summaryrefslogtreecommitdiffstats
path: root/debian/patches-rt/PREEMPT_AUTO.patch
blob: 323b18f798f5312568dd63901abb35285aaf4361 (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
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
From: Thomas Gleixner <tglx@linutronix.de>
Date: Sat, 23 Sep 2023 03:11:05 +0200
Subject: [PATCH] sched: define TIF_ALLOW_RESCHED
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/6.7/older/patches-6.7-rt6.tar.xz

On Fri, Sep 22 2023 at 00:55, Thomas Gleixner wrote:
> On Thu, Sep 21 2023 at 09:00, Linus Torvalds wrote:
>> That said - I think as a proof of concept and "look, with this we get
>> the expected scheduling event counts", that patch is perfect. I think
>> you more than proved the concept.
>
> There is certainly quite some analyis work to do to make this a one to
> one replacement.
>
> With a handful of benchmarks the PoC (tweaked with some obvious fixes)
> is pretty much on par with the current mainline variants (NONE/FULL),
> but the memtier benchmark makes a massive dent.
>
> It sports a whopping 10% regression with the LAZY mode versus the mainline
> NONE model. Non-LAZY and FULL behave unsurprisingly in the same way.
>
> That benchmark is really sensitive to the preemption model. With current
> mainline (DYNAMIC_PREEMPT enabled) the preempt=FULL model has ~20%
> performance drop versus preempt=NONE.

That 20% was a tired pilot error. The real number is in the 5% ballpark.

> I have no clue what's going on there yet, but that shows that there is
> obviously quite some work ahead to get this sorted.

It took some head scratching to figure that out. The initial fix broke
the handling of the hog issue, i.e. the problem that Ankur tried to
solve, but I hacked up a "solution" for that too.

With that the memtier benchmark is roughly back to the mainline numbers,
but my throughput benchmark know how is pretty close to zero, so that
should be looked at by people who actually understand these things.

Likewise the hog prevention is just at the PoC level and clearly beyond
my knowledge of scheduler details: It unconditionally forces a
reschedule when the looping task is not responding to a lazy reschedule
request before the next tick. IOW it forces a reschedule on the second
tick, which is obviously different from the cond_resched()/might_sleep()
behaviour.

The changes vs. the original PoC aside of the bug and thinko fixes:

    1) A hack to utilize the TRACE_FLAG_IRQS_NOSUPPORT flag to trace the
       lazy preempt bit as the trace_entry::flags field is full already.

       That obviously breaks the tracer ABI, but if we go there then
       this needs to be fixed. Steven?

    2) debugfs file to validate that loops can be force preempted w/o
       cond_resched()

       The usage is:

       # taskset -c 1 bash
       # echo 1 > /sys/kernel/debug/sched/hog &
       # echo 1 > /sys/kernel/debug/sched/hog &
       # echo 1 > /sys/kernel/debug/sched/hog &

       top shows ~33% CPU for each of the hogs and tracing confirms that
       the crude hack in the scheduler tick works:

            bash-4559    [001] dlh2.  2253.331202: resched_curr <-__update_curr
            bash-4560    [001] dlh2.  2253.340199: resched_curr <-__update_curr
            bash-4561    [001] dlh2.  2253.346199: resched_curr <-__update_curr
            bash-4559    [001] dlh2.  2253.353199: resched_curr <-__update_curr
            bash-4561    [001] dlh2.  2253.358199: resched_curr <-__update_curr
            bash-4560    [001] dlh2.  2253.370202: resched_curr <-__update_curr
            bash-4559    [001] dlh2.  2253.378198: resched_curr <-__update_curr
            bash-4561    [001] dlh2.  2253.389199: resched_curr <-__update_curr

       The 'l' instead of the usual 'N' reflects that the lazy resched
       bit is set. That makes __update_curr() invoke resched_curr()
       instead of the lazy variant. resched_curr() sets TIF_NEED_RESCHED
       and folds it into preempt_count so that preemption happens at the
       next possible point, i.e. either in return from interrupt or at
       the next preempt_enable().

That's as much as I wanted to demonstrate and I'm not going to spend
more cycles on it as I have already too many other things on flight and
the resulting scheduler woes are clearly outside of my expertice.

