summaryrefslogtreecommitdiffstats
path: root/debian/patches-rt/0032-sched-Add-support-for-lazy-preemption.patch
blob: 59d1a3cba9525a8d4c3d368d22e140ad0f6bf491 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
From 9ee683f4f85373204d8fd50d4ac8f6ab8154cf4b Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Fri, 26 Oct 2012 18:50:54 +0100
Subject: [PATCH 32/64] sched: Add support for lazy preemption
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.1/older/patches-6.1.82-rt27.tar.xz

It has become an obsession to mitigate the determinism vs. throughput
loss of RT. Looking at the mainline semantics of preemption points
gives a hint why RT sucks throughput wise for ordinary SCHED_OTHER
tasks. One major issue is the wakeup of tasks which are right away
preempting the waking task while the waking task holds a lock on which
the woken task will block right after having preempted the wakee. In
mainline this is prevented due to the implicit preemption disable of
spin/rw_lock held regions. On RT this is not possible due to the fully
preemptible nature of sleeping spinlocks.

Though for a SCHED_OTHER task preempting another SCHED_OTHER task this
is really not a correctness issue. RT folks are concerned about
SCHED_FIFO/RR tasks preemption and not about the purely fairness
driven SCHED_OTHER preemption latencies.

So I introduced a lazy preemption mechanism which only applies to
SCHED_OTHER tasks preempting another SCHED_OTHER task. Aside of the
existing preempt_count each tasks sports now a preempt_lazy_count
which is manipulated on lock acquiry and release. This is slightly
incorrect as for lazyness reasons I coupled this on
migrate_disable/enable so some other mechanisms get the same treatment
(e.g. get_cpu_light).

Now on the scheduler side instead of setting NEED_RESCHED this sets
NEED_RESCHED_LAZY in case of a SCHED_OTHER/SCHED_OTHER preemption and
therefor allows to exit the waking task the lock held region before
the woken task preempts. That also works better for cross CPU wakeups
as the other side can stay in the adaptive spinning loop.

For RT class preemption there is no change. This simply sets
NEED_RESCHED and forgoes the lazy preemption counter.

 Initial test do not expose any observable latency increasement, but
history shows that I've been proven wrong before :)

The lazy preemption mode is per default on, but with
CONFIG_SCHED_DEBUG enabled it can be disabled via:

 # echo NO_PREEMPT_LAZY >/sys/kernel/debug/sched_features

and reenabled via

 # echo PREEMPT_LAZY >/sys/kernel/debug/sched_features

The test results so far are very machine and workload dependent, but
there is a clear trend that it enhances the non RT workload
performance.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/preempt.h      | 54 ++++++++++++++++++++++--
 include/linux/sched.h        | 37 +++++++++++++++++
 include/linux/thread_info.h  | 12 +++++-
 include/linux/trace_events.h | 10 ++++-
 kernel/Kconfig.preempt       |  6 +++
 kernel/sched/core.c          | 79 +++++++++++++++++++++++++++++++++++-
 kernel/sched/fair.c          | 16 ++++----
 kernel/sched/features.h      |  3 ++
 kernel/sched/sched.h         |  9 ++++
 kernel/trace/trace.c         | 50 ++++++++++++++---------
 kernel/trace/trace_events.c  |  1 +
 kernel/trace/trace_output.c  | 18 +++++++-
 12 files changed, 260 insertions(+), 35 deletions(-)

diff --git a/include/linux/preempt.h b/include/linux/preempt.h
index 9aa6358a1a16..e9f0d08733f4 100644
--- a/include/linux/preempt.h
+++ b/include/linux/preempt.h
@@ -208,6 +208,20 @@ extern void preempt_count_sub(int val);
 #define preempt_count_inc() preempt_count_add(1)
 #define preempt_count_dec() preempt_count_sub(1)
 
