慢速查找流程分析.jpg

1、objc_msgSend满流程查找切入点

1.1在经过objc_msgSend流程分析发现，
开启缓存查找流程CacheLookup 主要是找imp或者执行objc_msgSend_uncached
会传入如下参数

// calls imp or objc_msgSend_uncached
CacheLookup NORMAL, _objc_msgSend, __objc_msgSend_uncached

CacheLookup 具体实现，截取部分代码，和部分对应的流程图，详细可看这里

macro CacheLookup Mode, Function, MissLabelDynamic, MissLabelConstant
...代码省略...

1:  ldp p17, p9, [x13], #-BUCKET_SIZE   //     {imp, sel} = *bucket--
    cmp p9, p1              //     if (sel != _cmd) {
    b.ne    3f              //         scan more
                        //     } else {
2:  CacheHit \Mode              // hit:    call or return imp
                        //     }
3:  cbz p9, \MissLabelDynamic       //     if (sel == 0) goto Miss;
    cmp p13, p10            // } while (bucket >= buckets)
    b.hs    1b

...代码省略...

最后一个元素查找完 if (sel == 0) goto Miss.png

执行cbz p9, \MissLabelDynamic，判断if (sel == 0) goto Miss，直接返回MissLabelDynamic，其对应的传入参数：__objc_msgSend_uncached汇编函数

接下来在objc-msg-arm64.s文件中查找__objc_msgSend_uncached的汇编实现，其中的核心是MethodTableLookup（即查询方法列表），其源码如下：

    STATIC_ENTRY __objc_msgLookup_uncached
    UNWIND __objc_msgLookup_uncached, FrameWithNoSaves

    // THIS IS NOT A CALLABLE C FUNCTION
    // Out-of-band p15 is the class to search
    
    MethodTableLookup
    ret

    END_ENTRY __objc_msgLookup_uncached

继续查看MethodTableLookup汇编实现

.macro MethodTableLookup
    
    SAVE_REGS MSGSEND

    // lookUpImpOrForward(obj, sel, cls, LOOKUP_INITIALIZE | LOOKUP_RESOLVER)
    // receiver and selector already in x0 and x1
    mov x2, x16
    mov x3, #3
    bl  _lookUpImpOrForward

    // IMP in x0
    mov x17, x0

    RESTORE_REGS MSGSEND

mov x17, x0在汇编里面 x0是第一个寄存器，同样也是返回值的存储位置，所以可以发现bl _lookUpImpOrForward就是我们IMP要查找的地方，_lookUpImpOrForward对应的我们查找lookUpImpOrForward(obj, sel, cls, LOOKUP_INITIALIZE | LOOKUP_RESOLVER)方法；

2、lookUpImpOrForward 实现源码分析

我们使用_lookUpImpOrForward搜索，没有发现汇编的实现代码，继而我们查找lookUpImpOrForward去这个函数，在objc-runtime-new.mm里

extern IMP lookUpImpOrForward(id obj, SEL, Class cls, int behavior);

备注：lookUpImpOrForward我们要的目标就是为了找到找到当前IMP的返回值

NEVER_INLINE
IMP lookUpImpOrForward(id inst, SEL sel, Class cls, int behavior)
{
    const IMP forward_imp = (IMP)_objc_msgForward_impcache;
    IMP imp = nil;  //初始化IMP
    Class curClass;

    runtimeLock.assertUnlocked();

//判断是否进行一些初始化处理    
if (slowpath(!cls->isInitialized())) {
        // The first message sent to a class is often +new or +alloc, or +self
        // which goes through objc_opt_* or various optimized entry points.
        //
        // However, the class isn't realized/initialized yet at this point,
        // and the optimized entry points fall down through objc_msgSend,
        // which ends up here.
        //
        // We really want to avoid caching these, as it can cause IMP caches
        // to be made with a single entry forever.
        //
        // Note that this check is racy as several threads might try to
        // message a given class for the first time at the same time,
        // in which case we might cache anyway.
        behavior |= LOOKUP_NOCACHE;
    }

    // runtimeLock is held during isRealized and isInitialized checking
    // to prevent races against concurrent realization.