Though definitely I'm putting a permanent NAK in place for any attempts
to duct tape the preempt=NONE model any further by sprinkling more
cond*() and whatever warts around.

Thanks,

        tglx

[tglx: s@CONFIG_PREEMPT_AUTO@CONFIG_PREEMPT_BUILD_AUTO@ ]

Link: https://lore.kernel.org/all/87jzshhexi.ffs@tglx/
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
 arch/x86/Kconfig                   |    1 
 arch/x86/include/asm/thread_info.h |    6 ++--
 drivers/acpi/processor_idle.c      |    2 -
 include/linux/entry-common.h       |    2 -
 include/linux/entry-kvm.h          |    2 -
 include/linux/sched.h              |   12 +++++---
 include/linux/sched/idle.h         |    8 ++---
 include/linux/thread_info.h        |   24 +++++++++++++++++
 include/linux/trace_events.h       |    8 ++---
 kernel/Kconfig.preempt             |   17 +++++++++++-
 kernel/entry/common.c              |    4 +-
 kernel/entry/kvm.c                 |    2 -
 kernel/sched/core.c                |   50 +++++++++++++++++++++++++------------
 kernel/sched/debug.c               |   19 ++++++++++++++
 kernel/sched/fair.c                |   46 ++++++++++++++++++++++------------
 kernel/sched/features.h            |    2 +
 kernel/sched/idle.c                |    3 --
 kernel/sched/sched.h               |    1 
 kernel/trace/trace.c               |    2 +
 kernel/trace/trace_output.c        |   16 ++++++++++-
 20 files changed, 171 insertions(+), 56 deletions(-)

--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -272,6 +272,7 @@ config X86
 	select HAVE_STATIC_CALL
 	select HAVE_STATIC_CALL_INLINE		if HAVE_OBJTOOL
 	select HAVE_PREEMPT_DYNAMIC_CALL
+	select HAVE_PREEMPT_AUTO
 	select HAVE_RSEQ
 	select HAVE_RUST			if X86_64
 	select HAVE_SYSCALL_TRACEPOINTS
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -81,8 +81,9 @@ struct thread_info {
 #define TIF_NOTIFY_RESUME	1	/* callback before returning to user */
 #define TIF_SIGPENDING		2	/* signal pending */
 #define TIF_NEED_RESCHED	3	/* rescheduling necessary */
-#define TIF_SINGLESTEP		4	/* reenable singlestep on user return*/
-#define TIF_SSBD		5	/* Speculative store bypass disable */
+#define TIF_ARCH_RESCHED_LAZY	4	/* Lazy rescheduling */
+#define TIF_SINGLESTEP		5	/* reenable singlestep on user return*/
+#define TIF_SSBD		6	/* Speculative store bypass disable */
 #define TIF_SPEC_IB		9	/* Indirect branch speculation mitigation */
 #define TIF_SPEC_L1D_FLUSH	10	/* Flush L1D on mm switches (processes) */
 #define TIF_USER_RETURN_NOTIFY	11	/* notify kernel of userspace return */
@@ -104,6 +105,7 @@ struct thread_info {
 #define _TIF_NOTIFY_RESUME	(1 << TIF_NOTIFY_RESUME)
 #define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)
+#define _TIF_ARCH_RESCHED_LAZY	(1 << TIF_ARCH_RESCHED_LAZY)
 #define _TIF_SINGLESTEP		(1 << TIF_SINGLESTEP)
 #define _TIF_SSBD		(1 << TIF_SSBD)
 #define _TIF_SPEC_IB		(1 << TIF_SPEC_IB)
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -108,7 +108,7 @@ static const struct dmi_system_id proces
  */
 static void __cpuidle acpi_safe_halt(void)
 {
-	if (!tif_need_resched()) {
+	if (!need_resched()) {
 		raw_safe_halt();
 		raw_local_irq_disable();
 	}
--- a/include/linux/entry-common.h
+++ b/include/linux/entry-common.h
@@ -60,7 +60,7 @@
 #define EXIT_TO_USER_MODE_WORK						\
 	(_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_UPROBE |		\
 	 _TIF_NEED_RESCHED | _TIF_PATCH_PENDING | _TIF_NOTIFY_SIGNAL |	\
-	 ARCH_EXIT_TO_USER_MODE_WORK)
+	 _TIF_NEED_RESCHED_LAZY | ARCH_EXIT_TO_USER_MODE_WORK)
 
