Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:
 "The main changes are:

   - lockless wakeup support for futexes and IPC message queues
     (Davidlohr Bueso, Peter Zijlstra)

   - Replace spinlocks with atomics in thread_group_cputimer(), to
     improve scalability (Jason Low)

   - NUMA balancing improvements (Rik van Riel)

   - SCHED_DEADLINE improvements (Wanpeng Li)

   - clean up and reorganize preemption helpers (Frederic Weisbecker)

   - decouple page fault disabling machinery from the preemption
     counter, to improve debuggability and robustness (David
     Hildenbrand)

   - SCHED_DEADLINE documentation updates (Luca Abeni)

   - topology CPU masks cleanups (Bartosz Golaszewski)

   - /proc/sched_debug improvements (Srikar Dronamraju)"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (79 commits)
  sched/deadline: Remove needless parameter in dl_runtime_exceeded()
  sched: Remove superfluous resetting of the p->dl_throttled flag
  sched/deadline: Drop duplicate init_sched_dl_class() declaration
  sched/deadline: Reduce rq lock contention by eliminating locking of non-feasible target
  sched/deadline: Make init_sched_dl_class() __init
  sched/deadline: Optimize pull_dl_task()
  sched/preempt: Add static_key() to preempt_notifiers
  sched/preempt: Fix preempt notifiers documentation about hlist_del() within unsafe iteration
  sched/stop_machine: Fix deadlock between multiple stop_two_cpus()
  sched/debug: Add sum_sleep_runtime to /proc/<pid>/sched
  sched/debug: Replace vruntime with wait_sum in /proc/sched_debug
  sched/debug: Properly format runnable tasks in /proc/sched_debug
  sched/numa: Only consider less busy nodes as numa balancing destinations
  Revert 095bebf61a46 ("sched/numa: Do not move past the balance point if unbalanced")
  sched/fair: Prevent throttling in early pick_next_task_fair()
  preempt: Reorganize the notrace definitions a bit
  preempt: Use preempt_schedule_context() as the official tracing preemption point
  sched: Make preempt_schedule_context() function-tracing safe
  x86: Remove cpu_sibling_mask() and cpu_core_mask()
  x86: Replace cpu_**_mask() with topology_**_cpumask()
  ...

1 files changed, 54 insertions, 33 deletions

diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index 0075da74abf0..892e3dae0aac 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -196,39 +196,62 @@ static int cpu_clock_sample(const clockid_t which_clock, struct task_struct *p,
 	return 0;
 }
 
-static void update_gt_cputime(struct task_cputime *a, struct task_cputime *b)
+/*
+ * Set cputime to sum_cputime if sum_cputime > cputime. Use cmpxchg
+ * to avoid race conditions with concurrent updates to cputime.
+ */
+static inline void __update_gt_cputime(atomic64_t *cputime, u64 sum_cputime)
 {
-	if (b->utime > a->utime)
-		a->utime = b->utime;
+	u64 curr_cputime;
+retry:
+	curr_cputime = atomic64_read(cputime);
+	if (sum_cputime > curr_cputime) {
+		if (atomic64_cmpxchg(cputime, curr_cputime, sum_cputime) != curr_cputime)
+			goto retry;
+	}
+}
 
-	if (b->stime > a->stime)
-		a->stime = b->stime;
+static void update_gt_cputime(struct task_cputime_atomic *cputime_atomic, struct task_cputime *sum)
+{
+	__update_gt_cputime(&cputime_atomic->utime, sum->utime);
+	__update_gt_cputime(&cputime_atomic->stime, sum->stime);
+	__update_gt_cputime(&cputime_atomic->sum_exec_runtime, sum->sum_exec_runtime);
+}
 
-	if (b->sum_exec_runtime > a->sum_exec_runtime)
-		a->sum_exec_runtime = b->sum_exec_runtime;
+/* Sample task_cputime_atomic values in "atomic_timers", store results in "times". */
+static inline void sample_cputime_atomic(struct task_cputime *times,
+					 struct task_cputime_atomic *atomic_times)
+{
+	times->utime = atomic64_read(&atomic_times->utime);
+	times->stime = atomic64_read(&atomic_times->stime);
+	times->sum_exec_runtime = atomic64_read(&atomic_times->sum_exec_runtime);
 }
 
 void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times)
 {
 	struct thread_group_cputimer *cputimer = &tsk->signal->cputimer;
 	struct task_cputime sum;
-	unsigned long flags;
 
