###### tags: `Linux` `Signal`

# Signal Handling in Linux
* 好文:
* http://courses.cms.caltech.edu/cs124/lectures-wi2016/CS124Lec15.pdf
* 其他篇筆記:
* https://hackmd.io/@LJP/BJAb95O1c
* 在 `task_struct` 有兩個 member:

/* Signal handlers: */
struct signal_struct        *signal;
struct sighand_struct __rcu *sighand;

* `signal` 用於存放此 task 有哪些 signal 要處理
* 若已經有同一種 signal 正在 pending, 則 signal 會被忽略
* 資料結構是 linked list
* `sighand` 用於紀錄 signal handler
* signal handler 可以是在 kernel 也可以是在 user mode 的
* 資料結構可以想成是 function pointer array
* 處理 signal 的時間點是當 process 準備回到 user mode 時
* 只有會影響到 process state 的 signal 會立即處理 e.g. SIGKILL
* 當 signal handler 位於 user mode 時, 會將 cpu context 存放至 user stack, 並設定 user signal handler 的 return address 呼叫 syscall sigreturn, 此 syscall 再從 user stack 中拿出原本的 cpu context, 以便回到發生 signal 前的狀態

# exit_to_user_mode
* https://elixir.bootlin.com/linux/v5.17.1/source/arch/arm64/kernel/entry-common.c#L137

至於所謂的**處理 signal 的時間點是當 process 準備回到 user mode 時**可以從 `exit_to_user_mode()` 開始看

static __always_inline void exit_to_user_mode(struct pt_regs *regs)
{
    prepare_exit_to_user_mode(regs);
    mte_check_tfsr_exit();
    __exit_to_user_mode();
}

* `prepare_exit_to_user_mode`:

static __always_inline void prepare_exit_to_user_mode(struct pt_regs *regs)
{
	unsigned long flags;

	local_daif_mask();

	flags = read_thread_flags();
	if (unlikely(flags & _TIF_WORK_MASK))
		do_notify_resume(regs, flags);
}

* 當有任何工作還要做的時候, 對應 `_TIF_WORK_MASK` 的 flags 不為 0, 執行 `do_notify_resume`

# do_notify_resume
* https://elixir.bootlin.com/linux/v5.17.1/source/arch/arm64/kernel/signal.c#L920

void do_notify_resume(struct pt_regs *regs, unsigned long thread_flags)
{
	do {
		if (thread_flags & _TIF_NEED_RESCHED) {
			/* Unmask Debug and SError for the next task */
			local_daif_restore(DAIF_PROCCTX_NOIRQ);

			schedule();
		} else {
			local_daif_restore(DAIF_PROCCTX);

			if (thread_flags & _TIF_UPROBE)
				uprobe_notify_resume(regs);

			if (thread_flags & _TIF_MTE_ASYNC_FAULT) {
				clear_thread_flag(TIF_MTE_ASYNC_FAULT);
				send_sig_fault(SIGSEGV, SEGV_MTEAERR,
					       (void __user *)NULL, current);
			}

			if (thread_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL))
				do_signal(regs);

			if (thread_flags & _TIF_NOTIFY_RESUME)
				tracehook_notify_resume(regs);

			if (thread_flags & _TIF_FOREIGN_FPSTATE)
				fpsimd_restore_current_state();
		}

		local_daif_mask();
		thread_flags = read_thread_flags();
	} while (thread_flags & _TIF_WORK_MASK);
}

* 這邊可以看到外層一個迴圈, 表示工作處理完後, 還有可能有其他工作
* 若在這邊 schedule 到其他 process, 之後再 schedule 回來後, 終究還是會在迴圈裡確認工作是否都完成
* 這邊關注 signal 怎麼被處理的, 可以看到 flags `_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL` 如果開啟, 則會執行 `do_signal`
* TODO: 如何處理多個 signal 的狀況?