+#ifdef CONFIG_PREEMPT_LAZY
+#define add_preempt_lazy_count(val)	do { preempt_lazy_count() += (val); } while (0)
+#define sub_preempt_lazy_count(val)	do { preempt_lazy_count() -= (val); } while (0)
+#define inc_preempt_lazy_count()	add_preempt_lazy_count(1)
+#define dec_preempt_lazy_count()	sub_preempt_lazy_count(1)
+#define preempt_lazy_count()		(current_thread_info()->preempt_lazy_count)
+#else
+#define add_preempt_lazy_count(val)	do { } while (0)
+#define sub_preempt_lazy_count(val)	do { } while (0)
+#define inc_preempt_lazy_count()	do { } while (0)
+#define dec_preempt_lazy_count()	do { } while (0)
+#define preempt_lazy_count()		(0)
+#endif
+
 #ifdef CONFIG_PREEMPT_COUNT
 
 #define preempt_disable() \
@@ -216,6 +230,12 @@ do { \
 	barrier(); \
 } while (0)
 
+#define preempt_lazy_disable() \
+do { \
+	inc_preempt_lazy_count(); \
+	barrier(); \
+} while (0)
+
 #define sched_preempt_enable_no_resched() \
 do { \
 	barrier(); \
@@ -247,6 +267,18 @@ do { \
 		__preempt_schedule(); \
 } while (0)
 
+/*
+ * open code preempt_check_resched() because it is not exported to modules and
+ * used by local_unlock() or bpf_enable_instrumentation().
+ */
+#define preempt_lazy_enable() \
+do { \
+	dec_preempt_lazy_count(); \
+	barrier(); \
+	if (should_resched(0)) \
+		__preempt_schedule(); \
+} while (0)
+
 #else /* !CONFIG_PREEMPTION */
 #define preempt_enable() \
 do { \
@@ -254,6 +286,12 @@ do { \
 	preempt_count_dec(); \
 } while (0)
 
+#define preempt_lazy_enable() \
+do { \
+	dec_preempt_lazy_count(); \
+	barrier(); \
+} while (0)
+
 #define preempt_enable_notrace() \
 do { \
 	barrier(); \
@@ -294,6 +332,9 @@ do { \
 #define preempt_enable_notrace()		barrier()
 #define preemptible()				0
 
+#define preempt_lazy_disable()			barrier()
+#define preempt_lazy_enable()			barrier()
+
 #endif /* CONFIG_PREEMPT_COUNT */
 
 #ifdef MODULE
@@ -312,7 +353,7 @@ do { \
 } while (0)
 #define preempt_fold_need_resched() \
 do { \
-	if (tif_need_resched()) \
+	if (tif_need_resched_now()) \
 		set_preempt_need_resched(); \
 } while (0)
 
@@ -428,8 +469,15 @@ extern void migrate_enable(void);
 
 #else
 
-static inline void migrate_disable(void) { }
-static inline void migrate_enable(void) { }
+static inline void migrate_disable(void)
+{
+	preempt_lazy_disable();
+}
+
+static inline void migrate_enable(void)
+{
+	preempt_lazy_enable();
+}
 
 #endif /* CONFIG_SMP */
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 0cac69902ec5..67ec36dbfacf 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2061,6 +2061,43 @@ static inline int test_tsk_need_resched(struct task_struct *tsk)
 	return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED));
 }
 
+#ifdef CONFIG_PREEMPT_LAZY
+static inline void set_tsk_need_resched_lazy(struct task_struct *tsk)
+{
+	set_tsk_thread_flag(tsk,TIF_NEED_RESCHED_LAZY);
+}
+
+static inline void clear_tsk_need_resched_lazy(struct task_struct *tsk)
+{
+	clear_tsk_thread_flag(tsk,TIF_NEED_RESCHED_LAZY);
+}
+
+static inline int test_tsk_need_resched_lazy(struct task_struct *tsk)
+{
+	return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED_LAZY));
+}
+
+static inline int need_resched_lazy(void)
+{
+	return test_thread_flag(TIF_NEED_RESCHED_LAZY);
+}
+
+static inline int need_resched_now(void)
+{
+	return test_thread_flag(TIF_NEED_RESCHED);
+}
+
+#else
+static inline void clear_tsk_need_resched_lazy(struct task_struct *tsk) { }
+static inline int need_resched_lazy(void) { return 0; }
+
+static inline int need_resched_now(void)
+{
+	return test_thread_flag(TIF_NEED_RESCHED);
+}
+
+#endif
+
 /*
  * cond_resched() and cond_resched_lock(): latency reduction via
  * explicit rescheduling in places that are safe. The return
diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h
index 9f392ec76f2b..779e0e96b9cb 100644
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -177,7 +177,17 @@ static __always_inline unsigned long read_ti_thread_flags(struct thread_info *ti
 	clear_ti_thread_flag(task_thread_info(t), TIF_##fl)
 #endif /* !CONFIG_GENERIC_ENTRY */
 