 /**
  * arch_enter_from_user_mode - Architecture specific sanity check for user mode regs
--- a/include/linux/entry-kvm.h
+++ b/include/linux/entry-kvm.h
@@ -18,7 +18,7 @@
 
 #define XFER_TO_GUEST_MODE_WORK						\
 	(_TIF_NEED_RESCHED | _TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL |	\
-	 _TIF_NOTIFY_RESUME | ARCH_XFER_TO_GUEST_MODE_WORK)
+	 _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED_LAZY | ARCH_XFER_TO_GUEST_MODE_WORK)
 
 struct kvm_vcpu;
 
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2055,17 +2055,17 @@ static inline void update_tsk_thread_fla
 	update_ti_thread_flag(task_thread_info(tsk), flag, value);
 }
 
-static inline int test_and_set_tsk_thread_flag(struct task_struct *tsk, int flag)
+static inline bool test_and_set_tsk_thread_flag(struct task_struct *tsk, int flag)
 {
 	return test_and_set_ti_thread_flag(task_thread_info(tsk), flag);
 }
 
-static inline int test_and_clear_tsk_thread_flag(struct task_struct *tsk, int flag)
+static inline bool test_and_clear_tsk_thread_flag(struct task_struct *tsk, int flag)
 {
 	return test_and_clear_ti_thread_flag(task_thread_info(tsk), flag);
 }
 
-static inline int test_tsk_thread_flag(struct task_struct *tsk, int flag)
+static inline bool test_tsk_thread_flag(struct task_struct *tsk, int flag)
 {
 	return test_ti_thread_flag(task_thread_info(tsk), flag);
 }
@@ -2078,9 +2078,11 @@ static inline void set_tsk_need_resched(
 static inline void clear_tsk_need_resched(struct task_struct *tsk)
 {
 	clear_tsk_thread_flag(tsk,TIF_NEED_RESCHED);
+	if (IS_ENABLED(CONFIG_PREEMPT_BUILD_AUTO))
+		clear_tsk_thread_flag(tsk, TIF_NEED_RESCHED_LAZY);
 }
 
-static inline int test_tsk_need_resched(struct task_struct *tsk)
+static inline bool test_tsk_need_resched(struct task_struct *tsk)
 {
 	return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED));
 }
@@ -2261,7 +2263,7 @@ static inline int rwlock_needbreak(rwloc
 
 static __always_inline bool need_resched(void)
 {
-	return unlikely(tif_need_resched());
+	return unlikely(tif_need_resched_lazy() || tif_need_resched());
 }
 
 /*
--- a/include/linux/sched/idle.h
+++ b/include/linux/sched/idle.h
@@ -63,7 +63,7 @@ static __always_inline bool __must_check
 	 */
 	smp_mb__after_atomic();
 
-	return unlikely(tif_need_resched());
+	return unlikely(need_resched());
 }
 
 static __always_inline bool __must_check current_clr_polling_and_test(void)
@@ -76,7 +76,7 @@ static __always_inline bool __must_check
 	 */
 	smp_mb__after_atomic();
 
-	return unlikely(tif_need_resched());
+	return unlikely(need_resched());
 }
 
 #else
@@ -85,11 +85,11 @@ static inline void __current_clr_polling
 
 static inline bool __must_check current_set_polling_and_test(void)
 {
-	return unlikely(tif_need_resched());
+	return unlikely(need_resched());
 }
 static inline bool __must_check current_clr_polling_and_test(void)
 {
-	return unlikely(tif_need_resched());
+	return unlikely(need_resched());
 }
 #endif
 
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -59,6 +59,16 @@ enum syscall_work_bit {
 
