objc_msgSend
是基于汇编实现的,hook objc_msgSend
和我们平时 hook OC 方法不一样,在 github 上有开源的项目通过 hook objc_msgSend
来监控每个函数的耗时情况。这篇文章对其 hook 逻辑的主要代码进行分析记录。阅读前建议先了解开源库 fishhook 的源码。
主流程
先看开源 项目 主要代码
#define call(b, value) \
__asm volatile ("stp x8, x9, [sp, #-16]!\n"); \
__asm volatile ("mov x12, %0\n" :: "r"(value)); \
__asm volatile ("ldp x8, x9, [sp], #16\n"); \
__asm volatile (#b " x12\n");
#define save() \
__asm volatile ( \
"stp x8, x9, [sp, #-16]!\n" \
"stp x6, x7, [sp, #-16]!\n" \
"stp x4, x5, [sp, #-16]!\n" \
"stp x2, x3, [sp, #-16]!\n" \
"stp x0, x1, [sp, #-16]!\n");
#define load() \
__asm volatile ( \
"ldp x0, x1, [sp], #16\n" \
"ldp x2, x3, [sp], #16\n" \
"ldp x4, x5, [sp], #16\n" \
"ldp x6, x7, [sp], #16\n" \
"ldp x8, x9, [sp], #16\n" );
#define link(b, value) \
__asm volatile ("stp x8, lr, [sp, #-16]!\n"); \
__asm volatile ("sub sp, sp, #16\n"); \
call(b, value); \
__asm volatile ("add sp, sp, #16\n"); \
__asm volatile ("ldp x8, lr, [sp], #16\n");
#define ret() __asm volatile ("ret\n");
__attribute__((__naked__))
static void hook_Objc_msgSend() {
// Save parameters.
/// Step 1
save()
/// Step 2
__asm volatile ("mov x2, lr\n");
__asm volatile ("mov x3, x4\n");
// Call our before_objc_msgSend.
/// Step 3
call(blr, &before_objc_msgSend)
// Load parameters.
/// Step 4
load()
// Call through to the original objc_msgSend.
/// Step 5
call(blr, orig_objc_msgSend)
// Save original objc_msgSend return value.
/// Step 6
save()
// Call our after_objc_msgSend.
/// Step 7
call(blr, &after_objc_msgSend)
// restore lr
/// Step 8
__asm volatile ("mov lr, x0\n");
// Load original objc_msgSend return value.
/// Step 9
load()
// return
/// Step 10
ret()
}
对以上代码我们分步骤来看
-
save()
保存函数入参(x0-x8)到栈内存,因为接下来你的函数调用修改原有参数。这里源码里面看到 x9 的值也被保存了,这里的原因是因为栈指针移动必须满足SP Mod 16 = 0
的条件,而在 x8 寄存器只占用8个字节,剩余8个字节控件由 x9 来填充#define save() \ __asm volatile ( \ "stp x8, x9, [sp, #-16]!\n" \ "stp x6, x7, [sp, #-16]!\n" \ "stp x4, x5, [sp, #-16]!\n" \ "stp x2, x3, [sp, #-16]!\n" \ "stp x0, x1, [sp, #-16]!\n");
-
保存 lr 到 x2,以便
call(blr, &before_objc_msgSend)
的调用,保存到 x2 是因为before_objc_msgSend
函数第三个参数需要传入 lr,方便后续返回;blr
指令会改变 lr 寄存器的值,所以调用前先保存 lr#define call(b, value) \ __asm volatile ("stp x8, x9, [sp, #-16]!\n"); \ __asm volatile ("mov x12, %0\n" :: "r"(value)); \ __asm volatile ("ldp x8, x9, [sp], #16\n"); \ __asm volatile (#b " x12\n"); void before_objc_msgSend(id self, SEL _cmd, uintptr_t lr) { push_call_record(self, object_getClass(self), _cmd, lr); } static inline void push_call_record(id _self, Class _cls, SEL _cmd, uintptr_t lr) { thread_call_stack *cs = get_thread_call_stack(); if (cs) { int nextIndex = (++cs->index); if (nextIndex >= cs->allocated_length) { cs->allocated_length += 64; cs->stack = (thread_call_record *)realloc(cs->stack, cs->allocated_length * sizeof(thread_call_record)); } thread_call_record *newRecord = &cs->stack[nextIndex]; newRecord->self = _self; newRecord->cls = _cls; newRecord->cmd = _cmd; newRecord->lr = lr; if (cs->is_main_thread && _call_record_enabled) { struct timeval now; gettimeofday(&now, NULL); newRecord->time = (now.tv_sec % 100) * 1000000 + now.tv_usec; } } }
__asm volatile ("mov x3, x4\n");
目前个人认为是冗余代码,在整个流程中貌似并没有实际作用。 -
通过
blr
指令 跳转执行before_objc_msgSend
函数。这里会先保存 x8、x9 寄存器的值,原因是__asm volatile ("mov x12, %0\n" :: "r"(value))
执行命令过程中会通过 x8 来保存函数地址,再进行跳转,所以这里会先要保存 x8,和步骤1相同,栈指针移动必须满足SP Mod 16 = 0
的条件,所以 x9 也被保存。执行完之后 x8、x9 恢复。#define call(b, value) \ __asm volatile ("stp x8, x9, [sp, #-16]!\n"); \ __asm volatile ("mov x12, %0\n" :: "r"(value)); \ __asm volatile ("ldp x8, x9, [sp], #16\n"); \ __asm volatile (#b " x12\n");
在
__asm volatile ("mov x12, %0\n" :: "r"(value))
下断点可以看到 cpu 是通过adrp
+add
2个指令结合寻址到函数的地址并执行,过程中改变了 x8 的值 Step 4 到 Step 6,恢复原有入参,执行原函数,然后保存入参
-
call(blr, &after_objc_msgSend)
和步骤3相似,执行 hook 收尾的函数,主要是通过 TSD 返回步骤3保存的原来 lr 寄存器保存的内容,也就是hook前的 lr 寄存器值static inline uintptr_t pop_call_record() { thread_call_stack *cs = get_thread_call_stack(); int curIndex = cs->index; int nextIndex = cs->index--; thread_call_record *pRecord = &cs->stack[nextIndex]; if (cs->is_main_thread && _call_record_enabled) { struct timeval now; gettimeofday(&now, NULL); uint64_t time = (now.tv_sec % 100) * 1000000 + now.tv_usec; if (time < pRecord->time) { time += 100 * 1000000; } uint64_t cost = time - pRecord->time; if (cost > _min_time_cost && cs->index < _max_call_depth) { if (!_smCallRecords) { _smRecordAlloc = 1024; _smCallRecords = malloc(sizeof(smCallRecord) * _smRecordAlloc); } _smRecordNum++; if (_smRecordNum >= _smRecordAlloc) { _smRecordAlloc += 1024; _smCallRecords = realloc(_smCallRecords, sizeof(smCallRecord) * _smRecordAlloc); } smCallRecord *log = &_smCallRecords[_smRecordNum - 1]; log->cls = pRecord->cls; log->depth = curIndex; log->sel = pRecord->cmd; log->time = cost; } } return pRecord->lr; }
__asm volatile ("mov lr, x0\n");
将步骤5返回的值(原来lr的初始值)到lr寄存器Step 9 - Step 10 恢复寄存器值,并返回。主要目的是还原原始函数的执行之后的状态。
遗留问题:
以上就是整个汇编 hook objc_msgSend
的主要过程,目前遗留一个问题是:
-
__asm volatile ("mov x3, x4\n");
这行代码是否属于冗余代码呢?
参考文章:
- arm64程序调用规则