一,cache源码分析
- cache_t源码
//源码338-550行这里只提供核心部分
struct cache_t {
private:
explicit_atomic<uintptr_t> _bucketsAndMaybeMask;
union {
struct {
explicit_atomic<mask_t> _maybeMask;
#if __LP64__
uint16_t _flags;
#endif
uint16_t _occupied;
};
explicit_atomic<preopt_cache_t *> _originalPreoptCache;
};
}
_bucketsAndMaybeMask变量uintptr_t占8字节和isa_t中的bits类似,也是一个指针类型里面存放地址联合体里有一个结构体和一个结构体指针_originalPreoptCache结构体中有三个成员变量_maybeMask,_flags,_occupied。__LP64__指的是Unix和Unix类系统_originalPreoptCache和结构体是互斥的,_originalPreoptCache初始时候的缓存,现在探究类中的缓存,这个变量基本不会用到cache_t提供了公用的方法去获取值,以及根据不同的架构系统去获取mask和buckets的掩码
public:
void incrementOccupied();
void setBucketsAndMask(struct bucket_t *newBuckets, mask_t newMask);
void reallocate(mask_t oldCapacity, mask_t newCapacity, bool freeOld);
unsigned capacity() const;
struct bucket_t *buckets() const;
Class cls() const;
void insert(SEL sel, IMP imp, id receiver);
- 在
cache_t有buckets(),这个类似于class_data_bits_t里面的提供的methods(),都是通过方法获取值。查看bucket_t源码
struct bucket_t {
private:
// IMP-first is better for arm64e ptrauth and no worse for arm64.
// SEL-first is better for armv7* and i386 and x86_64.
#if __arm64__
explicit_atomic<uintptr_t> _imp;
explicit_atomic<SEL> _sel;
#else
explicit_atomic<SEL> _sel;
explicit_atomic<uintptr_t> _imp;
#endif
//其他代码保留
}
- 从源码我们可以看到,我们缓存里面存放的是sel 和 imp。
二,LLDB调试探究
//新建类
@interface NBPerson : NSObject{
double height;
}
-(void)sayHello;
-(void)sayHello1;
-(void)sayHello2;
+(void)sayNB;
@end
@implementation NBPerson
-(void)sayHello{
NSLog(@"hello----");
}
-(void)sayHello1{
NSLog(@"hello----1");
}
-(void)sayHello2{
NSLog(@"hello----2");
}
+(void)sayNB{
NSLog(@"NB----");
}
@end
- 断点运行
//类地址+0x10为cache_t地址
//通过cache_t地址查看cahce_t
- 调试查看cache_t内部结构
(lldb) p/x [NBPerson class]
(Class) $0 = 0x0000000100008188 NBPerson
(lldb) p (cache_t*)(0x0000000100008188 +0x10)
(cache_t *) $1 = 0x0000000100008198
(lldb) p *$1
(cache_t) $2 = {
_bucketsAndMaybeMask = {
std::__1::atomic<unsigned long> = {
Value = 4298515296
}
}
= {
= {
_maybeMask = {
std::__1::atomic<unsigned int> = {
Value = 0
}
}
_flags = 32792
_occupied = 0
}
_originalPreoptCache = {
std::__1::atomic<preopt_cache_t *> = {
Value = 0x0000801800000000
}
}
}
}
(lldb)
- 源码第454行代码我们看到buckets
cache_t中的方法buckets()指向的是一块内存的首地址,也是第一个bucket的地址
- 那么我们接着调试
(lldb) p [nb sayHello]
2021-08-06 16:16:54.002681+0800 KCObjcBuild[52478:817482] hello----
(lldb) p *$1
(cache_t) $3 = {
_bucketsAndMaybeMask = {
std::__1::atomic<unsigned long> = {
Value = 4302714160
}
}
= {
= {
_maybeMask = {
std::__1::atomic<unsigned int> = {
Value = 7
}
}
_flags = 32792
_occupied = 1
}
_originalPreoptCache = {
std::__1::atomic<preopt_cache_t *> = {
Value = 0x0001801800000007
}
}
}
}
(lldb) p $3.buckets()[0].sel()
(SEL) $4 = <no value available>
(lldb) p $3.buckets()[1].sel()