 #include <asm/thread_info.h>
 
+#ifdef CONFIG_PREEMPT_BUILD_AUTO
+# define TIF_NEED_RESCHED_LAZY		TIF_ARCH_RESCHED_LAZY
+# define _TIF_NEED_RESCHED_LAZY		_TIF_ARCH_RESCHED_LAZY
+# define TIF_NEED_RESCHED_LAZY_OFFSET	(TIF_NEED_RESCHED_LAZY - TIF_NEED_RESCHED)
+#else
+# define TIF_NEED_RESCHED_LAZY		TIF_NEED_RESCHED
+# define _TIF_NEED_RESCHED_LAZY		_TIF_NEED_RESCHED
+# define TIF_NEED_RESCHED_LAZY_OFFSET	0
+#endif
+
 #ifdef __KERNEL__
 
 #ifndef arch_set_restart_data
@@ -185,6 +195,13 @@ static __always_inline bool tif_need_res
 			     (unsigned long *)(&current_thread_info()->flags));
 }
 
+static __always_inline bool tif_need_resched_lazy(void)
+{
+	return IS_ENABLED(CONFIG_PREEMPT_BUILD_AUTO) &&
+		arch_test_bit(TIF_NEED_RESCHED_LAZY,
+			      (unsigned long *)(&current_thread_info()->flags));
+}
+
 #else
 
 static __always_inline bool tif_need_resched(void)
@@ -193,6 +210,13 @@ static __always_inline bool tif_need_res
 			(unsigned long *)(&current_thread_info()->flags));
 }
 
+static __always_inline bool tif_need_resched_lazy(void)
+{
+	return IS_ENABLED(CONFIG_PREEMPT_BUILD_AUTO) &&
+		test_bit(TIF_NEED_RESCHED_LAZY,
+			 (unsigned long *)(&current_thread_info()->flags));
+}
+
 #endif /* _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H */
 
 #ifndef CONFIG_HAVE_ARCH_WITHIN_STACK_FRAMES
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -178,8 +178,8 @@ unsigned int tracing_gen_ctx_irq_test(un
 
 enum trace_flag_type {
 	TRACE_FLAG_IRQS_OFF		= 0x01,
-	TRACE_FLAG_IRQS_NOSUPPORT	= 0x02,
-	TRACE_FLAG_NEED_RESCHED		= 0x04,
+	TRACE_FLAG_NEED_RESCHED		= 0x02,
+	TRACE_FLAG_NEED_RESCHED_LAZY	= 0x04,
 	TRACE_FLAG_HARDIRQ		= 0x08,
 	TRACE_FLAG_SOFTIRQ		= 0x10,
 	TRACE_FLAG_PREEMPT_RESCHED	= 0x20,
@@ -205,11 +205,11 @@ static inline unsigned int tracing_gen_c
 
 static inline unsigned int tracing_gen_ctx_flags(unsigned long irqflags)
 {
-	return tracing_gen_ctx_irq_test(TRACE_FLAG_IRQS_NOSUPPORT);
+	return tracing_gen_ctx_irq_test(0);
 }
 static inline unsigned int tracing_gen_ctx(void)
 {
-	return tracing_gen_ctx_irq_test(TRACE_FLAG_IRQS_NOSUPPORT);
+	return tracing_gen_ctx_irq_test(0);
 }
 #endif
 
--- a/kernel/Kconfig.preempt
+++ b/kernel/Kconfig.preempt
@@ -11,6 +11,13 @@ config PREEMPT_BUILD
 	select PREEMPTION
 	select UNINLINE_SPIN_UNLOCK if !ARCH_INLINE_SPIN_UNLOCK
 
+config PREEMPT_BUILD_AUTO
+	bool
+	select PREEMPT_BUILD
+
+config HAVE_PREEMPT_AUTO
+	bool
+
 choice
 	prompt "Preemption Model"
 	default PREEMPT_NONE
@@ -67,9 +74,17 @@ config PREEMPT
 	  embedded system with latency requirements in the milliseconds
 	  range.
 
