分析OC对象方法调用底层的逻辑

---

我们先准备一个main.m文件,内容如下

#import <Foundation/Foundation.h>
int main(int argc, const char * argv[]) {
    @autoreleasepool {
        // insert code here...
        NSObject *objc1 = [[NSObject alloc] init];
        NSLog(@"Hello, World! %@",objc1);
    }
    return 0;
}

使用我们编译器前端clang命令来将main.m 重写成main.cpp,命令如下

$clang -rewrite-objc main.m -o main.cpp

查看转换为cpp的main函数，发现：NSObject 方法的调用，其实就是objc_msgSend方法的调用

image.png

分析objc_msgSend函数

1、当前查看objc_msgSend源码

#if !OBJC_OLD_DISPATCH_PROTOTYPES
#pragma clang diagnostic push
#pragma clang diagnostic ignored "-Wincompatible-library-redeclaration"
OBJC_EXPORT void
objc_msgSend(void /* id self, SEL op, ... */ )
    OBJC_AVAILABLE(10.0, 2.0, 9.0, 1.0, 2.0);

OBJC_EXPORT void
objc_msgSendSuper(void /* struct objc_super *super, SEL op, ... */ )
    OBJC_AVAILABLE(10.0, 2.0, 9.0, 1.0, 2.0);
#pragma clang diagnostic pop
#else

2、其实objc_msgSend实现方式在汇编逻辑里面，我们研究是iOS，所以我们直接看objc-msg-arm64.s的源码实现

    ENTRY _objc_msgSend
    UNWIND _objc_msgSend, NoFrame

    cmp p0, #0          // nil check and tagged pointer check
#if SUPPORT_TAGGED_POINTERS
    b.le    LNilOrTagged        //  (MSB tagged pointer looks negative)
#else
    b.eq    LReturnZero
#endif
    ldr p13, [x0]       // p13 = isa
    GetClassFromIsa_p16 p13     // p16 = class
LGetIsaDone:
    // calls imp or objc_msgSend_uncached
    CacheLookup NORMAL, _objc_msgSend

#if SUPPORT_TAGGED_POINTERS
LNilOrTagged:
    b.eq    LReturnZero     // nil check

    // tagged
    adrp    x10, _objc_debug_taggedpointer_classes@PAGE
    add x10, x10, _objc_debug_taggedpointer_classes@PAGEOFF
    ubfx    x11, x0, #60, #4
    ldr x16, [x10, x11, LSL #3]
    adrp    x10, _OBJC_CLASS_$___NSUnrecognizedTaggedPointer@PAGE
    add x10, x10, _OBJC_CLASS_$___NSUnrecognizedTaggedPointer@PAGEOFF
    cmp x10, x16
    b.ne    LGetIsaDone

    // ext tagged
    adrp    x10, _objc_debug_taggedpointer_ext_classes@PAGE
    add x10, x10, _objc_debug_taggedpointer_ext_classes@PAGEOFF
    ubfx    x11, x0, #52, #8
    ldr x16, [x10, x11, LSL #3]
    b   LGetIsaDone
// SUPPORT_TAGGED_POINTERS
#endif

LReturnZero:
    // x0 is already zero
    mov x1, #0
    movi    d0, #0
    movi    d1, #0
    movi    d2, #0
    movi    d3, #0
    ret

    END_ENTRY _objc_msgSend

这里使用汇编有两个原因
1、执行快
2、因为是直接操作电脑硬件，可以提供不确定参数的实现(即参数列表), 这一点c++不怎么好实现.

3、汇编分析

_objc_msgSend 分析:

• 1、比较p0是否为空,如果为空直接返回nil
• 2、将isa指针赋值给p13
• 3、查看GetClassFromIsa_p16 实现

.macro GetClassFromIsa_p16 /* src */

#if SUPPORT_INDEXED_ISA
    // Indexed isa
    mov p16, $0         // optimistically set dst = src
    tbz p16, #ISA_INDEX_IS_NPI_BIT, 1f  // done if not non-pointer isa
    // isa in p16 is indexed
    adrp    x10, _objc_indexed_classes@PAGE
    add x10, x10, _objc_indexed_classes@PAGEOFF
    ubfx    p16, p16, #ISA_INDEX_SHIFT, #ISA_INDEX_BITS  // extract index
    ldr p16, [x10, p16, UXTP #PTRSHIFT] // load class from array
1:

#elif __LP64__
    // 64-bit packed isa
    and p16, $0, #ISA_MASK

#else
    // 32-bit raw isa
    mov p16, $0

#endif

.endmacro

我们就看__LP64__ 64位系统下 and p16, $0, #ISA_MASK,其实就是将传入的isa指针&出对应的类对象的地址，即p16 = class

• 4、查看CacheLookup NORMAL, _objc_msgSend，此时的第一个参数为NORMAL

.macro CacheLookup
    //
    // Restart protocol:
    //
    //   As soon as we're past the LLookupStart$1 label we may have loaded
    //   an invalid cache pointer or mask.
    //
    //   When task_restartable_ranges_synchronize() is called,
    //   (or when a signal hits us) before we're past LLookupEnd$1,
    //   then our PC will be reset to LLookupRecover$1 which forcefully
    //   jumps to the cache-miss codepath which have the following
    //   requirements:
    //
    //   GETIMP:
    //     The cache-miss is just returning NULL (setting x0 to 0)
    //
    //   NORMAL and LOOKUP:
    //   - x0 contains the receiver
    //   - x1 contains the selector
    //   - x16 contains the isa
    //   - other registers are set as per calling conventions
    //
LLookupStart$1:

    // p1 = SEL, p16 = isa
    ldr p11, [x16, #CACHE]              // p11 = mask|buckets

#if CACHE_MASK_STORAGE == CACHE_MASK_STORAGE_HIGH_16
    and p10, p11, #0x0000ffffffffffff   // p10 = buckets
    and p12, p1, p11, LSR #48       // x12 = _cmd & mask
#elif CACHE_MASK_STORAGE == CACHE_MASK_STORAGE_LOW_4
    and p10, p11, #~0xf         // p10 = buckets
    and p11, p11, #0xf          // p11 = maskShift
    mov p12, #0xffff
    lsr p11, p12, p11               // p11 = mask = 0xffff >> p11
    and p12, p1, p11                // x12 = _cmd & mask
#else
#error Unsupported cache mask storage for ARM64.
#endif


    add p12, p10, p12, LSL #(1+PTRSHIFT)
                     // p12 = buckets + ((_cmd & mask) << (1+PTRSHIFT))

    ldp p17, p9, [x12]      // {imp, sel} = *bucket
1:  cmp p9, p1          // if (bucket->sel != _cmd)
    b.ne    2f          //     scan more
    CacheHit $0         // call or return imp
    
2:  // not hit: p12 = not-hit bucket
    CheckMiss $0            // miss if bucket->sel == 0
    cmp p12, p10        // wrap if bucket == buckets
    b.eq    3f
    ldp p17, p9, [x12, #-BUCKET_SIZE]!  // {imp, sel} = *--bucket
    b   1b          // loop

3:  // wrap: p12 = first bucket, w11 = mask
#if CACHE_MASK_STORAGE == CACHE_MASK_STORAGE_HIGH_16
    add p12, p12, p11, LSR #(48 - (1+PTRSHIFT))
                    // p12 = buckets + (mask << 1+PTRSHIFT)
#elif CACHE_MASK_STORAGE == CACHE_MASK_STORAGE_LOW_4
    add p12, p12, p11, LSL #(1+PTRSHIFT)
                    // p12 = buckets + (mask << 1+PTRSHIFT)
#else
#error Unsupported cache mask storage for ARM64.
#endif

    // Clone scanning loop to miss instead of hang when cache is corrupt.
    // The slow path may detect any corruption and halt later.

    ldp p17, p9, [x12]      // {imp, sel} = *bucket
1:  cmp p9, p1          // if (bucket->sel != _cmd)
    b.ne    2f          //     scan more
    CacheHit $0         // call or return imp
    
2:  // not hit: p12 = not-hit bucket
    CheckMiss $0            // miss if bucket->sel == 0
    cmp p12, p10        // wrap if bucket == buckets
    b.eq    3f
    ldp p17, p9, [x12, #-BUCKET_SIZE]!  // {imp, sel} = *--bucket
    b   1b          // loop

LLookupEnd$1:
LLookupRecover$1:
3:  // double wrap
    JumpMiss $0

.endmacro

前面的大段注释我都保留，方便大家阅读。下面是我的分析代码得出的结论点：

1、 ldr p11, [x16, #CACHE] 取出objc_class中cache对应的内存到p11
2、 取出buckets首地址到p10; 取出第一次_cmd对应的hash值到p12
3、 add p12, p10, p12, LSL #(1+PTRSHIFT) 根据p10 首地址偏移 p12 个#(1+PTRSHIFT)(这个值为4,左移这么多为16的单元,sizeof(bucket_t)=16)单位到目标地址,并且存入p12
4、 下面就是不断的去查找方法是否有对应bucket->sel == _cmd,找到了，证明缓存中间有,直接返回找到的imp
5、 如果一直没找到，则跳到JumpMiss $0 我们知道此时的$0就是进入CacheLookup的第一个参数NORMAL

• 5 分析 JumpMiss NORMAL

.macro JumpMiss
.if $0 == GETIMP
    b   LGetImpMiss
.elseif $0 == NORMAL
    b   __objc_msgSend_uncached
.elseif $0 == LOOKUP
    b   __objc_msgLookup_uncached
.else
.abort oops
.endif
.endmacro

了解到此时应该会走到__objc_msgSend_uncached

• 6、 分析__objc_msgSend_uncached

    STATIC_ENTRY __objc_msgSend_uncached
    UNWIND __objc_msgSend_uncached, FrameWithNoSaves

