ptrace系统调用允许父进程检查附加的子进程。例如，在Linux中，strace（使用ptrace系统调用实现）可以检查子进程调用的系统调用。
当附加的子进程调用系统调用时，可以通知ptracing父进程。但究竟是怎么发生的呢？我想知道这个机制背后的技术细节。
提前谢谢。
答案 0 :(得分：30)
当附加的子进程调用系统调用时，可以通知ptracing父进程。但究竟是怎么发生的？
父进程使用ptrace调用PTRACE_ATTACH，他的孩子使用ptrace选项调用PTRACE_TRACEME。该对将通过填充task_struct（kernel/ptrace.c: sys_ptrace内的某些字段来连接两个进程，子PT_PTRACED ptrace字段中的struct task_struct标记和pid ptracer进程为父级和ptrace_entry列表 - __ptrace_link;父级将在ptraced列表中记录子级的pid。）
然后strace将使用ptrace标志调用PTRACE_SYSCALL将自己注册为系统调用调试器，在子进程的TIF_SYSCALL_TRACE中设置thread_flag struct thread_info（类似于set_tsk_thread_flag(child, TIF_SYSCALL_TRACE); ）。 arch/x86/include/asm/thread_info.h：
67 /*
68 * thread information flags
69 * - these are process state flags that various assembly files
70 * may need to access ...*/
75 #define TIF_SYSCALL_TRACE 0 /* syscall trace active */
99 #define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE)
在每个系统调用条目或出口上，特定于体系结构的系统调用条目代码将检查此_TIF_SYSCALL_TRACE flag（直接在syscall的汇编程序实现中，例如x86 arch/x86/kernel/entry_32.S：jnz syscall_trace_entry {{1}和syscall_exit_work中的类似代码，如果设置了，ptracer将通过signal（SIGTRAP）通知，child将被临时停止。这通常在syscall_trace_enter和ENTRY(system_call)：
syscall_trace_leave 1457 long syscall_trace_enter(struct pt_regs *regs)
1483 if ((ret || test_thread_flag(TIF_SYSCALL_TRACE)) &&
1484 tracehook_report_syscall_entry(regs))
1485 ret = -1L;
1507 void syscall_trace_leave(struct pt_regs *regs)
1531 if (step || test_thread_flag(TIF_SYSCALL_TRACE))
1532 tracehook_report_syscall_exit(regs, step);
是这里的实际工作人员，他们会致电tracehook_report_syscall_*。 include/linux/tracehook.h：
ptrace_report_syscall ptrace_report_syscall generates SIGTRAP用于调试器或strace通过 80 /**
81 * tracehook_report_syscall_entry - task is about to attempt a system call
82 * @regs: user register state of current task
83 *
84 * This will be called if %TIF_SYSCALL_TRACE has been set, when the
85 * current task has just entered the kernel for a system call.
86 * Full user register state is available here. Changing the values
87 * in @regs can affect the system call number and arguments to be tried.
88 * It is safe to block here, preventing the system call from beginning.
89 *
90 * Returns zero normally, or nonzero if the calling arch code should abort
91 * the system call. That must prevent normal entry so no system call is
92 * made. If @task ever returns to user mode after this, its register state
93 * is unspecified, but should be something harmless like an %ENOSYS error
94 * return. It should preserve enough information so that syscall_rollback()
95 * can work (see asm-generic/syscall.h).
96 *
97 * Called without locks, just after entering kernel mode.
98 */
99 static inline __must_check int tracehook_report_syscall_entry(
100 struct pt_regs *regs)
101 {
102 return ptrace_report_syscall(regs);
103 }
104
105 /**
106 * tracehook_report_syscall_exit - task has just finished a system call
107 * @regs: user register state of current task
108 * @step: nonzero if simulating single-step or block-step
109 *
110 * This will be called if %TIF_SYSCALL_TRACE has been set, when the
111 * current task has just finished an attempted system call. Full
112 * user register state is available here. It is safe to block here,
113 * preventing signals from being processed.
114 *
115 * If @step is nonzero, this report is also in lieu of the normal
116 * trap that would follow the system call instruction because
117 * user_enable_block_step() or user_enable_single_step() was used.
118 * In this case, %TIF_SYSCALL_TRACE might not be set.
119 *
120 * Called without locks, just before checking for pending signals.
121 */
122 static inline void tracehook_report_syscall_exit(struct pt_regs *regs, int step)
123 {
...
130
131 ptrace_report_syscall(regs);
132 }
/ ptrace_notify：
ptrace_do_notify 55 /*
56 * ptrace report for syscall entry and exit looks identical.
57 */
58 static inline int ptrace_report_syscall(struct pt_regs *regs)
59 {
60 int ptrace = current->ptrace;
61
62 if (!(ptrace & PT_PTRACED))
63 return 0;
64
65 ptrace_notify(SIGTRAP | ((ptrace & PT_TRACESYSGOOD) ? 0x80 : 0));
66
67 /*
68 * this isn't the same as continuing with a signal, but it will do
69 * for normal use. strace only continues with a signal if the
70 * stopping signal is not SIGTRAP. -brl
71 */
72 if (current->exit_code) {
73 send_sig(current->exit_code, current, 1);
74 current->exit_code = 0;
75 }
76
77 return fatal_signal_pending(current);
78 }
在kernel/signal.c中实现，它会停止子进程并将sig_info传递给ptracer：
ptrace_notify 1961 static void ptrace_do_notify(int signr, int exit_code, int why)
1962 {
1963 siginfo_t info;
1964
1965 memset(&info, 0, sizeof info);
1966 info.si_signo = signr;
1967 info.si_code = exit_code;
1968 info.si_pid = task_pid_vnr(current);
1969 info.si_uid = from_kuid_munged(current_user_ns(), current_uid());
1970
1971 /* Let the debugger run. */
1972 ptrace_stop(exit_code, why, 1, &info);
1973 }
1974
1975 void ptrace_notify(int exit_code)
1976 {
1977 BUG_ON((exit_code & (0x7f | ~0xffff)) != SIGTRAP);
1978 if (unlikely(current->task_works))
1979 task_work_run();
1980
1981 spin_lock_irq(¤t->sighand->siglock);
1982 ptrace_do_notify(SIGTRAP, exit_code, CLD_TRAPPED);
1983 spin_unlock_irq(¤t->sighand->siglock);
1984 }
位于同一个ptrace_stop文件中，第1939行为3.13。