+config PREEMPT_AUTO
+	bool "Automagic preemption mode with runtime tweaking support"
+	depends on HAVE_PREEMPT_AUTO
+	select PREEMPT_BUILD_AUTO
+	help
+	  Add some sensible blurb here
+
 config PREEMPT_RT
 	bool "Fully Preemptible Kernel (Real-Time)"
 	depends on EXPERT && ARCH_SUPPORTS_RT
+	select PREEMPT_BUILD_AUTO if HAVE_PREEMPT_AUTO
 	select PREEMPTION
 	help
 	  This option turns the kernel into a real-time kernel by replacing
@@ -95,7 +110,7 @@ config PREEMPTION
 
 config PREEMPT_DYNAMIC
 	bool "Preemption behaviour defined on boot"
-	depends on HAVE_PREEMPT_DYNAMIC && !PREEMPT_RT
+	depends on HAVE_PREEMPT_DYNAMIC && !PREEMPT_RT && !PREEMPT_AUTO
 	select JUMP_LABEL if HAVE_PREEMPT_DYNAMIC_KEY
 	select PREEMPT_BUILD
 	default y if HAVE_PREEMPT_DYNAMIC_CALL
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -155,7 +155,7 @@ static unsigned long exit_to_user_mode_l
 
 		local_irq_enable_exit_to_user(ti_work);
 
-		if (ti_work & _TIF_NEED_RESCHED)
+		if (ti_work & (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY))
 			schedule();
 
 		if (ti_work & _TIF_UPROBE)
@@ -385,7 +385,7 @@ void raw_irqentry_exit_cond_resched(void
 		rcu_irq_exit_check_preempt();
 		if (IS_ENABLED(CONFIG_DEBUG_ENTRY))
 			WARN_ON_ONCE(!on_thread_stack());
-		if (need_resched())
+		if (test_tsk_need_resched(current))
 			preempt_schedule_irq();
 	}
 }
--- a/kernel/entry/kvm.c
+++ b/kernel/entry/kvm.c
@@ -13,7 +13,7 @@ static int xfer_to_guest_mode_work(struc
 			return -EINTR;
 		}
 
-		if (ti_work & _TIF_NEED_RESCHED)
+		if (ti_work & (_TIF_NEED_RESCHED | TIF_NEED_RESCHED_LAZY))
 			schedule();
 
 		if (ti_work & _TIF_NOTIFY_RESUME)
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -898,14 +898,15 @@ static inline void hrtick_rq_init(struct
 
 #if defined(CONFIG_SMP) && defined(TIF_POLLING_NRFLAG)
 /*
- * Atomically set TIF_NEED_RESCHED and test for TIF_POLLING_NRFLAG,
+ * Atomically set TIF_NEED_RESCHED[_LAZY] and test for TIF_POLLING_NRFLAG,
  * this avoids any races wrt polling state changes and thereby avoids
  * spurious IPIs.
  */
-static inline bool set_nr_and_not_polling(struct task_struct *p)
+static inline bool set_nr_and_not_polling(struct task_struct *p, int tif_bit)
 {
 	struct thread_info *ti = task_thread_info(p);
-	return !(fetch_or(&ti->flags, _TIF_NEED_RESCHED) & _TIF_POLLING_NRFLAG);
+
+	return !(fetch_or(&ti->flags, 1 << tif_bit) & _TIF_POLLING_NRFLAG);
 }
 
 /*
@@ -922,7 +923,7 @@ static bool set_nr_if_polling(struct tas
 	do {
 		if (!(val & _TIF_POLLING_NRFLAG))
 			return false;
-		if (val & _TIF_NEED_RESCHED)
+		if (val & (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY))
 			return true;
 	} while (!try_cmpxchg(&ti->flags, &val, val | _TIF_NEED_RESCHED));
 
@@ -930,9 +931,9 @@ static bool set_nr_if_polling(struct tas
 }
 
 #else
-static inline bool set_nr_and_not_polling(struct task_struct *p)
+static inline bool set_nr_and_not_polling(struct task_struct *p, int tif_bit)
 {
-	set_tsk_need_resched(p);
+	set_tsk_thread_flag(p, tif_bit);
 	return true;
 }
 
