summaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel/process_64.c
blob: 7f94dbbc397b7c1833054222b3ff075dd34d795c (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 *  Copyright (C) 1995  Linus Torvalds
 *
 *  Pentium III FXSR, SSE support
 *	Gareth Hughes <gareth@valinux.com>, May 2000
 *
 *  X86-64 port
 *	Andi Kleen.
 *
 *	CPU hotplug support - ashok.raj@intel.com
 */

/*
 * This file handles the architecture-dependent parts of process handling..
 */

#include <linux/cpu.h>
#include <linux/errno.h>
#include <linux/sched.h>
#include <linux/sched/task.h>
#include <linux/sched/task_stack.h>
#include <linux/fs.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/elfcore.h>
#include <linux/smp.h>
#include <linux/slab.h>
#include <linux/user.h>
#include <linux/interrupt.h>
#include <linux/delay.h>
#include <linux/export.h>
#include <linux/ptrace.h>
#include <linux/notifier.h>
#include <linux/kprobes.h>
#include <linux/kdebug.h>
#include <linux/prctl.h>
#include <linux/uaccess.h>
#include <linux/io.h>
#include <linux/ftrace.h>
#include <linux/syscalls.h>

#include <asm/processor.h>
#include <asm/pkru.h>
#include <asm/fpu/sched.h>
#include <asm/mmu_context.h>
#include <asm/prctl.h>
#include <asm/desc.h>
#include <asm/proto.h>
#include <asm/ia32.h>
#include <asm/debugreg.h>
#include <asm/switch_to.h>
#include <asm/xen/hypervisor.h>
#include <asm/vdso.h>
#include <asm/resctrl.h>
#include <asm/unistd.h>
#include <asm/fsgsbase.h>
#ifdef CONFIG_IA32_EMULATION
/* Not included via unistd.h */
#include <asm/unistd_32_ia32.h>
#endif

#include "process.h"

/* Prints also some state that isn't saved in the pt_regs */
void __show_regs(struct pt_regs *regs, enum show_regs_mode mode,
		 const char *log_lvl)
{
	unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L, fs, gs, shadowgs;
	unsigned long d0, d1, d2, d3, d6, d7;
	unsigned int fsindex, gsindex;
	unsigned int ds, es;

	show_iret_regs(regs, log_lvl);

	if (regs->orig_ax != -1)
		pr_cont(" ORIG_RAX: %016lx\n", regs->orig_ax);
	else
		pr_cont("\n");

	printk("%sRAX: %016lx RBX: %016lx RCX: %016lx\n",
	       log_lvl, regs->ax, regs->bx, regs->cx);
	printk("%sRDX: %016lx RSI: %016lx RDI: %016lx\n",
	       log_lvl, regs->dx, regs->si, regs->di);
	printk("%sRBP: %016lx R08: %016lx R09: %016lx\n",
	       log_lvl, regs->bp, regs->r8, regs->r9);
	printk("%sR10: %016lx R11: %016lx R12: %016lx\n",
	       log_lvl, regs->r10, regs->r11, regs->r12);
	printk("%sR13: %016lx R14: %016lx R15: %016lx\n",
	       log_lvl, regs->r13, regs->r14, regs->r15);

	if (mode == SHOW_REGS_SHORT)
		return;

	if (mode == SHOW_REGS_USER) {
		rdmsrl(MSR_FS_BASE, fs);
		rdmsrl(MSR_KERNEL_GS_BASE, shadowgs);
		printk("%sFS:  %016lx GS:  %016lx\n",
		       log_lvl, fs, shadowgs);
		return;
	}

	asm("movl %%ds,%0" : "=r" (ds));
	asm("movl %%es,%0" : "=r" (es));
	asm("movl %%fs,%0" : "=r" (fsindex));
	asm("movl %%gs,%0" : "=r" (gsindex));

	rdmsrl(MSR_FS_BASE, fs);
	rdmsrl(MSR_GS_BASE, gs);
	rdmsrl(MSR_KERNEL_GS_BASE, shadowgs);

	cr0 = read_cr0();
	cr2 = read_cr2();
	cr3 = __read_cr3();
	cr4 = __read_cr4();

	printk("%sFS:  %016lx(%04x) GS:%016lx(%04x) knlGS:%016lx\n",
	       log_lvl, fs, fsindex, gs, gsindex, shadowgs);
	printk("%sCS:  %04lx DS: %04x ES: %04x CR0: %016lx\n",
		log_lvl, regs->cs, ds, es, cr0);
	printk("%sCR2: %016lx CR3: %016lx CR4: %016lx\n",
		log_lvl, cr2, cr3, cr4);

	get_debugreg(d0, 0);
	get_debugreg(d1, 1);
	get_debugreg(d2, 2);
	get_debugreg(d3, 3);
	get_debugreg(d6, 6);
	get_debugreg(d7, 7);

