build: add --node-snapshot-main configure option

This adds a --build-snapshot runtime option which is currently only
supported by the node_mksnapshot binary, and a --node-snapshot-main
configure option that makes use it to run a custom script when
building the embedded snapshot. The idea is to have this experimental
feature in core as a configure-time feature for now, and investigate
the renaming V8 bugs before we make it available to more users via
making it a runtime option.

PR-URL: https://github.com/nodejs/node/pull/42466
Reviewed-By: Darshan Sen <raisinten@gmail.com>
Reviewed-By: Mohammed Keyvanzadeh <mohammadkeyvanzade94@gmail.com>
Reviewed-By: Khaidi Chu <i@2333.moe>
Reviewed-By: Chengzhong Wu <legendecas@gmail.com>

7 files changed, 100 insertions, 1 deletions

diff --git a/src/node.cc b/src/node.cc
index e503fd9f5b4..5ba03b75407 100644
--- a/src/node.cc
+++ b/src/node.cc
@@ -495,6 +495,10 @@ MaybeLocal<Value> StartExecution(Environment* env, StartExecutionCallback cb) {
     return StartExecution(env, "internal/main/inspect");
   }
 
+  if (per_process::cli_options->build_snapshot) {
+    return StartExecution(env, "internal/main/mksnapshot");
+  }
+
   if (per_process::cli_options->print_help) {
     return StartExecution(env, "internal/main/print_help");
   }
@@ -1153,6 +1157,12 @@ int Start(int argc, char** argv) {
     return result.exit_code;
   }
 
+  if (per_process::cli_options->build_snapshot) {
+    fprintf(stderr,
+            "--build-snapshot is not yet supported in the node binary\n");
+    return 1;
+  }
+
   {
     bool use_node_snapshot =
         per_process::cli_options->per_isolate->node_snapshot;
diff --git a/src/node_binding.cc b/src/node_binding.cc
index 050c5dff0ad..ed8ab9237fd 100644
--- a/src/node_binding.cc
+++ b/src/node_binding.cc
@@ -59,6 +59,7 @@
   V(js_udp_wrap)                                                               \
   V(messaging)                                                                 \
   V(module_wrap)                                                               \
+  V(mksnapshot)                                                                \
   V(native_module)                                                             \
   V(options)                                                                   \
   V(os)                                                                        \
diff --git a/src/node_external_reference.h b/src/node_external_reference.h
index c57a01ff39c..306c726631a 100644
--- a/src/node_external_reference.h
+++ b/src/node_external_reference.h
@@ -66,6 +66,7 @@ class ExternalReferenceRegistry {
   V(handle_wrap)                                                               \
   V(heap_utils)                                                                \
   V(messaging)                                                                 \
+  V(mksnapshot)                                                                \
   V(native_module)                                                             \
   V(options)                                                                   \
   V(os)                                                                        \
diff --git a/src/node_options.cc b/src/node_options.cc
index 35ee54d2231..bb568ce458a 100644
--- a/src/node_options.cc
+++ b/src/node_options.cc
@@ -725,6 +725,11 @@ PerProcessOptionsParser::PerProcessOptionsParser(
             "disable Object.prototype.__proto__",
             &PerProcessOptions::disable_proto,
             kAllowedInEnvironment);
+  AddOption("--build-snapshot",
+            "Generate a snapshot blob when the process exits."
+            "Currently only supported in the node_mksnapshot binary.",
+            &PerProcessOptions::build_snapshot,
+            kDisallowedInEnvironment);
 
   // 12.x renamed this inadvertently, so alias it for consistency within the
   // release line, while using the original name for consistency with older
diff --git a/src/node_options.h b/src/node_options.h
index 3335c12b8cd..7a73e6e5987 100644
--- a/src/node_options.h
+++ b/src/node_options.h
@@ -229,6 +229,7 @@ class PerProcessOptions : public Options {
   bool zero_fill_all_buffers = false;
   bool debug_arraybuffer_allocations = false;
   std::string disable_proto;
+  bool build_snapshot;
 
   std::vector<std::string> security_reverts;
   bool print_bash_completion = false;
diff --git a/src/node_snapshotable.cc b/src/node_snapshotable.cc
index 71b025df81e..327246743bb 100644
--- a/src/node_snapshotable.cc
+++ b/src/node_snapshotable.cc
@@ -18,12 +18,18 @@
 namespace node {
 
 using v8::Context;
+using v8::Function;
+using v8::FunctionCallbackInfo;
 using v8::HandleScope;
 using v8::Isolate;
 using v8::Local;
+using v8::MaybeLocal;
 using v8::Object;
+using v8::ScriptCompiler;
+using v8::ScriptOrigin;
 using v8::SnapshotCreator;
 using v8::StartupData;
+using v8::String;
 using v8::TryCatch;
 using v8::Value;
 