    // runtimeLock is held during method search to make
    // method-lookup + cache-fill atomic with respect to method addition.
    // Otherwise, a category could be added but ignored indefinitely because
    // the cache was re-filled with the old value after the cache flush on
    // behalf of the category.

    runtimeLock.lock();

    // We don't want people to be able to craft a binary blob that looks like
    // a class but really isn't one and do a CFI attack.
    //
    // To make these harder we want to make sure this is a class that was
    // either built into the binary or legitimately registered through
    // objc_duplicateClass, objc_initializeClassPair or objc_allocateClassPair.

  ///判断当前的的class是否注册到当前的缓存表里面去
    checkIsKnownClass(cls);
///对当前rw ro进行处理
    cls = realizeAndInitializeIfNeeded_locked(inst, cls, behavior & LOOKUP_INITIALIZE);
    // runtimeLock may have been dropped but is now locked again
    runtimeLock.assertLocked();
    curClass = cls;

    // The code used to lookup the class's cache again right after
    // we take the lock but for the vast majority of the cases
    // evidence shows this is a miss most of the time, hence a time loss.
    //
    // The only codepath calling into this without having performed some
    // kind of cache lookup is class_getInstanceMethod().

    for (unsigned attempts = unreasonableClassCount();;) {
        if (curClass->cache.isConstantOptimizedCache(/* strict */true)) {
#if CONFIG_USE_PREOPT_CACHES
            imp = cache_getImp(curClass, sel);
            if (imp) goto done_unlock;
            curClass = curClass->cache.preoptFallbackClass();
#endif
        } else {
            // curClass method list.
            Method meth = getMethodNoSuper_nolock(curClass, sel);
            if (meth) {
                imp = meth->imp(false);
                goto done;
            }

            if (slowpath((curClass = curClass->getSuperclass()) == nil)) {
                // No implementation found, and method resolver didn't help.
                // Use forwarding.
                imp = forward_imp;
                break;
            }
        }

        // Halt if there is a cycle in the superclass chain.
        if (slowpath(--attempts == 0)) {
            _objc_fatal("Memory corruption in class list.");
        }

        // Superclass cache.
        // 父类 快速 -> 慢速 ->
        imp = cache_getImp(curClass, sel);
        if (slowpath(imp == forward_imp)) {
            // Found a forward:: entry in a superclass.
            // Stop searching, but don't cache yet; call method
            // resolver for this class first.
            break;
        }
        if (fastpath(imp)) {
            // Found the method in a superclass. Cache it in this class.
            goto done;
        }
    }

    // No implementation found. Try method resolver once.

    if (slowpath(behavior & LOOKUP_RESOLVER)) {
        behavior ^= LOOKUP_RESOLVER;
        return resolveMethod_locked(inst, sel, cls, behavior);
    }

 done:
    if (fastpath((behavior & LOOKUP_NOCACHE) == 0)) {
#if CONFIG_USE_PREOPT_CACHES
        while (cls->cache.isConstantOptimizedCache(/* strict */true)) {
            cls = cls->cache.preoptFallbackClass();
        }
#endif
        log_and_fill_cache(cls, imp, sel, inst, curClass);
    }
 done_unlock:
    runtimeLock.unlock();
    if (slowpath((behavior & LOOKUP_NIL) && imp == forward_imp)) {
        return nil;
    }
    return imp;
}

备注：

2.1、slowpath(!cls->isInitialized())判断是否进行一些初始化处理

2.2、checkIsKnownClass(cls)判断当前的的class是否注册到当前的缓存表allocatedClasses里面去了，下面是调用源码

static void
checkIsKnownClass(Class cls)
{
    if (slowpath(!isKnownClass(cls))) {
        _objc_fatal("Attempt to use unknown class %p.", cls);
    }
}

static bool
isKnownClass(Class cls)
{
    if (fastpath(objc::dataSegmentsRanges.contains(cls->data()->witness, (uintptr_t)cls))) {
        return true;
    }
    auto &set = objc::allocatedClasses.get();
    return set.find(cls) != set.end() || dataSegmentsContain(cls);
}

