / value of the hash just to be the class
itself, thus preventing movement.
For some reason symbols (or classes) are being overridden in trunk
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@67598 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
This commit adds the new method `GC.compact` and compacting GC support.
Please see this issue for caveats:
https://bugs.ruby-lang.org/issues/15626
[Feature #15626]
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@67576 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
Because hard to specify commits related to r67479 only.
So please commit again.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@67499 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
This commit adds the new method `GC.compact` and compacting GC support.
Please see this issue for caveats:
https://bugs.ruby-lang.org/issues/15626
[Feature #15626]
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@67479 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
cfp->bp was (re-)introduced by Kokubun san, but VM doesn't use it
because I (ko1) want to remove it in a future. But using it make
leave instruction fast because of sp consisntency check.
So now VM uses cfp->bp.
To use cfp->bp, I checked the value and I found that it is not a
"initial value of sp" but a "initial value of ep". Fix this problem
and fix all bp references (this is why bp is renamed to bp_).
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@67342 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
zlib and bignum both contain unblocking functions which are
async-signal-safe and do not require spawning additional
threads.
We can execute those functions directly in signal handlers
without incurring overhead of extra threads, so provide C-API
users the ability to deal with that. Other C-API users may
have similar need.
This flexible API can supercede existing uses of
rb_thread_call_without_gvl and rb_thread_call_without_gvl2 by
introducing a flags argument to control behavior.
Note: this API is NOT finalized. It needs approval from other
committers. I prefer shorter name than previous
rb_thread_call_without_gvl* functions because my eyes requires
big fonts.
[Bug #15499]
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@66712 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
* ruby.c (process_options): script_compiled events are missed on
command line -e or specified file. this commit fix it.
[Bug #15471]
This patch should be backport to Ruby 2.6 branch.
* vm_core.h (rb_exec_event_hook_script_compiled): introduce utility
function to invoke a script_compiled event.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@66595 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
* iseq.c: before this patch, RubyVM::InstructionSequence.of(src) (ISeq in
short) returns different ISeq (wrapper) objects point to one ISeq internal
object. This patch changes this behavior to cache created ISeq (wrapper)
objects and return same ISeq object for an internal ISeq object.
* iseq.h (ISEQ_EXECUTABLE_P): introduced to check executable ISeq objects.
* iseq.h (ISEQ_COMPILE_DATA_ALLOC): reordr setting flag line to avoid
ISEQ_USE_COMPILE_DATA but compiled_data == NULL case.
* vm_core.h (rb_iseq_t): introduce `rb_iseq_t::wrapper` and
`rb_iseq_t::aux::exec`. Move `rb_iseq_t::local_hooks` to
`rb_iseq_t::aux::exec::local_hooks`.
* test/ruby/test_iseq.rb: add ISeq.of() tests.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@66246 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
postponed_job is safe to use in signal handlers, but is not
thread-safe for MJIT. Implement a workqueue for MJIT
thread-safety.
[Bug #15316]
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@66100 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
* vm_trace.c: `TracePoint#enable(target_line:)` is supported.
This option enables a hook only at specified target_line.
target_line should be combination with target and :line event.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@66008 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
* vm_trace.c (rb_tracepoint_enable_for_target): support targetting
TracePoint. [Feature #15289]
Tragetting TracePoint is only enabled on specified method, proc
and so on, example: `tp.enable(target: code)`.
`code` should be consisted of InstructionSeuqnece (iseq)
(RubyVM::InstructionSeuqnece.of(code) should not return nil)
If code is a tree of iseq, TracePoint is enabled on all of
iseqs in a tree.
Enabled tragetting TracePoints can not enabled again with
and without target.
* vm_core.h (rb_iseq_t): introduce `rb_iseq_t::local_hooks`
to store local hooks.
`rb_iseq_t::aux::trace_events` is renamed to
`global_trace_events` to contrast with `local_hooks`.
* vm_core.h (rb_hook_list_t): add `rb_hook_list_t::running`
to represent how many Threads/Fibers are used this list.
If this field is 0, nobody using this hooks and we can
delete it.
This is why we can remove code from cont.c.
* vm_core.h (rb_vm_t): because of above change, we can eliminate
`rb_vm_t::trace_running` field.
Also renamed from `rb_vm_t::event_hooks` to `global_hooks`.
* vm_core.h, vm.c (ruby_vm_event_enabled_global_flags): renamed
from `ruby_vm_event_enabled_flags.
* vm_core.h, vm.c (ruby_vm_event_local_num): added to count
enabled targetting TracePoints.
* vm_core.h, vm_trace.c (rb_exec_event_hooks): accepts
hook list.
* vm_core.h (rb_vm_global_hooks): added for convinience.
* method.h (rb_method_bmethod_t): added to maintain Proc
and `rb_hook_list_t` for bmethod (defined by define_method).
* prelude.rb (TracePoint#enable): extracet a keyword parameter
(because it is easy than writing in C).
It calls `TracePoint#__enable` internal method written in C.
* vm_insnhelper.c (vm_trace): check also iseq->local_hooks.
* vm.c (invoke_bmethod): check def->body.bmethod.hooks.
* vm.c (hook_before_rewind): check iseq->local_hooks
and def->body.bmethod.hooks before rewind by exception.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@66003 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
We already use "static inline" heavily and there should be no
penalty for modern compilers; this adds type-checking, too.
This will make future changes easier-to-review.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@65775 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
* vm_core.h: remove `rb_execution_context_t::passed_bmethod_me`
and fix functions to pass the `me` directly.
`passed_bmethod_me` was used to make bmethod (methods defined by
`defined_method`). `rb_vm_invoke_bmethod` invoke `Proc` with `me`
information as method frame (`lambda` frame, actually).
If the proc call is not bmethod call, `passed_bmethod_me` should
be NULL. However, there is a bug which passes wrong `me` for
normal block call.
http://ci.rvm.jp/results/trunk-asserts@silicon-docker/1449470
This is because wrong `me` was remained in `passed_bmethod_me`
(and used incorrectly it after collected by GC).
We need to clear `passed_bmethod_me` just after bmethod call,
but clearing is not enough.
