Make snapshots reproducible.

To keep the structure of the serializer more or less untouched, we use
some ingenious Corry-approved(TM) 3-step technology (a.k.a. "hack"):

   * Create copies of code objects.
   * Wipe out all absolute addresses in these copies.
   * Write out the cleaned copies instead of the originals.

In conjunction with --random-seed, our snapshots are reproducible now.

BUG=v8:2885
R=bmeurer@chromium.org, erik.corry@gmail.com

Review URL: https://codereview.chromium.org/54823002

git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@17473 ce2b1a6d-e550-0410-aec6-3dcde31c8c00

diff --git a/src/arm/assembler-arm-inl.h b/src/arm/assembler-arm-inl.h
index 9a83a42..ff09654 100644 (file)
--- a/src/arm/assembler-arm-inl.h
+++ b/src/arm/assembler-arm-inl.h
@@ -258,6 +258,15 @@ Object** RelocInfo::call_object_address() {
 }
 
 
+void RelocInfo::WipeOut() {
+  ASSERT(IsEmbeddedObject(rmode_) ||
+         IsCodeTarget(rmode_) ||
+         IsRuntimeEntry(rmode_) ||
+         IsExternalReference(rmode_));
+  Assembler::set_target_pointer_at(pc_, NULL);
+}
+
+
 bool RelocInfo::IsPatchedReturnSequence() {
   Instr current_instr = Assembler::instr_at(pc_);
   Instr next_instr = Assembler::instr_at(pc_ + Assembler::kInstrSize);

diff --git a/src/assembler.h b/src/assembler.h
index 11087da..ee51f23 100644 (file)
--- a/src/assembler.h
+++ b/src/assembler.h
@@ -435,6 +435,10 @@ class RelocInfo BASE_EMBEDDED {
   INLINE(void set_call_object(Object* target));
   INLINE(Object** call_object_address());
 
+  // Wipe out a relocation to a fixed value, used for making snapshots
+  // reproducible.
+  INLINE(void WipeOut());
+
   template<typename StaticVisitor> inline void Visit(Heap* heap);
   inline void Visit(Isolate* isolate, ObjectVisitor* v);
 

diff --git a/src/ia32/assembler-ia32-inl.h b/src/ia32/assembler-ia32-inl.h
index 00f7a63..ee5d991 100644 (file)
--- a/src/ia32/assembler-ia32-inl.h
+++ b/src/ia32/assembler-ia32-inl.h
@@ -243,6 +243,18 @@ Object** RelocInfo::call_object_address() {
 }
 
 
+void RelocInfo::WipeOut() {
+  if (IsEmbeddedObject(rmode_) || IsExternalReference(rmode_)) {
+    Memory::Address_at(pc_) = NULL;
+  } else if (IsCodeTarget(rmode_) || IsRuntimeEntry(rmode_)) {
+    // Effectively write zero into the relocation.
+    Assembler::set_target_address_at(pc_, pc_ + sizeof(int32_t));
+  } else {
+    UNREACHABLE();
+  }
+}
+
+
 bool RelocInfo::IsPatchedReturnSequence() {
   return *pc_ == kCallOpcode;
 }

diff --git a/src/mips/assembler-mips-inl.h b/src/mips/assembler-mips-inl.h
index b430b1f..d5af5b2 100644 (file)
--- a/src/mips/assembler-mips-inl.h
+++ b/src/mips/assembler-mips-inl.h
@@ -315,6 +315,15 @@ void RelocInfo::set_call_object(Object* target) {
 }
 
 
+void RelocInfo::WipeOut() {
+  ASSERT(IsEmbeddedObject(rmode_) ||
+         IsCodeTarget(rmode_) ||
+         IsRuntimeEntry(rmode_) ||
+         IsExternalReference(rmode_));
+  Assembler::set_target_address_at(pc_, NULL);
+}
+
+
 bool RelocInfo::IsPatchedReturnSequence() {
   Instr instr0 = Assembler::instr_at(pc_);
   Instr instr1 = Assembler::instr_at(pc_ + 1 * Assembler::kInstrSize);

diff --git a/src/objects-inl.h b/src/objects-inl.h
index 2acbe70..87ad8ec 100644 (file)
--- a/src/objects-inl.h
+++ b/src/objects-inl.h
@@ -5323,6 +5323,17 @@ ACCESSORS(Code, deoptimization_data, FixedArray, kDeoptimizationDataOffset)
 ACCESSORS(Code, raw_type_feedback_info, Object, kTypeFeedbackInfoOffset)
 