2.3、 cls = realizeAndInitializeIfNeeded_locked(inst, cls, behavior & LOOKUP_INITIALIZE),如果类没有实现，则实现给定的类，如果还没有初始化，则先初始化；
inst:是cls的一个实例或一个子类，如果不知道则为nil；
cls:要初始化或者实现的类；
behavior & LOOKUP_INITIALIZE：YES来初始化类，为NO来跳过初始化

static Class
realizeAndInitializeIfNeeded_locked(id inst, Class cls, bool initialize)
{
    runtimeLock.assertLocked();
    if (slowpath(!cls->isRealized())) {
        cls = realizeClassMaybeSwiftAndLeaveLocked(cls, runtimeLock);
    }

    if (slowpath(initialize && !cls->isInitialized())) {
        cls = initializeAndLeaveLocked(cls, inst, runtimeLock);
    }
    return cls;
}

realizeClassMaybeSwiftAndLeaveLocked(Class cls, mutex_t& lock)
{
    return realizeClassMaybeSwiftMaybeRelock(cls, lock, true);
}

realizeClassMaybeSwiftMaybeRelock(Class cls, mutex_t& lock, bool leaveLocked)
{
    lock.assertLocked();

    if (!cls->isSwiftStable_ButAllowLegacyForNow()) {
   //处理非Swift类的初始化执行如下：
        realizeClassWithoutSwift(cls, nil);
        if (!leaveLocked) lock.unlock();
    } else {
        //处理Swift类的初始化执行如下：
        lock.unlock();
        cls = realizeSwiftClass(cls);
        ASSERT(cls->isRealized());    // callback must have provoked realization
        if (leaveLocked) lock.lock();
    }

    return cls;
}

realizeClassWithoutSwift对类cls进行首次初始化，分配类cls读写数据，不执行任何swift端初始化。最终返回类的实际类结构。

static Class realizeClassWithoutSwift(Class cls, Class previously)
{
    runtimeLock.assertLocked();

    class_rw_t *rw;
    Class supercls;
    Class metacls;

    if (!cls) return nil;
    if (cls->isRealized()) {
        validateAlreadyRealizedClass(cls);
        return cls;
    }
    ASSERT(cls == remapClass(cls));

    // fixme verify class is not in an un-dlopened part of the shared cache?

    auto ro = (const class_ro_t *)cls->data();
    auto isMeta = ro->flags & RO_META;
    if (ro->flags & RO_FUTURE) {
        // 未知的类，提前已经分配了Rw数据。
        rw = cls->data();
        ro = cls->data()->ro();
        ASSERT(!isMeta);
        cls->changeInfo(RW_REALIZED|RW_REALIZING, RW_FUTURE);
    } else {
        // 正常的类。分配可写的类数据。.
        rw = objc::zalloc<class_rw_t>();
        rw->set_ro(ro);
        rw->flags = RW_REALIZED|RW_REALIZING|isMeta;
        cls->setData(rw);
    }
   ....
    代码省略
   ...
    return cls;
}

2.4 for (unsigned attempts = unreasonableClassCount();;)二分查找流程代码查看分析

for (unsigned attempts = unreasonableClassCount();;) {
//判断是否有共享缓存，为什么还要判断在共享缓存里面找一遍呢？我们在执行getMethodNoSuper_nolock之前，前面做了很多ro,rw的的操作，可能在某一时刻，已经将方法写入到缓存里面了，所以做多一次判断
        if (curClass->cache.isConstantOptimizedCache(/* strict */true)) {
#if CONFIG_USE_PREOPT_CACHES
            imp = cache_getImp(curClass, sel);
            if (imp) goto done_unlock;
            curClass = curClass->cache.preoptFallbackClass();
#endif
        } else {
            // curClass method list.
            Method meth = getMethodNoSuper_nolock(curClass, sel);
            if (meth) {
                imp = meth->imp(false);
                goto done;
            }

            if (slowpath((curClass = curClass->getSuperclass()) == nil)) {
                // No implementation found, and method resolver didn't help.
                // Use forwarding.
                imp = forward_imp;
                break;
            }
        }

getMethodNoSuper_nolock

getMethodNoSuper_nolock(Class cls, SEL sel)
{
    runtimeLock.assertLocked();

    ASSERT(cls->isRealized());
    // fixme nil cls? 
    // fixme nil sel?