To solve this issue, I removed `passed_bmethod_me` and pass `me`
information as a function parameter of `rb_vm_invoke_bmethod`,
`invoke_block_from_c_proc` and `invoke_iseq_block_from_c` in vm.c.
* vm.c (invoke_iseq_block_from_c): the number of parameters is too
long so that I try to specify `ALWAYS_INLINE`.
* vm.c (invoke_block_from_c_proc): ditto.
* vm_insnhelper.c (vm_yield_with_cfunc): now there are no pathes
to use bmethod here.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@65636 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
* vm_core.h (rb_thread_struct): introduce new fields `invoke_type`
and `invoke_arg`.
There are two types threads: invoking proc (normal Ruby thread
created by `Thread.new do ... end`) and invoking func, created
by C-API. `invoke_type` shows the types.
* thread.c (thread_do_start): copy `invoke_arg.proc.args` contents
from Array to ALLOCA stack memory if args length is enough small (<8).
We don't need to keep Array and don't need to cancel using transient heap.
* vm.c (thread_mark): For func invoking threads, they can pass (void *)
parameter (rb_thread_t::invoke_arg::func::arg). However, a rubyspec test
(thread_spec.c) passes an Array object and it expect to mark it.
Clealy it is out of scope (misuse of `rb_thread_create` C-API). However,
I'm not sure someone else has such kind of misunderstanding.
So now we mark conservatively this (void *) arg with rb_gc_mark_maybe.
This misuse is found by this error log.
http://ci.rvm.jp/results/trunk-theap-asserts@silicon-docker/1448164
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@65622 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
because it's not supported by this file. Also, shared `def_iseq_ptr`
instead of copying the main definition of it.
vm_core.h: moved `def_iseq_ptr` to this place. added `inline` to avoid
compiler warnings since it's not used in some files including vm_core.h.
vm_insnhelper.c: moved `def_iseq_ptr` to vm_core.h.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@65440 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
This reverts commit 5a1dfb04bc (r63451)
And mark the functions as async-signal-safe while we're at it to
prevent future developers from making the same mistake as I did :x
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@65316 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
The comment didn't make sense. As it's allocated with
`ZALLOC_N(struct rb_call_cache, body->ci_size + body->ci_kw_size)`,
it's very likely to be forgotten to press shift key on US keyboard.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@65277 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
The instructions were used only for branch coverage.
Instead, it now uses a trace framework [Feature #14104].
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@65225 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
We have several options to ensure there's no race condition between main
thread and MJIT thead about IC reference:
1) Give up caching ivar for multiple classes (or multiple versions of the
same class) in the same getinstancevariable (This commit's approach)
2) Allocate new inline cache every time
Other ideas we could think of couldn't eliminate possibilities of race
condition.
In 2, it's memory allocation would be slow and it may trigger JIT
cancellation frequently. So 1 would be fast for both VM and JIT
situations.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@65213 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
* configure.ac: introduce new configure option `--enable-mjit` and
`--disable-mjit`. Default is "enable".
`--disable-mjit` disables all of MJIT features so that `ruby --jit`
can't enable MJIT.
This option affect a macro `USE_MJIT`.
This change remove `--enable/disable-install-mjit-header` option.
* Makefile.in: introduce the `ENABLE_MJIT` variable.
* common.mk: use `ENABLE_MJIT` option.
* internal.h: respect `USE_MJIT`. Same as other *.c, *.h.
* test/ruby/test_jit.rb: check `ENABLE_MJIT` key of rbconfg.rb.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@65204 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
This patch introduces "oneshot_lines" mode for `Coverage.start`, which
checks "whether each line was executed at least once or not", instead of
"how many times each line was executed". A hook for each line is fired
at most once, and after it is fired, the hook flag was removed; it runs
with zero overhead.
See [Feature #15022] in detail.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@65195 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
Surprisingly, this constant (been there since around 1983) has
never been a part of any standards until now. We have to find
out the appropriate value.
NSIG_MAX is expected to become a part of forthcoming POSIX.
See: http://austingroupbugs.net/view.php?id=741
_SIG_MAXSIG is here because that is greater than NSIG. See
Python's relevant discussion: https://bugs.python.org/issue20584
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@65161 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
like "error: static declaration of 'xxx' follows non-static declaration".
r64940 is successfully built on mswin but not built on almost all other environments.
internal.h: ditto
include/ruby/intern.h: MJIT_STATIC is moved to this file since this file
also needs to use this.
mjit.h: MJIT_STATIC is moved from this.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@64941 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
because r64849 seems to fix issues which we were confused about.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@64850 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
This reverts commit r64829. I'll prepare another temporary fix, but I'll
separately commit that to make it easier to revert that later.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@64838 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
not optimizing Array#& and Array#| because vm_insnhelper.c can't easily
inline it (large amount of array.c code would be needed in vm_insnhelper.c)
and the method body is a little complicated compared to Integer's ones.
So I thought only Integer#& and Integer#| have a significant impact,
and eliminating unnecessary branches would contribute to JIT's performance.
vm_insnhelper.c: ditto
tool/transform_mjit_header.rb: make sure these instructions are inlined
on JIT.
compile.c: compile vm_opt_and and vm_opt_or.
id.def: define id for them to be used in compile.c and vm*.c
vm.c: track redefinition of Integer#& and Integer#|
vm_core.h: allow detecting redefinition of & and |
test/ruby/test_jit.rb: test new insns
test/ruby/test_optimization.rb: ditto
* Optcarrot benchmark
This is a kind of experimental thing but I'm committing this since the
performance impact is significant especially on Optcarrot with JIT.
$ benchmark-driver benchmark.yml --rbenv 'before::before --disable-gems;before+JIT::before --disable-gems --jit;after::after --disable-gems;after+JIT::after --disable-gems --jit' -v --repeat-count 24
before: ruby 2.6.0dev (2018-09-24 trunk 64821) [x86_64-linux]
before+JIT: ruby 2.6.0dev (2018-09-24 trunk 64821) +JIT [x86_64-linux]
after: ruby 2.6.0dev (2018-09-24 opt_and 64821) [x86_64-linux]
last_commit=opt_or
after+JIT: ruby 2.6.0dev (2018-09-24 opt_and 64821) +JIT [x86_64-linux]
last_commit=opt_or
Calculating -------------------------------------
before before+JIT after after+JIT
Optcarrot Lan_Master.nes 51.460 66.315 53.023 71.173 fps
Comparison:
Optcarrot Lan_Master.nes
after+JIT: 71.2 fps
before+JIT: 66.3 fps - 1.07x slower
after: 53.0 fps - 1.34x slower
before: 51.5 fps - 1.38x slower
[close https://github.com/ruby/ruby/pull/1963]
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@64824 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
This enhances rb_vm_insn_addr2insn which retrieves a decoded insn number
from encoded insn.