# do_signal
* https://elixir.bootlin.com/linux/v5.17.1/source/arch/arm64/kernel/signal.c#L849

/*
 * Note that 'init' is a special process: it doesn't get signals it doesn't
 * want to handle. Thus you cannot kill init even with a SIGKILL even by
 * mistake.
 *
 * Note that we go through the signals twice: once to check the signals that
 * the kernel can handle, and then we build all the user-level signal handling
 * stack-frames in one go after that.
 */
static void do_signal(struct pt_regs *regs)
{
	unsigned long continue_addr = 0, restart_addr = 0;
	int retval = 0;
	struct ksignal ksig;
	bool syscall = in_syscall(regs);

	/*
	 * If we were from a system call, check for system call restarting...
	 */
	if (syscall) {
		continue_addr = regs->pc;
		restart_addr = continue_addr - (compat_thumb_mode(regs) ? 2 : 4);
		retval = regs->regs[0];

		/*
		 * Avoid additional syscall restarting via ret_to_user.
		 */
		forget_syscall(regs);

		/*
		 * Prepare for system call restart. We do this here so that a
		 * debugger will see the already changed PC.
		 */
		switch (retval) {
		case -ERESTARTNOHAND:
		case -ERESTARTSYS:
		case -ERESTARTNOINTR:
		case -ERESTART_RESTARTBLOCK:
			regs->regs[0] = regs->orig_x0;
			regs->pc = restart_addr;
			break;
		}
	}

	/*
	 * Get the signal to deliver. When running under ptrace, at this point
	 * the debugger may change all of our registers.
	 */
	if (get_signal(&ksig)) {
		/*
		 * Depending on the signal settings, we may need to revert the
		 * decision to restart the system call, but skip this if a
		 * debugger has chosen to restart at a different PC.
		 */
		if (regs->pc == restart_addr &&
		    (retval == -ERESTARTNOHAND ||
		     retval == -ERESTART_RESTARTBLOCK ||
		     (retval == -ERESTARTSYS &&
		      !(ksig.ka.sa.sa_flags & SA_RESTART)))) {
			syscall_set_return_value(current, regs, -EINTR, 0);
			regs->pc = continue_addr;
		}

		handle_signal(&ksig, regs);
		return;
	}

	/*
	 * Handle restarting a different system call. As above, if a debugger
	 * has chosen to restart at a different PC, ignore the restart.
	 */
	if (syscall && regs->pc == restart_addr) {
		if (retval == -ERESTART_RESTARTBLOCK)
			setup_restart_syscall(regs);
		user_rewind_single_step(current);
	}

	restore_saved_sigmask();
}

* 如果要處理 signal 時的 process 是在 syscall 中, 則有不同的處理方式
* `get_signal` 爬出下一個要處理的 signal
* 呼叫 `handle_signal`

# handle_signal
* https://elixir.bootlin.com/linux/v5.17.1/source/arch/arm64/kernel/signal.c#L849

/*
 * OK, we're invoking a handler
 */
static void handle_signal(struct ksignal *ksig, struct pt_regs *regs)
{
	sigset_t *oldset = sigmask_to_save();
	int usig = ksig->sig;
	int ret;

	rseq_signal_deliver(ksig, regs);

	/*
	 * Set up the stack frame
	 */
	if (is_compat_task()) {
		if (ksig->ka.sa.sa_flags & SA_SIGINFO)
			ret = compat_setup_rt_frame(usig, ksig, oldset, regs);
		else
			ret = compat_setup_frame(usig, ksig, oldset, regs);
	} else {
		ret = setup_rt_frame(usig, ksig, oldset, regs);
	}

	/*
	 * Check that the resulting registers are actually sane.
	 */
	ret |= !valid_user_regs(&regs->user_regs, current);

	/* Step into the signal handler if we are stepping */
	signal_setup_done(ret, ksig, test_thread_flag(TIF_SINGLESTEP));
}