-#define tif_need_resched() test_thread_flag(TIF_NEED_RESCHED)
+#ifdef CONFIG_PREEMPT_LAZY
+#define tif_need_resched()	(test_thread_flag(TIF_NEED_RESCHED) || \
+				 test_thread_flag(TIF_NEED_RESCHED_LAZY))
+#define tif_need_resched_now()	(test_thread_flag(TIF_NEED_RESCHED))
+#define tif_need_resched_lazy()	test_thread_flag(TIF_NEED_RESCHED_LAZY)
+
+#else
+#define tif_need_resched()	test_thread_flag(TIF_NEED_RESCHED)
+#define tif_need_resched_now()	test_thread_flag(TIF_NEED_RESCHED)
+#define tif_need_resched_lazy()	0
+#endif
 
 #ifndef CONFIG_HAVE_ARCH_WITHIN_STACK_FRAMES
 static inline int arch_within_stack_frames(const void * const stack,
diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index c8b5e9781d01..743b1183d184 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -70,6 +70,7 @@ struct trace_entry {
 	unsigned char		flags;
 	unsigned char		preempt_count;
 	int			pid;
+	unsigned char		preempt_lazy_count;
 };
 
 #define TRACE_EVENT_TYPE_MAX						\
@@ -159,9 +160,10 @@ static inline void tracing_generic_entry_update(struct trace_entry *entry,
 						unsigned int trace_ctx)
 {
 	entry->preempt_count		= trace_ctx & 0xff;
+	entry->preempt_lazy_count	= (trace_ctx >> 16) & 0xff;
 	entry->pid			= current->pid;
 	entry->type			= type;
-	entry->flags =			trace_ctx >> 16;
+	entry->flags			= trace_ctx >> 24;
 }
 
 unsigned int tracing_gen_ctx_irq_test(unsigned int irqs_status);
@@ -172,7 +174,13 @@ enum trace_flag_type {
 	TRACE_FLAG_NEED_RESCHED		= 0x04,
 	TRACE_FLAG_HARDIRQ		= 0x08,
 	TRACE_FLAG_SOFTIRQ		= 0x10,
+#ifdef CONFIG_PREEMPT_LAZY
+	TRACE_FLAG_PREEMPT_RESCHED	= 0x00,
+	TRACE_FLAG_NEED_RESCHED_LAZY	= 0x20,
+#else
+	TRACE_FLAG_NEED_RESCHED_LAZY	= 0x00,
 	TRACE_FLAG_PREEMPT_RESCHED	= 0x20,
+#endif
 	TRACE_FLAG_NMI			= 0x40,
 	TRACE_FLAG_BH_OFF		= 0x80,
 };
diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt
index c2f1fd95a821..260c08efeb48 100644
--- a/kernel/Kconfig.preempt
+++ b/kernel/Kconfig.preempt
@@ -1,5 +1,11 @@
 # SPDX-License-Identifier: GPL-2.0-only
 
+config HAVE_PREEMPT_LAZY
+	bool
+
+config PREEMPT_LAZY
+	def_bool y if HAVE_PREEMPT_LAZY && PREEMPT_RT
+
 config PREEMPT_NONE_BUILD
 	bool
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 6bd06122850a..b72fc7d336e4 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1040,6 +1040,46 @@ void resched_curr(struct rq *rq)
 		trace_sched_wake_idle_without_ipi(cpu);
 }
 