	/* Only print out debug registers if they are in their non-default state. */
	if (!((d0 == 0) && (d1 == 0) && (d2 == 0) && (d3 == 0) &&
	    (d6 == DR6_RESERVED) && (d7 == 0x400))) {
		printk("%sDR0: %016lx DR1: %016lx DR2: %016lx\n",
		       log_lvl, d0, d1, d2);
		printk("%sDR3: %016lx DR6: %016lx DR7: %016lx\n",
		       log_lvl, d3, d6, d7);
	}

	if (cpu_feature_enabled(X86_FEATURE_OSPKE))
		printk("%sPKRU: %08x\n", log_lvl, read_pkru());
}

void release_thread(struct task_struct *dead_task)
{
	WARN_ON(dead_task->mm);
}

enum which_selector {
	FS,
	GS
};

/*
 * Out of line to be protected from kprobes and tracing. If this would be
 * traced or probed than any access to a per CPU variable happens with
 * the wrong GS.
 *
 * It is not used on Xen paravirt. When paravirt support is needed, it
 * needs to be renamed with native_ prefix.
 */
static noinstr unsigned long __rdgsbase_inactive(void)
{
	unsigned long gsbase;

	lockdep_assert_irqs_disabled();

	if (!static_cpu_has(X86_FEATURE_XENPV)) {
		native_swapgs();
		gsbase = rdgsbase();
		native_swapgs();
	} else {
		instrumentation_begin();
		rdmsrl(MSR_KERNEL_GS_BASE, gsbase);
		instrumentation_end();
	}

	return gsbase;
}

/*
 * Out of line to be protected from kprobes and tracing. If this would be
 * traced or probed than any access to a per CPU variable happens with
 * the wrong GS.
 *
 * It is not used on Xen paravirt. When paravirt support is needed, it
 * needs to be renamed with native_ prefix.
 */
static noinstr void __wrgsbase_inactive(unsigned long gsbase)
{
	lockdep_assert_irqs_disabled();

	if (!static_cpu_has(X86_FEATURE_XENPV)) {
		native_swapgs();
		wrgsbase(gsbase);
		native_swapgs();
	} else {
		instrumentation_begin();
		wrmsrl(MSR_KERNEL_GS_BASE, gsbase);
		instrumentation_end();
	}
}

/*
 * Saves the FS or GS base for an outgoing thread if FSGSBASE extensions are
 * not available.  The goal is to be reasonably fast on non-FSGSBASE systems.
 * It's forcibly inlined because it'll generate better code and this function
 * is hot.
 */
static __always_inline void save_base_legacy(struct task_struct *prev_p,
					     unsigned short selector,
					     enum which_selector which)
{
	if (likely(selector == 0)) {
		/*
		 * On Intel (without X86_BUG_NULL_SEG), the segment base could
		 * be the pre-existing saved base or it could be zero.  On AMD
		 * (with X86_BUG_NULL_SEG), the segment base could be almost
		 * anything.
		 *
		 * This branch is very hot (it's hit twice on almost every
		 * context switch between 64-bit programs), and avoiding
		 * the RDMSR helps a lot, so we just assume that whatever
		 * value is already saved is correct.  This matches historical
		 * Linux behavior, so it won't break existing applications.
		 *
		 * To avoid leaking state, on non-X86_BUG_NULL_SEG CPUs, if we
		 * report that the base is zero, it needs to actually be zero:
		 * see the corresponding logic in load_seg_legacy.
		 */
	} else {
		/*
		 * If the selector is 1, 2, or 3, then the base is zero on
		 * !X86_BUG_NULL_SEG CPUs and could be anything on
		 * X86_BUG_NULL_SEG CPUs.  In the latter case, Linux
		 * has never attempted to preserve the base across context
		 * switches.
		 *
		 * If selector > 3, then it refers to a real segment, and
		 * saving the base isn't necessary.
		 */
		if (which == FS)
			prev_p->thread.fsbase = 0;
		else
			prev_p->thread.gsbase = 0;
	}
}

static __always_inline void save_fsgs(struct task_struct *task)
{
	savesegment(fs, task->thread.fsindex);
	savesegment(gs, task->thread.gsindex);
	if (static_cpu_has(X86_FEATURE_FSGSBASE)) {
		/*
		 * If FSGSBASE is enabled, we can't make any useful guesses
		 * about the base, and user code expects us to save the current
		 * value.  Fortunately, reading the base directly is efficient.
		 */
		task->thread.fsbase = rdfsbase();
		task->thread.gsbase = __rdgsbase_inactive();
	} else {
		save_base_legacy(task, task->thread.fsindex, FS);
		save_base_legacy(task, task->thread.gsindex, GS);
	}
}

