前言
我们知道OC的上层方法调用时,在底层都会转化为objc_msgSend调用,那么它的流程是怎么样的呢,我们又如何理解它, 我们带着这些疑问来分析objc_msgSend。
首先我们先难证一下,OC的上层方法是不是会转化成objc_msgSend,如下图:

1

2

3
我们定义了一个RoPerson类的对象并调用了saySomething,通过汇编我们可以清楚的看到是转化为了objc_msgSend调用,这也就说明了OC上层的方法会被转化为objc_msgSend调用,并且是在libobjc.A.dylib这个动态库中,objc_msgSend是有汇编写的。
objc_msg_Send汇编分析
我们在objc(818版本)的源码中找到objc_msg_Send的代码,如代码所示:
ENTRY _objc_msgSend
UNWIND _objc_msgSend, NoFrame
cmp p0, #0 // nil check and tagged pointer check,判断当前的消息接受者是否为0,如果没有消息接受者,就无意义了
#if SUPPORT_TAGGED_POINTERS
b.le LNilOrTagged // (MSB tagged pointer looks negative)
#else
b.eq LReturnZero
#endif
ldr p13, [x0] // p13 = isa,把当前的isa给到p13寄存器
GetClassFromIsa_p16 p13, 1, x0 // p16 = class,p13就是isa,x0也就isa
LGetIsaDone: // 这里获取isa已经完成,开始执行下一步操作
// calls imp or objc_msgSend_uncached
CacheLookup NORMAL, _objc_msgSend, __objc_msgSend_uncached
// 这几行代码如果是*SUPPORT_TAGGED_POINTERS*(后续补充)执行*b.le LNilOrTagged*,否则执行*b.eq LReturnZero*。
#if SUPPORT_TAGGED_POINTERS
LNilOrTagged:
b.eq LReturnZero // nil check
GetTaggedClass
b LGetIsaDone
我们接着分析 GetClassFromIsa_p16这个函数,看看他到底做了什么,代码如下:
// p13(isa)也就是src参数, 1是needs_auth参数, x0(isa)是auth_address参数
.macro GetClassFromIsa_p16 src, needs_auth, auth_address /* note: auth_address is not required if !needs_auth */
#if SUPPORT_INDEXED_ISA
// Indexed isa
mov p16, src // 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
// 这里不是index isa,所以不执行,直接执行1
1:
#elif __LP64__
.if needs_auth == 0 // _cache_getImp takes an authed class already,needs_auth传过来的是1,所以下面一行代码不执行,执行.else的代码
mov p16, src
.else
// 64-bit packed isa
ExtractISA p16, src, auth_address // p16是一个空的的地址,src,auth_address都是isa
.endif
#else
// 32-bit raw isa
mov p16, src
#endif
.endmacro
我们再看下ExtractISA这个函数的流程执行,全局搜下:
// p16 = isa & ISA_MASK
.macro ExtractISA
and $0, $1, #ISA_MASK // 这行代码就是, $1 逻辑与(按位)ISA_MASK,然后给到$0 也就是p16,and是逻辑与,
.endmacro
这也就是解释了p16 就是class。
接着我们再来分析CacheLookup,我们搜下它的宏:
// Mode就是NORMAL, Function就是_objc_msgSend,__objc_msgSend_uncached, MissLabelDynamic , MissLabelConstant
.macro CacheLookup Mode, Function, MissLabelDynamic, MissLabelConstant
//
// Restart protocol:
//
// As soon as we're past the LLookupStartFunction 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 LLookupEndFunction,
// then our PC will be reset to LLookupRecoverFunction 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
//
mov x15, x16 // stash the original isa,这里x16就是p16,把x16移到x15寄存器中
LLookupStartFunction: // 开始找_objc_msgSend流程
// p1 = SEL, p16 = isa
#if CACHE_MASK_STORAGE == CACHE_MASK_STORAGE_HIGH_16_BIG_ADDRS
ldr p10, [x16, #CACHE] // p10 = mask|buckets
lsr p11, p10, #48 // p11 = mask
and p10, p10, #0xffffffffffff // p10 = buckets
and w12, w1, w11 // x12 = _cmd & mask
#elif CACHE_MASK_STORAGE == CACHE_MASK_STORAGE_HIGH_16 // 真机的架构。
ldr p11, [x16, #CACHE] // p11 = mask|buckets,把x16的地址平移CACHE大小,经过全局搜索CACHE是16字节,就是平移到cahce结构体的位置,这个时候p11=cache_t。
#if CONFIG_USE_PREOPT_CACHES // 这里从来的没找过,所以不执行,我们可以看下它的else,CONFIG_USE_PREOPT_CACHES这个值为1,可以全局搜下
#if __has_feature(ptrauth_calls)
tbnz p11, #0, LLookupPreoptFunction
and p10, p11, #0x0000ffffffffffff // p10 = buckets
#else
and p10, p11, #0x0000fffffffffffe // p10 = buckets,这里就是p11 & 0x0000fffffffffffe(掩码),并赋给10寄存器
tbnz p11, #0, LLookupPreoptFunction,p11与0做比较,如果p11不为0,跳转到LLookupPreopt。
#endif
eor p12, p1, p1, LSR #7 // p1右移7位存到p12中
and p12, p12, p11, LSR #48 // x12 = (_cmd ^ (_cmd >> 7)) & mask
#else
// p11 cache -> p10 = buckets
// p11, LSR #48 -> mask,
// p1(_cmd) & mask = index -> p12
and p10, p11, #0x 000 0ffffffffffff // p10 = buckets
and p12, p1, p11, LSR #48 // x12 = _cmd & mask,p11 右移48位得到mask值,然后与p1(sel也就是_cmd)进行&运算,得到index值,并赋给p12寄存器。
#endif // CONFIG_USE_PREOPT_CACHES
#elif CACHE_MASK_STORAGE == CACHE_MASK_STORAGE_LOW_4
ldr p11, [x16, #CACHE] // p11 = mask|buckets