@@ -130,16 +136,36 @@ void SnapshotBuilder::Generate(SnapshotData* out,
                             nullptr,
                             node::EnvironmentFlags::kDefaultFlags,
                             {});
+      // TODO(joyeecheung): run env->InitializeInspector({}) here.
       // Run scripts in lib/internal/bootstrap/
       {
         TryCatch bootstrapCatch(isolate);
-        v8::MaybeLocal<Value> result = env->RunBootstrapping();
+        MaybeLocal<Value> result = env->RunBootstrapping();
         if (bootstrapCatch.HasCaught()) {
           PrintCaughtException(isolate, context, bootstrapCatch);
         }
         result.ToLocalChecked();
       }
 
+      // If --build-snapshot is true, lib/internal/main/mksnapshot.js would be
+      // loaded via LoadEnvironment() to execute process.argv[1] as the entry
+      // point (we currently only support this kind of entry point, but we
+      // could also explore snapshotting other kinds of execution modes
+      // in the future).
+      if (per_process::cli_options->build_snapshot) {
+        TryCatch bootstrapCatch(isolate);
+        // TODO(joyeecheung): we could use the result for something special,
+        // like setting up initializers that should be invoked at snapshot
+        // dehydration.
+        MaybeLocal<Value> result =
+            LoadEnvironment(env, StartExecutionCallback{});
+        if (bootstrapCatch.HasCaught()) {
+          PrintCaughtException(isolate, context, bootstrapCatch);
+        }
+        result.ToLocalChecked();
+        // TODO(joyeecheung): run SpinEventLoop here.
+      }
+
       if (per_process::enabled_debug_list.enabled(DebugCategory::MKSNAPSHOT)) {
         env->PrintAllBaseObjects();
         printf("Environment = %p\n", env);
@@ -309,4 +335,57 @@ void SerializeBindingData(Environment* env,
   });
 }
 
+namespace mksnapshot {
+
+static void CompileSnapshotMain(const FunctionCallbackInfo<Value>& args) {
+  CHECK(args[0]->IsString());
+  Local<String> filename = args[0].As<String>();
+  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::CompileFunctionInContext(context,
+                                               &script_source,
+                                               parameters.size(),
+                                               parameters.data(),
+                                               0,
+                                               nullptr,
+                                               ScriptCompiler::kEagerCompile)
+          .ToLocal(&fn)) {
+    args.GetReturnValue().Set(fn);
+  }
+}
+
+static void Initialize(Local<Object> target,
+                       Local<Value> unused,
+                       Local<Context> context,
+                       void* priv) {
+  Environment* env = Environment::GetCurrent(context);
+  Isolate* isolate = context->GetIsolate();
+  env->SetMethod(target, "compileSnapshotMain", CompileSnapshotMain);
+  target
+      ->Set(context,
+            FIXED_ONE_BYTE_STRING(isolate, "cleanups"),
+            v8::Array::New(isolate))
+      .Check();
+}
+
+static void RegisterExternalReferences(ExternalReferenceRegistry* registry) {
+  registry->Register(CompileSnapshotMain);
+  registry->Register(MarkBootstrapComplete);
+}
+}  // namespace mksnapshot
 }  // namespace node
+
+NODE_MODULE_CONTEXT_AWARE_INTERNAL(mksnapshot, node::mksnapshot::Initialize)
+NODE_MODULE_EXTERNAL_REFERENCE(mksnapshot,
+                               node::mksnapshot::RegisterExternalReferences)
diff --git a/src/node_snapshotable.h b/src/node_snapshotable.h
index 1ccd9a93226..30b684eb68a 100644
--- a/src/node_snapshotable.h
+++ b/src/node_snapshotable.h
@@ -127,6 +127,8 @@ class SnapshotBuilder {
  public:
   static std::string Generate(const std::vector<std::string> args,
                               const std::vector<std::string> exec_args);
+
+  // Generate the snapshot into out.
   static void Generate(SnapshotData* out,
                        const std::vector<std::string> args,
                        const std::vector<std::string> exec_args);