* `setup_rt_frame` 做了主要的設定

# setup_rt_frame

static int setup_rt_frame(int usig, struct ksignal *ksig, sigset_t *set,
			  struct pt_regs *regs)
{
	struct rt_sigframe_user_layout user;
	struct rt_sigframe __user *frame;
	int err = 0;

	fpsimd_signal_preserve_current_state();

	if (get_sigframe(&user, ksig, regs))
		return 1;

	frame = user.sigframe;

	__put_user_error(0, &frame->uc.uc_flags, err);
	__put_user_error(NULL, &frame->uc.uc_link, err);

	err |= __save_altstack(&frame->uc.uc_stack, regs->sp);
	err |= setup_sigframe(&user, regs, set);
	if (err == 0) {
		setup_return(regs, &ksig->ka, &user, usig);
		if (ksig->ka.sa.sa_flags & SA_SIGINFO) {
			err |= copy_siginfo_to_user(&frame->info, &ksig->info);
			regs->regs[1] = (unsigned long)&frame->info;
			regs->regs[2] = (unsigned long)&frame->uc;
		}
	}

	return err;
}

* 設定 user stack frame, 將 cpu context 存放上去, 設定返回位址為 sigreturn
* `setup_return` 調整了待會回到 user mode 時的 user sp, 並將 user pc 設定為 user mode signal handler 位址
* 根據 signal handler flags 來決定傳參數給 signal handler 是傳 1 個還是 3 個
* 至此都設定完成, 等待返回到最上層函數後, return to user mode 就會處理 signal

# syscall kill
* https://elixir.bootlin.com/linux/v5.17.5/source/kernel/signal.c#L3773
* 前面關注的是在什麼時機點處理 signal
* 接下來關注看看從送 signal 的角度, 發生什麼事

/**
 *  sys_kill - send a signal to a process
 *  @pid: the PID of the process
 *  @sig: signal to be sent
 */
SYSCALL_DEFINE2(kill, pid_t, pid, int, sig)
{
	struct kernel_siginfo info;

	prepare_kill_siginfo(sig, &info);

	return kill_something_info(sig, &info, pid);
}

# kill_something_info
* https://elixir.bootlin.com/linux/v5.17.5/source/kernel/signal.c#L1588

/*
 * kill_something_info() interprets pid in interesting ways just like kill(2).
 *
 * POSIX specifies that kill(-1,sig) is unspecified, but what we have
 * is probably wrong.  Should make it like BSD or SYSV.
 */

static int kill_something_info(int sig, struct kernel_siginfo *info, pid_t pid)
{
	int ret;

	if (pid > 0)
		return kill_proc_info(sig, info, pid);

	/* -INT_MIN is undefined.  Exclude this case to avoid a UBSAN warning */
	if (pid == INT_MIN)
		return -ESRCH;

	read_lock(&tasklist_lock);
	if (pid != -1) {
		ret = __kill_pgrp_info(sig, info,
				pid ? find_vpid(-pid) : task_pgrp(current));
	} else {
		int retval = 0, count = 0;
		struct task_struct * p;

		for_each_process(p) {
			if (task_pid_vnr(p) > 1 &&
					!same_thread_group(p, current)) {
				int err = group_send_sig_info(sig, info, p,
							      PIDTYPE_MAX);
				++count;
				if (err != -EPERM)
					retval = err;
			}
		}
		ret = count ? retval : -ESRCH;
	}
	read_unlock(&tasklist_lock);

	return ret;
}

* 根據 pid 不同, 對象 process 不同
* 這邊先假設 pid 大於 0, 就是送 signal 給 pid process

# kill_proc_info
* https://elixir.bootlin.com/linux/v5.17.5/source/kernel/signal.c#L1492

static int kill_proc_info(int sig, struct kernel_siginfo *info, pid_t pid)
{
	int error;
	rcu_read_lock();
	error = kill_pid_info(sig, info, find_vpid(pid));
	rcu_read_unlock();
	return error;
}

int kill_pid_info(int sig, struct kernel_siginfo *info, struct pid *pid)
{
	int error = -ESRCH;
	struct task_struct *p;

	for (;;) {
		rcu_read_lock();
		p = pid_task(pid, PIDTYPE_PID);
		if (p)
			error = group_send_sig_info(sig, info, p, PIDTYPE_TGID);
		rcu_read_unlock();
		if (likely(!p || error != -ESRCH))
			return error;

