[PATCH v2 1/5] signal: allow taks to temporarily block TIF_NOTIFY_SIGNAL

TIF_NOTIFY_SIGNAL is used to kick a task in uninterruptible sleep to
return to userspace and run task work and then go back to sleep. This
mechanism works well but breaks e.g., coredumps. dump_interrupted() only
allows fatal signals to interrupt a coredump and the whole regular write
path going to actual filesystems is impervious to TIF_NOTIFY_SIGNAL as
well.

Add PF_NO_NOTIFY_SIGNAL and helpers to raise and restore it. This is the
same approach as memalloc_nofs_save(). signal_pending() will not report
a fake pending signal via TIF_NOTIFY_SIGNAL if inside a
PF_NO_NOTIFY_SIGNAL section.

No functional changes.

Cc: [email protected]
Signed-off-by: Christian Brauner (Amutable) <[email protected]>
---
 include/linux/sched.h        |  2 +-
 include/linux/sched/signal.h | 27 +++++++++++++++++++++++++--
 2 files changed, 26 insertions(+), 3 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 3f100d69b053..82b43f20218a 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1807,7 +1807,7 @@ extern struct pid *cad_pid;
 						 * I am cleaning dirty pages from some other bdi. */
 #define PF_KTHREAD		0x00200000	/* I am a kernel thread */
 #define PF_RANDOMIZE		0x00400000	/* Randomize virtual address space */
-#define PF__HOLE__00800000	0x00800000
+#define PF_NO_NOTIFY_SIGNAL	0x00800000	/* see no_notify_signal_save() */
 #define PF__HOLE__01000000	0x01000000
 #define PF__HOLE__02000000	0x02000000
 #define PF_NO_SETAFFINITY	0x04000000	/* Userland is not allowed to meddle with cpus_mask */
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index 584ae88b435e..6164995da980 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -2,6 +2,7 @@
 #ifndef _LINUX_SCHED_SIGNAL_H
 #define _LINUX_SCHED_SIGNAL_H
 
+#include <linux/cleanup.h>
 #include <linux/rculist.h>
 #include <linux/signal.h>
 #include <linux/sched.h>
@@ -384,14 +385,36 @@ static inline int task_sigpending(struct task_struct *p)
 	return unlikely(test_tsk_thread_flag(p,TIF_SIGPENDING));
 }
 
+/* Prevent TIF_NOTIFY_SIGNAL from interrupting this task. */
+static inline unsigned int no_notify_signal_save(void)
+{
+	unsigned int flags = current->flags;
+
+	current->flags |= PF_NO_NOTIFY_SIGNAL;
+	return flags;
+}
+
+/* Restore the previous PF_NO_NOTIFY_SIGNAL state. */
+static inline void no_notify_signal_restore(unsigned int flags)
+{
+	current_restore_flags(flags, PF_NO_NOTIFY_SIGNAL);
+}
+
+DEFINE_LOCK_GUARD_0(no_notify_signal,
+		    _T->flags = no_notify_signal_save(),
+		    no_notify_signal_restore(_T->flags),
+		    unsigned int flags)
+
 static inline int signal_pending(struct task_struct *p)
 {
 	/*
 	 * 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.
+	 * so that notify signal callbacks can be processed. Not for a task
+	 * that asked not to be interrupted by it, see no_notify_signal_save().
 	 */
-	if (unlikely(test_tsk_thread_flag(p, TIF_NOTIFY_SIGNAL)))
+	if (unlikely(test_tsk_thread_flag(p, TIF_NOTIFY_SIGNAL)) &&
+	    likely(!(READ_ONCE(p->flags) & PF_NO_NOTIFY_SIGNAL)))
 		return 1;
 	return task_sigpending(p);
 }

-- 
2.53.0