jvm开发笔记5 - 虚拟机内存管理

一、 前言

     ajvm是笔者正在开发中的一个java虚拟机， 想通过编写这个jvm帮助程序员了解jvm的具体实现细节， 它是国内第一个开源的java虚拟机项目：https://github.com/cloudsec/ajvm， 同时笔者把它的开发笔记也分享到了ata上。 在前面4篇笔记中， 已经实现了class文件加载器， 反汇编器，jvm的crash信息处理， 同时它已经能运行简单的java代码了。 在今天的这篇笔记中， 将开始分享ajvm的内存管理模块是如何编写的。

二、内存分配

   看下面一段java代码：

public class test6 {
        public static void main(String args[]) {
                int[] data, data1;
                int i;
                int num = 0;

                data = new int[2];
                for (i = 0; i < 2; i++) {
                        data[i] = i;
                }

                data1 = new int[3];
        }
}

   首先用javac编译下， 然后用ajvm的反汇编器查看bytecode：

$./wvm -d test/test6.class
Diassember bytecode:

    ()V
stack: 1    local: 1

    0: aload_0
    1: invokespecial #1
    4: return

main    ([Ljava/lang/String;)V
stack: 3    local: 5

    0: iconst_0
    1: istore 4
    3: iconst_2
    4: newarray 10
    6: astore_1
    7: iconst_0
    8: istore_3
    9: iload_3
   10: iconst_2
   11: if_icmpge 13
   14: aload_1
   15: iload_3
   16: iload_3
   17: iastore
   18: iinc 3 1
   21: goto 0xfffffff4
   24: iconst_3
   25: newarray 10
   27: astore_2
   28: return

   源码中data = new int[2];对应的汇编指令为：

    4: newarray 10

    根据jvm虚拟机规范的描述， newarray指令的作用是， 从操作数堆栈用取出data数组的元素个数，然后根据newarray后面的type进行计算要申请的内存大小， type的值在虚拟机规范中如下：

#define T_BOOLEAN                               4
#define T_CHAR                                  5
#define T_FLOAT                                 6
#define T_DOUBLE                                7
#define T_BYTE                                  8
#define T_SHORT                                 9
#define T_INT                                   10
#define T_LONG                                  11

    所以10代表这个int类型的数组， 接下来就要给data这个数组从heap中分配内存了。

void *alloc_newarray_memroy(u1 atype, int count)
{
        void *addr = NULL;

        switch (atype) {
        case T_BOOLEAN:
        case T_CHAR:
        case T_BYTE:
                addr = (void *)slab_alloc(jvm_thread_mem, count * sizeof(char));
                break;
        case T_SHORT:
                addr = (void *)slab_alloc(jvm_thread_mem, count * sizeof(short));
                break;
        case T_INT:
        case T_FLOAT:
                addr = (void *)slab_alloc(jvm_thread_mem, count * sizeof(int));
                break;
        case T_LONG:
        case T_DOUBLE:
                addr = (void *)slab_alloc(jvm_thread_mem, count * sizeof(long long));
                break;
        default:
                error("bad atype value.n");
                return NULL;
        }

        return addr;
}

   ajvm的内存堆用的是slab算法， slab的内存结构如下：

   -------     ------     ------    ------
   |cache|-->  |slab| --> |slab| -->|slab|
   -------     ------     ------    ------
   |cache|
   -----
   |cache| ...
   -----      ------     ------    ------
   |cache|--> |slab| --> |slab| -->|slab|
   -----      ------     -----     ------
   |cache| ...
   -------    
   |cache|
   -------
   |cache|-->|slab|-->|slab| -->|slab|
   -------   ------   ------    ------

    源码中的slab.c是它完整的实现， 不熟悉slab的同学请自行google。

三、垃圾回收

    gc是java程序员普遍关心的问题， 当内存不够时， 将会触发jvm的垃圾回收机制。
    ajvm使用最原始的引用计数法， 需要建立一个新的数据结构：

typedef struct jvm_object {
        int ref_count;
        CLASS *class;
        void *addr;
        int size;
        struct list_head list;
}JVM_OBJECT;

