aboutsummaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel/process.c
blob: 3053c85e0e42db9abbb5261673fa78e897efe20e (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
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
// SPDX-License-Identifier: GPL-2.0
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/errno.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/smp.h>
#include <linux/prctl.h>
#include <linux/slab.h>
#include <linux/sched.h>
#include <linux/sched/idle.h>
#include <linux/sched/debug.h>
#include <linux/sched/task.h>
#include <linux/sched/task_stack.h>
#include <linux/init.h>
#include <linux/export.h>
#include <linux/pm.h>
#include <linux/tick.h>
#include <linux/random.h>
#include <linux/user-return-notifier.h>
#include <linux/dmi.h>
#include <linux/utsname.h>
#include <linux/stackprotector.h>
#include <linux/cpuidle.h>
#include <linux/acpi.h>
#include <linux/elf-randomize.h>
#include <trace/events/power.h>
#include <linux/hw_breakpoint.h>
#include <asm/cpu.h>
#include <asm/apic.h>
#include <asm/syscalls.h>
#include <linux/uaccess.h>
#include <asm/mwait.h>
#include <asm/fpu/internal.h>
#include <asm/debugreg.h>
#include <asm/nmi.h>
#include <asm/tlbflush.h>
#include <asm/mce.h>
#include <asm/vm86.h>
#include <asm/switch_to.h>
#include <asm/desc.h>
#include <asm/prctl.h>
#include <asm/spec-ctrl.h>
#include <asm/io_bitmap.h>
#include <asm/proto.h>

#include "process.h"

/*
 * per-CPU TSS segments. Threads are completely 'soft' on Linux,
 * no more per-task TSS's. The TSS size is kept cacheline-aligned
 * so they are allowed to end up in the .data..cacheline_aligned
 * section. Since TSS's are completely CPU-local, we want them
 * on exact cacheline boundaries, to eliminate cacheline ping-pong.
 */
__visible DEFINE_PER_CPU_PAGE_ALIGNED(struct tss_struct, cpu_tss_rw) = {
	.x86_tss = {
		/*
		 * .sp0 is only used when entering ring 0 from a lower
		 * privilege level.  Since the init task never runs anything
		 * but ring 0 code, there is no need for a valid value here.
		 * Poison it.
		 */
		.sp0 = (1UL << (BITS_PER_LONG-1)) + 1,

		/*
		 * .sp1 is cpu_current_top_of_stack.  The init task never
		 * runs user code, but cpu_current_top_of_stack should still
		 * be well defined before the first context switch.
		 */
		.sp1 = TOP_OF_INIT_STACK,

#ifdef CONFIG_X86_32
		.ss0 = __KERNEL_DS,
		.ss1 = __KERNEL_CS,
#endif
		.io_bitmap_base	= IO_BITMAP_OFFSET_INVALID,
	 },
};
EXPORT_PER_CPU_SYMBOL(cpu_tss_rw);

DEFINE_PER_CPU(bool, __tss_limit_invalid);
EXPORT_PER_CPU_SYMBOL_GPL(__tss_limit_invalid);

/*
 * this gets called so that we can store lazy state into memory and copy the
 * current task into the new thread.
 */
int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
{
	memcpy(dst, src, arch_task_struct_size);
#ifdef CONFIG_VM86
	dst->thread.vm86 = NULL;
#endif

	return fpu__copy(dst, src);
}

/*
 * Free current thread data structures etc..
 */
void exit_thread(struct task_struct *tsk)
{
	struct thread_struct *t = &tsk->thread;
	struct fpu *fpu = &t->fpu;

	if (test_thread_flag(TIF_IO_BITMAP))
		io_bitmap_exit();

	free_vm86(t);

	fpu__drop(fpu);
}

static int set_new_tls(struct task_struct *p, unsigned long tls)
{
	struct user_desc __user *utls = (struct user_desc __user *)tls;

	if (in_ia32_syscall())
		return do_set_thread_area(p, -1, utls, 0);
	else
		return do_set_thread_area_64(p, ARCH_SET_FS, tls);
}