+#ifdef CONFIG_PREEMPT_LAZY
+
+static int tsk_is_polling(struct task_struct *p)
+{
+#ifdef TIF_POLLING_NRFLAG
+	return test_tsk_thread_flag(p, TIF_POLLING_NRFLAG);
+#else
+	return 0;
+#endif
+}
+
+void resched_curr_lazy(struct rq *rq)
+{
+	struct task_struct *curr = rq->curr;
+	int cpu;
+
+	if (!sched_feat(PREEMPT_LAZY)) {
+		resched_curr(rq);
+		return;
+	}
+
+	if (test_tsk_need_resched(curr))
+		return;
+
+	if (test_tsk_need_resched_lazy(curr))
+		return;
+
+	set_tsk_need_resched_lazy(curr);
+
+	cpu = cpu_of(rq);
+	if (cpu == smp_processor_id())
+		return;
+
+	/* NEED_RESCHED_LAZY must be visible before we test polling */
+	smp_mb();
+	if (!tsk_is_polling(curr))
+		smp_send_reschedule(cpu);
+}
+#endif
+
 void resched_cpu(int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
@@ -2224,6 +2264,7 @@ void migrate_disable(void)
 	preempt_disable();
 	this_rq()->nr_pinned++;
 	p->migration_disabled = 1;
+	preempt_lazy_disable();
 	preempt_enable();
 }
 EXPORT_SYMBOL_GPL(migrate_disable);
@@ -2255,6 +2296,7 @@ void migrate_enable(void)
 	barrier();
 	p->migration_disabled = 0;
 	this_rq()->nr_pinned--;
+	preempt_lazy_enable();
 	preempt_enable();
 }
 EXPORT_SYMBOL_GPL(migrate_enable);
@@ -4722,6 +4764,9 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 	p->on_cpu = 0;
 #endif
 	init_task_preempt_count(p);
+#ifdef CONFIG_HAVE_PREEMPT_LAZY
+	task_thread_info(p)->preempt_lazy_count = 0;
+#endif
 #ifdef CONFIG_SMP
 	plist_node_init(&p->pushable_tasks, MAX_PRIO);
 	RB_CLEAR_NODE(&p->pushable_dl_tasks);
@@ -6592,6 +6637,7 @@ static void __sched notrace __schedule(unsigned int sched_mode)
 
 	next = pick_next_task(rq, prev, &rf);
 	clear_tsk_need_resched(prev);
+	clear_tsk_need_resched_lazy(prev);
 	clear_preempt_need_resched();
 #ifdef CONFIG_SCHED_DEBUG
 	rq->last_seen_need_resched_ns = 0;
@@ -6806,6 +6852,30 @@ static void __sched notrace preempt_schedule_common(void)
 	} while (need_resched());
 }
 
+#ifdef CONFIG_PREEMPT_LAZY
+/*
+ * If TIF_NEED_RESCHED is then we allow to be scheduled away since this is
+ * set by a RT task. Oterwise we try to avoid beeing scheduled out as long as
+ * preempt_lazy_count counter >0.
+ */
+static __always_inline int preemptible_lazy(void)
+{
+	if (test_thread_flag(TIF_NEED_RESCHED))
+		return 1;
+	if (current_thread_info()->preempt_lazy_count)
+		return 0;
+	return 1;
+}
+
+#else
+
+static inline int preemptible_lazy(void)
+{
+	return 1;
+}
+
+#endif
+
 #ifdef CONFIG_PREEMPTION
 /*
  * This is the entry point to schedule() from in-kernel preemption
@@ -6819,6 +6889,8 @@ asmlinkage __visible void __sched notrace preempt_schedule(void)
 	 */
 	if (likely(!preemptible()))
 		return;
+	if (!preemptible_lazy())
+		return;
 	preempt_schedule_common();
 }
 NOKPROBE_SYMBOL(preempt_schedule);
@@ -6866,6 +6938,9 @@ asmlinkage __visible void __sched notrace preempt_schedule_notrace(void)
 	if (likely(!preemptible()))
 		return;
 
