String.intern源码

前言

以JDK8为例来分析

String.java

public native String intern();

String.c

openjdk8\openjdk\jdk\src\share\native\java\lang\String.c

#include "jvm.h"
#include "java_lang_String.h"

JNIEXPORT jobject JNICALL
Java_java_lang_String_intern(JNIEnv *env, jobject this)
{
    return JVM_InternString(env, this);
}

jvm.cpp

openjdk8\openjdk\hotspot\src\share\vm\prims\jvm.cpp

JVM_ENTRY(jstring, JVM_InternString(JNIEnv *env, jstring str))
  JVMWrapper("JVM_InternString");
  JvmtiVMObjectAllocEventCollector oam;
  if (str == NULL) return NULL;
  oop string = JNIHandles::resolve_non_null(str);
  oop result = StringTable::intern(string, CHECK_NULL);
  return (jstring) JNIHandles::make_local(env, result);
JVM_END

StringTable::intern

openjdk8\openjdk\hotspot\src\share\vm\classfile\symbolTable.cpp中找到

oop StringTable::intern(Symbol* symbol, TRAPS) {
  if (symbol == NULL) return NULL;
  ResourceMark rm(THREAD);
  int length;
  jchar* chars = symbol->as_unicode(length);
  Handle string;
  oop result = intern(string, chars, length, CHECK_NULL);
  return result;
}

oop StringTable::intern(Handle string_or_null, jchar* name,
                        int len, TRAPS) {
  unsigned int hashValue = hash_string(name, len);
  int index = the_table()->hash_to_index(hashValue);
  oop found_string = the_table()->lookup(index, name, len, hashValue);

  // Found
  if (found_string != NULL) {
    ensure_string_alive(found_string);
    return found_string; // 在the_table中找到字符串实例就返回
  }

  debug_only(StableMemoryChecker smc(name, len * sizeof(name[0])));
  assert(!Universe::heap()->is_in_reserved(name),
         "proposed name of symbol must be stable");

  Handle string;
  // try to reuse the string if possible
  if (!string_or_null.is_null()) { 
    string = string_or_null; // 上面常量池中不存在，则重用堆中的string对象
  } else {
    string = java_lang_String::create_from_unicode(name, len, CHECK_NULL);
  }

#if INCLUDE_ALL_GCS
  if (G1StringDedup::is_enabled()) {
    // Deduplicate the string before it is interned. Note that we should never
    // deduplicate a string after it has been interned. Doing so will counteract
    // compiler optimizations done on e.g. interned string literals.
    G1StringDedup::deduplicate(string());
  }
#endif

  // Grab the StringTable_lock before getting the_table() because it could
  // change at safepoint.
  oop added_or_found;
  {
    MutexLocker ml(StringTable_lock, THREAD);
    // Otherwise, add to symbol to table
    added_or_found = the_table()->basic_add(index, string, name, len,
                                  hashValue, CHECK_NULL);
  }

  ensure_string_alive(added_or_found);

  return added_or_found;
}

StringTable::basic_add

oop StringTable::basic_add(int index_arg, Handle string, jchar* name,
                           int len, unsigned int hashValue_arg, TRAPS) {

  assert(java_lang_String::equals(string(), name, len),
         "string must be properly initialized");
  // Cannot hit a safepoint in this function because the "this" pointer can move.
  No_Safepoint_Verifier nsv;

  // Check if the symbol table has been rehashed, if so, need to recalculate
  // the hash value and index before second lookup.
  unsigned int hashValue;
  int index;
  if (use_alternate_hashcode()) {
    hashValue = hash_string(name, len);
    index = hash_to_index(hashValue);
  } else {
    hashValue = hashValue_arg;
    index = index_arg;
  }

  // Since look-up was done lock-free, we need to check if another
  // thread beat us in the race to insert the symbol.

  oop test = lookup(index, name, len, hashValue); // calls lookup(u1*, int)
  if (test != NULL) {
    // Entry already added
    return test;
  }

  HashtableEntry<oop, mtSymbol>* entry = new_entry(hashValue, string());
  add_entry(index, entry);
  return string();
}

hashtable.hpp

openjdk8\openjdk\hotspot\src\share\vm\utilities\hashtable.hpp

template <class T, MEMFLAGS F> class HashtableEntry : public BasicHashtableEntry<F> {
  friend class VMStructs;
private:
  T               _literal;          // ref to item in table.

public:
  // Literal
  T literal() const                   { return _literal; }
  T* literal_addr()                   { return &_literal; }
  void set_literal(T s)               { _literal = s; }

  HashtableEntry* next() const {
    return (HashtableEntry*)BasicHashtableEntry<F>::next();
  }
  HashtableEntry** next_addr() {
    return (HashtableEntry**)BasicHashtableEntry<F>::next_addr();
  }
};

hashtable.inline.hpp

template <class T, MEMFLAGS F> HashtableEntry<T, F>* Hashtable<T, F>::new_entry(unsigned int hashValue, T obj) {
  HashtableEntry<T, F>* entry;

  entry = (HashtableEntry<T, F>*)BasicHashtable<F>::new_entry(hashValue);
  entry->set_literal(obj);
  return entry;
}

template <MEMFLAGS F> inline void BasicHashtable<F>::add_entry(int index, BasicHashtableEntry<F>* entry) {
  entry->set_next(bucket(index));
  _buckets[index].set_entry(entry);
  ++_number_of_entries;
}