(SEL) $5 = "class"
(lldb) p $3.buckets()[2].sel()
(SEL) $6 = <no value available>
(lldb) p $3.buckets()[3].sel()
(SEL) $7 = <no value available>
(lldb) p $3.buckets()[4].sel()
(SEL) $8 = "sayHello"
(lldb) p $3.buckets()[4].imp(nil,[NBPerson class])
(IMP) $9 = 0x0000000100003e00 (KCObjcBuild`-[NBPerson sayHello] at main.m:33)
(lldb)
- 调用sayHello后,_mayMask和occupied被赋值,这两个变量应该和缓存是有关系
- bucket_t结构提供了sel()和imp(nil,[NBPerson class])方法
- sayhello方法的sel和imp,存在bucket中而
buckets存在cache中
这种方式需要objc源码,而且断点调试有点不够暴力
-
脱离源码咱们也能测试
//这里我们模仿objc源码
typedef uint32_t mask_t;
struct nb_bucket_t {
SEL _sel;
IMP _imp;
};
struct nb_cache_t{
struct nb_bucket_t * _buckets;
mask_t _maybeMask;
uint16_t _flags;
uint16_t _occupied;
};
struct nb_class_data_bits_t{
uintptr_t bits;
};
struct nb_objc_class {
Class ISA;
Class superclass;
struct nb_cache_t cache;
struct nb_class_data_bits_t bits;
};
int main(int argc, const char * argv[]) {
@autoreleasepool {
NBPerson *nb = [NBPerson alloc];
[nb sayHello];
Class nbClass = [NBPerson class];
struct nb_objc_class * nb_class = (__bridge struct nb_objc_class *)(nbClass);
NSLog(@" - %hu - %u",nb_class->cache._occupied,nb_class->cache._maybeMask);
for (int i = 0; i < nb_class->cache._maybeMask; i++) {
struct nb_bucket_t bucket =nb_class->cache._buckets[i];
NSLog(@"%@ - %p",NSStringFromSelector(bucket._sel),bucket._imp);
}
}
return NSApplicationMain(argc, argv);
}
- 运行代码输出结果
//注释 [nb sayHello];输出结果
2021-08-06 17:10:51.921202+0800 对象与isa之间的关系[54912:852133] - 0 - 0
//放开 [nb sayHello];输出结果
2021-08-06 17:14:17.837195+0800 对象与isa之间的关系[55083:855095] hello----
2021-08-06 17:14:17.837264+0800 对象与isa之间的关系[55083:855095] - 1 - 3
2021-08-06 17:14:17.837295+0800 对象与isa之间的关系[55083:855095] (null) - 0x0
2021-08-06 17:14:17.837348+0800 对象与isa之间的关系[55083:855095] sayHello - 0x63e0
2021-08-06 17:14:17.837370+0800 对象与isa之间的关系[55083:855095] (null) - 0x0
- 然后我们加上
nb.name = @"name";
//输出结果
2021-08-06 17:24:54.976660+0800 对象与isa之间的关系[55612:865082] hello----
2021-08-06 17:24:54.976735+0800 对象与isa之间的关系[55612:865082] - 2 - 3
2021-08-06 17:24:54.976793+0800 对象与isa之间的关系[55612:865082] sayHello - 0x1a2e0
2021-08-06 17:24:54.976835+0800 对象与isa之间的关系[55612:865082] setName: - 0x1a360
2021-08-06 17:24:54.976856+0800 对象与isa之间的关系[55612:865082] (null) - 0x0
- 再加上
[nb sayHello1];
[nb sayHello2];
[nb sayHello3];
[nb sayHello4];
[nb sayHello5];
//输出结果
2021-08-06 17:26:16.365782+0800 对象与isa之间的关系[55671:866374] hello----
2021-08-06 17:26:16.365848+0800 对象与isa之间的关系[55671:866374] hello----1
2021-08-06 17:26:16.365875+0800 对象与isa之间的关系[55671:866374] hello----2
2021-08-06 17:26:16.365894+0800 对象与isa之间的关系[55671:866374] hello----3
2021-08-06 17:26:16.365911+0800 对象与isa之间的关系[55671:866374] hello----4
2021-08-06 17:26:16.365926+0800 对象与isa之间的关系[55671:866374] hello----5