    当数组申请完内存后， 将会建立一个新的JVM_OBJECT与其对应， ref_count被初始化为0, addr指向数组的首地址， size表示数组的大小， JVM_OBJECT将会被加入到jvm_obj_list_head链表中， 在这将来的垃圾回收时将会用到。

int jvm_interp_newarray(u2 len, char *symbol, void *base)
{
    ...
        addr = (void *)alloc_newarray_memroy(atype, count);
        if (!addr) {
                error("slab alloc failed.n");
                return -1;
        }
        printf("addr: 0x%xn", addr);

        new_obj = create_new_obj(addr, count);
        if (!new_obj) {
                error("create new obj failed.n");
                return -1;
        }
    ...
}

   当数组被引用时， 我们跟数组的地址在JVM_OBJECT链表中找到它， 并且把ref_count加1, 表示这个数组在被引用。 比如上面的：

      17: iastore

   这条指令就会对data数组进行引用， 我们只要在iastore的解释代码里， 对data对应的ref_count加1即可：

int jvm_interp_iastore(u2 len, char *symbol, void *base)
{
        int *addr, index, value;

        if (jvm_arg->disass_class) {
                printf("%sn", symbol);
                return 0;
        }

        pop_operand_stack(int, value)
        pop_operand_stack(int, index)
        pop_operand_stack(int, addr)

        printf("addr: 0x%xtindex: %dt%dn", addr, index, value);
        *(int *)(addr + index) = value;

        if (inc_obj_ref(addr, (&jvm_obj_list_head)) == -1) {
                jvm_error(VM_ERROR_INTERP, "inc jvm obj ref failed.n");
                return -1;
        }

        jvm_pc.pc += len;
        return 0;
}

       对于数组data1, 同样进行了内存分配， 但是始终没有被引用到， 所以data1将会是gc回收时要释放的对象。

 

void start_gc(struct list_head *list_head)
{
        JVM_OBJECT *s;
        struct list_head *p, *q;

        list_for_each_safe(p, q, list_head) {
                s = list_entry(p, JVM_OBJECT, list);
                if (s && s->ref_count == 0) {
                        printf("free addr: 0x%xtsize: %dtref_count: %dn",
                                s->addr, s->size, s->ref_count);
                        list_del(p);
                        free_jvm_obj(s);
                }
        }
}

      这是ajvm最简单的gc算法了， 后续将会对其进行优化。

四、演示执行

    下面是ajvm对上述java代码的解释和执行过程：

$./wvm -c test test6
jvm pc init at: 0x630510

main    ([Ljava/lang/String;)V
stack: 3    local : 5
code:
0x3 0x36 0x4 0x5 0xbc 0xa 0x4c 0x3 0x3e 0x1d 0x5 0xa2 0x0 0xd 0x2b 0x1d
0x1d 0x4f 0x84 0x3 0x1 0xa7 0xff 0xf4 0x6 0xbc 0xa 0x4d 0xb1
#local at: 0x630540    #stack at: 0x630554

