mjit_compile.c: resurrect local variable stack

This optimization was reverted on r63863, but this commit resurrects the
optimization to skip some sp motions on JIT execution.

tool/ruby_vm/views/_mjit_compile_insn_body.erb: ditto
tool/ruby_vm/views/_mjit_compile_insn.erb: ditto

insns.def: resurrect handles_frame as handles_stack, which was deleted
on r63763.
tool/ruby_vm/models/bare_instructions.rb: ditto

vm_insnhelper.c: prevent moving sp outside insns.def to allow modifying
it by JIT.

* Optcarrot benchmark

$ benchmark-driver benchmark.yml --rbenv 'before --jit;after --jit' --repeat-count 12 -v
before --jit: ruby 2.6.0dev (2018-07-17 trunk 63987) +JIT [x86_64-linux]
after --jit: ruby 2.6.0dev (2018-07-17 local-stack 63987) +JIT [x86_64-linux]
last_commit=mjit_compile.c: resurrect local variable stack
Calculating -------------------------------------
                         before --jit  after --jit
Optcarrot Lan_Master.nes       70.518       72.144 fps

Comparison:
             Optcarrot Lan_Master.nes
             after --jit:        72.1 fps
            before --jit:        70.5 fps - 1.02x  slower

git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@63988 b2dd03c8-39d4-4d8f-98ff-823fe69b080e

5 files changed, 54 insertions, 4 deletions

diff --git a/tool/ruby_vm/views/_mjit_compile_insn.erb b/tool/ruby_vm/views/_mjit_compile_insn.erb
index 90127aa330..9f18aefe20 100644
--- a/tool/ruby_vm/views/_mjit_compile_insn.erb
+++ b/tool/ruby_vm/views/_mjit_compile_insn.erb
@@ -20,6 +20,16 @@
         MAYBE_UNUSED(<%= ope.fetch(:decl) %>) = (<%= ope.fetch(:type) %>)operands[<%= i %>];
 % end
 %
+% # JIT: Declare stack_size to be used in some macro of _mjit_compile_insn_body.erb
+        if (status->local_stack_p) {
+% # TODO: can we use some functions to calculate this?
+% if insn.name == 'send' || insn.name == 'invokesuper'
+            fprintf(f, "    MAYBE_UNUSED(unsigned int) stack_size = %u;\n", b->stack_size - <%= insn.pops.size %> - ((ci->flag & VM_CALL_ARGS_BLOCKARG) ? 1 : 0));
+% else
+            fprintf(f, "    MAYBE_UNUSED(unsigned int) stack_size = %u;\n", b->stack_size - <%= insn.pops.size %>);
+% end
+        }
+%
 % # JIT: Declare variables for operands, popped values and return values
 % insn.declarations.each do |decl|
         fprintf(f, "    <%= decl %>;\n");
diff --git a/tool/ruby_vm/views/_mjit_compile_insn_body.erb b/tool/ruby_vm/views/_mjit_compile_insn_body.erb
index 0fef07da25..c40756c9da 100644
--- a/tool/ruby_vm/views/_mjit_compile_insn_body.erb
+++ b/tool/ruby_vm/views/_mjit_compile_insn_body.erb
@@ -69,8 +69,28 @@
 %     end
 %   when /\A\s+DISPATCH_ORIGINAL_INSN\([^)]+\);\s+\z/
 %     # For `opt_xxx`'s fallbacks.
+        fprintf(f, "            reg_cfp->sp = (VALUE *)reg_cfp->bp + %d;\n", b->stack_size + 1);
         fprintf(f, "            reg_cfp->pc = original_body_iseq + %d;\n", pos);
         fprintf(f, "            goto cancel;\n");
+%   # If local_stack_p is TRUE, stack values are only available in local variables
+%   # for stack. So we need to replace those macros if local_stack_p is TRUE here.
+%   when /\bGET_SP\(\)/
+%     # reg_cfp->sp
+        fprintf(f, <%= to_cstr.call(line.sub(/\bGET_SP\(\)/, '%s')) %>, (status->local_stack_p ? "(stack + stack_size)" : "GET_SP()"));
+%   when /\bSTACK_ADDR_FROM_TOP\((?<num>[^)]+)\)/
+%     # #define STACK_ADDR_FROM_TOP(n) (GET_SP()-(n))
+%     num = Regexp.last_match[:num]
+        fprintf(f, <%= to_cstr.call(line.sub(/\bSTACK_ADDR_FROM_TOP\(([^)]+)\)/, '%s')) %>,
+                (status->local_stack_p ? "stack + (stack_size - (<%= num %>))" : "STACK_ADDR_FROM_TOP(<%= num %>)"));
+%   when /\bTOPN\((?<num>[^)]+)\)/
+%     # #define TOPN(n) (*(GET_SP()-(n)-1))
+%     num = Regexp.last_match[:num]
+        fprintf(f, <%= to_cstr.call(line.sub(/\bTOPN\(([^)]+)\)/, '%s')) %>,
+                (status->local_stack_p ? "*(stack + (stack_size - (<%= num %>) - 1))" : "TOPN(<%= num %>)"));
+%   when /\bPOPN\([^)]+\)/ # skip sp motion on JIT
+        fprintf(f, <%= to_cstr.call(line.sub(/\bPOPN\((?<num>[^)]+)\)/) { Regexp.last_match[:num] }) %>);
+%   when /\bINC_SP\([^)]+\)/ # skip sp motion on JIT
+        fprintf(f, <%= to_cstr.call(line.sub(/\bINC_SP\((?<num>[^)]+)\)/) { Regexp.last_match[:num] }) %>);
 %   else
         fprintf(f, <%= to_cstr.call(line) %>);
 %   end
diff --git a/tool/ruby_vm/views/_mjit_compile_pc_and_sp.erb b/tool/ruby_vm/views/_mjit_compile_pc_and_sp.erb
index 6004504c06..64a31c65d1 100644
--- a/tool/ruby_vm/views/_mjit_compile_pc_and_sp.erb
+++ b/tool/ruby_vm/views/_mjit_compile_pc_and_sp.erb
@@ -12,4 +12,19 @@
         }
 %
 % # JIT: move sp to use or preserve stack variables
-        fprintf(f, "    reg_cfp->sp = (VALUE *)reg_cfp->bp + %d;\n", b->stack_size + 1 - <%= insn.pops.size %>); /* POPN(INSN_ATTR(popn)); */
+        if (status->local_stack_p) {
+% # sp motion is optimized away for `handles_frame? #=> false` case.
+% # Thus sp should be set properly before `goto cancel`.
+% if insn.handles_stack?
+%           # JIT-only behavior (pushing JIT's local variables to VM's stack):
+            rb_snum_t i, push_size;
+            push_size = -<%= insn.call_attribute('sp_inc') %> + <%= insn.rets.size %> - <%= insn.pops.size %>;
+            fprintf(f, "    reg_cfp->sp = (VALUE *)reg_cfp->bp + %d;\n", b->stack_size + 1 - <%= insn.pops.size %>); /* POPN(INSN_ATTR(popn)); */
+            for (i = 0; i < push_size; i++) { /* TODO: use memcpy? */
+                fprintf(f, "    *(reg_cfp->sp + %ld) = stack[%ld];\n", i - push_size, (rb_snum_t)b->stack_size - push_size + i);
+            }
+% end
+        }
+        else {
+            fprintf(f, "    reg_cfp->sp = (VALUE *)reg_cfp->bp + %d;\n", b->stack_size + 1 - <%= insn.pops.size %>); /* POPN(INSN_ATTR(popn)); */
+        }
diff --git a/tool/ruby_vm/views/_mjit_compile_send.erb b/tool/ruby_vm/views/_mjit_compile_send.erb
index 6944903821..5fd5a403fd 100644
--- a/tool/ruby_vm/views/_mjit_compile_send.erb
+++ b/tool/ruby_vm/views/_mjit_compile_send.erb
@@ -24,6 +24,11 @@
             int param_size = iseq->body->param.size; /* TODO: check calling->argc for argument_arity_error */
 
