sea: add support for V8 bytecode-only caching

Refs: nodejs/single-executable#73
Signed-off-by: Darshan Sen <raisinten@gmail.com>

Author: RaisinTen

lib/internal/modules/cjs/loader.js

@@ -127,6 +127,7 @@ let hasLoadedAnyUserCJSModule = false;
 
 const {
   codes: {
+    ERR_INTERNAL_ASSERTION,
     ERR_INVALID_ARG_VALUE,
     ERR_INVALID_MODULE_SPECIFIER,
     ERR_REQUIRE_ESM,
@@ -1147,7 +1148,7 @@ Module.prototype.require = function(id) {
 let resolvedArgv;
 let hasPausedEntry = false;
 let Script;
-function wrapSafe(filename, content, cjsModuleInstance) {
+function wrapSafe(filename, content, cjsModuleInstance, codeCache) {
   if (patched) {
     const wrapper = Module.wrap(content);
     if (Script === undefined) {
@@ -1182,13 +1183,18 @@ function wrapSafe(filename, content, cjsModuleInstance) {
       '__dirname',
     ], {
       filename,
+      cachedData: codeCache,
       importModuleDynamically(specifier, _, importAssertions) {
         const cascadedLoader = getCascadedLoader();
         return cascadedLoader.import(specifier, normalizeReferrerURL(filename),
                                      importAssertions);
       },
     });
 
+    if (codeCache && result.cachedDataRejected !== false) {
+      throw new ERR_INTERNAL_ASSERTION('Code cache data rejected.');
+    }
+
     // Cache the source map for the module if present.
     if (result.sourceMapURL) {
       maybeCacheSourceMap(filename, content, this, false, undefined, result.sourceMapURL);

lib/internal/util/embedding.js

@@ -1,7 +1,8 @@
 'use strict';
-const { codes: { ERR_UNKNOWN_BUILTIN_MODULE } } = require('internal/errors');
 const { BuiltinModule: { normalizeRequirableId } } = require('internal/bootstrap/realm');
 const { Module, wrapSafe } = require('internal/modules/cjs/loader');
+const { codes: { ERR_UNKNOWN_BUILTIN_MODULE } } = require('internal/errors');
+const { getCodeCache } = internalBinding('sea');
 
 // This is roughly the same as:
 //
@@ -15,7 +16,7 @@ const { Module, wrapSafe } = require('internal/modules/cjs/loader');
 
 function embedderRunCjs(contents) {
   const filename = process.execPath;
-  const compiledWrapper = wrapSafe(filename, contents);
+  const compiledWrapper = wrapSafe(filename, contents, undefined, getCodeCache());
 
   const customModule = new Module(filename, null);
   customModule.filename = filename;

src/json_parser.cc

@@ -4,34 +4,15 @@
 #include "util-inl.h"
 
 namespace node {
-using v8::ArrayBuffer;
 using v8::Context;
 using v8::Isolate;
 using v8::Local;
 using v8::Object;
 using v8::String;
 using v8::Value;
 
-static Isolate* NewIsolate(v8::ArrayBuffer::Allocator* allocator) {
-  Isolate* isolate = Isolate::Allocate();
-  CHECK_NOT_NULL(isolate);
-  per_process::v8_platform.Platform()->RegisterIsolate(isolate,
-                                                       uv_default_loop());
-  Isolate::CreateParams params;
-  params.array_buffer_allocator = allocator;
-  Isolate::Initialize(isolate, params);
-  return isolate;
-}
-
-void JSONParser::FreeIsolate(Isolate* isolate) {
-  per_process::v8_platform.Platform()->UnregisterIsolate(isolate);
-  isolate->Dispose();
-}
-
 JSONParser::JSONParser()
-    : allocator_(ArrayBuffer::Allocator::NewDefaultAllocator()),
-      isolate_(NewIsolate(allocator_.get())),
-      handle_scope_(isolate_.get()),
+    : handle_scope_(isolate_.get()),
       context_(isolate_.get(), Context::New(isolate_.get())),
       context_scope_(context_.Get(isolate_.get())) {}
 