int copy_thread_tls(unsigned long clone_flags, unsigned long sp,
		    unsigned long arg, struct task_struct *p, unsigned long tls)
{
	struct inactive_task_frame *frame;
	struct fork_frame *fork_frame;
	struct pt_regs *childregs;
	int ret = 0;

	childregs = task_pt_regs(p);
	fork_frame = container_of(childregs, struct fork_frame, regs);
	frame = &fork_frame->frame;

	frame->bp = 0;
	frame->ret_addr = (unsigned long) ret_from_fork;
	p->thread.sp = (unsigned long) fork_frame;
	p->thread.io_bitmap = NULL;
	memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps));

#ifdef CONFIG_X86_64
	savesegment(gs, p->thread.gsindex);
	p->thread.gsbase = p->thread.gsindex ? 0 : current->thread.gsbase;
	savesegment(fs, p->thread.fsindex);
	p->thread.fsbase = p->thread.fsindex ? 0 : current->thread.fsbase;
	savesegment(es, p->thread.es);
	savesegment(ds, p->thread.ds);
#else
	p->thread.sp0 = (unsigned long) (childregs + 1);
	/*
	 * Clear all status flags including IF and set fixed bit. 64bit
	 * does not have this initialization as the frame does not contain
	 * flags. The flags consistency (especially vs. AC) is there
	 * ensured via objtool, which lacks 32bit support.
	 */
	frame->flags = X86_EFLAGS_FIXED;
#endif

	/* Kernel thread ? */
	if (unlikely(p->flags & PF_KTHREAD)) {
		memset(childregs, 0, sizeof(struct pt_regs));
		kthread_frame_init(frame, sp, arg);
		return 0;
	}

	frame->bx = 0;
	*childregs = *current_pt_regs();
	childregs->ax = 0;
	if (sp)
		childregs->sp = sp;

#ifdef CONFIG_X86_32
	task_user_gs(p) = get_user_gs(current_pt_regs());
#endif

	/* Set a new TLS for the child thread? */
	if (clone_flags & CLONE_SETTLS)
		ret = set_new_tls(p, tls);

	if (!ret && unlikely(test_tsk_thread_flag(current, TIF_IO_BITMAP)))
		io_bitmap_share(p);

	return ret;
}

void flush_thread(void)
{
	struct task_struct *tsk = current;

	flush_ptrace_hw_breakpoint(tsk);
	memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array));

	fpu__clear(&tsk->thread.fpu);
}

void disable_TSC(void)
{
	preempt_disable();
	if (!test_and_set_thread_flag(TIF_NOTSC))
		/*
		 * Must flip the CPU state synchronously with
		 * TIF_NOTSC in the current running context.
		 */
		cr4_set_bits(X86_CR4_TSD);
	preempt_enable();
}

static void enable_TSC(void)
{
	preempt_disable();
	if (test_and_clear_thread_flag(TIF_NOTSC))
		/*
		 * Must flip the CPU state synchronously with
		 * TIF_NOTSC in the current running context.
		 */
		cr4_clear_bits(X86_CR4_TSD);
	preempt_enable();
}

int get_tsc_mode(unsigned long adr)
{
	unsigned int val;

	if (test_thread_flag(TIF_NOTSC))
		val = PR_TSC_SIGSEGV;
	else
		val = PR_TSC_ENABLE;

	return put_user(val, (unsigned int __user *)adr);
}

int set_tsc_mode(unsigned int val)
{
	if (val == PR_TSC_SIGSEGV)
		disable_TSC();
	else if (val == PR_TSC_ENABLE)
		enable_TSC();
	else
		return -EINVAL;

	return 0;
}

DEFINE_PER_CPU(u64, msr_misc_features_shadow);

static void set_cpuid_faulting(bool on)
{
	u64 msrval;