@@ -1037,28 +1038,47 @@ void wake_up_q(struct wake_q_head *head)
  * might also involve a cross-CPU call to trigger the scheduler on
  * the target CPU.
  */
-void resched_curr(struct rq *rq)
+static void __resched_curr(struct rq *rq, int lazy)
 {
+	int cpu, tif_bit = TIF_NEED_RESCHED + lazy;
 	struct task_struct *curr = rq->curr;
-	int cpu;
 
 	lockdep_assert_rq_held(rq);
 
-	if (test_tsk_need_resched(curr))
+	if (unlikely(test_tsk_thread_flag(curr, tif_bit)))
 		return;
 
 	cpu = cpu_of(rq);
 
 	if (cpu == smp_processor_id()) {
-		set_tsk_need_resched(curr);
-		set_preempt_need_resched();
+		set_tsk_thread_flag(curr, tif_bit);
+		if (!lazy)
+			set_preempt_need_resched();
 		return;
 	}
 
-	if (set_nr_and_not_polling(curr))
-		smp_send_reschedule(cpu);
-	else
+	if (set_nr_and_not_polling(curr, tif_bit)) {
+		if (!lazy)
+			smp_send_reschedule(cpu);
+	} else {
 		trace_sched_wake_idle_without_ipi(cpu);
+	}
+}
+
+void resched_curr(struct rq *rq)
+{
+	__resched_curr(rq, 0);
+}
+
+void resched_curr_lazy(struct rq *rq)
+{
+	int lazy = IS_ENABLED(CONFIG_PREEMPT_BUILD_AUTO) && !sched_feat(FORCE_NEED_RESCHED) ?
+		TIF_NEED_RESCHED_LAZY_OFFSET : 0;
+
+	if (lazy && unlikely(test_tsk_thread_flag(rq->curr, TIF_NEED_RESCHED)))
+		return;
+
+	__resched_curr(rq, lazy);
 }
 
 void resched_cpu(int cpu)
@@ -1131,7 +1151,7 @@ static void wake_up_idle_cpu(int cpu)
 	if (cpu == smp_processor_id())
 		return;
 
-	if (set_nr_and_not_polling(rq->idle))
+	if (set_nr_and_not_polling(rq->idle, TIF_NEED_RESCHED))
 		smp_send_reschedule(cpu);
 	else
 		trace_sched_wake_idle_without_ipi(cpu);
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -333,6 +333,23 @@ static const struct file_operations sche
 	.release	= seq_release,
 };
 
+static ssize_t sched_hog_write(struct file *filp, const char __user *ubuf,
+			       size_t cnt, loff_t *ppos)
+{
+	unsigned long end = jiffies + 60 * HZ;
+
+	for (; time_before(jiffies, end) && !signal_pending(current);)
+		cpu_relax();
+
+	return cnt;
+}
+
+static const struct file_operations sched_hog_fops = {
+	.write		= sched_hog_write,
+	.open		= simple_open,
+	.llseek		= default_llseek,
+};
+
 static struct dentry *debugfs_sched;
 
 static __init int sched_init_debug(void)
@@ -374,6 +391,8 @@ static __init int sched_init_debug(void)
 
 	debugfs_create_file("debug", 0444, debugfs_sched, NULL, &sched_debug_fops);
 
+	debugfs_create_file("hog", 0200, debugfs_sched, NULL, &sched_hog_fops);
+
 	return 0;
 }
 late_initcall(sched_init_debug);
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1001,8 +1001,10 @@ static void clear_buddies(struct cfs_rq
  * XXX: strictly: vd_i += N*r_i/w_i such that: vd_i > ve_i
  * this is probably good enough.
  */
-static void update_deadline(struct cfs_rq *cfs_rq, struct sched_entity *se)
+static void update_deadline(struct cfs_rq *cfs_rq, struct sched_entity *se, bool tick)
 {
+	struct rq *rq = rq_of(cfs_rq);
+
 	if ((s64)(se->vruntime - se->deadline) < 0)
 		return;
 