The insn data table include not only decoded insn number, but also its
len, trace and non-trace version of encoded insn.
This table can be used to simplify trace instrumentation.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@64518 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
Spurious interrupts from SIGCHLD cause Mutex#sleep (via
ConditionVariable#wait) to return early and breaks some use
cases. Since these are outside the programs's control with
MJIT, we will only consider pending interrupts (e.g. those
from Thread#run) and signals which cause a Ruby-level Signal.trap
handler to fire as "spurious" wakeups.
[ruby-core:88537] [Feature #15002]
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@64444 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
On a 64-bit system, this reduces rb_thread_t from 536 to 520 bytes.
Depending on the allocation, this can reduce cacheline access
for checking the abort_on_exception, report_on_exception and
pending_interrupt_queue_checked flags.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@64376 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
This reverts commit 194a6a2c68 (r64203).
Race conditions which caused the original reversion will be fixed
in the subsequent commit.
[ruby-core:88360] [Misc #14937]
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@64352 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
This is just a refactoring.
The receiver of "invokesuper" was a boolean to represent if it is ZSUPER
or not. This was used in vm_search_super_method to prohibit ZSUPER call
in define_method. (It is currently prohibited because of the limitation
of the implementation.)
This change removes the hack by introducing an explicit flag,
VM_CALL_SUPER, to signal the information. Now, the implementation of
"invokesuper" is consistent with "send" instruction.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@64268 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
By this commit's changes in other files, now MJIT started to work on VC++.
Unfortunately some features are still broken and they'll be fixed later.
This also suppresses cl.exe's default output to stdout because there
seems to be no option to do it. Tweaking some log messages as well.
vm_core.h: declare `__declspec(dllimport)` to export them correctly on mswin.
vm_insnhelper.h: ditto
mjit.h: ditto
test_jit.rb: skipped some pending tests.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@64221 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
To reduce resource use and reduce CI failure; remove
timer-thread. Single-threaded Ruby processes (including forked
children) will never see extra thread overhead. This prevents
glibc and jemalloc from going into multi-threaded mode and
initializing locks or causing fragmentation via arena explosion.
The GVL is implements its own wait-queue as a ccan/list to
permit controlling wakeup order. Timeslice under contention is
handled by a designated timer thread (similar to choosing a
"patrol_thread" for current deadlock checking).
There is only one self-pipe, now, as wakeups for timeslice are
done independently using condition variables. This reduces FD
pressure slightly.
Signal handling is handled directly by a Ruby Thread (instead
of timer-thread) by exposing signal self-pipe to callers of
rb_thread_fd_select, native_sleep, rb_wait_for_single_fd, etc...
Acquiring, using, and releasing the self-pipe is exposed via 4
new internal functions:
1) rb_sigwait_fd_get - exclusively acquire timer_thread_pipe.normal[0]
2) rb_sigwait_fd_sleep - sleep and wait for signal (and no other FDs)
3) rb_sigwait_fd_put - release acquired result from rb_sigwait_fd_get
4) rb_sigwait_fd_migrate - migrate signal handling to another thread
after calling rb_sigwait_fd_put.
rb_sigwait_fd_migrate is necessary for waitpid callers because
only one thread can wait on self-pipe at a time, otherwise a
deadlock will occur if threads fight over the self-pipe.
TRAP_INTERRUPT_MASK is now set for the main thread directly in
signal handler via rb_thread_wakeup_timer_thread.
Originally, I wanted to use POSIX timers
(timer_create/timer_settime) for this. Unfortunately, this
proved unfeasible as Mutex#sleep resumes on spurious wakeups and
test/thread/test_cv.rb::test_condvar_timed_wait failed. Using
pthread_sigmask to mask out SIGVTALRM fixed that test, but
test/fiddle/test_function.rb::test_nogvl_poll proved there'd be
some unavoidable (and frequent) incompatibilities from that
approach.
Finally, this allows us to drop thread_destruct_lock and
interrupt current ec directly.
We don't need to rely on vm->thread_destruct_lock or a coherent
vm->running_thread on any platform. Separate timer-thread for
time slice and signal handling is relegated to thread_win32.c,
now.
[ruby-core:88088] [Misc #14937]
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@64107 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
Otherwise, an altstack may live past ObjectSpace destruction
and xfree-ing the altstack will segfault.
[ruby-core:85621] [Feature #14487]
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@64102 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
Repack rb_thread_struct, rb_execution_context_struct, args_info and
iseq_compile_data to save 1 word per struct.
re_pattern_buffer remains unpacked due to the possible binary
compatibility.
[Fix GH-1907]
Based on the patch
From: Lourens Naudé <lourens@bearmetal.eu>
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@64096 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
Revert r63968 and cast at caller side to prevent unintentional casting.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@63972 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
* variable.c (rb_const_search): call #const_missing method on
private constants, as well as uninitialized constants.
[Feature #14328]
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@63871 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
Reading win32/win32.c waitpid implementation, maybe waitpid(-1, ...)
on that platform will never conflict with mjit use of waitpid.
In any case, I've added WAITPID_USE_SIGCHLD macro to vm_core.h
so it can be easy for Linux/BSD users to test (hopefully!)
win32-compatible code.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@63855 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
The change is unstable on Windows. Please re-commit it when it correctly
supports Windows.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@63852 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
Some systems lack SIGCHLD or have incomplete SIGCHLD
implementations. So enable polling mode for them.
[ruby-core:87705] [Bug #14867]
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@63795 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
Use a global SIGCHLD handler to guard all callers of rb_waitpid.
To work safely with multi-threaded programs, we introduce a
VM-wide waitpid_lock to be acquired BEFORE fork/vfork spawns the
process. This is to be combined with the new ruby_waitpid_locked
function used by mjit.c in a non-Ruby thread.