	msrval = this_cpu_read(msr_misc_features_shadow);
	msrval &= ~MSR_MISC_FEATURES_ENABLES_CPUID_FAULT;
	msrval |= (on << MSR_MISC_FEATURES_ENABLES_CPUID_FAULT_BIT);
	this_cpu_write(msr_misc_features_shadow, msrval);
	wrmsrl(MSR_MISC_FEATURES_ENABLES, msrval);
}

static void disable_cpuid(void)
{
	preempt_disable();
	if (!test_and_set_thread_flag(TIF_NOCPUID)) {
		/*
		 * Must flip the CPU state synchronously with
		 * TIF_NOCPUID in the current running context.
		 */
		set_cpuid_faulting(true);
	}
	preempt_enable();
}

static void enable_cpuid(void)
{
	preempt_disable();
	if (test_and_clear_thread_flag(TIF_NOCPUID)) {
		/*
		 * Must flip the CPU state synchronously with
		 * TIF_NOCPUID in the current running context.
		 */
		set_cpuid_faulting(false);
	}
	preempt_enable();
}

static int get_cpuid_mode(void)
{
	return !test_thread_flag(TIF_NOCPUID);
}

static int set_cpuid_mode(struct task_struct *task, unsigned long cpuid_enabled)
{
	if (!boot_cpu_has(X86_FEATURE_CPUID_FAULT))
		return -ENODEV;

	if (cpuid_enabled)
		enable_cpuid();
	else
		disable_cpuid();

	return 0;
}

/*
 * Called immediately after a successful exec.
 */
void arch_setup_new_exec(void)
{
	/* If cpuid was previously disabled for this task, re-enable it. */
	if (test_thread_flag(TIF_NOCPUID))
		enable_cpuid();

	/*
	 * Don't inherit TIF_SSBD across exec boundary when
	 * PR_SPEC_DISABLE_NOEXEC is used.
	 */
	if (test_thread_flag(TIF_SSBD) &&
	    task_spec_ssb_noexec(current)) {
		clear_thread_flag(TIF_SSBD);
		task_clear_spec_ssb_disable(current);
		task_clear_spec_ssb_noexec(current);
		speculation_ctrl_update(task_thread_info(current)->flags);
	}
}

#ifdef CONFIG_X86_IOPL_IOPERM
static inline void tss_invalidate_io_bitmap(struct tss_struct *tss)
{
	/*
	 * Invalidate the I/O bitmap by moving io_bitmap_base outside the
	 * TSS limit so any subsequent I/O access from user space will
	 * trigger a #GP.
	 *
	 * This is correct even when VMEXIT rewrites the TSS limit
	 * to 0x67 as the only requirement is that the base points
	 * outside the limit.
	 */
	tss->x86_tss.io_bitmap_base = IO_BITMAP_OFFSET_INVALID;
}

static inline void switch_to_bitmap(unsigned long tifp)
{
	/*
	 * Invalidate I/O bitmap if the previous task used it. This prevents
	 * any possible leakage of an active I/O bitmap.
	 *
	 * If the next task has an I/O bitmap it will handle it on exit to
	 * user mode.
	 */
	if (tifp & _TIF_IO_BITMAP)
		tss_invalidate_io_bitmap(this_cpu_ptr(&cpu_tss_rw));
}

static void tss_copy_io_bitmap(struct tss_struct *tss, struct io_bitmap *iobm)
{
	/*
	 * Copy at least the byte range of the incoming tasks bitmap which
	 * covers the permitted I/O ports.
	 *
	 * If the previous task which used an I/O bitmap had more bits
	 * permitted, then the copy needs to cover those as well so they
	 * get turned off.
	 */
	memcpy(tss->io_bitmap.bitmap, iobm->bitmap,
	       max(tss->io_bitmap.prev_max, iobm->max));

	/*
	 * Store the new max and the sequence number of this bitmap
	 * and a pointer to the bitmap itself.
	 */
	tss->io_bitmap.prev_max = iobm->max;
	tss->io_bitmap.prev_sequence = iobm->sequence;
}