		/*
		 * The task was unhashed in between, try again.  If it
		 * is dead, pid_task() will return NULL, if we race with
		 * de_thread() it will find the new leader.
		 */
	}
}

/*
 * send signal info to all the members of a group
 */
int group_send_sig_info(int sig, struct kernel_siginfo *info,
			struct task_struct *p, enum pid_type type)
{
	int ret;

	rcu_read_lock();
	ret = check_kill_permission(sig, info, p);
	rcu_read_unlock();

	if (!ret && sig)
		ret = do_send_sig_info(sig, info, p, type);

	return ret;
}

/*
 * Bad permissions for sending the signal
 * - the caller must hold the RCU read lock
 */
static int check_kill_permission(int sig, struct kernel_siginfo *info,
				 struct task_struct *t)
{
	struct pid *sid;
	int error;

	if (!valid_signal(sig))
		return -EINVAL;

	if (!si_fromuser(info))
		return 0;

	error = audit_signal_info(sig, t); /* Let audit system see the signal */
	if (error)
		return error;

	if (!same_thread_group(current, t) &&
	    !kill_ok_by_cred(t)) {
		switch (sig) {
		case SIGCONT:
			sid = task_session(t);
			/*
			 * We don't return the error if sid == NULL. The
			 * task was unhashed, the caller must notice this.
			 */
			if (!sid || sid == task_session(current))
				break;
			fallthrough;
		default:
			return -EPERM;
		}
	}

	return security_task_kill(t, info, sig, NULL);
}

* `valid_signal()` 檢查 signal number 有無超出範圍

int do_send_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *p,
			enum pid_type type)
{
	unsigned long flags;
	int ret = -ESRCH;

	if (lock_task_sighand(p, &flags)) {
		ret = send_signal(sig, info, p, type);
		unlock_task_sighand(p, &flags);
	}

	return ret;
}

static int send_signal(int sig, struct kernel_siginfo *info, struct task_struct *t,
			enum pid_type type)
{
	/* Should SIGKILL or SIGSTOP be received by a pid namespace init? */
	bool force = false;

	if (info == SEND_SIG_NOINFO) {
		/* Force if sent from an ancestor pid namespace */
		force = !task_pid_nr_ns(current, task_active_pid_ns(t));
	} else if (info == SEND_SIG_PRIV) {
		/* Don't ignore kernel generated signals */
		force = true;
	} else if (has_si_pid_and_uid(info)) {
		/* SIGKILL and SIGSTOP is special or has ids */
		struct user_namespace *t_user_ns;

		rcu_read_lock();
		t_user_ns = task_cred_xxx(t, user_ns);
		if (current_user_ns() != t_user_ns) {
			kuid_t uid = make_kuid(current_user_ns(), info->si_uid);
			info->si_uid = from_kuid_munged(t_user_ns, uid);
		}
		rcu_read_unlock();

		/* A kernel generated signal? */
		force = (info->si_code == SI_KERNEL);

