在C语言中，我们定义了NULL来表示空指针，空指针是一个特殊的指针，它其实就是0指针，*p = NULL和*p=0是等价的写法。空指针是一个未赋值的指针，毫无意义的指针，如果访问到该地址，那么程序会出错。
如果在Linux应用程序中访问NULL指针：
会收到Segmentation Fault信号，一般行为是该用户进程会杀死自己，程序当然也可以捕获对应的信号自行处理，这种用户态的错误是不会导致系统crash的。
如果是在内核中访问到NULL指针分多种情况：
（1）如果是在内核态的进程上下文中访问，那么会执行oops动作，杀死当前进程，并打印相关信息。
（2）如果是在内核态的其他上下文中（比如中断上下文），那么系统会执行panic动作。
（3）如果内核中有配置panic_on_oops，那么上面发生oops的场景也会发生panic。
接下来我们来看一下代码中是如何执行的，当我们访问一个页表中不存在的地址时，那么CPU首先会触发一个异常，缺页异常由硬件自动触发。
首先我们需要看中断向量表，当发生data abort异常时，ARM64会首先去执行entry.S中定义的：
el1_da:
......
mov x2, sp // struct pt_regs
bl do_mem_abort //主处理函数，C代码
......
el0_da:
/*
* Data abort handling
*/
mrs x26, far_el1
// enable interrupts before calling the main handler
enable_dbg_and_irq
ct_user_exit
clear_address_tag x0, x26
mov x1, x25
mov x2, sp
bl do_mem_abort //主处理函数，C代码
b ret_to_user 下面我们以此跟踪下去，可以看到会执行到arch/arm64/mm/fault.c:
/*
* Dispatch a data abort to the relevant handler.
*/
asmlinkage void __exception do_mem_abort(unsigned long addr, unsigned int esr,
struct pt_regs *regs)
{
const struct fault_info *inf = esr_to_fault_info(esr); //根据esr找到对应的fault_info数组成员
struct siginfo info;
if (!inf->fn(addr, esr, regs))
return;
pr_alert("Unhandled fault: %s (0x%08x) at 0x%016lx\n",
inf->name, esr, addr);
info.si_signo = inf->sig;
info.si_errno = 0;
info.si_code = inf->code;
info.si_addr = (void __user *)addr;
arm64_notify_die("", regs, &info, esr);
} static inline const struct fault_info *esr_to_fault_info(unsigned int esr)
{
return fault_info + (esr & 63);
} 下面来看fault info数组的定义：
static const struct fault_info fault_info[] = {
{ do_bad, SIGBUS, 0, "ttbr address size fault" },
{ do_bad, SIGBUS, 0, "level 1 address size fault" },
{ do_bad, SIGBUS, 0, "level 2 address size fault" },
{ do_bad, SIGBUS, 0, "level 3 address size fault" },
{ do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 0 translation fault" },
{ do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 1 translation fault" },
{ do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 2 translation fault" },
{ do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 3 translation fault" },
{ do_bad, SIGBUS, 0, "unknown 8" },
{ do_page_fault, SIGSEGV, SEGV_ACCERR, "level 1 access flag fault" },
{ do_page_fault, SIGSEGV, SEGV_ACCERR, "level 2 access flag fault" },
{ do_page_fault, SIGSEGV, SEGV_ACCERR, "level 3 access flag fault" },
{ do_bad, SIGBUS, 0, "unknown 12" },
{ do_page_fault, SIGSEGV, SEGV_ACCERR, "level 1 permission fault" },
{ do_page_fault, SIGSEGV, SEGV_ACCERR, "level 2 permission fault" },
{ do_page_fault, SIGSEGV, SEGV_ACCERR, "level 3 permission fault" },
{ do_bad, SIGBUS, 0, "synchronous external abort" },
{ do_bad, SIGBUS, 0, "unknown 17" },
{ do_bad, SIGBUS, 0, "unknown 18" },
{ do_bad, SIGBUS, 0, "unknown 19" },
{ do_bad, SIGBUS, 0, "synchronous external abort (translation table walk)" },
{ do_bad, SIGBUS, 0, "synchronous external abort (translation table walk)" },
{ do_bad, SIGBUS, 0, "synchronous external abort (translation table walk)" },
{ do_bad, SIGBUS, 0, "synchronous external abort (translation table walk)" },
{ do_bad, SIGBUS, 0, "synchronous parity error" },
{ do_bad, SIGBUS, 0, "unknown 25" },
{ do_bad, SIGBUS, 0, "unknown 26" },
{ do_bad, SIGBUS, 0, "unknown 27" },
{ do_bad, SIGBUS, 0, "synchronous parity error (translation table walk)" },
{ do_bad, SIGBUS, 0, "synchronous parity error (translation table walk)" },
{ do_bad, SIGBUS, 0, "synchronous parity error (translation table walk)" },