Ruby-level SIGCHLD handlers registered with Signal.trap(:CHLD)
continues to work as before and there should be no regressions
in any existing use cases.
Splitting the wait queues for PID > 0 and groups (PID <= 0)
ensures we favor PID > 0 callers.
The disabling of SIGCHLD in rb_f_system is longer necessary,
as we use deferred signal handling and no longer make ANY
blocking waitpid syscalls in other threads which could "beat"
the waitpid call made by rb_f_system.
We prevent SIGCHLD from firing in normal Ruby Threads and only
enable it in the timer-thread, to prevent spurious wakeups
from in test/-ext-/gvl/test_last_thread.rb with MJIT enabled.
I've tried to guard as much of the code for RUBY_SIGCHLD==0
using C "if" statements rather than CPP "#if" so to reduce
the likelyhood of portability problems as the compiler will
see more code.
We also work to suppress false-positives from
Process.wait(-1, Process::WNOHANG) to quiets warnings from
spec/ruby/core/process/wait2_spec.rb with MJIT enabled.
Lastly, we must implement rb_grantpt for ext/pty. We need a
MJIT-compatible way of supporting grantpt(3) which may spawn
the `pt_chown' binary and call waitpid(2) on it.
[ruby-core:87605] [Ruby trunk Bug#14867]
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@63758 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
vm->sleeper is never modified in signal handlers or without GVL,
so there's no need for volatile hocus-pocus.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@63713 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
The current VM_INSTRUCTION_SIZE is 198, so the linear search
painful during a major GC phase.
I noticed rb_vm_insn_addr2insn2 showing up at the top of some
profiles while working on some malloc-related stuff, so I
decided to attack it.
Most notably, the benchmark/bm_vm3_gc.rb improves by over 40%:
https://80x24.org/spew/20180602220554.GA9991@whir/raw
[ruby-core:87361] [Feature #14814]
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@63594 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
* vm_core.h (VM_ENV_DATA_INDEX_ENV_PROC): ep[VM_ENV_DATA_INDEX_ENV_PROC] is
allocated to mark a Proc which is created from iseq block.
However, `lep[0]` keeps Proc object itself as a block handler (Proc).
So we don't need to keep it.
* vm_core.h (VM_ENV_PROCVAL): ditto.
* vm.c (vm_make_env_each): do not need to keep blockprocval as special value.
* vm.c (vm_block_handler_escape): simply return Proc value.
* proc.c (proc_new): we don't need to check Env because a Proc type block
handler is a Proc object itself.
[Bug #14782]
* test/ruby/test_proc.rb: add a test for [Bug #14782]
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@63494 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
st_table allows the use of st_shift to act as an order-preserving
queue while allowing fast lookups to prevent duplicate jobs.
In typical Ruby apps, this table will only have one entry
for gc_finalize_deferred_register.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@63451 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
rb_atomic_t is 32-bit on 64-bit platforms (including the popular
x86-64 Linux), so save 4 bytes on this structure. This doesn't
result in any final size reduction due to padding, yet, but
future changes are possible to shrink rb_execution_context_t
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@63435 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
This ec->machine.regs is marked by GC. However jmp_buf is
not defined by us. There are chances of unaligned access.
We should force it VALUE-aligned.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@63375 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
Don't abuse struct RString to hold arbitrary memory region.
Raw pointer should just suffice.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@63368 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
Instead of allocating and registering the altstack in different
places, do it together to reduce code and improve readability.
When thread cache is enabled, storing altstack in rb_thread_t
is wasteful and we may reuse altstack in the same pthread.
This also lets us clearly allow use of xmalloc to allow GC to
recover from ENOMEM.
[ruby-core:85621] [Feature #14487]
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@63213 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
This is fairly non-intrusive bugfix to prevent children
from trying to reach into thread stacks of the parent.
I will probably reuse this idea and redo r62934, too
(same bug).
* vm_core.h (typedef struct rb_vm_struct): add fork_gen counter
* thread.c (rb_thread_atfork_internal): increment fork_gen
* variable.c (struct autoload_data_i): store fork_gen
* variable.c (check_autoload_data): remove (replaced with get_...)
* variable.c (get_autoload_data): check fork_gen when retrieving
* variable.c (check_autoload_required): use get_autoload_data
* variable.c (rb_autoloading_value): ditto
* variable.c (rb_autoload_p): ditto
* variable.c (current_autoload_data): ditto
* variable.c (autoload_reset): reset fork_gen, adjust indent
* variable.c (rb_autoload_load): set fork_gen when setting state
* test/ruby/test_autoload.rb (test_autoload_fork): new test
[ruby-core:86410] [Bug #14634]
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@63210 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
We need to mark default values for kwarg methods. This also fixes
Bootsnap. IBF iseq loading needed to mark iseqs as "having markable
objects".
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@62851 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
Directly marking iseq operands allows us to eliminate the "mark array"
stored on ISEQ objects, which will reduce the amount of memory ISEQ
objects consume. This patch changes the iseq mark function to:
* Directly marks ISEQ operands
* Iterate over and mark child ISEQs
It also introduces two flags on the ISEQ object. In order to mark
instruction operands, we have to disassemble the instructions and find
the instruction parameters and types. Instructions may also be
translated to jump addresses. Instruction sequences may get marked by
the GC *while* they're mid flight (being compiled). The
`ISEQ_TRANSLATED` flag is used to indicate whether or not the
instructions have been translated to jump addresses so that when we
decode the instructions we know whether or not we need to go from jump
location back to original instruction or not.
Not all ISEQ objects have any markable objects embedded in their
instructions. We can detect whether or not an ISEQ has markable objects
in the instructions at compile time. If the instructions contain
markable objects, we set a flag `ISEQ_MARKABLE_ISEQ` on the ISEQ object.
This means that during the mark phase, we can skip decompilation if the
flag is *not* set. In other words, we can avoid decompilation of we
know in advance there is nothing to mark.
`once` instructions have an operand that contains the result of a
one-time compilation of a regex. Before this patch, that operand was
called an "inline cache", even though the struct was actually an "inline
storage". This patch changes the operand to be an "inline storage" so
that we can differentiate between caches that need marking (the inline
storage) and caches that don't need marking (inline cache).