/*
 * While a process is running,current->thread.fsbase and current->thread.gsbase
 * may not match the corresponding CPU registers (see save_base_legacy()).
 */
void current_save_fsgs(void)
{
	unsigned long flags;

	/* Interrupts need to be off for FSGSBASE */
	local_irq_save(flags);
	save_fsgs(current);
	local_irq_restore(flags);
}
#if IS_ENABLED(CONFIG_KVM)
EXPORT_SYMBOL_GPL(current_save_fsgs);
#endif

static __always_inline void loadseg(enum which_selector which,
				    unsigned short sel)
{
	if (which == FS)
		loadsegment(fs, sel);
	else
		load_gs_index(sel);
}

static __always_inline void load_seg_legacy(unsigned short prev_index,
					    unsigned long prev_base,
					    unsigned short next_index,
					    unsigned long next_base,
					    enum which_selector which)
{
	if (likely(next_index <= 3)) {
		/*
		 * The next task is using 64-bit TLS, is not using this
		 * segment at all, or is having fun with arcane CPU features.
		 */
		if (next_base == 0) {
			/*
			 * Nasty case: on AMD CPUs, we need to forcibly zero
			 * the base.
			 */
			if (static_cpu_has_bug(X86_BUG_NULL_SEG)) {
				loadseg(which, __USER_DS);
				loadseg(which, next_index);
			} else {
				/*
				 * We could try to exhaustively detect cases
				 * under which we can skip the segment load,
				 * but there's really only one case that matters
				 * for performance: if both the previous and
				 * next states are fully zeroed, we can skip
				 * the load.
				 *
				 * (This assumes that prev_base == 0 has no
				 * false positives.  This is the case on
				 * Intel-style CPUs.)
				 */
				if (likely(prev_index | next_index | prev_base))
					loadseg(which, next_index);
			}
		} else {
			if (prev_index != next_index)
				loadseg(which, next_index);
			wrmsrl(which == FS ? MSR_FS_BASE : MSR_KERNEL_GS_BASE,
			       next_base);
		}
	} else {
		/*
		 * The next task is using a real segment.  Loading the selector
		 * is sufficient.
		 */
		loadseg(which, next_index);
	}
}

/*
 * Store prev's PKRU value and load next's PKRU value if they differ. PKRU
 * is not XSTATE managed on context switch because that would require a
 * lookup in the task's FPU xsave buffer and require to keep that updated
 * in various places.
 */
static __always_inline void x86_pkru_load(struct thread_struct *prev,
					  struct thread_struct *next)
{
	if (!cpu_feature_enabled(X86_FEATURE_OSPKE))
		return;

	/* Stash the prev task's value: */
	prev->pkru = rdpkru();

	/*
	 * PKRU writes are slightly expensive.  Avoid them when not
	 * strictly necessary:
	 */
	if (prev->pkru != next->pkru)
		wrpkru(next->pkru);
}

static __always_inline void x86_fsgsbase_load(struct thread_struct *prev,
					      struct thread_struct *next)
{
	if (static_cpu_has(X86_FEATURE_FSGSBASE)) {
		/* Update the FS and GS selectors if they could have changed. */
		if (unlikely(prev->fsindex || next->fsindex))
			loadseg(FS, next->fsindex);
		if (unlikely(prev->gsindex || next->gsindex))
			loadseg(GS, next->gsindex);

		/* Update the bases. */
		wrfsbase(next->fsbase);
		__wrgsbase_inactive(next->gsbase);
	} else {
		load_seg_legacy(prev->fsindex, prev->fsbase,
				next->fsindex, next->fsbase, FS);
		load_seg_legacy(prev->gsindex, prev->gsbase,
				next->gsindex, next->gsbase, GS);
	}
}

unsigned long x86_fsgsbase_read_task(struct task_struct *task,
				     unsigned short selector)
{
	unsigned short idx = selector >> 3;
	unsigned long base;

	if (likely((selector & SEGMENT_TI_MASK) == 0)) {
		if (unlikely(idx >= GDT_ENTRIES))
			return 0;

		/*
		 * There are no user segments in the GDT with nonzero bases
		 * other than the TLS segments.
		 */
		if (idx < GDT_ENTRY_TLS_MIN || idx > GDT_ENTRY_TLS_MAX)
			return 0;

		idx -= GDT_ENTRY_TLS_MIN;
		base = get_desc_base(&task->thread.tls_array[idx]);
	} else {
#ifdef CONFIG_MODIFY_LDT_SYSCALL
		struct ldt_struct *ldt;

