posix_cpu_timer: Reduce unnecessary sighand lock contention

It was found while running a database workload on large systems that
significant time was spent trying to acquire the sighand lock.

The issue was that whenever an itimer expired, many threads ended up
simultaneously trying to send the signal. Most of the time, nothing
happened after acquiring the sighand lock because another thread
had just already sent the signal and updated the "next expire" time.
The fastpath_timer_check() didn't help much since the "next expire"
time was updated after the threads exit fastpath_timer_check().

This patch addresses this by having the thread_group_cputimer structure
maintain a boolean to signify when a thread in the group is already
checking for process wide timers, and adds extra logic in the fastpath
to check the boolean.

Signed-off-by: Jason Low <jason.low2@hp.com>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Reviewed-by: George Spelvin <linux@horizon.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: hideaki.kimura@hpe.com
Cc: terry.rudd@hpe.com
Cc: scott.norton@hpe.com
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1444849677-29330-5-git-send-email-jason.low2@hp.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

include/linux/init_task.h

@@ -60,6 +60,7 @@ extern struct fs_struct init_fs;
 	.cputimer	= { 						\
 		.cputime_atomic	= INIT_CPUTIME_ATOMIC,			\
 		.running	= false,				\
+		.checking_timer = false,				\
 	},								\
 	INIT_PREV_CPUTIME(sig)						\
 	.cred_guard_mutex =						\

include/linux/sched.h

@@ -619,13 +619,16 @@ struct task_cputime_atomic {
  * @cputime_atomic:	atomic thread group interval timers.
  * @running:		true when there are timers running and
  *			@cputime_atomic receives updates.
+ * @checking_timer:	true when a thread in the group is in the
+ *			process of checking for thread group timers.
  *
  * This structure contains the version of task_cputime, above, that is
  * used for thread group CPU timer calculations.
  */
 struct thread_group_cputimer {
 	struct task_cputime_atomic cputime_atomic;
 	bool running;
+	bool checking_timer;
 };
 
 #include <linux/rwsem.h>

kernel/time/posix-cpu-timers.c

@@ -975,6 +975,12 @@ static void check_process_timers(struct task_struct *tsk,
 	if (!READ_ONCE(tsk->signal->cputimer.running))
 		return;
 
+        /*
+	 * Signify that a thread is checking for process timers.
+	 * Write access to this field is protected by the sighand lock.
+	 */
+	sig->cputimer.checking_timer = true;
+
 	/*
 	 * Collect the current process totals.
 	 */
@@ -1029,6 +1035,8 @@ static void check_process_timers(struct task_struct *tsk,
 	sig->cputime_expires.sched_exp = sched_expires;
 	if (task_cputime_zero(&sig->cputime_expires))
 		stop_process_timers(sig);
+
+	sig->cputimer.checking_timer = false;
 }
 
 /*
@@ -1142,8 +1150,22 @@ static inline int fastpath_timer_check(struct task_struct *tsk)
 	}
 
 	sig = tsk->signal;
-	/* Check if cputimer is running. This is accessed without locking. */
-	if (READ_ONCE(sig->cputimer.running)) {
+	/*
+	 * Check if thread group timers expired when the cputimer is
+	 * running and no other thread in the group is already checking
+	 * for thread group cputimers. These fields are read without the
+	 * sighand lock. However, this is fine because this is meant to
+	 * be a fastpath heuristic to determine whether we should try to
+	 * acquire the sighand lock to check/handle timers.
+	 *
+	 * In the worst case scenario, if 'running' or 'checking_timer' gets
+	 * set but the current thread doesn't see the change yet, we'll wait
+	 * until the next thread in the group gets a scheduler interrupt to
+	 * handle the timer. This isn't an issue in practice because these
+	 * types of delays with signals actually getting sent are expected.
+	 */
+	if (READ_ONCE(sig->cputimer.running) &&
+	    !READ_ONCE(sig->cputimer.checking_timer)) {
 		struct task_cputime group_sample;
 
 		sample_cputime_atomic(&group_sample, &sig->cputimer.cputime_atomic);