[    1] iconst_0    pc: 0x630510 -> 0x3
#local: 0x0 0x0 0x0 0x0 0x0     #stack: 0x0 0x0 0x0
#local: 0x0 0x0 0x0 0x0 0x0     #stack: 0x0 0x0 0x0
[    2] istore    pc: 0x630511 -> 0x36
#local: 0x0 0x0 0x0 0x0 0x0     #stack: 0x0 0x0 0x0
#local: 0x0 0x0 0x0 0x0 0x0     #stack: 0x0 0x0 0x0
#local: 0x0 0x0 0x0 0x0 0x0     #stack: 0x0 0x0 0x0
#local: 0x0 0x0 0x0 0x0 0x0     #stack: 0x0 0x0 0x0
[    3] iconst_2    pc: 0x630513 -> 0x5
#local: 0x0 0x0 0x0 0x0 0x0     #stack: 0x0 0x0 0x0
#local: 0x0 0x0 0x0 0x0 0x0     #stack: 0x2 0x0 0x0
[    4] newarray    pc: 0x630514 -> 0xbc
#local: 0x0 0x0 0x0 0x0 0x0     #stack: 0x2 0x0 0x0
#local: 0x0 0x0 0x0 0x0 0x0     #stack: 0x0 0x0 0x0
#local: 0x0 0x0 0x0 0x0 0x0     #stack: 0x0 0x0 0x0
#local: 0x0 0x0 0x0 0x0 0x0     #stack: 0x627c20 0x0 0x0
[    5] astore_1    pc: 0x630516 -> 0x4c
#local: 0x0 0x0 0x0 0x0 0x0     #stack: 0x627c20 0x0 0x0
#local: 0x0 0x0 0x0 0x0 0x0     #stack: 0x0 0x0 0x0
#local: 0x0 0x0 0x0 0x0 0x0     #stack: 0x0 0x0 0x0
#local: 0x0 0x627c20 0x0 0x0 0x0     #stack: 0x0 0x0 0x0
[    6] iconst_0    pc: 0x630517 -> 0x3
#local: 0x0 0x627c20 0x0 0x0 0x0     #stack: 0x0 0x0 0x0
#local: 0x0 0x627c20 0x0 0x0 0x0     #stack: 0x0 0x0 0x0
[    7] istore_3    pc: 0x630518 -> 0x3e
#local: 0x0 0x627c20 0x0 0x0 0x0     #stack: 0x0 0x0 0x0
#local: 0x0 0x627c20 0x0 0x0 0x0     #stack: 0x0 0x0 0x0
#local: 0x0 0x627c20 0x0 0x0 0x0     #stack: 0x0 0x0 0x0
#local: 0x0 0x627c20 0x0 0x0 0x0     #stack: 0x0 0x0 0x0
[    8] iload_3    pc: 0x630519 -> 0x1d
#local: 0x0 0x627c20 0x0 0x0 0x0     #stack: 0x0 0x0 0x0
#local: 0x0 0x627c20 0x0 0x0 0x0     #stack: 0x0 0x0 0x0
#local: 0x0 0x627c20 0x0 0x0 0x0     #stack: 0x0 0x0 0x0
#local: 0x0 0x627c20 0x0 0x0 0x0     #stack: 0x0 0x0 0x0
[    9] iconst_2    pc: 0x63051a -> 0x5
#local: 0x0 0x627c20 0x0 0x0 0x0     #stack: 0x0 0x0 0x0
#local: 0x0 0x627c20 0x0 0x0 0x0     #stack: 0x0 0x2 0x0
[   10] if_icmpge    pc: 0x63051b -> 0xa2
#local: 0x0 0x627c20 0x0 0x0 0x0     #stack: 0x0 0x2 0x0
#local: 0x0 0x627c20 0x0 0x0 0x0     #stack: 0x0 0x0 0x0
#local: 0x0 0x627c20 0x0 0x0 0x0     #stack: 0x0 0x0 0x0
#local: 0x0 0x627c20 0x0 0x0 0x0     #stack: 0x0 0x0 0x0
[   11] aload_1    pc: 0x63051e -> 0x2b
#local: 0x0 0x627c20 0x0 0x0 0x0     #stack: 0x0 0x0 0x0
#local: 0x0 0x627c20 0x0 0x0 0x0     #stack: 0x0 0x0 0x0
#local: 0x0 0x627c20 0x0 0x0 0x0     #stack: 0x0 0x0 0x0
#local: 0x0 0x627c20 0x0 0x0 0x0     #stack: 0x627c20 0x0 0x0
[   12] iload_3    pc: 0x63051f -> 0x1d