		/* From an ancestor pid namespace? */
		if (!task_pid_nr_ns(current, task_active_pid_ns(t))) {
			info->si_pid = 0;
			force = true;
		}
	}
	return __send_signal(sig, info, t, type, force);
}

static int __send_signal(int sig, struct kernel_siginfo *info, struct task_struct *t,
			enum pid_type type, bool force)
{
	struct sigpending *pending;
	struct sigqueue *q;
	int override_rlimit;
	int ret = 0, result;

	assert_spin_locked(&t->sighand->siglock);

	result = TRACE_SIGNAL_IGNORED;
	if (!prepare_signal(sig, t, force))
		goto ret;

	pending = (type != PIDTYPE_PID) ? &t->signal->shared_pending : &t->pending;
	/*
	 * Short-circuit ignored signals and support queuing
	 * exactly one non-rt signal, so that we can get more
	 * detailed information about the cause of the signal.
	 */
	result = TRACE_SIGNAL_ALREADY_PENDING;
	if (legacy_queue(pending, sig))
		goto ret;

	result = TRACE_SIGNAL_DELIVERED;
	/*
	 * Skip useless siginfo allocation for SIGKILL and kernel threads.
	 */
	if ((sig == SIGKILL) || (t->flags & PF_KTHREAD))
		goto out_set;

	/*
	 * Real-time signals must be queued if sent by sigqueue, or
	 * some other real-time mechanism.  It is implementation
	 * defined whether kill() does so.  We attempt to do so, on
	 * the principle of least surprise, but since kill is not
	 * allowed to fail with EAGAIN when low on memory we just
	 * make sure at least one signal gets delivered and don't
	 * pass on the info struct.
	 */
	if (sig < SIGRTMIN)
		override_rlimit = (is_si_special(info) || info->si_code >= 0);
	else
		override_rlimit = 0;

	q = __sigqueue_alloc(sig, t, GFP_ATOMIC, override_rlimit, 0);

	if (q) {
		list_add_tail(&q->list, &pending->list);
		switch ((unsigned long) info) {
		case (unsigned long) SEND_SIG_NOINFO:
			clear_siginfo(&q->info);
			q->info.si_signo = sig;
			q->info.si_errno = 0;
			q->info.si_code = SI_USER;
			q->info.si_pid = task_tgid_nr_ns(current,
							task_active_pid_ns(t));
			rcu_read_lock();
			q->info.si_uid =
				from_kuid_munged(task_cred_xxx(t, user_ns),
						 current_uid());
			rcu_read_unlock();
			break;
		case (unsigned long) SEND_SIG_PRIV:
			clear_siginfo(&q->info);
			q->info.si_signo = sig;
			q->info.si_errno = 0;
			q->info.si_code = SI_KERNEL;
			q->info.si_pid = 0;
			q->info.si_uid = 0;
			break;
		default:
			copy_siginfo(&q->info, info);
			break;
		}
	} else if (!is_si_special(info) &&
		   sig >= SIGRTMIN && info->si_code != SI_USER) {
		/*
		 * Queue overflow, abort.  We may abort if the
		 * signal was rt and sent by user using something
		 * other than kill().
		 */
		result = TRACE_SIGNAL_OVERFLOW_FAIL;
		ret = -EAGAIN;
		goto ret;
	} else {
		/*
		 * This is a silent loss of information.  We still
		 * send the signal, but the *info bits are lost.
		 */
		result = TRACE_SIGNAL_LOSE_INFO;
	}

out_set:
	signalfd_notify(t, sig);
	sigaddset(&pending->signal, sig);

	/* Let multiprocess signals appear after on-going forks */
	if (type > PIDTYPE_TGID) {
		struct multiprocess_signals *delayed;
		hlist_for_each_entry(delayed, &t->signal->multiprocess, node) {
			sigset_t *signal = &delayed->signal;
			/* Can't queue both a stop and a continue signal */
			if (sig == SIGCONT)
				sigdelsetmask(signal, SIG_KERNEL_STOP_MASK);
			else if (sig_kernel_stop(sig))
				sigdelset(signal, SIGCONT);
			sigaddset(signal, sig);
		}
	}

	complete_signal(sig, t, type);
ret:
	trace_signal_generate(sig, info, t, type != PIDTYPE_PID, result);
	return ret;
}