@@ -1021,10 +1023,19 @@ static void update_deadline(struct cfs_r
 	/*
 	 * The task has consumed its request, reschedule.
 	 */
-	if (cfs_rq->nr_running > 1) {
-		resched_curr(rq_of(cfs_rq));
-		clear_buddies(cfs_rq, se);
+	if (cfs_rq->nr_running < 2)
+		return;
+
+	if (!IS_ENABLED(CONFIG_PREEMPT_BUILD_AUTO) || sched_feat(FORCE_NEED_RESCHED)) {
+		resched_curr(rq);
+	} else {
+		/* Did the task ignore the lazy reschedule request? */
+		if (tick && test_tsk_thread_flag(rq->curr, TIF_NEED_RESCHED_LAZY))
+			resched_curr(rq);
+		else
+			resched_curr_lazy(rq);
 	}
+	clear_buddies(cfs_rq, se);
 }
 
 #include "pelt.h"
@@ -1132,7 +1143,7 @@ static void update_tg_load_avg(struct cf
 /*
  * Update the current task's runtime statistics.
  */
-static void update_curr(struct cfs_rq *cfs_rq)
+static void __update_curr(struct cfs_rq *cfs_rq, bool tick)
 {
 	struct sched_entity *curr = cfs_rq->curr;
 	u64 now = rq_clock_task(rq_of(cfs_rq));
@@ -1159,7 +1170,7 @@ static void update_curr(struct cfs_rq *c
 	schedstat_add(cfs_rq->exec_clock, delta_exec);
 
 	curr->vruntime += calc_delta_fair(delta_exec, curr);
-	update_deadline(cfs_rq, curr);
+	update_deadline(cfs_rq, curr, tick);
 	update_min_vruntime(cfs_rq);
 
 	if (entity_is_task(curr)) {
@@ -1173,6 +1184,11 @@ static void update_curr(struct cfs_rq *c
 	account_cfs_rq_runtime(cfs_rq, delta_exec);
 }
 
+static inline void update_curr(struct cfs_rq *cfs_rq)
+{
+	__update_curr(cfs_rq, false);
+}
+
 static void update_curr_fair(struct rq *rq)
 {
 	update_curr(cfs_rq_of(&rq->curr->se));
@@ -5449,7 +5465,7 @@ entity_tick(struct cfs_rq *cfs_rq, struc
 	/*
 	 * Update run-time statistics of the 'current'.
 	 */
-	update_curr(cfs_rq);
+	__update_curr(cfs_rq, true);
 
 	/*
 	 * Ensure that runnable average is periodically updated.
@@ -5463,7 +5479,7 @@ entity_tick(struct cfs_rq *cfs_rq, struc
 	 * validating it and just reschedule.
 	 */
 	if (queued) {
-		resched_curr(rq_of(cfs_rq));
+		resched_curr_lazy(rq_of(cfs_rq));
 		return;
 	}
 	/*
@@ -5609,7 +5625,7 @@ static void __account_cfs_rq_runtime(str
 	 * 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
@@ -5869,7 +5885,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cf
 
 	/* Determine whether we need to wake up potentially idle CPU: */
 	if (rq->curr == rq->idle && rq->cfs.nr_running)
-		resched_curr(rq);
+		resched_curr_lazy(rq);
 }
 
 #ifdef CONFIG_SMP
@@ -6584,7 +6600,7 @@ static void hrtick_start_fair(struct rq
 
 		if (delta < 0) {
 			if (task_current(rq, p))
-				resched_curr(rq);
+				resched_curr_lazy(rq);
 			return;
 		}
 		hrtick_start(rq, delta);
@@ -8240,7 +8256,7 @@ static void check_preempt_wakeup_fair(st
 	 * prevents us from potentially nominating it as a false LAST_BUDDY
 	 * below.
 	 */
-	if (test_tsk_need_resched(curr))
+	if (need_resched())
 		return;
 
 	/* Idle tasks are by definition preempted by non-idle tasks. */
@@ -8282,7 +8298,7 @@ static void check_preempt_wakeup_fair(st
 	return;
 
 preempt:
-	resched_curr(rq);
+	resched_curr_lazy(rq);
 }
 
 #ifdef CONFIG_SMP
@@ -12449,7 +12465,7 @@ static inline void task_tick_core(struct
 	 */
 	if (rq->core->core_forceidle_count && rq->cfs.nr_running == 1 &&
 	    __entity_slice_used(&curr->se, MIN_NR_TASKS_DURING_FORCEIDLE))
-		resched_curr(rq);
+		resched_curr_lazy(rq);
 }
 