2021-08-06 17:26:16.365943+0800 对象与isa之间的关系[55671:866374] - 5 - 7
2021-08-06 17:26:16.365989+0800 对象与isa之间的关系[55671:866374] sayHello2 - 0x1a308
2021-08-06 17:26:16.366011+0800 对象与isa之间的关系[55671:866374] sayHello3 - 0x1a338
2021-08-06 17:26:16.366029+0800 对象与isa之间的关系[55671:866374] (null) - 0x0
2021-08-06 17:26:16.366062+0800 对象与isa之间的关系[55671:866374] sayHello4 - 0x1a368
2021-08-06 17:26:16.366172+0800 对象与isa之间的关系[55671:866374] (null) - 0x0
2021-08-06 17:26:16.366274+0800 对象与isa之间的关系[55671:866374] sayHello1 - 0x1a0d8
2021-08-06 17:26:16.366338+0800 对象与isa之间的关系[55671:866374] sayHello5 - 0x1a398
- 通过调试,我们知道了调用方法会有缓存 从结果中我们会发现一些奇怪的地方
- 输出的顺序不对
- 输出的方法有一些不在里面
继续源码分析
//insert为插入事件⌚️
void cache_t::insert(SEL sel, IMP imp, id receiver)
{
......
// Use the cache as-is if until we exceed our expected fill ratio.
mask_t newOccupied = occupied() + 1;
unsigned oldCapacity = capacity(), capacity = oldCapacity;
if (slowpath(isConstantEmptyCache())) {
// Cache is read-only. Replace it.
if (!capacity) capacity = INIT_CACHE_SIZE;
/// 1. 这里先判断是否是第一次执行,如果是就去开辟内存。
reallocate(oldCapacity, capacity, /* freeOld */false);//这里false代表新开辟内存
}
else if (fastpath(newOccupied + CACHE_END_MARKER <= cache_fill_ratio(capacity))) {
/// 2. 这里表示当前的buckets 的mask 数量大于 occupied,就不用开辟新的内存空间
}
#if CACHE_ALLOW_FULL_UTILIZATION
else if (capacity <= FULL_UTILIZATION_CACHE_SIZE && newOccupied + CACHE_END_MARKER <= capacity) {
// Allow 100% cache utilization for small buckets. Use it as-is.
}
#endif
else {
/// 3. 这里表示要插入的的bucket 没有了空间,需要扩容并且重新开辟新的内存,并且释放掉之前旧的内存空间。
/// 比如,当前有2个缓存,然后当要插入第 3 个缓存的时候,newOccupied = 3,newOccupied + CACHE_END_MARKER <= cache_fill_ratio(capacity) = 3 不成了,所以就会扩容。
/// 至于为什么要释放旧的内存空间,大概是为了优化内存,长时间没用的缓存就释放掉,等下一次调用的时候在重新缓存。
capacity = capacity ? capacity * 2 : INIT_CACHE_SIZE;
if (capacity > MAX_CACHE_SIZE) {
capacity = MAX_CACHE_SIZE; ///这里也限制了,最多可以有 2^16 个缓存
}
reallocate(oldCapacity, capacity, true);//这里true代表已有内存需要扩容
}
bucket_t *b = buckets();
mask_t m = capacity - 1;
mask_t begin = cache_hash(sel, m); /// 采用哈希算法获取当前的bucket 需要存放的位置,
mask_t i = begin;
/// 4. 这里就是插入 bucket 到指定的缓存位置。
do {
if (fastpath(b[i].sel() == 0)) {
/// 如果当前的位置不存在数据,或者为一片空的内存空间,那么就插入这个bucket。并且让 _occupied 自增1。
incrementOccupied();
b[i].set<Atomic, Encoded>(b, sel, imp, cls());
return;
}
if (b[i].sel() == sel) {
/// 如果当前 bucket 里面的sel 和 将要存入的一样,则跳过。
return;
}
/// 这里是循环的终止条件,一直寻找下一个 i 直到找到了最初的位置,即处理hash 冲突
} while (fastpath((i = cache_next(i, m)) != begin));
bad_cache(receiver, (SEL)sel);
#endif // !DEBUG_TASK_THREADS
}
- 然后开辟内存的方法
void cache_t::reallocate(mask_t oldCapacity, mask_t newCapacity, bool freeOld)
{
bucket_t *oldBuckets = buckets();
bucket_t *newBuckets = allocateBuckets(newCapacity);
// Cache's old contents are not propagated.