[ruby-core:84909]
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@62706 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
to be used for MJIT's optimization. It's not used for optimization
in this commit yet.
vm_core.h: added catch_except_p field.
iseq.c: show the flag in ISeq disasm for debugging.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@62654 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
* vm_insnhelper.c (vm_get_ev_const): add flag argument of
`rb_autoloading_value`.
* constant.h (rb_autoloading_value): moved the declaration from
vm_core.h for `rb_const_flag_t`. [ruby-core:85516] [Bug #14469]
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@62394 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
No implicit cast is defined between these types. Should be explicit.
Also, NULL is defined to be ((void*)0) so not usable as a function
pointer value.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@62221 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
which has been developed by Takashi Kokubun <takashikkbn@gmail> as
YARV-MJIT. Many of its bugs are fixed by wanabe <s.wanabe@gmail.com>.
This JIT compiler is designed to be a safe migration path to introduce
JIT compiler to MRI. So this commit does not include any bytecode
changes or dynamic instruction modifications, which are done in original
MJIT.
This commit even strips off some aggressive optimizations from
YARV-MJIT, and thus it's slower than YARV-MJIT too. But it's still
fairly faster than Ruby 2.5 in some benchmarks (attached below).
Note that this JIT compiler passes `make test`, `make test-all`, `make
test-spec` without JIT, and even with JIT. Not only it's perfectly safe
with JIT disabled because it does not replace VM instructions unlike
MJIT, but also with JIT enabled it stably runs Ruby applications
including Rails applications.
I'm expecting this version as just "initial" JIT compiler. I have many
optimization ideas which are skipped for initial merging, and you may
easily replace this JIT compiler with a faster one by just replacing
mjit_compile.c. `mjit_compile` interface is designed for the purpose.
common.mk: update dependencies for mjit_compile.c.
internal.h: declare `rb_vm_insn_addr2insn` for MJIT.
vm.c: exclude some definitions if `-DMJIT_HEADER` is provided to
compiler. This avoids to include some functions which take a long time
to compile, e.g. vm_exec_core. Some of the purpose is achieved in
transform_mjit_header.rb (see `IGNORED_FUNCTIONS`) but others are
manually resolved for now. Load mjit_helper.h for MJIT header.
mjit_helper.h: New. This is a file used only by JIT-ed code. I'll
refactor `mjit_call_cfunc` later.
vm_eval.c: add some #ifdef switches to skip compiling some functions
like Init_vm_eval.
win32/mkexports.rb: export thread/ec functions, which are used by MJIT.
include/ruby/defines.h: add MJIT_FUNC_EXPORTED macro alis to clarify
that a function is exported only for MJIT.
array.c: export a function used by MJIT.
bignum.c: ditto.
class.c: ditto.
compile.c: ditto.
error.c: ditto.
gc.c: ditto.
hash.c: ditto.
iseq.c: ditto.
numeric.c: ditto.
object.c: ditto.
proc.c: ditto.
re.c: ditto.
st.c: ditto.
string.c: ditto.
thread.c: ditto.
variable.c: ditto.
vm_backtrace.c: ditto.
vm_insnhelper.c: ditto.
vm_method.c: ditto.
I would like to improve maintainability of function exports, but I
believe this way is acceptable as initial merging if we clarify the
new exports are for MJIT (so that we can use them as TODO list to fix)
and add unit tests to detect unresolved symbols.
I'll add unit tests of JIT compilations in succeeding commits.
Author: Takashi Kokubun <takashikkbn@gmail.com>
Contributor: wanabe <s.wanabe@gmail.com>
Part of [Feature #14235]
---
* Known issues
* Code generated by gcc is faster than clang. The benchmark may be worse
in macOS. Following benchmark result is provided by gcc w/ Linux.
* Performance is decreased when Google Chrome is running
* JIT can work on MinGW, but it doesn't improve performance at least
in short running benchmark.
* Currently it doesn't perform well with Rails. We'll try to fix this
before release.
---
* Benchmark reslts
Benchmarked with:
Intel 4.0GHz i7-4790K with 16GB memory under x86-64 Ubuntu 8 Cores
- 2.0.0-p0: Ruby 2.0.0-p0
- r62186: Ruby trunk (early 2.6.0), before MJIT changes
- JIT off: On this commit, but without `--jit` option
- JIT on: On this commit, and with `--jit` option
** Optcarrot fps
Benchmark: https://github.com/mame/optcarrot
| |2.0.0-p0 |r62186 |JIT off |JIT on |
|:--------|:--------|:--------|:--------|:--------|
|fps |37.32 |51.46 |51.31 |58.88 |
|vs 2.0.0 |1.00x |1.38x |1.37x |1.58x |
** MJIT benchmarks
Benchmark: https://github.com/benchmark-driver/mjit-benchmarks
(Original: https://github.com/vnmakarov/ruby/tree/rtl_mjit_branch/MJIT-benchmarks)
| |2.0.0-p0 |r62186 |JIT off |JIT on |
|:----------|:--------|:--------|:--------|:--------|
|aread |1.00 |1.09 |1.07 |2.19 |
|aref |1.00 |1.13 |1.11 |2.22 |
|aset |1.00 |1.50 |1.45 |2.64 |
|awrite |1.00 |1.17 |1.13 |2.20 |
|call |1.00 |1.29 |1.26 |2.02 |
|const2 |1.00 |1.10 |1.10 |2.19 |
|const |1.00 |1.11 |1.10 |2.19 |
|fannk |1.00 |1.04 |1.02 |1.00 |
|fib |1.00 |1.32 |1.31 |1.84 |
|ivread |1.00 |1.13 |1.12 |2.43 |
|ivwrite |1.00 |1.23 |1.21 |2.40 |
|mandelbrot |1.00 |1.13 |1.16 |1.28 |
|meteor |1.00 |2.97 |2.92 |3.17 |
|nbody |1.00 |1.17 |1.15 |1.49 |
|nest-ntimes|1.00 |1.22 |1.20 |1.39 |
|nest-while |1.00 |1.10 |1.10 |1.37 |
|norm |1.00 |1.18 |1.16 |1.24 |
|nsvb |1.00 |1.16 |1.16 |1.17 |
|red-black |1.00 |1.02 |0.99 |1.12 |
|sieve |1.00 |1.30 |1.28 |1.62 |
|trees |1.00 |1.14 |1.13 |1.19 |
|while |1.00 |1.12 |1.11 |2.41 |
** Discourse's script/bench.rb
Benchmark: https://github.com/discourse/discourse/blob/v1.8.7/script/bench.rb
NOTE: Rails performance was somehow a little degraded with JIT for now.
