Merge branch 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm…

…/linux/kernel/git/tip/tip Pull scheduler fixes from Ingo Molnar: "Two fixes: a guest-cputime accounting fix, and a cgroup bandwidth quota precision fix" * 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: sched/vtime: Fix guest/system mis-accounting on task switch sched/fair: Scale bandwidth quota and period without losing quota/period ratio precision
kawasaki · Oct 12, 2019 · 328fefa · 328fefa
2 parents 465a7e2 + 68e7a4d
commit 328fefa
Show file tree

Hide file tree

Showing 2 changed files with 25 additions and 17 deletions.
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
@@ -740,7 +740,7 @@ void vtime_account_system(struct task_struct *tsk)
 
 	write_seqcount_begin(&vtime->seqcount);
 	/* We might have scheduled out from guest path */
-	if (current->flags & PF_VCPU)
+	if (tsk->flags & PF_VCPU)
 		vtime_account_guest(tsk, vtime);
 	else
 		__vtime_account_system(tsk, vtime);
@@ -783,7 +783,7 @@ void vtime_guest_enter(struct task_struct *tsk)
 	 */
 	write_seqcount_begin(&vtime->seqcount);
 	__vtime_account_system(tsk, vtime);
-	current->flags |= PF_VCPU;
+	tsk->flags |= PF_VCPU;
 	write_seqcount_end(&vtime->seqcount);
 }
 EXPORT_SYMBOL_GPL(vtime_guest_enter);
@@ -794,7 +794,7 @@ void vtime_guest_exit(struct task_struct *tsk)
 
 	write_seqcount_begin(&vtime->seqcount);
 	vtime_account_guest(tsk, vtime);
-	current->flags &= ~PF_VCPU;
+	tsk->flags &= ~PF_VCPU;
 	write_seqcount_end(&vtime->seqcount);
 }
 EXPORT_SYMBOL_GPL(vtime_guest_exit);

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
@@ -4926,20 +4926,28 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer)
 		if (++count > 3) {
 			u64 new, old = ktime_to_ns(cfs_b->period);
 
-			new = (old * 147) / 128; /* ~115% */
-			new = min(new, max_cfs_quota_period);
-
-			cfs_b->period = ns_to_ktime(new);
-
-			/* since max is 1s, this is limited to 1e9^2, which fits in u64 */
-			cfs_b->quota *= new;
-			cfs_b->quota = div64_u64(cfs_b->quota, old);
-
-			pr_warn_ratelimited(
-	"cfs_period_timer[cpu%d]: period too short, scaling up (new cfs_period_us %lld, cfs_quota_us = %lld)\n",
-				smp_processor_id(),
-				div_u64(new, NSEC_PER_USEC),
-				div_u64(cfs_b->quota, NSEC_PER_USEC));
+			/*
+			 * Grow period by a factor of 2 to avoid losing precision.
+			 * Precision loss in the quota/period ratio can cause __cfs_schedulable
+			 * to fail.
+			 */
+			new = old * 2;
+			if (new < max_cfs_quota_period) {
+				cfs_b->period = ns_to_ktime(new);
+				cfs_b->quota *= 2;
+
+				pr_warn_ratelimited(
+	"cfs_period_timer[cpu%d]: period too short, scaling up (new cfs_period_us = %lld, cfs_quota_us = %lld)\n",
+					smp_processor_id(),
+					div_u64(new, NSEC_PER_USEC),
+					div_u64(cfs_b->quota, NSEC_PER_USEC));
+			} else {
+				pr_warn_ratelimited(
+	"cfs_period_timer[cpu%d]: period too short, but cannot scale up without losing precision (cfs_period_us = %lld, cfs_quota_us = %lld)\n",
+					smp_processor_id(),
+					div_u64(old, NSEC_PER_USEC),
+					div_u64(cfs_b->quota, NSEC_PER_USEC));
+			}
 
 			/* reset count so we don't come right back in here */
 			count = 0;