// This is thought to save cache memory at the cost of extra cache fills.
// fixme re-measure this
ASSERT(newCapacity > 0);
ASSERT((uintptr_t)(mask_t)(newCapacity-1) == newCapacity-1);
setBucketsAndMask(newBuckets, newCapacity - 1);
if (freeOld) {//释放之前内存
collect_free(oldBuckets, oldCapacity);
}
}
.....
bucket_t *cache_t::allocateBuckets(mask_t newCapacity)
{
// Allocate one extra bucket to mark the end of the list.
// This can't overflow mask_t because newCapacity is a power of 2.
bucket_t *newBuckets = (bucket_t *)calloc(bytesForCapacity(newCapacity), 1);
// 这里开辟了一段连续的空间,用于存放 ‘newCapacity’ 个 ‘bucket_t’ 结构体。
......
void cache_t::setBucketsAndMask(struct bucket_t *newBuckets, mask_t newMask)
{
// ensure other threads see new buckets before new mask
_maybeMask.store(newMask, memory_order_release);
/// 通过这个方法,就重新设置里buckets * 和 maybeMask 这两个数据了
......
///通过这个方法,我们知道开辟的内存为大小为 newCapacity * sizeof(bucket) 的大小(即 16 的倍数),所以获取指定的 bucket_t 都可以通过内存平移的方式去寻找,因为这里开辟的内存是连续的,并且存放 bucket_t 数据。
代码的大致逻辑是
- 当前有没有缓存
buckets如果没有,那么就调用reallocate -> allocateBuckets去开辟新的缓存内存空间; - 如果有缓存空间并且空间的3/4足够插入当前要缓存的
bucket那么就直接通过hash算法寻找对应的缓存下标去缓存对应的数据; - 如果缓存空间的3/4不足一插入下一个
bucket,那么就开辟新的扩容空间并且释放掉之前的空间,把当前的数据插入到指新的空间里面。
然后分析一波运行结果
-
_mask是当前缓存可以存放的缓存个数的大小,其值为常量capacity - 1 -
_occupied是当前缓存的具体个数 -
第一次运行结果 _occupid和_mask 1,3 //1个缓存,缓存空间3
-
第二次运行结果 _occupid和_mask 2,3 //2个缓存,缓存空间3
-
第三次运行结果 _occupid和_mask 5,7 //5个缓存,缓存空间7
-
前两次结果容易理解,第三次为什么让人不解呢? 第三次是调用了7个方法,当调用到第三个方法的时候(
3+1)>(3+1)*(3/4)(源码逻辑第三条)
这时会做两件事
- 扩容:就要扩容
(3+1)*2-1 = 7 - 清除:清除之前的两个缓存
清除缓存源码
void cache_t::collect_free(bucket_t *data, mask_t capacity)
{
#if CONFIG_USE_CACHE_LOCK
cacheUpdateLock.assertLocked();
#else
runtimeLock.assertLocked();
#endif
if (PrintCaches) recordDeadCache(capacity);
_garbage_make_room ();
garbage_byte_size += cache_t::bytesForCapacity(capacity);
garbage_refs[garbage_count++] = data;
cache_t::collectNolock(false);
}
- bucket下标计算
static inline mask_t cache_hash(SEL sel, mask_t mask)
{
uintptr_t value = (uintptr_t)sel;
#if CONFIG_USE_PREOPT_CACHES
value ^= value >> 7;
#endif
return (mask_t)(value & mask);
}
#if CACHE_END_MARKER
static inline mask_t cache_next(mask_t i, mask_t mask) {
return (i+1) & mask;
}
#elif __arm64__
static inline mask_t cache_next(mask_t i, mask_t mask) {
return i ? i-1 : mask;
}
cache_hash主要是生成hash下标,cache_next主要是解决hash冲突
二,imp编码解码
bucket中的的imp地址,存储的是经过编码以后强转成uintptr_t类型数据,解码是会还原成原来的imp
- 编码源码
#if __arm64__
template<Atomicity atomicity, IMPEncoding impEncoding>
void bucket_t::set(bucket_t *base, SEL newSel, IMP newImp, Class cls)
