Re: Arm Linux系统调用流程详细解析
Posted: 2025-03-06T03:15:26+00:00
最后再罗嗦一点，如果用sys_open来搜的话，是搜不到系统调用open的定义的，系统调用函数都是用宏来定义的，比如对于open，在文件fs/open.c文件中这样定义：
继续回到vector_swi，而如果系统调用号不正确，则会调用arm_syscall函数来进行处理，这个函数在文件arch/arm/kernel/traps.c中定义：
Code: Select all
SYSCALL_DEFINE3(open, const char __user *, filename, int, flags, int, mode)
{
long ret;
if (force_o_largefile())
flags |= O_LARGEFILE;
ret = do_sys_open(AT_FDCWD, filename, flags, mode);
/* avoid REGPARM breakage on x86: */
asmlinkage_protect(3, ret, filename, flags, mode);
return ret;
}
Code: Select all
/*
* Handle all unrecognised system calls.
* 0x9f0000 - 0x9fffff are some more esoteric system calls
*/
#define NR(x) ((__ARM_NR_##x) - __ARM_NR_BASE)
asmlinkage int arm_syscall(int no, struct pt_regs *regs)
{
struct thread_info *thread = current_thread_info();
siginfo_t info;
if ((no >> 16) != (__ARM_NR_BASE>> 16))
return bad_syscall(no, regs);
switch (no & 0xffff) {
case 0: /* branch through 0 */
info.si_signo = SIGSEGV;
info.si_errno = 0;
info.si_code = SEGV_MAPERR;
info.si_addr = NULL;
arm_notify_die("branch through zero", regs, &info, 0, 0);
return 0;
case NR(breakpoint): /* SWI BREAK_POINT */
regs->ARM_pc -= thumb_mode(regs) ? 2 : 4;
ptrace_break(current, regs);
return regs->ARM_r0;
/*
* Flush a region from virtual address 'r0' to virtual address 'r1'
* _exclusive_. There is no alignment requirement on either address;
* user space does not need to know the hardware cache layout.
*
* r2 contains flags. It should ALWAYS be passed as ZERO until it
* is defined to be something else. For now we ignore it, but may
* the fires of hell burn in your belly if you break this rule. ;)
*
* (at a later date, we may want to allow this call to not flush
* various aspects of the cache. Passing '0' will guarantee that
* everything necessary gets flushed to maintain consistency in
* the specified region).
*/
case NR(cacheflush):
do_cache_op(regs->ARM_r0, regs->ARM_r1, regs->ARM_r2);
return 0;
case NR(usr26):
if (!(elf_hwcap & HWCAP_26BIT))
break;
regs->ARM_cpsr &= ~MODE32_BIT;
return regs->ARM_r0;
case NR(usr32):
if (!(elf_hwcap & HWCAP_26BIT))
break;
regs->ARM_cpsr |= MODE32_BIT;
return regs->ARM_r0;
case NR(set_tls):
thread->tp_value = regs->ARM_r0;
if (tls_emu)
return 0;
if (has_tls_reg) {
asm ("mcr p15, 0, %0, c13, c0, 3"
: : "r" (regs->ARM_r0));
} else {
/*
* User space must never try to access this directly.
* Expect your app to break eventually if you do so.
* The user helper at 0xffff0fe0 must be used instead.
* (see entry-armv.S for details)
*/
*((unsigned int *)0xffff0ff0) = regs->ARM_r0;
}
return 0;
#ifdef CONFIG_NEEDS_SYSCALL_FOR_CMPXCHG
/*
* Atomically store r1 in *r2 if *r2 is equal to r0 for user space.
* Return zero in r0 if *MEM was changed or non-zero if no exchange
* happened. Also set the user C flag accordingly.
* If access permissions have to be fixed up then non-zero is
* returned and the operation has to be re-attempted.
*
* *NOTE*: This is a ghost syscall private to the kernel. Only the
* __kuser_cmpxchg code in entry-armv.S should be aware of its
* existence. Don't ever use this from user code.
*/
case NR(cmpxchg):
for (;;) {
extern void do_DataAbort(unsigned long addr, unsigned int fsr,
struct pt_regs *regs);
unsigned long val;
unsigned long addr = regs->ARM_r2;
struct mm_struct *mm = current->mm;
pgd_t *pgd; pmd_t *pmd; pte_t *pte;
spinlock_t *ptl;
regs->ARM_cpsr &= ~PSR_C_BIT;
down_read(&mm->mmap_sem);
pgd = pgd_offset(mm, addr);
if (!pgd_present(*pgd))
goto bad_access;
pmd = pmd_offset(pgd, addr);
if (!pmd_present(*pmd))
goto bad_access;
pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
if (!pte_present(*pte) || !pte_dirty(*pte)) {
pte_unmap_unlock(pte, ptl);
goto bad_access;
}
val = *(unsigned long *)addr;
val -= regs->ARM_r0;
if (val == 0) {
*(unsigned long *)addr = regs->ARM_r1;
regs->ARM_cpsr |= PSR_C_BIT;
}
pte_unmap_unlock(pte, ptl);
up_read(&mm->mmap_sem);
return val;
bad_access:
up_read(&mm->mmap_sem);
/* simulate a write access fault */
do_DataAbort(addr, 15 + (1 << 11), regs);
}
#endif
default:
/* Calls 9f00xx..9f07ff are defined to return -ENOSYS
if not implemented, rather than raising SIGILL. This
way the calling program can gracefully determine whether
a feature is supported. */
if ((no & 0xffff) <= 0x7ff)
return -ENOSYS;
break;
}
#ifdef CONFIG_DEBUG_USER
/*
* experience shows that these seem to indicate that
* something catastrophic has happened
*/
if (user_debug & UDBG_SYSCALL) {
printk("[%d] %s: arm syscall %d\n",
task_pid_nr(current), current->comm, no);
dump_instr("", regs);
if (user_mode(regs)) {
__show_regs(regs);
c_backtrace(regs->ARM_fp, processor_mode(regs));
}
}
#endif
info.si_signo = SIGILL;
info.si_errno = 0;
info.si_code = ILL_ILLTRP;
info.si_addr = (void __user *)instruction_pointer(regs) -
(thumb_mode(regs) ? 2 : 4);
arm_notify_die("Oops - bad syscall(2)", regs, &info, no, 0);
return 0;
}