/**
 * tss_update_io_bitmap - Update I/O bitmap before exiting to usermode
 */
void native_tss_update_io_bitmap(void)
{
	struct tss_struct *tss = this_cpu_ptr(&cpu_tss_rw);
	struct thread_struct *t = &current->thread;
	u16 *base = &tss->x86_tss.io_bitmap_base;

	if (!test_thread_flag(TIF_IO_BITMAP)) {
		tss_invalidate_io_bitmap(tss);
		return;
	}

	if (IS_ENABLED(CONFIG_X86_IOPL_IOPERM) && t->iopl_emul == 3) {
		*base = IO_BITMAP_OFFSET_VALID_ALL;
	} else {
		struct io_bitmap *iobm = t->io_bitmap;

		/*
		 * Only copy bitmap data when the sequence number differs. The
		 * update time is accounted to the incoming task.
		 */
		if (tss->io_bitmap.prev_sequence != iobm->sequence)
			tss_copy_io_bitmap(tss, iobm);

		/* Enable the bitmap */
		*base = IO_BITMAP_OFFSET_VALID_MAP;
	}

	/*
	 * Make sure that the TSS limit is covering the IO bitmap. It might have
	 * been cut down by a VMEXIT to 0x67 which would cause a subsequent I/O
	 * access from user space to trigger a #GP because tbe bitmap is outside
	 * the TSS limit.
	 */
	refresh_tss_limit();
}
#else /* CONFIG_X86_IOPL_IOPERM */
static inline void switch_to_bitmap(unsigned long tifp) { }
#endif

#ifdef CONFIG_SMP

struct ssb_state {
	struct ssb_state	*shared_state;
	raw_spinlock_t		lock;
	unsigned int		disable_state;
	unsigned long		local_state;
};

#define LSTATE_SSB	0

static DEFINE_PER_CPU(struct ssb_state, ssb_state);

void speculative_store_bypass_ht_init(void)
{
	struct ssb_state *st = this_cpu_ptr(&ssb_state);
	unsigned int this_cpu = smp_processor_id();
	unsigned int cpu;

	st->local_state = 0;

	/*
	 * Shared state setup happens once on the first bringup
	 * of the CPU. It's not destroyed on CPU hotunplug.
	 */
	if (st->shared_state)
		return;

	raw_spin_lock_init(&st->lock);

	/*
	 * Go over HT siblings and check whether one of them has set up the
	 * shared state pointer already.
	 */
	for_each_cpu(cpu, topology_sibling_cpumask(this_cpu)) {
		if (cpu == this_cpu)
			continue;

		if (!per_cpu(ssb_state, cpu).shared_state)
			continue;

		/* Link it to the state of the sibling: */
		st->shared_state = per_cpu(ssb_state, cpu).shared_state;
		return;
	}

	/*
	 * First HT sibling to come up on the core.  Link shared state of
	 * the first HT sibling to itself. The siblings on the same core
	 * which come up later will see the shared state pointer and link
	 * themself to the state of this CPU.
	 */
	st->shared_state = st;
}

/*
 * Logic is: First HT sibling enables SSBD for both siblings in the core
 * and last sibling to disable it, disables it for the whole core. This how
 * MSR_SPEC_CTRL works in "hardware":
 *
 *  CORE_SPEC_CTRL = THREAD0_SPEC_CTRL | THREAD1_SPEC_CTRL
 */
static __always_inline void amd_set_core_ssb_state(unsigned long tifn)
{
	struct ssb_state *st = this_cpu_ptr(&ssb_state);
	u64 msr = x86_amd_ls_cfg_base;

	if (!static_cpu_has(X86_FEATURE_ZEN)) {
		msr |= ssbd_tif_to_amd_ls_cfg(tifn);
		wrmsrl(MSR_AMD64_LS_CFG, msr);
		return;
	}

	if (tifn & _TIF_SSBD) {
		/*
		 * Since this can race with prctl(), block reentry on the
		 * same CPU.
		 */
		if (__test_and_set_bit(LSTATE_SSB, &st->local_state))
			return;