 
+void Code::WipeOutHeader() {
+  WRITE_FIELD(this, kRelocationInfoOffset, NULL);
+  WRITE_FIELD(this, kHandlerTableOffset, NULL);
+  WRITE_FIELD(this, kDeoptimizationDataOffset, NULL);
+  // Do not wipe out e.g. a minor key.
+  if (!READ_FIELD(this, kTypeFeedbackInfoOffset)->IsSmi()) {
+    WRITE_FIELD(this, kTypeFeedbackInfoOffset, NULL);
+  }
+}
+
+
 Object* Code::type_feedback_info() {
   ASSERT(kind() == FUNCTION);
   return raw_type_feedback_info();

diff --git a/src/objects.h b/src/objects.h
index e7567cd..33f5396 100644 (file)
--- a/src/objects.h
+++ b/src/objects.h
@@ -5198,6 +5198,15 @@ class Code: public HeapObject {
 
   void ReplaceNthCell(int n, Cell* replace_with);
 
+  // The entire code object including its header is copied verbatim to the
+  // snapshot so that it can be written in one, fast, memcpy during
+  // deserialization. The deserializer will overwrite some pointers, rather
+  // like a runtime linker, but the random allocation addresses used in the
+  // mksnapshot process would still be present in the unlinked snapshot data,
+  // which would make snapshot production non-reproducible. This method wipes
+  // out the to-be-overwritten header data for reproducible snapshots.
+  inline void WipeOutHeader();
+
   class ExtraICStateStrictMode: public BitField<StrictModeFlag, 0, 1> {};
   class ExtraICStateKeyedAccessStoreMode:
       public BitField<KeyedAccessStoreMode, 1, 4> {};  // NOLINT

diff --git a/src/serialize.cc b/src/serialize.cc
index 130fbee..3cc7053 100644 (file)
--- a/src/serialize.cc
+++ b/src/serialize.cc
@@ -1776,10 +1776,29 @@ void Serializer::ObjectSerializer::VisitExternalAsciiString(
 }
 
 
+static Code* CloneCodeObject(HeapObject* code) {
+  Address copy = new byte[code->Size()];
+  OS::MemCopy(copy, code->address(), code->Size());
+  return Code::cast(HeapObject::FromAddress(copy));
+}
+
+
+static void WipeOutRelocations(Code* code) {
+  int mode_mask =
+      RelocInfo::kCodeTargetMask |
+      RelocInfo::ModeMask(RelocInfo::EMBEDDED_OBJECT) |
+      RelocInfo::ModeMask(RelocInfo::EXTERNAL_REFERENCE) |
+      RelocInfo::ModeMask(RelocInfo::RUNTIME_ENTRY);
+  for (RelocIterator it(code, mode_mask); !it.done(); it.next()) {
+    it.rinfo()->WipeOut();
+  }
+}
+
+
 int Serializer::ObjectSerializer::OutputRawData(
     Address up_to, Serializer::ObjectSerializer::ReturnSkip return_skip) {
   Address object_start = object_->address();
-  Address base = object_start + bytes_processed_so_far_;
+  int base = bytes_processed_so_far_;
   int up_to_offset = static_cast<int>(up_to - object_start);
   int to_skip = up_to_offset - bytes_processed_so_far_;
   int bytes_to_output = to_skip;
@@ -1809,10 +1828,22 @@ int Serializer::ObjectSerializer::OutputRawData(
       sink_->Put(kRawData, "RawData");
       sink_->PutInt(bytes_to_output, "length");
     }
+
+    // To make snapshots reproducible, we need to wipe out all pointers in code.
+    if (code_object_) {
+      Code* code = CloneCodeObject(object_);
+      WipeOutRelocations(code);
+      // We need to wipe out the header fields *after* wiping out the
+      // relocations, because some of these fields are needed for the latter.
+      code->WipeOutHeader();
+      object_start = code->address();
+    }
+
+    const char* description = code_object_ ? "Code" : "Byte";
     for (int i = 0; i < bytes_to_output; i++) {
-      unsigned int data = base[i];
-      sink_->PutSection(data, "Byte");
+      sink_->PutSection(object_start[base + i], description);
     }
+    if (code_object_) delete[] object_start;
   }
   if (to_skip != 0 && return_skip == kIgnoringReturn) {
     sink_->Put(kSkip, "Skip");

diff --git a/src/x64/assembler-x64-inl.h b/src/x64/assembler-x64-inl.h
index f4ee4e6..073fcbe 100644 (file)
--- a/src/x64/assembler-x64-inl.h
+++ b/src/x64/assembler-x64-inl.h
@@ -364,6 +364,18 @@ void RelocInfo::set_target_cell(Cell* cell, WriteBarrierMode mode) {
 }
 
 
+void RelocInfo::WipeOut() {
+  if (IsEmbeddedObject(rmode_) || IsExternalReference(rmode_)) {
+    Memory::Address_at(pc_) = NULL;
+  } else if (IsCodeTarget(rmode_) || IsRuntimeEntry(rmode_)) {
+    // Effectively write zero into the relocation.
+    Assembler::set_target_address_at(pc_, pc_ + sizeof(int32_t));
+  } else {
+    UNREACHABLE();
+  }
+}
+
+
 bool RelocInfo::IsPatchedReturnSequence() {
   // The recognized call sequence is:
   //  movq(kScratchRegister, address); call(kScratchRegister);