#local: 0x0 0x627c20 0x0 0x0 0x0     #stack: 0x627c20 0x0 0x0
#local: 0x0 0x627c20 0x0 0x0 0x0     #stack: 0x627c20 0x0 0x0
#local: 0x0 0x627c20 0x0 0x0 0x0     #stack: 0x627c20 0x0 0x0
#local: 0x0 0x627c20 0x0 0x0 0x0     #stack: 0x627c20 0x0 0x0
[   13] iload_3    pc: 0x630520 -> 0x1d
#local: 0x0 0x627c20 0x0 0x0 0x0     #stack: 0x627c20 0x0 0x0
#local: 0x0 0x627c20 0x0 0x0 0x0     #stack: 0x627c20 0x0 0x0
#local: 0x0 0x627c20 0x0 0x0 0x0     #stack: 0x627c20 0x0 0x0
#local: 0x0 0x627c20 0x0 0x0 0x0     #stack: 0x627c20 0x0 0x0
[   14] iastore    pc: 0x630521 -> 0x4f
#local: 0x0 0x627c20 0x0 0x0 0x0     #stack: 0x627c20 0x0 0x0
#local: 0x0 0x627c20 0x0 0x0 0x0     #stack: 0x627c20 0x0 0x0
#local: 0x0 0x627c20 0x0 0x0 0x0     #stack: 0x627c20 0x0 0x0
#local: 0x0 0x627c20 0x0 0x0 0x0     #stack: 0x627c20 0x0 0x0
#local: 0x0 0x627c20 0x0 0x0 0x0     #stack: 0x627c20 0x0 0x0
#local: 0x0 0x627c20 0x0 0x0 0x0     #stack: 0x0 0x0 0x0
[   15] iinc    pc: 0x630522 -> 0x84
#local: 0x0 0x627c20 0x0 0x0 0x0     #stack: 0x0 0x0 0x0
#local: 0x0 0x627c20 0x0 0x0 0x0     #stack: 0x0 0x0 0x0
#local: 0x0 0x627c20 0x0 0x0 0x0     #stack: 0x0 0x0 0x0
#local: 0x0 0x627c20 0x0 0x1 0x0     #stack: 0x0 0x0 0x0
[   16] goto    pc: 0x630525 -> 0xa7
[   17] iload_3    pc: 0x630519 -> 0x1d
#local: 0x0 0x627c20 0x0 0x1 0x0     #stack: 0x0 0x0 0x0
#local: 0x0 0x627c20 0x0 0x1 0x0     #stack: 0x0 0x0 0x0
#local: 0x0 0x627c20 0x0 0x1 0x0     #stack: 0x0 0x0 0x0
#local: 0x0 0x627c20 0x0 0x1 0x0     #stack: 0x1 0x0 0x0
[   18] iconst_2    pc: 0x63051a -> 0x5
#local: 0x0 0x627c20 0x0 0x1 0x0     #stack: 0x1 0x0 0x0
#local: 0x0 0x627c20 0x0 0x1 0x0     #stack: 0x1 0x2 0x0
[   19] if_icmpge    pc: 0x63051b -> 0xa2
#local: 0x0 0x627c20 0x0 0x1 0x0     #stack: 0x1 0x2 0x0
#local: 0x0 0x627c20 0x0 0x1 0x0     #stack: 0x1 0x0 0x0
#local: 0x0 0x627c20 0x0 0x1 0x0     #stack: 0x1 0x0 0x0
#local: 0x0 0x627c20 0x0 0x1 0x0     #stack: 0x0 0x0 0x0
[   20] aload_1    pc: 0x63051e -> 0x2b
#local: 0x0 0x627c20 0x0 0x1 0x0     #stack: 0x0 0x0 0x0
#local: 0x0 0x627c20 0x0 0x1 0x0     #stack: 0x0 0x0 0x0
#local: 0x0 0x627c20 0x0 0x1 0x0     #stack: 0x0 0x0 0x0
#local: 0x0 0x627c20 0x0 0x1 0x0     #stack: 0x627c20 0x0 0x0
[   21] iload_3    pc: 0x63051f -> 0x1d
#local: 0x0 0x627c20 0x0 0x1 0x0     #stack: 0x627c20 0x0 0x0
#local: 0x0 0x627c20 0x0 0x1 0x0     #stack: 0x627c20 0x0 0x0
#local: 0x0 0x627c20 0x0 0x1 0x0     #stack: 0x627c20 0x0 0x0
#local: 0x0 0x627c20 0x0 0x1 0x0     #stack: 0x627c20 0x1 0x0
[   22] iload_3    pc: 0x630520 -> 0x1d