		msr |= x86_amd_ls_cfg_ssbd_mask;

		raw_spin_lock(&st->shared_state->lock);
		/* First sibling enables SSBD: */
		if (!st->shared_state->disable_state)
			wrmsrl(MSR_AMD64_LS_CFG, msr);
		st->shared_state->disable_state++;
		raw_spin_unlock(&st->shared_state->lock);
	} else {
		if (!__test_and_clear_bit(LSTATE_SSB, &st->local_state))
			return;

		raw_spin_lock(&st->shared_state->lock);
		st->shared_state->disable_state--;
		if (!st->shared_state->disable_state)
			wrmsrl(MSR_AMD64_LS_CFG, msr);
		raw_spin_unlock(&st->shared_state->lock);
	}
}
#else
static __always_inline void amd_set_core_ssb_state(unsigned long tifn)
{
	u64 msr = x86_amd_ls_cfg_base | ssbd_tif_to_amd_ls_cfg(tifn);

	wrmsrl(MSR_AMD64_LS_CFG, msr);
}
#endif

static __always_inline void amd_set_ssb_virt_state(unsigned long tifn)
{
	/*
	 * SSBD has the same definition in SPEC_CTRL and VIRT_SPEC_CTRL,
	 * so ssbd_tif_to_spec_ctrl() just works.
	 */
	wrmsrl(MSR_AMD64_VIRT_SPEC_CTRL, ssbd_tif_to_spec_ctrl(tifn));
}

/*
 * Update the MSRs managing speculation control, during context switch.
 *
 * tifp: Previous task's thread flags
 * tifn: Next task's thread flags
 */
static __always_inline void __speculation_ctrl_update(unsigned long tifp,
						      unsigned long tifn)
{
	unsigned long tif_diff = tifp ^ tifn;
	u64 msr = x86_spec_ctrl_base;
	bool updmsr = false;

	lockdep_assert_irqs_disabled();

	/*
	 * If TIF_SSBD is different, select the proper mitigation
	 * method. Note that if SSBD mitigation is disabled or permanentely
	 * enabled this branch can't be taken because nothing can set
	 * TIF_SSBD.
	 */
	if (tif_diff & _TIF_SSBD) {
		if (static_cpu_has(X86_FEATURE_VIRT_SSBD)) {
			amd_set_ssb_virt_state(tifn);
		} else if (static_cpu_has(X86_FEATURE_LS_CFG_SSBD)) {
			amd_set_core_ssb_state(tifn);
		} else if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) ||
			   static_cpu_has(X86_FEATURE_AMD_SSBD)) {
			msr |= ssbd_tif_to_spec_ctrl(tifn);
			updmsr  = true;
		}
	}

	/*
	 * Only evaluate TIF_SPEC_IB if conditional STIBP is enabled,
	 * otherwise avoid the MSR write.
	 */
	if (IS_ENABLED(CONFIG_SMP) &&
	    static_branch_unlikely(&switch_to_cond_stibp)) {
		updmsr |= !!(tif_diff & _TIF_SPEC_IB);
		msr |= stibp_tif_to_spec_ctrl(tifn);
	}

	if (updmsr)
		wrmsrl(MSR_IA32_SPEC_CTRL, msr);
}

static unsigned long speculation_ctrl_update_tif(struct task_struct *tsk)
{
	if (test_and_clear_tsk_thread_flag(tsk, TIF_SPEC_FORCE_UPDATE)) {
		if (task_spec_ssb_disable(tsk))
			set_tsk_thread_flag(tsk, TIF_SSBD);
		else
			clear_tsk_thread_flag(tsk, TIF_SSBD);

		if (task_spec_ib_disable(tsk))
			set_tsk_thread_flag(tsk, TIF_SPEC_IB);
		else
			clear_tsk_thread_flag(tsk, TIF_SPEC_IB);
	}
	/* Return the updated threadinfo flags*/
	return task_thread_info(tsk)->flags;
}

void speculation_ctrl_update(unsigned long tif)
{
	unsigned long flags;

