sched/fair: Add lsub_positive() and use it consistently

The following pattern:

   var -= min_t(typeof(var), var, val);

is used multiple times in fair.c.

The existing sub_positive() already captures that pattern, but it also
adds an explicit load-store to properly support lockless observations.
In other cases the pattern above is used to update local, and/or not
concurrently accessed, variables.

Let's add a simpler version of sub_positive(), targeted at local variables
updates, which gives the same readability benefits at calling sites,
without enforcing {READ,WRITE}_ONCE() barriers.

Signed-off-by: Patrick Bellasi <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Cc: Dietmar Eggemann <[email protected]>
Cc: Juri Lelli <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Morten Rasmussen <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Quentin Perret <[email protected]>
Cc: Steve Muckle <[email protected]>
Cc: Suren Baghdasaryan <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Todd Kjos <[email protected]>
Cc: Vincent Guittot <[email protected]>
Link: https://lore.kernel.org/lkml/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>

1 files changed, 17 insertions, 7 deletions

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 28ee60cabba1..2cac9a469df4 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2734,6 +2734,17 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	WRITE_ONCE(*ptr, res);					\
 } while (0)
 
+/*
+ * Remove and clamp on negative, from a local variable.
+ *
+ * A variant of sub_positive(), which does not use explicit load-store
+ * and is thus optimized for local variable updates.
+ */
+#define lsub_positive(_ptr, _val) do {				\
+	typeof(_ptr) ptr = (_ptr);				\
+	*ptr -= min_t(typeof(*ptr), *ptr, _val);		\
+} while (0)
+
 #ifdef CONFIG_SMP
 static inline void
 enqueue_runnable_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
@@ -4639,7 +4650,7 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun)
 		cfs_b->distribute_running = 0;
 		throttled = !list_empty(&cfs_b->throttled_cfs_rq);
 
-		cfs_b->runtime -= min(runtime, cfs_b->runtime);
+		lsub_positive(&cfs_b->runtime, runtime);
 	}
 
 	/*
@@ -4773,7 +4784,7 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b)
 
 	raw_spin_lock(&cfs_b->lock);
 	if (expires == cfs_b->runtime_expires)
-		cfs_b->runtime -= min(runtime, cfs_b->runtime);
+		lsub_positive(&cfs_b->runtime, runtime);
 	cfs_b->distribute_running = 0;
 	raw_spin_unlock(&cfs_b->lock);
 }
@@ -6240,7 +6251,7 @@ static unsigned long cpu_util_without(int cpu, struct task_struct *p)
 	util = READ_ONCE(cfs_rq->avg.util_avg);
 
 	/* Discount task's util from CPU's util */
-	util -= min_t(unsigned int, util, task_util(p));
+	lsub_positive(&util, task_util(p));
 
 	/*
 	 * Covered cases:
@@ -6289,10 +6300,9 @@ static unsigned long cpu_util_without(int cpu, struct task_struct *p)
 		 * properly fix the execl regression and it helps in further
 		 * reducing the chances for the above race.
 		 */
-		if (unlikely(task_on_rq_queued(p) || current == p)) {
-			estimated -= min_t(unsigned int, estimated,
-					   _task_util_est(p));
-		}
+		if (unlikely(task_on_rq_queued(p) || current == p))
+			lsub_positive(&estimated, _task_util_est(p));
+
 		util = max(util, estimated);
 	}