src/json_parser.h

@@ -24,9 +24,7 @@ class JSONParser {
  private:
   // We might want a lighter-weight JSON parser for this use case. But for now
   // using V8 is good enough.
-  static void FreeIsolate(v8::Isolate* isolate);
-  std::unique_ptr<v8::ArrayBuffer::Allocator> allocator_;
-  DeleteFnPtr<v8::Isolate, FreeIsolate> isolate_;
+  RAIIIsolate isolate_;
   v8::HandleScope handle_scope_;
   v8::Global<v8::Context> context_;
   v8::Context::Scope context_scope_;

src/node_contextify.cc

@@ -935,6 +935,30 @@ Maybe<bool> StoreCodeCacheResult(
   return Just(true);
 }
 
+// TODO(RaisinTen): Reuse in ContextifyContext::CompileFunction().
+MaybeLocal<Function> CompileFunction(Isolate* isolate,
+                                     Local<Context> context,
+                                     Local<String> filename,
+                                     Local<String> content,
+                                     std::vector<Local<String>> parameters) {
+  ScriptOrigin script_origin(isolate, filename, 0, 0, true);
+  ScriptCompiler::Source script_source(content, script_origin);
+
+  Local<Function> fn;
+  if (!ScriptCompiler::CompileFunction(context,
+                                       &script_source,
+                                       parameters.size(),
+                                       parameters.data(),
+                                       0,
+                                       nullptr,
+                                       ScriptCompiler::kEagerCompile)
+           .ToLocal(&fn)) {
+    return {};
+  }
+
+  return fn;
+}
+
 bool ContextifyScript::InstanceOf(Environment* env,
                                   const Local<Value>& value) {
   return !value.IsEmpty() &&

src/node_contextify.h

@@ -210,6 +210,13 @@ v8::Maybe<bool> StoreCodeCacheResult(
     bool produce_cached_data,
     std::unique_ptr<v8::ScriptCompiler::CachedData> new_cached_data);
 
+v8::MaybeLocal<v8::Function> CompileFunction(
+    v8::Isolate* isolate,
+    v8::Local<v8::Context> context,
+    v8::Local<v8::String> filename,
+    v8::Local<v8::String> content,
+    std::vector<v8::Local<v8::String>> parameters);
+
 }  // namespace contextify
 }  // namespace node
 

src/node_sea.cc

@@ -4,9 +4,13 @@
 #include "debug_utils-inl.h"
 #include "env-inl.h"
 #include "json_parser.h"
+#include "node_contextify.h"
+#include "node_errors.h"
 #include "node_external_reference.h"
 #include "node_internals.h"
 #include "node_union_bytes.h"
+#include "node_v8_platform-inl.h"
+#include "util-inl.h"
 
 // The POSTJECT_SENTINEL_FUSE macro is a string of random characters selected by
 // the Node.js project that is present only once in the entire binary. It is
@@ -26,9 +30,14 @@
 
 using node::ExitCode;
 using v8::Context;
+using v8::Function;
 using v8::FunctionCallbackInfo;
+using v8::HandleScope;
+using v8::Isolate;
 using v8::Local;
 using v8::Object;
+using v8::ScriptCompiler;
+using v8::String;
 using v8::Value;
 
 namespace node {
@@ -78,6 +87,11 @@ size_t SeaSerializer::Write(const SeaResource& sea) {
         sea.code.data(),
         sea.code.size());
   written_total += WriteStringView(sea.code, StringLogMode::kAddressAndContent);
+
+  Debug("Write SEA resource code cache %p, size=%zu\n",
+        sea.code_cache.data(),
+        sea.code_cache.size());
+  written_total += WriteStringView(sea.code_cache, StringLogMode::kAddressOnly);
   return written_total;
 }
 