	/* Forced update. Make sure all relevant TIF flags are different */
	local_irq_save(flags);
	__speculation_ctrl_update(~tif, tif);
	local_irq_restore(flags);
}

/* Called from seccomp/prctl update */
void speculation_ctrl_update_current(void)
{
	preempt_disable();
	speculation_ctrl_update(speculation_ctrl_update_tif(current));
	preempt_enable();
}

void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p)
{
	unsigned long tifp, tifn;

	tifn = READ_ONCE(task_thread_info(next_p)->flags);
	tifp = READ_ONCE(task_thread_info(prev_p)->flags);

	switch_to_bitmap(tifp);

	propagate_user_return_notify(prev_p, next_p);

	if ((tifp & _TIF_BLOCKSTEP || tifn & _TIF_BLOCKSTEP) &&
	    arch_has_block_step()) {
		unsigned long debugctl, msk;

		rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
		debugctl &= ~DEBUGCTLMSR_BTF;
		msk = tifn & _TIF_BLOCKSTEP;
		debugctl |= (msk >> TIF_BLOCKSTEP) << DEBUGCTLMSR_BTF_SHIFT;
		wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
	}

	if ((tifp ^ tifn) & _TIF_NOTSC)
		cr4_toggle_bits_irqsoff(X86_CR4_TSD);

	if ((tifp ^ tifn) & _TIF_NOCPUID)
		set_cpuid_faulting(!!(tifn & _TIF_NOCPUID));

	if (likely(!((tifp | tifn) & _TIF_SPEC_FORCE_UPDATE))) {
		__speculation_ctrl_update(tifp, tifn);
	} else {
		speculation_ctrl_update_tif(prev_p);
		tifn = speculation_ctrl_update_tif(next_p);

		/* Enforce MSR update to ensure consistent state */
		__speculation_ctrl_update(~tifn, tifn);
	}
}

/*
 * Idle related variables and functions
 */
unsigned long boot_option_idle_override = IDLE_NO_OVERRIDE;
EXPORT_SYMBOL(boot_option_idle_override);

static void (*x86_idle)(void);

#ifndef CONFIG_SMP
static inline void play_dead(void)
{
	BUG();
}
#endif

void arch_cpu_idle_enter(void)
{
	tsc_verify_tsc_adjust(false);
	local_touch_nmi();
}

void arch_cpu_idle_dead(void)
{
	play_dead();
}

/*
 * Called from the generic idle code.
 */
void arch_cpu_idle(void)
{
	x86_idle();
}

/*
 * We use this if we don't have any better idle routine..
 */
void __cpuidle default_idle(void)
{
	trace_cpu_idle_rcuidle(1, smp_processor_id());
	safe_halt();
	trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
}
#if defined(CONFIG_APM_MODULE) || defined(CONFIG_HALTPOLL_CPUIDLE_MODULE)
EXPORT_SYMBOL(default_idle);
#endif

#ifdef CONFIG_XEN
bool xen_set_default_idle(void)
{
	bool ret = !!x86_idle;

	x86_idle = default_idle;

	return ret;
}
#endif

void stop_this_cpu(void *dummy)
{
	local_irq_disable();
	/*
	 * Remove this CPU:
	 */
	set_cpu_online(smp_processor_id(), false);
	disable_local_APIC();
	mcheck_cpu_clear(this_cpu_ptr(&cpu_info));

	/*
	 * Use wbinvd on processors that support SME. This provides support
	 * for performing a successful kexec when going from SME inactive
	 * to SME active (or vice-versa). The cache must be cleared so that
	 * if there are entries with the same physical address, both with and
	 * without the encryption bit, they don't race each other when flushed
	 * and potentially end up with the wrong entry being committed to
	 * memory.
	 */
	if (boot_cpu_has(X86_FEATURE_SME))
		native_wbinvd();
	for (;;) {
		/*
		 * Use native_halt() so that memory contents don't change
		 * (stack usage and variables) after possibly issuing the
		 * native_wbinvd() above.
		 */
		native_halt();
	}
}