#local: 0x0 0x627c20 0x0 0x1 0x0     #stack: 0x627c20 0x1 0x0
#local: 0x0 0x627c20 0x0 0x1 0x0     #stack: 0x627c20 0x1 0x0
#local: 0x0 0x627c20 0x0 0x1 0x0     #stack: 0x627c20 0x1 0x0
#local: 0x0 0x627c20 0x0 0x1 0x0     #stack: 0x627c20 0x1 0x1
[   23] iastore    pc: 0x630521 -> 0x4f
#local: 0x0 0x627c20 0x0 0x1 0x0     #stack: 0x627c20 0x1 0x1
#local: 0x0 0x627c20 0x0 0x1 0x0     #stack: 0x627c20 0x1 0x0
#local: 0x0 0x627c20 0x0 0x1 0x0     #stack: 0x627c20 0x1 0x0
#local: 0x0 0x627c20 0x0 0x1 0x0     #stack: 0x627c20 0x0 0x0
#local: 0x0 0x627c20 0x0 0x1 0x0     #stack: 0x627c20 0x0 0x0
#local: 0x0 0x627c20 0x0 0x1 0x0     #stack: 0x0 0x0 0x0
[   24] iinc    pc: 0x630522 -> 0x84
#local: 0x0 0x627c20 0x0 0x1 0x0     #stack: 0x0 0x0 0x0
#local: 0x0 0x627c20 0x0 0x1 0x0     #stack: 0x0 0x0 0x0
#local: 0x0 0x627c20 0x0 0x1 0x0     #stack: 0x0 0x0 0x0
#local: 0x0 0x627c20 0x0 0x2 0x0     #stack: 0x0 0x0 0x0
[   25] goto    pc: 0x630525 -> 0xa7
[   26] iload_3    pc: 0x630519 -> 0x1d
#local: 0x0 0x627c20 0x0 0x2 0x0     #stack: 0x0 0x0 0x0
#local: 0x0 0x627c20 0x0 0x2 0x0     #stack: 0x0 0x0 0x0
#local: 0x0 0x627c20 0x0 0x2 0x0     #stack: 0x0 0x0 0x0
#local: 0x0 0x627c20 0x0 0x2 0x0     #stack: 0x2 0x0 0x0
[   27] iconst_2    pc: 0x63051a -> 0x5
#local: 0x0 0x627c20 0x0 0x2 0x0     #stack: 0x2 0x0 0x0
#local: 0x0 0x627c20 0x0 0x2 0x0     #stack: 0x2 0x2 0x0
[   28] if_icmpge    pc: 0x63051b -> 0xa2
#local: 0x0 0x627c20 0x0 0x2 0x0     #stack: 0x2 0x2 0x0
#local: 0x0 0x627c20 0x0 0x2 0x0     #stack: 0x2 0x0 0x0
#local: 0x0 0x627c20 0x0 0x2 0x0     #stack: 0x2 0x0 0x0
#local: 0x0 0x627c20 0x0 0x2 0x0     #stack: 0x0 0x0 0x0
[   29] iconst_3    pc: 0x630528 -> 0x6
#local: 0x0 0x627c20 0x0 0x2 0x0     #stack: 0x0 0x0 0x0
#local: 0x0 0x627c20 0x0 0x2 0x0     #stack: 0x3 0x0 0x0
[   30] newarray    pc: 0x630529 -> 0xbc
#local: 0x0 0x627c20 0x0 0x2 0x0     #stack: 0x3 0x0 0x0
#local: 0x0 0x627c20 0x0 0x2 0x0     #stack: 0x0 0x0 0x0
#local: 0x0 0x627c20 0x0 0x2 0x0     #stack: 0x0 0x0 0x0
#local: 0x0 0x627c20 0x0 0x2 0x0     #stack: 0x627c80 0x0 0x0
[   31] astore_2    pc: 0x63052b -> 0x4d
#local: 0x0 0x627c20 0x0 0x2 0x0     #stack: 0x627c80 0x0 0x0
#local: 0x0 0x627c20 0x0 0x2 0x0     #stack: 0x0 0x0 0x0
#local: 0x0 0x627c20 0x0 0x2 0x0     #stack: 0x0 0x0 0x0
#local: 0x0 0x627c20 0x627c80 0x2 0x0     #stack: 0x0 0x0 0x0
[   32] return    pc: 0x63052c -> 0xb1
#local: 0x0 0x627c20 0x627c80 0x2 0x0     #stack: 0x0 0x0 0x0
jvm stack depth is zero.
interpret bytecode done.