 /*
@@ -12614,7 +12630,7 @@ prio_changed_fair(struct rq *rq, struct
 	 */
 	if (task_current(rq, p)) {
 		if (p->prio > oldprio)
-			resched_curr(rq);
+			resched_curr_lazy(rq);
 	} else
 		wakeup_preempt(rq, p, 0);
 }
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -88,3 +88,5 @@ SCHED_FEAT(UTIL_EST_FASTUP, true)
 SCHED_FEAT(LATENCY_WARN, false)
 
 SCHED_FEAT(HZ_BW, true)
+
+SCHED_FEAT(FORCE_NEED_RESCHED, false)
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -57,8 +57,7 @@ static noinline int __cpuidle cpu_idle_p
 	ct_cpuidle_enter();
 
 	raw_local_irq_enable();
-	while (!tif_need_resched() &&
-	       (cpu_idle_force_poll || tick_check_broadcast_expired()))
+	while (!need_resched() && (cpu_idle_force_poll || tick_check_broadcast_expired()))
 		cpu_relax();
 	raw_local_irq_disable();
 
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2419,6 +2419,7 @@ extern void init_sched_fair_class(void);
 extern void reweight_task(struct task_struct *p, int prio);
 
 extern void resched_curr(struct rq *rq);
+extern void resched_curr_lazy(struct rq *rq);
 extern void resched_cpu(int cpu);
 
 extern struct rt_bandwidth def_rt_bandwidth;
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -2723,6 +2723,8 @@ unsigned int tracing_gen_ctx_irq_test(un
 
 	if (tif_need_resched())
 		trace_flags |= TRACE_FLAG_NEED_RESCHED;
+	if (tif_need_resched_lazy())
+		trace_flags |= TRACE_FLAG_NEED_RESCHED_LAZY;
 	if (test_preempt_need_resched())
 		trace_flags |= TRACE_FLAG_PREEMPT_RESCHED;
 	return (trace_flags << 16) | (min_t(unsigned int, pc & 0xff, 0xf)) |
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -460,17 +460,29 @@ int trace_print_lat_fmt(struct trace_seq
 		(entry->flags & TRACE_FLAG_IRQS_OFF && bh_off) ? 'D' :
 		(entry->flags & TRACE_FLAG_IRQS_OFF) ? 'd' :
 		bh_off ? 'b' :
-		(entry->flags & TRACE_FLAG_IRQS_NOSUPPORT) ? 'X' :
+		!IS_ENABLED(CONFIG_TRACE_IRQFLAGS_SUPPORT) ? 'X' :
 		'.';
 
-	switch (entry->flags & (TRACE_FLAG_NEED_RESCHED |
+	switch (entry->flags & (TRACE_FLAG_NEED_RESCHED | TRACE_FLAG_NEED_RESCHED_LAZY |
 				TRACE_FLAG_PREEMPT_RESCHED)) {
+	case TRACE_FLAG_NEED_RESCHED | TRACE_FLAG_NEED_RESCHED_LAZY | TRACE_FLAG_PREEMPT_RESCHED:
+		need_resched = 'B';
+		break;
 	case TRACE_FLAG_NEED_RESCHED | TRACE_FLAG_PREEMPT_RESCHED:
 		need_resched = 'N';
 		break;
+	case TRACE_FLAG_NEED_RESCHED_LAZY | TRACE_FLAG_PREEMPT_RESCHED:
+		need_resched = 'L';
+		break;
+	case TRACE_FLAG_NEED_RESCHED | TRACE_FLAG_NEED_RESCHED_LAZY:
+		need_resched = 'b';
+		break;
 	case TRACE_FLAG_NEED_RESCHED:
 		need_resched = 'n';
 		break;
+	case TRACE_FLAG_NEED_RESCHED_LAZY:
+		need_resched = 'l';
+		break;
 	case TRACE_FLAG_PREEMPT_RESCHED:
 		need_resched = 'p';
 		break;