/*
 * AMD Erratum 400 aware idle routine. We handle it the same way as C3 power
 * states (local apic timer and TSC stop).
 */
static void amd_e400_idle(void)
{
	/*
	 * We cannot use static_cpu_has_bug() here because X86_BUG_AMD_APIC_C1E
	 * gets set after static_cpu_has() places have been converted via
	 * alternatives.
	 */
	if (!boot_cpu_has_bug(X86_BUG_AMD_APIC_C1E)) {
		default_idle();
		return;
	}

	tick_broadcast_enter();

	default_idle();

	/*
	 * The switch back from broadcast mode needs to be called with
	 * interrupts disabled.
	 */
	local_irq_disable();
	tick_broadcast_exit();
	local_irq_enable();
}

/*
 * Intel Core2 and older machines prefer MWAIT over HALT for C1.
 * We can't rely on cpuidle installing MWAIT, because it will not load
 * on systems that support only C1 -- so the boot default must be MWAIT.
 *
 * Some AMD machines are the opposite, they depend on using HALT.
 *
 * So for default C1, which is used during boot until cpuidle loads,
 * use MWAIT-C1 on Intel HW that has it, else use HALT.
 */
static int prefer_mwait_c1_over_halt(const struct cpuinfo_x86 *c)
{
	if (c->x86_vendor != X86_VENDOR_INTEL)
		return 0;

	if (!cpu_has(c, X86_FEATURE_MWAIT) || boot_cpu_has_bug(X86_BUG_MONITOR))
		return 0;

	return 1;
}

/*
 * MONITOR/MWAIT with no hints, used for default C1 state. This invokes MWAIT
 * with interrupts enabled and no flags, which is backwards compatible with the
 * original MWAIT implementation.
 */
static __cpuidle void mwait_idle(void)
{
	if (!current_set_polling_and_test()) {
		trace_cpu_idle_rcuidle(1, smp_processor_id());
		if (this_cpu_has(X86_BUG_CLFLUSH_MONITOR)) {
			mb(); /* quirk */
			clflush((void *)&current_thread_info()->flags);
			mb(); /* quirk */
		}

		__monitor((void *)&current_thread_info()->flags, 0, 0);
		if (!need_resched())
			__sti_mwait(0, 0);
		else
			local_irq_enable();
		trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
	} else {
		local_irq_enable();
	}
	__current_clr_polling();
}

void select_idle_routine(const struct cpuinfo_x86 *c)
{
#ifdef CONFIG_SMP
	if (boot_option_idle_override == IDLE_POLL && smp_num_siblings > 1)
		pr_warn_once("WARNING: polling idle and HT enabled, performance may degrade\n");
#endif
	if (x86_idle || boot_option_idle_override == IDLE_POLL)
		return;

	if (boot_cpu_has_bug(X86_BUG_AMD_E400)) {
		pr_info("using AMD E400 aware idle routine\n");
		x86_idle = amd_e400_idle;
	} else if (prefer_mwait_c1_over_halt(c)) {
		pr_info("using mwait in idle threads\n");
		x86_idle = mwait_idle;
	} else
		x86_idle = default_idle;
}

void amd_e400_c1e_apic_setup(void)
{
	if (boot_cpu_has_bug(X86_BUG_AMD_APIC_C1E)) {
		pr_info("Switch to broadcast mode on CPU%d\n", smp_processor_id());
		local_irq_disable();
		tick_broadcast_force();
		local_irq_enable();
	}
}

void __init arch_post_acpi_subsys_init(void)
{
	u32 lo, hi;

	if (!boot_cpu_has_bug(X86_BUG_AMD_E400))
		return;