{ do_bad, SIGBUS, 0, "synchronous parity error (translation table walk)" },
{ do_bad, SIGBUS, 0, "unknown 32" },
{ do_alignment_fault, SIGBUS, BUS_ADRALN, "alignment fault" },
{ do_bad, SIGBUS, 0, "unknown 34" },
{ do_bad, SIGBUS, 0, "unknown 35" },
{ do_bad, SIGBUS, 0, "unknown 36" },
{ do_bad, SIGBUS, 0, "unknown 37" },
{ do_bad, SIGBUS, 0, "unknown 38" },
{ do_bad, SIGBUS, 0, "unknown 39" },
{ do_bad, SIGBUS, 0, "unknown 40" },
{ do_bad, SIGBUS, 0, "unknown 41" },
{ do_bad, SIGBUS, 0, "unknown 42" },
{ do_bad, SIGBUS, 0, "unknown 43" },
{ do_bad, SIGBUS, 0, "unknown 44" },
{ do_bad, SIGBUS, 0, "unknown 45" },
{ do_bad, SIGBUS, 0, "unknown 46" },
{ do_bad, SIGBUS, 0, "unknown 47" },
{ do_tlb_conf_fault, SIGBUS, 0, "TLB conflict abort" },
{ do_bad, SIGBUS, 0, "unknown 49" },
{ do_bad, SIGBUS, 0, "unknown 50" },
{ do_bad, SIGBUS, 0, "unknown 51" },
{ do_bad, SIGBUS, 0, "implementation fault (lockdown abort)" },
{ do_bad, SIGBUS, 0, "implementation fault (unsupported exclusive)" },
{ do_bad, SIGBUS, 0, "unknown 54" },
{ do_bad, SIGBUS, 0, "unknown 55" },
{ do_bad, SIGBUS, 0, "unknown 56" },
{ do_bad, SIGBUS, 0, "unknown 57" },
{ do_bad, SIGBUS, 0, "unknown 58" },
{ do_bad, SIGBUS, 0, "unknown 59" },
{ do_bad, SIGBUS, 0, "unknown 60" },
{ do_bad, SIGBUS, 0, "section domain fault" },
{ do_bad, SIGBUS, 0, "page domain fault" },
{ do_bad, SIGBUS, 0, "unknown 63" },
};上面定义的fault info，主要关键的处理函数就如下几个，分别是：
do_bad/do_alignment_fault/do_tlb_conf_fault/do_translation_fault/do_page_fault。
回到最初的问题，如果我们想要访问的是指针0地址，那么硬件会执行到do_page_fault这个函数中来进行处理。我们来继续跟踪一下，看看这个函数具体做了什么吧。
static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
struct pt_regs *regs)
{
struct task_struct *tsk;
struct mm_struct *mm;
int fault, sig, code;
unsigned long vm_flags = VM_READ | VM_WRITE;
unsigned int mm_flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
if (notify_page_fault(regs, esr))
return 0;
tsk = current;
mm = tsk->mm;
/*
* If we're in an interrupt or have no user context, we must not take
* the fault.
*/
if (faulthandler_disabled() || !mm) //faulthandler_disabled()函数判断是否faulthandler被disabled了或者是否处于中断上下文
//!mm用来判断是否没有用户进程的上下文，如果都处于中断上下文或者没有用户上下文，那么直接跳转
goto no_context;
if (user_mode(regs))
mm_flags |= FAULT_FLAG_USER;
if (is_el0_instruction_abort(esr)) {
vm_flags = VM_EXEC;
} else if (((esr & ESR_ELx_WNR) && !(esr & ESR_ELx_CM)) ||
((esr & ESR_ELx_CM) && !(mm_flags & FAULT_FLAG_USER))) {
vm_flags = VM_WRITE;
mm_flags |= FAULT_FLAG_WRITE;
}
if (addr < USER_DS && is_permission_fault(esr, regs)) {
/* regs->orig_addr_limit may be 0 if we entered from EL0 */
if (regs->orig_addr_limit == KERNEL_DS)
die("Accessing user space memory with fs=KERNEL_DS", regs, esr);
if (is_el1_instruction_abort(esr))
die("Attempting to execute userspace memory", regs, esr);
if (!search_exception_tables(regs->pc))
die("Accessing user space memory outside uaccess.h routines", regs, esr);
}
/*
* As per x86, we may deadlock here. However, since the kernel only
* validly references user space from well defined areas of the code,
* we can bug out early if this is from code which shouldn't.
*/
if (!down_read_trylock(&mm->mmap_sem)) {
if (!user_mode(regs) && !search_exception_tables(regs->pc))
goto no_context;
retry:
down_read(&mm->mmap_sem);
} else {
/*
* The above down_read_trylock() might have succeeded in which
* case, we'll have missed the might_sleep() from down_read().