{
ASSERT(_sel.load(memory_order_relaxed) == 0 ||
_sel.load(memory_order_relaxed) == newSel);
static_assert(offsetof(bucket_t,_imp) == 0 &&
offsetof(bucket_t,_sel) == sizeof(void *),
"bucket_t layout doesn't match arm64 bucket_t::set()");
uintptr_t encodedImp = (impEncoding == Encoded
? encodeImp(base, newImp, newSel, cls)
: (uintptr_t)newImp);
// LDP/STP guarantees that all observers get
// either imp/sel or newImp/newSel
stp(encodedImp, (uintptr_t)newSel, this);
}
#else
template<Atomicity atomicity, IMPEncoding impEncoding>
void bucket_t::set(bucket_t *base, SEL newSel, IMP newImp, Class cls)
{
ASSERT(_sel.load(memory_order_relaxed) == 0 ||
_sel.load(memory_order_relaxed) == newSel);
// objc_msgSend uses sel and imp with no locks.
// It is safe for objc_msgSend to see new imp but NULL sel
// (It will get a cache miss but not dispatch to the wrong place.)
// It is unsafe for objc_msgSend to see old imp and new sel.
// Therefore we write new imp, wait a lot, then write new sel.
//原有的imp进行编码(和class进行异或运算)转成 uintptr_t 类型数据
uintptr_t newIMP = (impEncoding == Encoded
? encodeImp(base, newImp, newSel, cls)
: (uintptr_t)newImp);
if (atomicity == Atomic) {
_imp.store(newIMP, memory_order_relaxed);
if (_sel.load(memory_order_relaxed) != newSel) {
#ifdef __arm__
mega_barrier();
_sel.store(newSel, memory_order_relaxed);
#elif __x86_64__ || __i386__
_sel.store(newSel, memory_order_release);
#else
#error Don't know how to do bucket_t::set on this architecture.
#endif
}
} else {
_imp.store(newIMP, memory_order_relaxed);
_sel.store(newSel, memory_order_relaxed);
}
}
#endif
- 解码
inline IMP imp(UNUSED_WITHOUT_PTRAUTH bucket_t *base, Class cls) const {
uintptr_t imp = _imp.load(memory_order_relaxed);
if (!imp) return nil;
#if CACHE_IMP_ENCODING == CACHE_IMP_ENCODING_PTRAUTH
SEL sel = _sel.load(memory_order_relaxed);
return (IMP)
ptrauth_auth_and_resign((const void *)imp,
ptrauth_key_process_dependent_code,
modifierForSEL(base, sel, cls),
ptrauth_key_function_pointer, 0);
#elif CACHE_IMP_ENCODING == CACHE_IMP_ENCODING_ISA_XOR
return (IMP)(imp ^ (uintptr_t)cls);
#elif CACHE_IMP_ENCODING == CACHE_IMP_ENCODING_NONE
return (IMP)imp;
#else
#error Unknown method cache IMP encoding.
#endif
}
异或运算解析
- 异或运算:参与运算的两个值,如果两个相应位相同,则结果为
0,否则为1 异是同否
int a = 3; int b = 12; int c = 15;
NSLog(@"%d-%d-%d",a,b,c);
//调试
(lldb) p a ^ b
(int) $0 = 15
(lldb) p c^ b
(int) $1 = 3
(lldb)
二进制解析
a = 3 0000 0011
b = 12 0000 1100
a ^ b 0000 0011 ^ 0000 1100 = 0000 1111 = 15
c ^ b 0000 1111 ^ 0000 1100 = 0000 0011 = 3