	/*
	 * AMD E400 detection needs to happen after ACPI has been enabled. If
	 * the machine is affected K8_INTP_C1E_ACTIVE_MASK bits are set in
	 * MSR_K8_INT_PENDING_MSG.
	 */
	rdmsr(MSR_K8_INT_PENDING_MSG, lo, hi);
	if (!(lo & K8_INTP_C1E_ACTIVE_MASK))
		return;

	boot_cpu_set_bug(X86_BUG_AMD_APIC_C1E);

	if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC))
		mark_tsc_unstable("TSC halt in AMD C1E");
	pr_info("System has AMD C1E enabled\n");
}

static int __init idle_setup(char *str)
{
	if (!str)
		return -EINVAL;

	if (!strcmp(str, "poll")) {
		pr_info("using polling idle threads\n");
		boot_option_idle_override = IDLE_POLL;
		cpu_idle_poll_ctrl(true);
	} else if (!strcmp(str, "halt")) {
		/*
		 * When the boot option of idle=halt is added, halt is
		 * forced to be used for CPU idle. In such case CPU C2/C3
		 * won't be used again.
		 * To continue to load the CPU idle driver, don't touch
		 * the boot_option_idle_override.
		 */
		x86_idle = default_idle;
		boot_option_idle_override = IDLE_HALT;
	} else if (!strcmp(str, "nomwait")) {
		/*
		 * If the boot option of "idle=nomwait" is added,
		 * it means that mwait will be disabled for CPU C2/C3
		 * states. In such case it won't touch the variable
		 * of boot_option_idle_override.
		 */
		boot_option_idle_override = IDLE_NOMWAIT;
	} else
		return -1;

	return 0;
}
early_param("idle", idle_setup);

unsigned long arch_align_stack(unsigned long sp)
{
	if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space)
		sp -= get_random_int() % 8192;
	return sp & ~0xf;
}

unsigned long arch_randomize_brk(struct mm_struct *mm)
{
	return randomize_page(mm->brk, 0x02000000);
}

/*
 * Called from fs/proc with a reference on @p to find the function
 * which called into schedule(). This needs to be done carefully
 * because the task might wake up and we might look at a stack
 * changing under us.
 */
unsigned long get_wchan(struct task_struct *p)
{
	unsigned long start, bottom, top, sp, fp, ip, ret = 0;
	int count = 0;

	if (p == current || p->state == TASK_RUNNING)
		return 0;

	if (!try_get_task_stack(p))
		return 0;

	start = (unsigned long)task_stack_page(p);
	if (!start)
		goto out;

	/*
	 * Layout of the stack page:
	 *
	 * ----------- topmax = start + THREAD_SIZE - sizeof(unsigned long)
	 * PADDING
	 * ----------- top = topmax - TOP_OF_KERNEL_STACK_PADDING
	 * stack
	 * ----------- bottom = start
	 *
	 * The tasks stack pointer points at the location where the
	 * framepointer is stored. The data on the stack is:
	 * ... IP FP ... IP FP
	 *
	 * We need to read FP and IP, so we need to adjust the upper
	 * bound by another unsigned long.
	 */
	top = start + THREAD_SIZE - TOP_OF_KERNEL_STACK_PADDING;
	top -= 2 * sizeof(unsigned long);
	bottom = start;

	sp = READ_ONCE(p->thread.sp);
	if (sp < bottom || sp > top)
		goto out;

	fp = READ_ONCE_NOCHECK(((struct inactive_task_frame *)sp)->bp);
	do {
		if (fp < bottom || fp > top)
			goto out;
		ip = READ_ONCE_NOCHECK(*(unsigned long *)(fp + sizeof(unsigned long)));
		if (!in_sched_functions(ip)) {
			ret = ip;
			goto out;
		}
		fp = READ_ONCE_NOCHECK(*(unsigned long *)fp);
	} while (count++ < 16 && p->state != TASK_RUNNING);

out:
	put_task_stack(p);
	return ret;
}

long do_arch_prctl_common(struct task_struct *task, int option,
			  unsigned long cpuid_enabled)
{
	switch (option) {
	case ARCH_GET_CPUID:
		return get_cpuid_mode();
	case ARCH_SET_CPUID:
		return set_cpuid_mode(task, cpuid_enabled);
	}

	return -EINVAL;
}