*/
might_sleep();
#ifdef CONFIG_DEBUG_VM
if (!user_mode(regs) && !search_exception_tables(regs->pc))
goto no_context;
#endif
}
fault = __do_page_fault(mm, addr, mm_flags, vm_flags, tsk);
/*
* If we need to retry but a fatal signal is pending, handle the
* signal first. We do not need to release the mmap_sem because it
* would already be released in __lock_page_or_retry in mm/filemap.c.
*/
if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) {
if (!user_mode(regs))
goto no_context;
return 0;
}
/*
* Major/minor page fault accounting is only done on the initial
* attempt. If we go through a retry, it is extremely likely that the
* page will be found in page cache at that point.
*/
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr);
if (mm_flags & FAULT_FLAG_ALLOW_RETRY) {
if (fault & VM_FAULT_MAJOR) {
tsk->maj_flt++;
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs,
addr);
} else {
tsk->min_flt++;
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs,
addr);
}
if (fault & VM_FAULT_RETRY) {
/*
* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk of
* starvation.
*/
mm_flags &= ~FAULT_FLAG_ALLOW_RETRY;
mm_flags |= FAULT_FLAG_TRIED;
goto retry;
}
}
up_read(&mm->mmap_sem);
/*
* Handle the "normal" case first - VM_FAULT_MAJOR
*/
if (likely(!(fault & (VM_FAULT_ERROR | VM_FAULT_BADMAP |
VM_FAULT_BADACCESS))))
return 0;
/*
* If we are in kernel mode at this point, we have no context to
* handle this fault with.
*/
if (!user_mode(regs))
goto no_context;
if (fault & VM_FAULT_OOM) {
/*
* We ran out of memory, call the OOM killer, and return to
* userspace (which will retry the fault, or kill us if we got
* oom-killed).
*/
pagefault_out_of_memory();
return 0;
}
if (fault & VM_FAULT_SIGBUS) {
/*
* We had some memory, but were unable to successfully fix up
* this page fault.
*/
sig = SIGBUS;
code = BUS_ADRERR;
} else {
/*
* Something tried to access memory that isn't in our memory
* map.
*/
sig = SIGSEGV;
code = fault == VM_FAULT_BADACCESS ?
SEGV_ACCERR : SEGV_MAPERR;
}
__do_user_fault(tsk, addr, esr, sig, code, regs); //在用户进程上下文中发现地址无法被映射，比如地址0,那么就会执行到此处，do user fault
return 0;
no_context: //没有进程上下文的情况会直接跳到此执行do kernel fault
__do_kernel_fault(mm, addr, esr, regs);
return 0;
}此函数的中间部分都是进行缺页异常的处理，比如重新建立页表，从伙伴系统分配内存等等，我们暂且不去进一步分析。只看最后出现异常的情况，异常分两种，一种是有用户上下文，一种没有用户上下文，分别会去执行__do_user_fault和__do_kernel_fault。这不就是和我们前面的描述，两种访问0地址的方式场景匹配了嘛。
/*
* Something tried to access memory that isn't in our memory map. User mode
* accesses just cause a SIGSEGV
*/
static void __do_user_fault(struct task_struct *tsk, unsigned long addr,
unsigned int esr, unsigned int sig, int code,
struct pt_regs *regs)
{
struct siginfo si;
const struct fault_info *inf;
trace_user_fault(tsk, addr, esr);
if (unhandled_signal(tsk, sig) && show_unhandled_signals_ratelimited()) {
inf = esr_to_fault_info(esr);
pr_info("%s[%d]: unhandled %s (%d) at 0x%08lx, esr 0x%03x\n",
tsk->comm, task_pid_nr(tsk), inf->name, sig,
addr, esr);
show_pte(tsk->mm, addr);
show_regs(regs);
}
tsk->thread.fault_address = addr;
tsk->thread.fault_code = esr;
si.si_signo = sig;
si.si_errno = 0;
si.si_code = code;
si.si_addr = (void __user *)addr;
force_sig_info(sig, &si, tsk);
}/*
* The kernel tried to access some page that wasn't present.
*/
static void __do_kernel_fault(struct mm_struct *mm, unsigned long addr,
unsigned int esr, struct pt_regs *regs)
{
/*
* Are we prepared to handle this kernel fault?
* We are almost certainly not prepared to handle instruction faults.
*/
if (!is_el1_instruction_abort(esr) && fixup_exception(regs))
return;
/*
* No handler, we'll have to terminate things with extreme prejudice.
*/
bust_spinlocks(1);
pr_alert("Unable to handle kernel %s at virtual address %08lx\n",
(addr < PAGE_SIZE) ? "NULL pointer dereference" :
"paging request", addr);
show_pte(mm, addr);
die("Oops", regs, esr);
bust_spinlocks(0);
do_exit(SIGKILL);
}