+	if (!preemptible_lazy())
+		return;
+
 	do {
 		/*
 		 * Because the function tracer can trace preempt_count_sub()
@@ -9131,7 +9206,9 @@ void __init init_idle(struct task_struct *idle, int cpu)
 
 	/* Set the preempt count _outside_ the spinlocks! */
 	init_idle_preempt_count(idle, cpu);
-
+#ifdef CONFIG_HAVE_PREEMPT_LAZY
+	task_thread_info(idle)->preempt_lazy_count = 0;
+#endif
 	/*
 	 * The idle tasks have their own, simple scheduling class:
 	 */
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 2558ab9033be..2dc35af7b5a6 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4914,7 +4914,7 @@ check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr)
 	ideal_runtime = sched_slice(cfs_rq, curr);
 	delta_exec = curr->sum_exec_runtime - curr->prev_sum_exec_runtime;
 	if (delta_exec > ideal_runtime) {
-		resched_curr(rq_of(cfs_rq));
+		resched_curr_lazy(rq_of(cfs_rq));
 		/*
 		 * The current task ran long enough, ensure it doesn't get
 		 * re-elected due to buddy favours.
@@ -4938,7 +4938,7 @@ check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr)
 		return;
 
 	if (delta > ideal_runtime)
-		resched_curr(rq_of(cfs_rq));
+		resched_curr_lazy(rq_of(cfs_rq));
 }
 
 static void
@@ -5084,7 +5084,7 @@ entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued)
 	 * validating it and just reschedule.
 	 */
 	if (queued) {
-		resched_curr(rq_of(cfs_rq));
+		resched_curr_lazy(rq_of(cfs_rq));
 		return;
 	}
 	/*
@@ -5233,7 +5233,7 @@ static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec)
 	 * hierarchy can be throttled
 	 */
 	if (!assign_cfs_rq_runtime(cfs_rq) && likely(cfs_rq->curr))
-		resched_curr(rq_of(cfs_rq));
+		resched_curr_lazy(rq_of(cfs_rq));
 }
 
 static __always_inline
@@ -5984,7 +5984,7 @@ static void hrtick_start_fair(struct rq *rq, struct task_struct *p)
 
 		if (delta < 0) {
 			if (task_current(rq, p))
-				resched_curr(rq);
+				resched_curr_lazy(rq);
 			return;
 		}
 		hrtick_start(rq, delta);
@@ -7712,7 +7712,7 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
 	return;
 
 preempt:
-	resched_curr(rq);
+	resched_curr_lazy(rq);
 	/*
 	 * Only set the backward buddy when the current task is still
 	 * on the rq. This can happen when a wakeup gets interleaved
@@ -11877,7 +11877,7 @@ static void task_fork_fair(struct task_struct *p)
 		 * 'current' within the tree based on its new key value.
 		 */
 		swap(curr->vruntime, se->vruntime);
-		resched_curr(rq);
+		resched_curr_lazy(rq);
 	}
 
 	se->vruntime -= cfs_rq->min_vruntime;
@@ -11904,7 +11904,7 @@ prio_changed_fair(struct rq *rq, struct task_struct *p, int oldprio)
 	 */
 	if (task_current(rq, p)) {
 		if (p->prio > oldprio)
-			resched_curr(rq);
+			resched_curr_lazy(rq);
 	} else
 		check_preempt_curr(rq, p, 0);
 }
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index ee7f23c76bd3..e13090e33f3c 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -48,6 +48,9 @@ SCHED_FEAT(NONTASK_CAPACITY, true)
 
 #ifdef CONFIG_PREEMPT_RT
 SCHED_FEAT(TTWU_QUEUE, false)
+# ifdef CONFIG_PREEMPT_LAZY
+SCHED_FEAT(PREEMPT_LAZY, true)
+# endif
 #else
 
 /*
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index b62d53d7c264..f2577f511a41 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2350,6 +2350,15 @@ extern void reweight_task(struct task_struct *p, int prio);
 extern void resched_curr(struct rq *rq);
 extern void resched_cpu(int cpu);
 