    // THIS IS NOT A CALLABLE C FUNCTION
    // Out-of-band p16 is the class to search
    
    MethodTableLookup
    TailCallFunctionPointer x17

    END_ENTRY __objc_msgSend_uncached

这里的方法会进入MethodTableLookup

• 7 分析MethodTableLookup

.macro MethodTableLookup
    
    // push frame
    SignLR
    stp fp, lr, [sp, #-16]!
    mov fp, sp

    // save parameter registers: x0..x8, q0..q7
    sub sp, sp, #(10*8 + 8*16)
    stp q0, q1, [sp, #(0*16)]
    stp q2, q3, [sp, #(2*16)]
    stp q4, q5, [sp, #(4*16)]
    stp q6, q7, [sp, #(6*16)]
    stp x0, x1, [sp, #(8*16+0*8)]
    stp x2, x3, [sp, #(8*16+2*8)]
    stp x4, x5, [sp, #(8*16+4*8)]
    stp x6, x7, [sp, #(8*16+6*8)]
    str x8,     [sp, #(8*16+8*8)]

    // 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 registers and return
    ldp q0, q1, [sp, #(0*16)]
    ldp q2, q3, [sp, #(2*16)]
    ldp q4, q5, [sp, #(4*16)]
    ldp q6, q7, [sp, #(6*16)]
    ldp x0, x1, [sp, #(8*16+0*8)]
    ldp x2, x3, [sp, #(8*16+2*8)]
    ldp x4, x5, [sp, #(8*16+4*8)]
    ldp x6, x7, [sp, #(8*16+6*8)]
    ldr x8,     [sp, #(8*16+8*8)]

    mov sp, fp
    ldp fp, lr, [sp], #16
    AuthenticateLR

.endmacro

我这里简单分析,这里前面大段的是存储指令作用是:存下当前的上下文，以及为接下来的函数准备参数;接下来调用的函数是:_lookUpImpOrForward

• 8、_lookUpImpOrForward其实这个函数是在c++中实现的

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

    runtimeLock.assertUnlocked();

    // Optimistic cache lookup
    if (fastpath(behavior & LOOKUP_CACHE)) {
        imp = cache_getImp(cls, sel);
        if (imp) goto done_nolock;
    }

    // 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.
    //
    // TODO: this check is quite costly during process startup.
    checkIsKnownClass(cls);

    if (slowpath(!cls->isRealized())) {
        cls = realizeClassMaybeSwiftAndLeaveLocked(cls, runtimeLock);
        // runtimeLock may have been dropped but is now locked again
    }

    if (slowpath((behavior & LOOKUP_INITIALIZE) && !cls->isInitialized())) {
        cls = initializeAndLeaveLocked(cls, inst, runtimeLock);
        // runtimeLock may have been dropped but is now locked again

        // If sel == initialize, class_initialize will send +initialize and 
        // then the messenger will send +initialize again after this 
        // procedure finishes. Of course, if this is not being called 
        // from the messenger then it won't happen. 2778172
    }

    runtimeLock.assertLocked();
    curClass = cls;

    // The code used to lookpu 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();;) {
        // curClass method list.
        Method meth = getMethodNoSuper_nolock(curClass, sel);
        if (meth) {
            imp = meth->imp;
            goto done;
        }

        if (slowpath((curClass = curClass->superclass) == 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.
        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:
    log_and_fill_cache(cls, imp, sel, inst, curClass);
    runtimeLock.unlock();
 done_nolock:
    if (slowpath((behavior & LOOKUP_NIL) && imp == forward_imp)) {
        return nil;
    }
    return imp;
}

这里其实就是方法的查找;核心逻辑在里面的for循环；

1、getMethodNoSuper_nolock在当前类的bits里面查找方法

static method_t *
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;
}

2、 imp = cache_getImp(curClass, sel);查找父类的缓存,并且将父类指向到当前curClass,其实就是顺着继承链去查找
3、当没有找到方法的时候会走到resolveMethod_locked,到了消息的转发，我们先不做探究
4、当查找到了正确的方法会走到done标识符对应的代码段log_and_fill_cache(cls, imp, sel, inst, curClass); 最后将找到的方法返回

• 9、分析 log_and_fill_cache() 函数

static 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
    cache_fill(cls, sel, imp, receiver);
}
//....此处代码省略
void cache_fill(Class cls, SEL sel, IMP imp, id receiver)
{
    runtimeLock.assertLocked();

#if !DEBUG_TASK_THREADS
    // Never cache before +initialize is done
    if (cls->isInitialized()) {
        cache_t *cache = getCache(cls);
#if CONFIG_USE_CACHE_LOCK
        mutex_locker_t lock(cacheUpdateLock);
#endif
        cache->insert(cls, sel, imp, receiver);
    }
#else
    _collecting_in_critical();
#endif
}

这其实是方法返回前将其存入到cache的逻辑

总结

image.png