    auto const methods = cls->data()->methods();
    for (auto mlists = methods.beginLists(),
              end = methods.endLists();
         mlists != end;
         ++mlists)
    {
        // <rdar://problem/46904873> getMethodNoSuper_nolock is the hottest
        // caller of search_method_list, inlining it turns
        // getMethodNoSuper_nolock into a frame-less function and eliminates
        // any store from this codepath.
        method_t *m = search_method_list_inline(*mlists, sel);
        if (m) return m;
    }

    return nil;
}

search_method_list_inline

search_method_list_inline(const method_list_t *mlist, SEL sel)
{
    int methodListIsFixedUp = mlist->isFixedUp();
    int methodListHasExpectedSize = mlist->isExpectedSize();
    
    if (fastpath(methodListIsFixedUp && methodListHasExpectedSize)) {
        return findMethodInSortedMethodList(sel, mlist);
    } else {
        // Linear search of unsorted method list
        if (auto *m = findMethodInUnsortedMethodList(sel, mlist))
            return m;
    }

#if DEBUG
    // sanity-check negative results
    if (mlist->isFixedUp()) {
        for (auto& meth : *mlist) {
            if (meth.name() == sel) {
                _objc_fatal("linear search worked when binary search did not");
            }
        }
    }
#endif

    return nil;
}

findMethodInSortedMethodList

findMethodInSortedMethodList(SEL key, const method_list_t *list)
{
    if (list->isSmallList()) {
        if (CONFIG_SHARED_CACHE_RELATIVE_DIRECT_SELECTORS && objc::inSharedCache((uintptr_t)list)) {
            return findMethodInSortedMethodList(key, list, [](method_t &m) { return m.getSmallNameAsSEL(); });
        } else {
            return findMethodInSortedMethodList(key, list, [](method_t &m) { return m.getSmallNameAsSELRef(); });
        }
    } else {
        return findMethodInSortedMethodList(key, list, [](method_t &m) { return m.big().name; });
    }
}

findMethodInSortedMethodList

findMethodInSortedMethodList(SEL key, const method_list_t *list, const getNameFunc &getName)
{
    ASSERT(list);

    auto first = list->begin();
    auto base = first;
    decltype(first) probe;

    uintptr_t keyValue = (uintptr_t)key;
    uint32_t count;
    
    //分析
    //假定count = 8 ，进行右移1操作
    //1000 - 0100
    //8 - 1 = 7  >>  -> 0011  3 >> 1 == 1
    //0 + 4 = 4
    //5 - 8
    // 6- 7
    for (count = list->count; count != 0; count >>= 1) {
        probe = base + (count >> 1);
        
        uintptr_t probeValue = (uintptr_t)getName(probe);
        
        if (keyValue == probeValue) {
            // `probe` is a match.
            // Rewind looking for the *first* occurrence of this value.
            // This is required for correct category overrides.
            //分类和主类有相同的方法，优先调用分类的方法
            while (probe > first && keyValue == (uintptr_t)getName((probe - 1))) {
                probe--;
            }
            return &*probe;
        }
        
        if (keyValue > probeValue) {
            base = probe + 1;
            count--;
        }
    }
    
    return nil;
}

2.5二分查找流程结束后 获取到imp，之后进行 goto done方法调用，在调用log_and_fill_cache方法进行一个方法缓存填充，也就是说记录一个方法的调用，如果有记录的话，就会来进行方法的缓存填充。这样以来就不用每次都进行二分查找的操作，下次查找时直接走快速查找流程，具体代码如下：

tatic void
log_and_fill_cache(Class cls, IMP imp, SEL sel, id receiver, Class implementer)
{
#if SUPPORT_MESSAGE_LOGGING
    if (slowpath(objcMsgLogEnabled && implementer)) {
        bool cacheIt = logMessageSend(implementer->isMetaClass(), 
                                      cls->nameForLogging(),
                                      implementer->nameForLogging(), 
                                      sel);
        if (!cacheIt) return;
    }
#endif
    cls->cache.insert(sel, imp, receiver);
}

2.6二分查找流程结束后如果没有获取到imp，则会进行父类的方法查找流程(slowpath((curClass = curClass->getSuperclass()) == nil))，最后会进行父类快速查找和慢速度流程，如果最终找不到，系统会进行消息动态决议和消息转发，这个具体后面章节在做分析