+#ifdef CONFIG_PREEMPT_LAZY
+extern void resched_curr_lazy(struct rq *rq);
+#else
+static inline void resched_curr_lazy(struct rq *rq)
+{
+	resched_curr(rq);
+}
+#endif
+
 extern struct rt_bandwidth def_rt_bandwidth;
 extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime);
 extern bool sched_rt_bandwidth_account(struct rt_rq *rt_rq);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index f667d6bdddda..3bc4f34507f0 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -2644,11 +2644,19 @@ unsigned int tracing_gen_ctx_irq_test(unsigned int irqs_status)
 	if (softirq_count() >> (SOFTIRQ_SHIFT + 1))
 		trace_flags |= TRACE_FLAG_BH_OFF;
 
-	if (tif_need_resched())
+	if (tif_need_resched_now())
 		trace_flags |= TRACE_FLAG_NEED_RESCHED;
+#ifdef CONFIG_PREEMPT_LAZY
+	/* Run out of bits. Share the LAZY and PREEMPT_RESCHED */
+	if (need_resched_lazy())
+		trace_flags |= TRACE_FLAG_NEED_RESCHED_LAZY;
+#else
 	if (test_preempt_need_resched())
 		trace_flags |= TRACE_FLAG_PREEMPT_RESCHED;
-	return (trace_flags << 16) | (min_t(unsigned int, pc & 0xff, 0xf)) |
+#endif
+
+	return (trace_flags << 24) | (min_t(unsigned int, pc & 0xff, 0xf)) |
+		(preempt_lazy_count() & 0xff) << 16 |
 		(min_t(unsigned int, migration_disable_value(), 0xf)) << 4;
 }
 
@@ -4240,15 +4248,17 @@ unsigned long trace_total_entries(struct trace_array *tr)
 
 static void print_lat_help_header(struct seq_file *m)
 {
-	seq_puts(m, "#                    _------=> CPU#            \n"
-		    "#                   / _-----=> irqs-off/BH-disabled\n"
-		    "#                  | / _----=> need-resched    \n"
-		    "#                  || / _---=> hardirq/softirq \n"
-		    "#                  ||| / _--=> preempt-depth   \n"
-		    "#                  |||| / _-=> migrate-disable \n"
-		    "#                  ||||| /     delay           \n"
-		    "#  cmd     pid     |||||| time  |   caller     \n"
-		    "#     \\   /        ||||||  \\    |    /       \n");
+	seq_puts(m, "#                    _--------=> CPU#            \n"
+		    "#                   / _-------=> irqs-off/BH-disabled\n"
+		    "#                  | / _------=> need-resched    \n"
+		    "#                  || / _-----=> need-resched-lazy\n"
+		    "#                  ||| / _----=> hardirq/softirq \n"
+		    "#                  |||| / _---=> preempt-depth   \n"
+		    "#                  ||||| / _--=> preempt-lazy-depth\n"
+		    "#                  |||||| / _-=> migrate-disable \n"
+		    "#                  ||||||| /     delay           \n"
+		    "#  cmd     pid     |||||||| time  |   caller     \n"
+		    "#     \\   /        ||||||||  \\    |    /       \n");
 }
 
 static void print_event_info(struct array_buffer *buf, struct seq_file *m)
@@ -4282,14 +4292,16 @@ static void print_func_help_header_irq(struct array_buffer *buf, struct seq_file
 
 	print_event_info(buf, m);
 