             fprintf(f, "{\n");
+% # JIT: Declare stack_size to be used in some macro of _mjit_compile_insn_body.erb
+            if (status->local_stack_p) {
+                /* TODO: can we use some functions to calculate this? */
+                fprintf(f, "    MAYBE_UNUSED(unsigned int) stack_size = %u;\n", b->stack_size - <%= insn.pops.size %> - ((ci->flag & VM_CALL_ARGS_BLOCKARG) ? 1 : 0));
+            }
 
 % # JIT: Invalidate call cache if it requires vm_search_method. This allows to inline some of following things.
 <%= render 'mjit_compile_send_guard' -%>
diff --git a/tool/ruby_vm/views/mjit_compile.inc.erb b/tool/ruby_vm/views/mjit_compile.inc.erb
index 7749984c36..ee29693894 100644
--- a/tool/ruby_vm/views/mjit_compile.inc.erb
+++ b/tool/ruby_vm/views/mjit_compile.inc.erb
@@ -31,13 +31,13 @@
 % #   reg_cfp: the second argument of _mjitXXX
 % #   GET_CFP(): refers to `reg_cfp`
 % #   GET_EP(): refers to `reg_cfp->ep`
-% #   GET_SP(): refers to `reg_cfp->sp`
+% #   GET_SP(): refers to `reg_cfp->sp`, or `(stack + stack_size)` if local_stack_p
 % #   GET_SELF(): refers to `reg_cfp->self`
 % #   GET_LEP(): refers to `VM_EP_LEP(reg_cfp->ep)`
 % #   EXEC_EC_CFP(): refers to `val = vm_exec(ec, TRUE)` with frame setup
 % #   CALL_METHOD(): using `GET_CFP()` and `EXEC_EC_CFP()`
-% #   TOPN(): refers to `reg_cfp->sp`
-% #   STACK_ADDR_FROM_TOP(): refers to `reg_cfp->sp`
+% #   TOPN(): refers to `reg_cfp->sp`, or `*(stack + (stack_size - num - 1))` if local_stack_p
+% #   STACK_ADDR_FROM_TOP(): refers to `reg_cfp->sp`, or `stack + (stack_size - num)` if local_stack_p
 % #   DISPATCH_ORIGINAL_INSN(): expanded in _mjit_compile_insn.erb
 % #   THROW_EXCEPTION(): specially defined for JIT
 % #   RESTORE_REGS(): specially defined for `leave`