UPSTREAM: task_work: Use TIF_NOTIFY_SIGNAL if available

[ Upstream commit 114518eb64 ]

If the arch supports TIF_NOTIFY_SIGNAL, then use that for TWA_SIGNAL as
it's more efficient than using the signal delivery method. This is
especially true on threaded applications, where ->sighand is shared across
threads, but it's also lighter weight on non-shared cases.

io_uring is a heavy consumer of TWA_SIGNAL based task_work. A test with
threads shows a nice improvement running an io_uring based echo server.

stock kernel:
0.01% <= 0.1 milliseconds
95.86% <= 0.2 milliseconds
98.27% <= 0.3 milliseconds
99.71% <= 0.4 milliseconds
100.00% <= 0.5 milliseconds
100.00% <= 0.6 milliseconds
100.00% <= 0.7 milliseconds
100.00% <= 0.8 milliseconds
100.00% <= 0.9 milliseconds
100.00% <= 1.0 milliseconds
100.00% <= 1.1 milliseconds
100.00% <= 2 milliseconds
100.00% <= 3 milliseconds
100.00% <= 3 milliseconds
1378930.00 requests per second
~1600% CPU

1.38M requests/second, and all 16 CPUs are maxed out.

patched kernel:
0.01% <= 0.1 milliseconds
98.24% <= 0.2 milliseconds
99.47% <= 0.3 milliseconds
99.99% <= 0.4 milliseconds
100.00% <= 0.5 milliseconds
100.00% <= 0.6 milliseconds
100.00% <= 0.7 milliseconds
100.00% <= 0.8 milliseconds
100.00% <= 0.9 milliseconds
100.00% <= 1.2 milliseconds
1666111.38 requests per second
~1450% CPU

1.67M requests/second, and we're no longer just hammering on the sighand
lock. The original reporter states:

"For 5.7.15 my benchmark achieves 1.6M qps and system cpu is at ~80%.
 for 5.7.16 or later it achieves only 1M qps and the system cpu is is
 at ~100%"

with the only difference there being that TWA_SIGNAL is used
unconditionally in 5.7.16, since it's required to be able to handle the
inability to run task_work if the application is waiting in the kernel
already on an event that needs task_work run to be satisfied. Also see
commit 0ba9c9edcd.

Reported-by: Roman Gershman <romger@amazon.com>
Change-Id: I80788634e6b91012ebf94e0ab6bf897c99f9f732
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/20201026203230.386348-5-axboe@kernel.dk
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
(cherry picked from commit eb42e7b304)
Bug: 268174392
Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>

kernel/task_work.c

@@ -5,6 +5,34 @@
 
 static struct callback_head work_exited; /* all we need is ->next == NULL */
 
+/*
+ * TWA_SIGNAL signaling - use TIF_NOTIFY_SIGNAL, if available, as it's faster
+ * than TIF_SIGPENDING as there's no dependency on ->sighand. The latter is
+ * shared for threads, and can cause contention on sighand->lock. Even for
+ * the non-threaded case TIF_NOTIFY_SIGNAL is more efficient, as no locking
+ * or IRQ disabling is involved for notification (or running) purposes.
+ */
+static void task_work_notify_signal(struct task_struct *task)
+{
+#if defined(TIF_NOTIFY_SIGNAL)
+	set_notify_signal(task);
+#else
+	unsigned long flags;
+
+	/*
+	 * Only grab the sighand lock if we don't already have some
+	 * task_work pending. This pairs with the smp_store_mb()
+	 * in get_signal(), see comment there.
+	 */
+	if (!(READ_ONCE(task->jobctl) & JOBCTL_TASK_WORK) &&
+	    lock_task_sighand(task, &flags)) {
+		task->jobctl |= JOBCTL_TASK_WORK;
+		signal_wake_up(task, 0);
+		unlock_task_sighand(task, &flags);
+	}
+#endif
+}
+
 /**
  * task_work_add - ask the @task to execute @work->func()
  * @task: the task which should run the callback
@@ -33,7 +61,6 @@ int task_work_add(struct task_struct *task, struct callback_head *work,
 		  enum task_work_notify_mode notify)
 {
 	struct callback_head *head;
-	unsigned long flags;
 
 	/* record the work call stack in order to print it in KASAN reports */
 	kasan_record_aux_stack(work);
@@ -52,17 +79,7 @@ int task_work_add(struct task_struct *task, struct callback_head *work,
 		set_notify_resume(task);
 		break;
 	case TWA_SIGNAL:
-		/*
+		task_work_notify_signal(task);
-		 * Only grab the sighand lock if we don't already have some
-		 * task_work pending. This pairs with the smp_store_mb()
-		 * in get_signal(), see comment there.
-		 */
-		if (!(READ_ONCE(task->jobctl) & JOBCTL_TASK_WORK) &&
-		    lock_task_sighand(task, &flags)) {
-			task->jobctl |= JOBCTL_TASK_WORK;
-			signal_wake_up(task, 0);
-			unlock_task_sighand(task, &flags);
-		}
 		break;
 	default:
 		WARN_ON_ONCE(1);