-	seq_printf(m, "#                            %.*s  _-----=> irqs-off/BH-disabled\n", prec, space);
-	seq_printf(m, "#                            %.*s / _----=> need-resched\n", prec, space);
-	seq_printf(m, "#                            %.*s| / _---=> hardirq/softirq\n", prec, space);
-	seq_printf(m, "#                            %.*s|| / _--=> preempt-depth\n", prec, space);
-	seq_printf(m, "#                            %.*s||| / _-=> migrate-disable\n", prec, space);
-	seq_printf(m, "#                            %.*s|||| /     delay\n", prec, space);
-	seq_printf(m, "#           TASK-PID  %.*s CPU#  |||||  TIMESTAMP  FUNCTION\n", prec, "     TGID   ");
-	seq_printf(m, "#              | |    %.*s   |   |||||     |         |\n", prec, "       |    ");
+	seq_printf(m, "#                            %.*s  _-------=> irqs-off/BH-disabled\n", prec, space);
+	seq_printf(m, "#                            %.*s / _------=> need-resched\n", prec, space);
+	seq_printf(m, "#                            %.*s| / _-----=> need-resched-lazy\n", prec, space);
+	seq_printf(m, "#                            %.*s|| / _----=> hardirq/softirq\n", prec, space);
+	seq_printf(m, "#                            %.*s||| / _---=> preempt-depth\n", prec, space);
+	seq_printf(m, "#                            %.*s|||| / _--=> preempt-lazy-depth\n", prec, space);
+	seq_printf(m, "#                            %.*s||||| / _-=> migrate-disable\n", prec, space);
+	seq_printf(m, "#                            %.*s|||||| /     delay\n", prec, space);
+	seq_printf(m, "#           TASK-PID  %.*s CPU#  |||||||  TIMESTAMP  FUNCTION\n", prec, "     TGID   ");
+	seq_printf(m, "#              | |    %.*s   |   |||||||      |         |\n", prec, "       |    ");
 }
 
 void
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index a6d2f99f847d..493c3f9cf01a 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -208,6 +208,7 @@ static int trace_define_common_fields(void)
 	/* Holds both preempt_count and migrate_disable */
 	__common_field(unsigned char, preempt_count);
 	__common_field(int, pid);
+	__common_field(unsigned char, preempt_lazy_count);
 
 	return ret;
 }
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index bf1965b18099..133f15d3b886 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -442,6 +442,7 @@ int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry)
 {
 	char hardsoft_irq;
 	char need_resched;
+	char need_resched_lazy;
 	char irqs_off;
 	int hardirq;
 	int softirq;
@@ -462,20 +463,27 @@ int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry)
 
 	switch (entry->flags & (TRACE_FLAG_NEED_RESCHED |
 				TRACE_FLAG_PREEMPT_RESCHED)) {
+#ifndef CONFIG_PREEMPT_LAZY
 	case TRACE_FLAG_NEED_RESCHED | TRACE_FLAG_PREEMPT_RESCHED:
 		need_resched = 'N';
 		break;
+#endif
 	case TRACE_FLAG_NEED_RESCHED:
 		need_resched = 'n';
 		break;
+#ifndef CONFIG_PREEMPT_LAZY
 	case TRACE_FLAG_PREEMPT_RESCHED:
 		need_resched = 'p';
 		break;
+#endif
 	default:
 		need_resched = '.';
 		break;
 	}
 
+	need_resched_lazy =
+		(entry->flags & TRACE_FLAG_NEED_RESCHED_LAZY) ? 'L' : '.';
+
 	hardsoft_irq =
 		(nmi && hardirq)     ? 'Z' :
 		nmi                  ? 'z' :
@@ -484,14 +492,20 @@ int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry)
 		softirq              ? 's' :
 		                       '.' ;
 
-	trace_seq_printf(s, "%c%c%c",
-			 irqs_off, need_resched, hardsoft_irq);
+	trace_seq_printf(s, "%c%c%c%c",
+			 irqs_off, need_resched, need_resched_lazy,
+			 hardsoft_irq);
 
 	if (entry->preempt_count & 0xf)
 		trace_seq_printf(s, "%x", entry->preempt_count & 0xf);
 	else
 		trace_seq_putc(s, '.');
 
+	if (entry->preempt_lazy_count)
+		trace_seq_printf(s, "%x", entry->preempt_lazy_count);
+	else
+		trace_seq_putc(s, '.');
+
 	if (entry->preempt_count & 0xf0)
 		trace_seq_printf(s, "%x", entry->preempt_count >> 4);
 	else
-- 
2.44.0