We should fix this.
(At least I know opt_aref is performing badly in JIT and I have an idea
to fix it. Please wait for the fix.)
*** JIT off
Your Results: (note for timings- percentile is first, duration is second in millisecs)
categories_admin:
50: 17
75: 18
90: 22
99: 29
home_admin:
50: 21
75: 21
90: 27
99: 40
topic_admin:
50: 17
75: 18
90: 22
99: 32
categories:
50: 35
75: 41
90: 43
99: 77
home:
50: 39
75: 46
90: 49
99: 95
topic:
50: 46
75: 52
90: 56
99: 101
*** JIT on
Your Results: (note for timings- percentile is first, duration is second in millisecs)
categories_admin:
50: 19
75: 21
90: 25
99: 33
home_admin:
50: 24
75: 26
90: 30
99: 35
topic_admin:
50: 19
75: 20
90: 25
99: 30
categories:
50: 40
75: 44
90: 48
99: 76
home:
50: 42
75: 48
90: 51
99: 89
topic:
50: 49
75: 55
90: 58
99: 99
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@62197 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
that allows to JIT-compile Ruby methods by generating C code and
using C compiler. See the first comment of mjit.c to know what this
file does.
mjit.c is authored by Vladimir Makarov <vmakarov@redhat.com>.
After he invented great method JIT infrastructure for MRI as MJIT,
Lars Kanis <lars@greiz-reinsdorf.de> sent the patch to support MinGW
in MJIT. In addition to merging it, I ported pthread to Windows native
threads. Now this MJIT infrastructure can be compiled on Visual Studio.
This commit simplifies mjit.c to decrease code at initial merge. For
example, this commit does not provide multiple JIT threads support.
We can resurrect them later if we really want them, but I wanted to minimize
diff to make it easier to review this patch.
`/tmp/_mjitXXX` file is renamed to `/tmp/_ruby_mjitXXX` because non-Ruby
developers may not know the name "mjit" and the file name should make
sure it's from Ruby and not from some harmful programs. TODO: it may be
better to store this to some temporary directory which Ruby is already using
by Tempfile, if it's not bad for performance.
mjit.h: New. It has `mjit_exec` interface similar to `vm_exec`, which is
for triggering MJIT. This drops interface for AOT compared to the original
MJIT.
Makefile.in: define macros to let MJIT know the path of MJIT header.
Probably we can refactor this to reduce the number of macros (TODO).
win32/Makefile.sub: ditto.
common.mk: compile mjit.o and mjit_compile.o. Unlike original MJIT, this
commit separates MJIT infrastructure and JIT compiler code as independent
object files. As initial patch is NOT going to have ultra-fast JIT compiler,
it's likely to replace JIT compiler, e.g. original MJIT's compiler or some
future JIT impelementations which are not public now.
inits.c: define MJIT module. This is added because `MJIT.enabled?` was
necessary for testing.
test/lib/zombie_hunter.rb: skip if `MJIT.enabled?`. Obviously this
wouldn't work with current code when JIT is enabled.
test/ruby/test_io.rb: skip this too. This would make no sense with MJIT.
ruby.c: define MJIT CLI options. As major difference from original MJIT,
"-j:l"/"--jit:llvm" are renamed to "--jit-cc" because I want to support
not only gcc/clang but also cl.exe (Visual Studio) in the future. But it
takes only "--jit-cc=gcc", "--jit-cc=clang" for now. And only long "--jit"
options are allowed since some Ruby committers preferred it at Ruby
developers Meeting on January, and some of options are renamed.
This file also triggers to initialize MJIT thread and variables.
eval.c: finalize MJIT worker thread and variables.
test/ruby/test_rubyoptions.rb: fix number of CLI options for --jit.
thread_pthread.c: change for pthread abstraction in MJIT. Prefix rb_ for
functions which are used by other files.
thread_win32.c: ditto, for Windows. Those pthread porting is one of major
works that YARV-MJIT created, which is my fork of MJIT, in Feature 14235.
thread.c: follow rb_ prefix changes
vm.c: trigger MJIT call on VM invocation. Also trigger `mjit_mark` to avoid
SEGV by race between JIT and GC of ISeq. The improvement was provided by
wanabe <s.wanabe@gmail.com>.
In JIT compiler I created and am going to add in my next commit, I found
that having `mjit_exec` after `vm_loop_start:` is harmful because the
JIT-ed function doesn't proceed other ISeqs on RESTORE_REGS of leave insn.
Executing non-FINISH frame is unexpected for my JIT compiler and
`exception_handler` triggers executions of such ISeqs. So `mjit_exec`
here should be executed only when it directly comes from `vm_exec` call.
`RubyVM::MJIT` module and `.enabled?` method is added so that we can skip
some tests which don't expect JIT threads or compiler file descriptors.
vm_insnhelper.h: trigger MJIT on method calls during VM execution.
vm_core.h: add fields required for mjit.c. `bp` must be `cfp[6]` because
rb_control_frame_struct is likely to be casted to another struct. The
last position is the safest place to add the new field.
vm_insnhelper.c: save initial value of cfp->ep as cfp->bp. This is an
optimization which are done in both MJIT and YARV-MJIT. So this change
is added in this commit. Calculating bp from ep is a little heavy work,
so bp is kind of cache for it.
iseq.c: notify ISeq GC to MJIT. We should know which iseq in MJIT queue
is GCed to avoid SEGV. TODO: unload some GCed units in some safe way.
gc.c: add hooks so that MJIT can wait GC, and vice versa. Simultaneous
JIT and GC executions may cause SEGV and so we should synchronize them.
cont.c: save continuation information in MJIT worker. As MJIT shouldn't
unload JIT-ed code which is being used, MJIT wants to know full list of
saved execution contexts for continuation and detect ISeqs in use.
mjit_compile.c: added empty JIT compiler so that you can reuse this commit
to build your own JIT compiler. This commit tries to compile ISeqs but
all of them are considered as not supported in this commit. So you can't
use JIT compiler in this commit yet while we added --jit option now.