-	if (!cputimer->running) {
+	/* Check if cputimer isn't running. This is accessed without locking. */
+	if (!READ_ONCE(cputimer->running)) {
 		/*
 		 * The POSIX timer interface allows for absolute time expiry
 		 * values through the TIMER_ABSTIME flag, therefore we have
-		 * to synchronize the timer to the clock every time we start
-		 * it.
+		 * to synchronize the timer to the clock every time we start it.
 		 */
 		thread_group_cputime(tsk, &sum);
-		raw_spin_lock_irqsave(&cputimer->lock, flags);
-		cputimer->running = 1;
-		update_gt_cputime(&cputimer->cputime, &sum);
-	} else
-		raw_spin_lock_irqsave(&cputimer->lock, flags);
-	*times = cputimer->cputime;
-	raw_spin_unlock_irqrestore(&cputimer->lock, flags);
+		update_gt_cputime(&cputimer->cputime_atomic, &sum);
+
+		/*
+		 * We're setting cputimer->running without a lock. Ensure
+		 * this only gets written to in one operation. We set
+		 * running after update_gt_cputime() as a small optimization,
+		 * but barriers are not required because update_gt_cputime()
+		 * can handle concurrent updates.
+		 */
+		WRITE_ONCE(cputimer->running, 1);
+	}
+	sample_cputime_atomic(times, &cputimer->cputime_atomic);
 }
 
 /*
@@ -582,7 +605,8 @@ bool posix_cpu_timers_can_stop_tick(struct task_struct *tsk)
 	if (!task_cputime_zero(&tsk->cputime_expires))
 		return false;
 
-	if (tsk->signal->cputimer.running)
+	/* Check if cputimer is running. This is accessed without locking. */
+	if (READ_ONCE(tsk->signal->cputimer.running))
 		return false;
 
 	return true;
@@ -852,10 +876,10 @@ static void check_thread_timers(struct task_struct *tsk,
 	/*
 	 * Check for the special case thread timers.
 	 */
-	soft = ACCESS_ONCE(sig->rlim[RLIMIT_RTTIME].rlim_cur);
+	soft = READ_ONCE(sig->rlim[RLIMIT_RTTIME].rlim_cur);
 	if (soft != RLIM_INFINITY) {
 		unsigned long hard =
-			ACCESS_ONCE(sig->rlim[RLIMIT_RTTIME].rlim_max);
+			READ_ONCE(sig->rlim[RLIMIT_RTTIME].rlim_max);
 
 		if (hard != RLIM_INFINITY &&
 		    tsk->rt.timeout > DIV_ROUND_UP(hard, USEC_PER_SEC/HZ)) {
@@ -882,14 +906,12 @@ static void check_thread_timers(struct task_struct *tsk,
 	}
 }
 
-static void stop_process_timers(struct signal_struct *sig)
+static inline void stop_process_timers(struct signal_struct *sig)
 {
 	struct thread_group_cputimer *cputimer = &sig->cputimer;
-	unsigned long flags;
 
-	raw_spin_lock_irqsave(&cputimer->lock, flags);
-	cputimer->running = 0;
-	raw_spin_unlock_irqrestore(&cputimer->lock, flags);
+	/* Turn off cputimer->running. This is done without locking. */
+	WRITE_ONCE(cputimer->running, 0);
 }
 
 static u32 onecputick;
@@ -958,11 +980,11 @@ static void check_process_timers(struct task_struct *tsk,
 			 SIGPROF);
 	check_cpu_itimer(tsk, &sig->it[CPUCLOCK_VIRT], &virt_expires, utime,
 			 SIGVTALRM);
-	soft = ACCESS_ONCE(sig->rlim[RLIMIT_CPU].rlim_cur);
+	soft = READ_ONCE(sig->rlim[RLIMIT_CPU].rlim_cur);
 	if (soft != RLIM_INFINITY) {
 		unsigned long psecs = cputime_to_secs(ptime);
 		unsigned long hard =
-			ACCESS_ONCE(sig->rlim[RLIMIT_CPU].rlim_max);
+			READ_ONCE(sig->rlim[RLIMIT_CPU].rlim_max);
 		cputime_t x;
 		if (psecs >= hard) {
 			/*
@@ -1111,12 +1133,11 @@ static inline int fastpath_timer_check(struct task_struct *tsk)
 	}
 
 	sig = tsk->signal;
-	if (sig->cputimer.running) {
+	/* Check if cputimer is running. This is accessed without locking. */
+	if (READ_ONCE(sig->cputimer.running)) {
 		struct task_cputime group_sample;
 
-		raw_spin_lock(&sig->cputimer.lock);
-		group_sample = sig->cputimer.cputime;
-		raw_spin_unlock(&sig->cputimer.lock);
+		sample_cputime_atomic(&group_sample, &sig->cputimer.cputime_atomic);
 
 		if (task_cputime_expired(&group_sample, &sig->cputime_expires))
 			return 1;
@@ -1157,7 +1178,7 @@ void run_posix_cpu_timers(struct task_struct *tsk)
 	 * If there are any active process wide timers (POSIX 1.b, itimers,
 	 * RLIMIT_CPU) cputimer must be running.
 	 */
-	if (tsk->signal->cputimer.running)
+	if (READ_ONCE(tsk->signal->cputimer.running))
 		check_process_timers(tsk, &firing);
 
 	/*