entry: Add support for TIF_NOTIFY_SIGNAL

Add TIF_NOTIFY_SIGNAL handling in the generic entry code, which if set,
will return true if signal_pending() is used in a wait loop. That causes an
exit of the loop so that notify_signal tracehooks can be run. If the wait
loop is currently inside a system call, the system call is restarted once
task_work has been processed.

In preparation for only having arch_do_signal() handle syscall restarts if
_TIF_SIGPENDING isn't set, rename it to arch_do_signal_or_restart().  Pass
in a boolean that tells the architecture specific signal handler if it
should attempt to get a signal, or just process a potential syscall
restart.

For !CONFIG_GENERIC_ENTRY archs, add the TIF_NOTIFY_SIGNAL handling to
get_signal(). This is done to minimize the needed architecture changes to
support this feature.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Link: https://lore.kernel.org/r/20201026203230.386348-3-axboe@kernel.dk

4 files changed, 47 insertions, 6 deletions

diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h
index efebbffcd5cc..c7bfac45f951 100644
--- a/include/linux/entry-common.h
+++ b/include/linux/entry-common.h
@@ -37,6 +37,10 @@
 # define _TIF_UPROBE			(0)
 #endif
 
+#ifndef _TIF_NOTIFY_SIGNAL
+# define _TIF_NOTIFY_SIGNAL		(0)
+#endif
+
 /*
  * TIF flags handled in syscall_enter_from_usermode()
  */
@@ -69,7 +73,7 @@
 
 #define EXIT_TO_USER_MODE_WORK						\
 	(_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_UPROBE |		\
-	 _TIF_NEED_RESCHED | _TIF_PATCH_PENDING |			\
+	 _TIF_NEED_RESCHED | _TIF_PATCH_PENDING | _TIF_NOTIFY_SIGNAL |	\
 	 ARCH_EXIT_TO_USER_MODE_WORK)
 
 /**
@@ -226,12 +230,13 @@ static __always_inline void arch_exit_to_user_mode(void) { }
 #endif
 
 /**
- * arch_do_signal -  Architecture specific signal delivery function
+ * arch_do_signal_or_restart -  Architecture specific signal delivery function
  * @regs:	Pointer to currents pt_regs
+ * @has_signal:	actual signal to handle
  *
  * Invoked from exit_to_user_mode_loop().
  */
-void arch_do_signal(struct pt_regs *regs);
+void arch_do_signal_or_restart(struct pt_regs *regs, bool has_signal);
 
 /**
  * arch_syscall_exit_tracehook - Wrapper around tracehook_report_syscall_exit()
diff --git a/include/linux/entry-kvm.h b/include/linux/entry-kvm.h
index 0cef17afb41a..9b93f8584ff7 100644
--- a/include/linux/entry-kvm.h
+++ b/include/linux/entry-kvm.h
@@ -11,8 +11,8 @@
 # define ARCH_XFER_TO_GUEST_MODE_WORK	(0)
 #endif
 
-#define XFER_TO_GUEST_MODE_WORK					\
-	(_TIF_NEED_RESCHED | _TIF_SIGPENDING |			\
+#define XFER_TO_GUEST_MODE_WORK						\
+	(_TIF_NEED_RESCHED | _TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL |	\
 	 _TIF_NOTIFY_RESUME | ARCH_XFER_TO_GUEST_MODE_WORK)
 
 struct kvm_vcpu;
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index 404145dc536e..bd5afa076189 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -360,6 +360,15 @@ static inline int task_sigpending(struct task_struct *p)
 
 static inline int signal_pending(struct task_struct *p)
 {
+#if defined(TIF_NOTIFY_SIGNAL)
+	/*
+	 * TIF_NOTIFY_SIGNAL isn't really a signal, but it requires the same
+	 * behavior in terms of ensuring that we break out of wait loops
+	 * so that notify signal callbacks can be processed.
+	 */
+	if (unlikely(test_tsk_thread_flag(p, TIF_NOTIFY_SIGNAL)))
+		return 1;
+#endif
 	return task_sigpending(p);
 }
 
@@ -507,7 +516,7 @@ extern int set_user_sigmask(const sigset_t __user *umask, size_t sigsetsize);
 static inline void restore_saved_sigmask_unless(bool interrupted)
 {
 	if (interrupted)
-		WARN_ON(!test_thread_flag(TIF_SIGPENDING));
+		WARN_ON(!signal_pending(current));
 	else
 		restore_saved_sigmask();
 }
diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h
index 36fb3bbed6b2..1e8caca92e1f 100644
--- a/include/linux/tracehook.h
+++ b/include/linux/tracehook.h
@@ -198,4 +198,31 @@ static inline void tracehook_notify_resume(struct pt_regs *regs)
 	blkcg_maybe_throttle_current();
 }
 
+/*
+ * called by exit_to_user_mode_loop() if ti_work & _TIF_NOTIFY_SIGNAL. This
+ * is currently used by TWA_SIGNAL based task_work, which requires breaking
+ * wait loops to ensure that task_work is noticed and run.
+ */
+static inline void tracehook_notify_signal(void)
+{
+#if defined(TIF_NOTIFY_SIGNAL)
+	clear_thread_flag(TIF_NOTIFY_SIGNAL);
+	smp_mb__after_atomic();
+	if (current->task_works)
+		task_work_run();
+#endif
+}
+
+/*
+ * Called when we have work to process from exit_to_user_mode_loop()
+ */
+static inline void set_notify_signal(struct task_struct *task)
+{
+#if defined(TIF_NOTIFY_SIGNAL)
+	if (!test_and_set_tsk_thread_flag(task, TIF_NOTIFY_SIGNAL) &&
+	    !wake_up_state(task, TASK_INTERRUPTIBLE))
+		kick_process(task);
+#endif
+}
+
 #endif	/* <linux/tracehook.h> */