Patch author: Vladimir Makarov <vmakarov@redhat.com>.
Contributors:
Takashi Kokubun <takashikkbn@gmail.com>.
wanabe <s.wanabe@gmail.com>.
Lars Kanis <lars@greiz-reinsdorf.de>.
Part of Feature 12589 and 14235.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@62189 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
We treat this as "int" through the vm_living_thread_num API
anyways, and "pid_t" is still 32-bits with glibc on 64-bit
platforms. I expect it'll be a long time before anybody needs
more than 2 billion native threads. For now, let's save one
cacheline on x86-64 (as reported by pahole(1)):
before: size: 1288, cachelines: 21, members: 45
after: size: 1280, cachelines: 20, members: 45
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@62075 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
* vm_core.h (VM_INSN_INFO_TABLE_IMPL): use 1 (binary search)
because 2 (succinct bitvector) doesn't work on Rasbian (x86_64).
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@61748 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
Because the name "code_range" is ambiguous with encoding's.
Abbreviations ("crange", and "cr") are also renamed to "loc".
The traditional "code_location" (a pair of lineno and column) is
renamed to "code_position". Abbreviations are also renamed
(first_loc to beg_pos, and last_loc to end_pos).
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@61721 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
* insns.def (getblockparamproxy): introduce new instruction to return
the `rb_block_param_proxy` object if possible. This object responds
to `call` method and invoke given block (completely similar to `yield`).
* method.h (OPTIMIZED_METHOD_TYPE_BLOCK_CALL): add new optimized call type
which is for `rb_block_param_proxy.cal`.
* vm_insnhelper.c (vm_call_method_each_type): ditto.
* vm_insnhelper.c (vm_call_opt_block_call): ditto.
* vm_core.h (BOP_CALL, PROC_REDEFINED_OP_FLAG): add check for `Proc#call`
redefinition.
* compile.c (iseq_compile_each0): compile to use new insn
`getblockparamproxy` for method call.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@61659 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
This commit removes ISEQ_TYPE_DEFINED_GUARD because it is no longer
needed. And this introduces ISEQ_TYPE_PLAIN which means that the iseq
does nothing special but just wrap an expression. Currently, this is
used for once execution: `/foo#{ bar }baz/o`.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@61601 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
It is too error-prone to pass IMEMO_IFUNC object as NODE*.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@61592 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
* gc.c (rb_raw_obj_info): check block before using it.
* vm_core.h (vm_block_iseq): r61565 introduced NULL check but this
check is only needed by `rb_raw_obj_info()` and it is called at GC
debug mode. Above fix for `rb_raw_obj_info()` solves this problem and
NULL check should not be needed any more.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@61571 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
Currently, VM_INSN_INFO_TABLE_IMPL == 0 means linear search, and
VM_INSN_INFO_TABLE_IMPL == 1 means binary search. I plan to add
succinct bitvector algorithm later.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@61537 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
This makes TracePoint a bit fast by reducing cache misses of
`get_insn_info_binary_search`.
Also, I plan to use succinct bitvector algorithm for `get_insn_info`
instead of binary search. This change will make it easy.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@61536 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
This factors rb_iseq_constant_body#insns_info and #insns_info_size to
struct iseq_insn_info.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@61534 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
* vm_core.h (rb_vm_t): move `rb_execution_context_t::safe_level` to
`rb_vm_t::safe_level_` because `$SAFE` is a process (VM) global state.
* vm_core.h (rb_proc_t): remove `rb_proc_t::safe_level` because `Proc`
objects don't need to keep `$SAFE` at the creation.
Also make `is_from_method` and `is_lambda` as 1 bit fields.
* cont.c (cont_restore_thread): no need to keep `$SAFE` for Continuation.
* eval.c (ruby_cleanup): use `rb_set_safe_level_force()` instead of access
`vm->safe_level_` directly.
* eval_jump.c: End procs `END{}` doesn't keep `$SAFE`.
* proc.c (proc_dup): removed and introduce `rb_proc_dup` in vm.c.
* safe.c (rb_set_safe_level): don't check `$SAFE` 1 -> 0 changes.
* safe.c (safe_setter): use `rb_set_safe_level()`.
* thread.c (rb_thread_safe_level): `Thread#safe_level` returns `$SAFE`.
It should be obsolete.
* transcode.c (load_transcoder_entry): `rb_safe_level()` only returns
0 or 1 so that this check is not needed.
* vm.c (vm_proc_create_from_captured): don't need to keep `$SAFE` for Proc.
* vm.c (rb_proc_create): renamed to `proc_create`.
* vm.c (rb_proc_dup): moved from proc.c.
* vm.c (vm_invoke_proc): do not need to set and restore `$SAFE`
for `Proc#call`.
* vm_eval.c (rb_eval_cmd): rename a local variable to represent clearer
meaning.
* lib/drb/drb.rb: restore `$SAFE`.
* lib/erb.rb: restore `$SAFE`, too.
* test/lib/leakchecker.rb: check `$SAFE == 0` at the end of tests.
* test/rubygems/test_gem.rb: do not set `$SAFE = 1`.
* bootstraptest/test_proc.rb: catch up this change.
* spec/ruby/optional/capi/string_spec.rb: ditto.
* test/bigdecimal/test_bigdecimal.rb: ditto.
* test/fiddle/test_func.rb: ditto.
* test/fiddle/test_handle.rb: ditto.
* test/net/imap/test_imap_response_parser.rb: ditto.
* test/pathname/test_pathname.rb: ditto.
* test/readline/test_readline.rb: ditto.
* test/ruby/test_file.rb: ditto.
* test/ruby/test_optimization.rb: ditto.
* test/ruby/test_proc.rb: ditto.
* test/ruby/test_require.rb: ditto.
* test/ruby/test_thread.rb: ditto.
* test/rubygems/test_gem_specification.rb: ditto.