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
// objc - 源码调试 + 汇编
// p11 cache -> p10 = buckets
// p1(_cmd) & mask = index -> p12
// (_cmd & mask) b + i
// p13 当前要查找的bucket
// PTRSHIFT=3
add p13, p10, p12, LSL #(1+PTRSHIFT)
// p13 = buckets + ((_cmd & mask) = buckets)
b.hs 1b // 跳转到1,继续执行
// wrap-around:
// p10 = first bucket
// p11 = mask (and maybe other bits o n LP64)
// p12 = _cmd & mask
//
// A full cache can happen with CACHE_ALLOW_FULL_UTILIZATION.
// So stop when we circle back to the first probed bucket
// rather than when hitting the first bucket again.
//
// Note that we might probe the initial bucket twice
// when the first probed slot is the last entry.
#if CACHE_MASK_STORAGE == CACHE_MASK_STORAGE_HIGH_16_BIG_ADDRS
add p13, p10, w11, UXTW #(1+PTRSHIFT)
// p13 = buckets + (mask first_probed)
b.hi 4b
LLookupEndFunction:
LLookupRecoverFunction:
b MissLabelDynamic
#if CONFIG_USE_PREOPT_CACHES
#if CACHE_MASK_STORAGE != CACHE_MASK_STORAGE_HIGH_16
#error config unsupported
#endif
LLookupPreoptFunction:
#if __has_feature(ptrauth_calls)
and p10, p11, #0x007ffffffffffffe // p10 = buckets
autdb x10, x16 // auth as early as possible
#endif
// x12 = (_cmd - first_shared_cache_sel)
adrp x9, _MagicSelRef@PAGE
ldr p9, [x9, _MagicSelRef@PAGEOFF]
sub p12, p1, p9
// w9 = ((_cmd - first_shared_cache_sel) >> hash_shift & hash_mask)
#if __has_feature(ptrauth_calls)
// bits 63..60 of x11 are the number of bits in hash_mask
// bits 59..55 of x11 is hash_shift
lsr x17, x11, #55 // w17 = (hash_shift, ...)
lsr w9, w12, w17 // >>= shift
lsr x17, x11, #60 // w17 = mask_bits
mov x11, #0x7fff
lsr x11, x11, x17 // p11 = mask (0x7fff >> mask_bits)
and x9, x9, x11 // &= mask
#else
// bits 63..53 of x11 is hash_mask
// bits 52..48 of x11 is hash_shift
lsr x17, x11, #48 // w17 = (hash_shift, hash_mask)
lsr w9, w12, w17 // >>= shift
and x9, x9, x11, LSR #53 // &= mask
#endif
ldr x17, [x10, x9, LSL #3] // x17 == sel_offs | (imp_offs
这里我们分析下LLookupPreopt这个函数,搜到如下:
LLookupPreoptFunction:
#if __has_feature(ptrauth_calls)
and p10, p11, #0x007ffffffffffffe // p10 = buckets, 这里是p11寄存器逻辑与(按位)0x007ffffffffffffe,给到p10,也就是说p10=buckets。
autdb x10, x16 // auth as early as possible
#endif
// x12 = (_cmd - first_shared_cache_sel)
adrp x9, _MagicSelRef@PAGE
ldr p9, [x9, _MagicSelRef@PAGEOFF]
sub p12, p1, p9
// w9 = ((_cmd - first_shared_cache_sel) >> hash_shift & hash_mask)
#if __has_feature(ptrauth_calls)
// bits 63..60 of x11 are the number of bits in hash_mask
// bits 59..55 of x11 is hash_shift
lsr x17, x11, #55 // w17 = (hash_shift, ...)
lsr w9, w12, w17 // >>= shift
lsr x17, x11, #60 // w17 = mask_bits
mov x11, #0x7fff
lsr x11, x11, x17 // p11 = mask (0x7fff >> mask_bits)
and x9, x9, x11 // &= mask
#else
// bits 63..53 of x11 is hash_mask
// bits 52..48 of x11 is hash_shift
lsr x17, x11, #48 // w17 = (hash_shift, hash_mask)
lsr w9, w12, w17 // >>= shift
and x9, x9, x11, LSR #53 // &= mask
#endif
ldr x17, [x10, x9, LSL #3] // x17 == sel_offs | (imp_offs
我们再来看下CacheHit这个函数,代码如下:
// CacheHit: x17 = cached IMP, x10 = address of buckets, x1 = SEL, x16 = isa
.macro CacheHit
.if $0 == NORMAL
TailCallCachedImp x17, x10, x1, x16 // authenticate and call imp
.elseif $0 == GETIMP
mov p0, p17
cbz p0, 9f // don't ptrauth a nil imp
AuthAndResignAsIMP x0, x10, x1, x16 // authenticate imp and re-sign as IMP
9: ret // return IMP
.elseif $0 == LOOKUP
// No nil check for ptrauth: the caller would crash anyway when they
// jump to a nil IMP. We don't care if that jump also fails ptrauth.
AuthAndResignAsIMP x17, x10, x1, x16 // authenticate imp and re-sign as IMP
cmp x16, x15
cinc x16, x16, ne // x16 += 1 when x15 != x16 (for instrumentation ; fallback to the parent class)
ret // return imp via x17
.else
.abort oops
.endif
.endmacro
TailCallCachedImp这个函数,就是对imp进行编码,并跳转到imp