Add ragel machine generators to SCONS

src/trusted/validator_ragel/build.scons

+# -*- python -*-
+# Copyright (c) 2012 The Native Client Authors. All rights reserved.
+# Use of this source code is governed by a BSD-style license that can be
+# found in the LICENSE file.
+
+Import('env')
+
+#
+#
+# Build on x86 only.
+#
+#
+if not env.Bit('target_x86'):
+  Return()
+
+# General adjustments to the environment for builds.
+
+# TODO(khim): eliminate need for the following piece
+# See http://code.google.com/p/nativeclient/issues/detail?id=2718 for details.
+if env.Bit('windows'):
+  env.FilterOut(CCFLAGS=['/O1'])
+  env.Append(CCFLAGS=['/O0'])
+
+# Defines the source directory where validator generated files should be added.
+rl_src_dir = '$OBJ_ROOT/src/trusted/validator_ragel'
+val_src_dir = '$MAIN_DIR/src/trusted/validator_ragel/generated'
+
+# Source generation:
+#
+#   valgen : Regenerate any autogenerated source files.
+
+gen_env = env.Clone();
+gen_env.Append(CCFLAGS=['-DNACL_TRUSTED_BUT_NOT_TCB'])
+
+generate = False
+if ('valgen' in COMMAND_LINE_TARGETS) or ('valclean' in COMMAND_LINE_TARGETS):
+  generate = True
+
+# Set of generated (source) decoder tables.
+tables = []
+
+# Ragel generator:
+#
+# We have generator which reads .def files and produced automata definition.
+#
+# Ragel is included in most Linux distributions, but it's not standard tool
+# on MacOS/Windows thus we only support gneration of automata under Linux.
+# This also means that we don't need to make sure gen-dfa.cc is portable to
+# non-POSIX platforms (in particular it's not Windows compatible).
+
+env_gen_dfa = env.Clone()
+env_gen_dfa.Append(CCFLAGS=['-std=c++0x', '-DNACL_TRUSTED_BUT_NOT_TCB'])
+
+gen_dfa = env_gen_dfa.ComponentProgram(
+    'gen-dfa',
+    ['unreviewed/gen-dfa.cc'])
+
+#  Source generation step 2: Generate decoder tables.
+#
+# Now we are back to conditionally defining the large tables generated
+# by gen-dfa.
+
+# Generate 32 and 64 bit versions of decoders and validators.
+if generate:
+  for bits in ['32', '64']:
+    for automata in ['decoder', 'validator']:
+      # We are cheating here: there are two autogenerated files:
+      #  .rl and -consts.c, but we only track .rl one.  This is safe because
+      #  -consts.c file includes constants referenced by .rl file and if .rl
+      #  file is not changed -consts.c is guaranteed to be the same (reverse
+      #  is not true).
+      rl_file = '%s-x86_%s-instruction.rl' % (automata, bits)
+      const_file = '%s/%s-x86_%s-instruction-consts.c' % (
+          val_src_dir, automata, bits)
+      exe_path = '${STAGING_DIR}/${PROGPREFIX}gen-dfa${PROGSUFFIX}'
+      gen_env.Command(
+          target=rl_file,
+          source=[
+            exe_path,
+            'unreviewed/general-purpose-instructions.def',
+            'unreviewed/system-instructions.def',
+            'unreviewed/x87-instructions.def',
+            'unreviewed/mmx-instructions.def',
+            'unreviewed/xmm-instructions.def',
+            'unreviewed/nops.def'],
+          action=[('${SOURCES[0]} -o ${TARGET} -c %s -m %s -d %s ${SOURCES[1]} '
+            '${SOURCES[2]} ${SOURCES[3]} ${SOURCES[4]} ${SOURCES[5]} '
+            '${SOURCES[6]}') % (
+            # Const file (-c): not tracked by SCONS (see above)
+            const_file,
+            # Argument for CPU type (-m): either "ia32" or "amd64".
+            {'32': 'ia32', '64': 'amd64'}[bits],
+            # Argument for actions selection (-d): selects only actions we need.
+            {'decoder32':
+              'check_access,opcode,parse_operands_states,mark_data_fields',
+             'decoder64':
+              'check_access,opcode,parse_operands_states,mark_data_fields',
+             'validator32':
+              ('check_access,opcode,parse_operands,parse_operands_states,'
+                'instruction_name,mark_data_fields,nacl-forbidden,'
+                'imm_operand_action,rel_operand_action'),
+            'validator64':
+              'opcode,instruction_name,mark_data_fields,rel_operand_action,' +
+              'nacl-forbidden'}[automata+bits])]
+      )
+      tables.append(rl_file)
+      c_file = '%s/%s-x86_%s.c' % (val_src_dir, automata, bits)
+      gen_env.Command(
+          target=c_file,
+          source=['unreviewed/%s-x86_%s.rl' % (automata, bits), rl_file],
+          action=['ragel -G2 -I%s ${SOURCES[0]} -o ${TARGET}' % (rl_src_dir)]
+      )
+      tables.append(c_file)
+
+  # Generate 32 and 64 bit versions of decoders and validators
+  gen_env.AlwaysBuild(
+      gen_env.Alias('valgen', tables))
+  gen_env.AlwaysBuild(
+      gen_env.Alias('valclean', action=[Delete(x) for x in tables]))
+
+# Generate 32 and 64 bit versions of decoders and validators.
+for bits in ['32', '64']:
+  for automata in ['decoder', 'validator']:
+    env.ComponentLibrary('%s-x86_%s' % (automata, bits),

[pasko-google - do not use, 2012/04/09 10:04:27]

you suggest a validator library be named like:
validator-x86_64.a

I'd like to:
* distinguish it from the existing validator
* bring more consistency between dash and underscore
* refer to it as 'validate', not 'validator' because:
  (a) it is not a standalone validator, only a library
  (b) the current library of similar purpose is called 'ncvalidate', would be
more natural to people knowing about it

Proposed name:
dfa_validate_x86_64.a

[pasko-google - do not use, 2012/04/09 10:38:54]

hm, in fact it is called libvalidator-x86_64.a, but has to be referenced as
"validator..." in scons files

+                         ['generated/%s-x86_%s.c' % (automata, bits)])
+
+env.ComponentProgram(
+    'decoder-test',
+    ['unreviewed/decoder-test.c'],
+    EXTRA_LIBS=['decoder-x86_32', 'decoder-x86_64'])
+
+env.ComponentProgram(
+    'validator-test',
+    ['unreviewed/validator-test.c'],
+    EXTRA_LIBS=['validator-x86_32', 'validator-x86_64'])