@@ -105,7 +119,12 @@ SeaResource SeaDeserializer::Read() {
 
   std::string_view code = ReadStringView(StringLogMode::kAddressAndContent);
   Debug("Read SEA resource code %p, size=%zu\n", code.data(), code.size());
-  return {flags, code};
+
+  std::string_view code_cache = ReadStringView(StringLogMode::kAddressOnly);
+  Debug("Read SEA resource code cache %p, size=%zu\n",
+        code_cache.data(),
+        code_cache.size());
+  return {flags, code, code_cache};
 }
 
 std::string_view FindSingleExecutableBlob() {
@@ -161,6 +180,27 @@ void IsExperimentalSeaWarningNeeded(const FunctionCallbackInfo<Value>& args) {
       sea_resource.flags & SeaFlags::kDisableExperimentalSeaWarning));
 }
 
+void GetCodeCache(const FunctionCallbackInfo<Value>& args) {
+  if (!IsSingleExecutable()) {
+    return;
+  }
+
+  Environment* env = Environment::GetCurrent(args);
+  Isolate* isolate = env->isolate();
+  HandleScope scope(isolate);
+
+  SeaResource sea_resource = FindSingleExecutableResource();
+
+  Local<Object> buf =
+      Buffer::Copy(
+          env,
+          reinterpret_cast<const char*>(sea_resource.code_cache.data()),
+          sea_resource.code_cache.length())
+          .ToLocalChecked();
+
+  args.GetReturnValue().Set(buf);
+}
+
 std::tuple<int, char**> FixupArgsForSEA(int argc, char** argv) {
   // Repeats argv[0] at position 1 on argv as a replacement for the missing
   // entry point file path.
@@ -238,6 +278,49 @@ std::optional<SeaConfig> ParseSingleExecutableConfig(
   return result;
 }
 
+std::optional<std::string> GenerateCodeCache(std::string_view main_path,
+                                             std::string_view main_script) {
+  RAIIIsolate raii_isolate;
+  Isolate* isolate = raii_isolate.get();
+
+  HandleScope handle_scope(isolate);
+  Local<Context> context = Context::New(isolate);
+  Context::Scope context_scope(context);
+
+  errors::PrinterTryCatch bootstrapCatch(
+      isolate, errors::PrinterTryCatch::kPrintSourceLine);
+
+  Local<String> filename;
+  if (!String::NewFromUtf8(isolate, main_path.data()).ToLocal(&filename)) {
+    return {};
+  }
+
+  Local<String> content;
+  if (!String::NewFromUtf8(isolate, main_script.data()).ToLocal(&content)) {
+    return {};
+  }
+
+  std::vector<Local<String>> parameters = {
+      FIXED_ONE_BYTE_STRING(isolate, "exports"),
+      FIXED_ONE_BYTE_STRING(isolate, "require"),
+      FIXED_ONE_BYTE_STRING(isolate, "module"),
+      FIXED_ONE_BYTE_STRING(isolate, "__filename"),
+      FIXED_ONE_BYTE_STRING(isolate, "__dirname"),
+  };
+
+  Local<Function> fn;
+  if (!contextify::CompileFunction(
+           isolate, context, filename, content, std::move(parameters))
+           .ToLocal(&fn)) {
+    return {};
+  }
+
+  std::unique_ptr<ScriptCompiler::CachedData> cache{
+      ScriptCompiler::CreateCodeCacheForFunction(fn)};
+  std::string code_cache(cache->data, cache->data + cache->length);
+  return code_cache;
+}
+
 ExitCode GenerateSingleExecutableBlob(const SeaConfig& config) {
   std::string main_script;
   // TODO(joyeecheung): unify the file utils.
@@ -248,7 +331,15 @@ ExitCode GenerateSingleExecutableBlob(const SeaConfig& config) {
     return ExitCode::kGenericUserError;
   }
 
-  SeaResource sea{config.flags, main_script};
+  std::optional<std::string> optional_code_cache =
+      GenerateCodeCache(config.main_path, main_script);
+  if (!optional_code_cache.has_value()) {
+    FPrintF(stderr, "Cannot generate V8 code cache\n");
+    return ExitCode::kGenericUserError;
+  }
+  std::string code_cache = optional_code_cache.value();
+
+  SeaResource sea{config.flags, main_script, code_cache};
 