* test/test_tempfile.rb: ditto.
* test/test_tmpdir.rb: ditto.
* test/win32ole/test_win32ole.rb: ditto.
* test/win32ole/test_win32ole_event.rb: ditto.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@61510 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2.5's line coverage measurement was about two times slower than 2.4
because of two reasons; (1) vm_trace uses rb_iseq_event_flags (which
takes O(n) currently where n is the length of iseq) to get an event
type, and (2) RUBY_EVENT_LINE uses setjmp to call an event hook.
This change adds a special event for line coverage,
RUBY_EVENT_COVERAGE_LINE, and adds `tracecoverage` instructions where
the event occurs in iseq.
`tracecoverage` instruction calls an event hook without vm_trace.
And, RUBY_EVENT_COVERAGE_LINE is an internal event which does not
use setjmp.
This change also cancells lineno change due to the deletion of trace
instructions [Feature #14104]. So fixes [Bug #14191].
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@61350 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
* vm.c: introduce `ruby_vm_event_enabled_flags` which represents which
event flags are enabled before.
* vm_trace.c: do not turn off `trace_` prefix instructions because turn on
overhead is a matter if a program repeats turn on and turn off frequently.
* iseq.c (finish_iseq_build): respect `ruby_vm_event_enabled_flags`.
* vm_insnhelper.c (vm_trace): check `ruby_vm_event_flags` and disable
lazy trace-off technique (do not disable traces).
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@61122 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
This change moves RUBY_EVENT_COVERAGE from include/ruby/ruby.h to
vm_core.h and renames it to RUBY_EVENT_COVERAGE_BRANCH.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@61049 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
This change makes each ISeq keep NODE's code range. This information is
needed for method coverage.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@61025 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
Traditionally, method coverage measurement was implemented by inserting
`trace2` instruction to the head of method iseq. So, it just measured
methods defined by `def` keyword.
This commit drastically changes the measuring mechanism of method
coverage; at `RUBY_EVENT_CALL`, it keeps a hash from rb_method_entry_t*
to runs (i.e., it counts the runs per method entry), and at
`Coverage.result`, it creates the result hash by enumerating all
`rb_method_entry_t*` objects (by `ObjectSpace.each_object`).
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@61023 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
Currently the Fiber stack size is small for powerpc64 and it causes
test/ruby/test_backtrace.rb test to break, since it is using a 8kb stack
size.
It breaks on powerpc64 due to the fact that a frame in the stack is
usually 50% bigger on powerpc64 compared to Intel, due to some
considerations:
* The powerpc64 minimum frame is 2x bigger than on Intel
* Powerpc has more registers that might be saved in the frame compared
to Intel.
I ran the same ruby test that is failing on both Intel and Powerpc, and
each Fiber frame is ~50% bigger on powerpc64 for every single lambda
function, thus, we need to increase the stack size on powerpc64 to
accomodate the same tests/applications.
This fixes bug#13757.
Signed-off-by: Breno Leitao <leitao@debian.org>
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@61020 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
* vm_insnhelper.c (vm_trace): use EXEC_EVENT_HOOK() instead of
EXEC_EVENT_HOOK_VM_TRACE(). The latter macro assumes
`ruby_vm_event_flags` is constant in `vm_trace()` function,
but it can be changed in hook functions.
* vm_core.h (EXEC_EVENT_HOOK_VM_TRACE): removed.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@60923 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
* vm_core.h (rb_iseq_t::aux): add `trace_events` which represents
which events are enabled on this iseq. With this information,
we can skip useless trace-on changes for ISeqs.
* vm_trace.c (RUBY_EVENTS_TRACE_BY_ISEQ): moved to iseq.h and rename it
with ISEQ_TRACE_EVENTS.
* iseq.h: introduce ISEQ_USE_COMPILE_DATA iseq (imemo) flag to represent
COMPILE_DATA is available. In other words, iseq->aux.trace_events is not
available when this flag is set.
* ISEQ_COMPILE_DATA() is changed from a macro.
* ISEQ_COMPILE_DATA_ALLOC() is added.
* ISEQ_COMPILE_DATA_CLEAR() is added.
* iseq.c: use them.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@60838 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
* vm_core.h (EXEC_EVENT_HOOK_VM_TRACE): added to pass vm_event_flags
(== ruby_vm_event_flags) as a macro parameter.
* vm_insnhelper.c (vm_trace): use an added macro.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@60819 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
* vm_core.h (rb_thread_t): remove rb_thread_t::event_hooks.
* vm_trace.c: all hooks are connected to vm->event_hooks and
add rb_event_hook_t::filter::th to filter invoke thread.
It will simplify invoking hooks code.
* thread.c (thread_start_func_2): clear thread specific trace_func.
* test/ruby/test_settracefunc.rb: add a test for Thread#add_trace_func.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@60776 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
* iseq.h (iseq_line_info_entry): rename to iseq_insn_info_entry.
* vm_core.h (rb_iseq_constant_body): rename field name line_info_table
to insns_info and also from line_info_size to insns_info_size.
* compile.c (INSN): add struct insn_info to contain per insn information.
* compile.c (add_insn_info): added to add new insn_info entry.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@60726 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
* vm_core.h (rb_execution_context_t): renmae ec::fiber to
ec::fiber_ptr make consistent with ec::thread_ptr.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@60670 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
* eval_error.c (rb_threadptr_error_print): renamed to
rb_ec_error_print() and it accepts `ec`.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@60545 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
* vm.c (rb_thread_method_id_and_class): rename to
rb_ec_frame_method_id_and_class() and accepts `ec` instead of `th`.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@60513 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
* vm_core.h: move rb_thread_t::passed_block_handler to
rb_execution_context_t::passed_block_handler.
Also move rb_thread_t::passed_bmethod_me to
rb_execution_context_t::passed_bmethod_me.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@60503 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
Koichi Sasada
卜部昌平
Lourens Naudé
Jeremy Evans
Alan Wu
Nobuyoshi Nakada
Yusuke Endoh
Aaron Patterson
Fangrui Song
Takashi Kokubun
Samuel Williams
tenderlove
svn
kazu
k0kubun
ko1
nobu
normal
yui-knk
mame
shyouhei
ktsj
naruse
hsbt