   SeaSerializer serializer;
   serializer.Write(sea);
@@ -288,10 +379,12 @@ void Initialize(Local<Object> target,
             target,
             "isExperimentalSeaWarningNeeded",
             IsExperimentalSeaWarningNeeded);
+  SetMethod(context, target, "getCodeCache", GetCodeCache);
 }
 
 void RegisterExternalReferences(ExternalReferenceRegistry* registry) {
   registry->Register(IsExperimentalSeaWarningNeeded);
+  registry->Register(GetCodeCache);
 }
 
 }  // namespace sea

src/node_sea.h

@@ -26,6 +26,7 @@ enum class SeaFlags : uint32_t {
 struct SeaResource {
   SeaFlags flags = SeaFlags::kDefault;
   std::string_view code;
+  std::string_view code_cache;
 
   static constexpr size_t kHeaderSize = sizeof(kMagic) + sizeof(SeaFlags);
 };

src/node_snapshotable.cc

@@ -42,7 +42,6 @@ using v8::MaybeLocal;
 using v8::Object;
 using v8::ObjectTemplate;
 using v8::ScriptCompiler;
-using v8::ScriptOrigin;
 using v8::SnapshotCreator;
 using v8::StartupData;
 using v8::String;
@@ -1254,23 +1253,16 @@ void CompileSerializeMain(const FunctionCallbackInfo<Value>& args) {
   Local<String> source = args[1].As<String>();
   Isolate* isolate = args.GetIsolate();
   Local<Context> context = isolate->GetCurrentContext();
-  ScriptOrigin origin(isolate, filename, 0, 0, true);
   // TODO(joyeecheung): do we need all of these? Maybe we would want a less
   // internal version of them.
   std::vector<Local<String>> parameters = {
       FIXED_ONE_BYTE_STRING(isolate, "require"),
       FIXED_ONE_BYTE_STRING(isolate, "__filename"),
       FIXED_ONE_BYTE_STRING(isolate, "__dirname"),
   };
-  ScriptCompiler::Source script_source(source, origin);
   Local<Function> fn;
-  if (ScriptCompiler::CompileFunction(context,
-                                      &script_source,
-                                      parameters.size(),
-                                      parameters.data(),
-                                      0,
-                                      nullptr,
-                                      ScriptCompiler::kEagerCompile)
+  if (contextify::CompileFunction(
+          isolate, context, filename, source, std::move(parameters))
           .ToLocal(&fn)) {
     args.GetReturnValue().Set(fn);
   }

src/util.cc

@@ -28,6 +28,7 @@
 #include "node_errors.h"
 #include "node_internals.h"
 #include "node_util.h"
+#include "node_v8_platform-inl.h"
 #include "string_bytes.h"
 #include "uv.h"
 
@@ -55,6 +56,7 @@ static std::atomic_int seq = {0};  // Sequence number for diagnostic filenames.
 
 namespace node {
 
+using v8::ArrayBuffer;
 using v8::ArrayBufferView;
 using v8::Context;
 using v8::FunctionTemplate;
@@ -618,4 +620,20 @@ Local<String> UnionBytes::ToStringChecked(Isolate* isolate) const {
   }
 }
 
+RAIIIsolate::RAIIIsolate()
+    : allocator_{ArrayBuffer::Allocator::NewDefaultAllocator()} {
+  isolate_ = Isolate::Allocate();
+  CHECK_NOT_NULL(isolate_);
+  per_process::v8_platform.Platform()->RegisterIsolate(isolate_,
+                                                       uv_default_loop());
+  Isolate::CreateParams params;
+  params.array_buffer_allocator = allocator_.get();
+  Isolate::Initialize(isolate_, params);
+}
+
+RAIIIsolate::~RAIIIsolate() {
+  per_process::v8_platform.Platform()->UnregisterIsolate(isolate_);
+  isolate_->Dispose();
+}
+
 }  // namespace node