		/*
		 * If performance here mattered, we could protect the LDT
		 * with RCU.  This is a slow path, though, so we can just
		 * take the mutex.
		 */
		mutex_lock(&task->mm->context.lock);
		ldt = task->mm->context.ldt;
		if (unlikely(!ldt || idx >= ldt->nr_entries))
			base = 0;
		else
			base = get_desc_base(ldt->entries + idx);
		mutex_unlock(&task->mm->context.lock);
#else
		base = 0;
#endif
	}

	return base;
}

unsigned long x86_gsbase_read_cpu_inactive(void)
{
	unsigned long gsbase;

	if (boot_cpu_has(X86_FEATURE_FSGSBASE)) {
		unsigned long flags;

		local_irq_save(flags);
		gsbase = __rdgsbase_inactive();
		local_irq_restore(flags);
	} else {
		rdmsrl(MSR_KERNEL_GS_BASE, gsbase);
	}

	return gsbase;
}

void x86_gsbase_write_cpu_inactive(unsigned long gsbase)
{
	if (boot_cpu_has(X86_FEATURE_FSGSBASE)) {
		unsigned long flags;

		local_irq_save(flags);
		__wrgsbase_inactive(gsbase);
		local_irq_restore(flags);
	} else {
		wrmsrl(MSR_KERNEL_GS_BASE, gsbase);
	}
}

unsigned long x86_fsbase_read_task(struct task_struct *task)
{
	unsigned long fsbase;

	if (task == current)
		fsbase = x86_fsbase_read_cpu();
	else if (boot_cpu_has(X86_FEATURE_FSGSBASE) ||
		 (task->thread.fsindex == 0))
		fsbase = task->thread.fsbase;
	else
		fsbase = x86_fsgsbase_read_task(task, task->thread.fsindex);

	return fsbase;
}

unsigned long x86_gsbase_read_task(struct task_struct *task)
{
	unsigned long gsbase;

	if (task == current)
		gsbase = x86_gsbase_read_cpu_inactive();
	else if (boot_cpu_has(X86_FEATURE_FSGSBASE) ||
		 (task->thread.gsindex == 0))
		gsbase = task->thread.gsbase;
	else
		gsbase = x86_fsgsbase_read_task(task, task->thread.gsindex);

	return gsbase;
}

void x86_fsbase_write_task(struct task_struct *task, unsigned long fsbase)
{
	WARN_ON_ONCE(task == current);

	task->thread.fsbase = fsbase;
}

void x86_gsbase_write_task(struct task_struct *task, unsigned long gsbase)
{
	WARN_ON_ONCE(task == current);

	task->thread.gsbase = gsbase;
}

static void
start_thread_common(struct pt_regs *regs, unsigned long new_ip,
		    unsigned long new_sp,
		    unsigned int _cs, unsigned int _ss, unsigned int _ds)
{
	WARN_ON_ONCE(regs != current_pt_regs());

	if (static_cpu_has(X86_BUG_NULL_SEG)) {
		/* Loading zero below won't clear the base. */
		loadsegment(fs, __USER_DS);
		load_gs_index(__USER_DS);
	}

	loadsegment(fs, 0);
	loadsegment(es, _ds);
	loadsegment(ds, _ds);
	load_gs_index(0);

	regs->ip		= new_ip;
	regs->sp		= new_sp;
	regs->cs		= _cs;
	regs->ss		= _ss;
	regs->flags		= X86_EFLAGS_IF;
}

void
start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp)
{
	start_thread_common(regs, new_ip, new_sp,
			    __USER_CS, __USER_DS, 0);
}
EXPORT_SYMBOL_GPL(start_thread);

#ifdef CONFIG_COMPAT
void compat_start_thread(struct pt_regs *regs, u32 new_ip, u32 new_sp, bool x32)
{
	start_thread_common(regs, new_ip, new_sp,
			    x32 ? __USER_CS : __USER32_CS,
			    __USER_DS, __USER_DS);
}
#endif

/*
 *	switch_to(x,y) should switch tasks from x to y.
 *
 * This could still be optimized:
 * - fold all the options into a flag word and test it with a single test.
 * - could test fs/gs bitsliced
 *
 * Kprobes not supported here. Set the probe on schedule instead.
 * Function graph tracer not supported too.
 */
__no_kmsan_checks
__visible __notrace_funcgraph struct task_struct *
__switch_to(struct task_struct *prev_p, struct task_struct *next_p)
{
	struct thread_struct *prev = &prev_p->thread;
	struct thread_struct *next = &next_p->thread;
	struct fpu *prev_fpu = &prev->fpu;
	int cpu = smp_processor_id();

	WARN_ON_ONCE(IS_ENABLED(CONFIG_DEBUG_ENTRY) &&
		     this_cpu_read(hardirq_stack_inuse));

	if (!test_thread_flag(TIF_NEED_FPU_LOAD))
		switch_fpu_prepare(prev_fpu, cpu);

	/* We must save %fs and %gs before load_TLS() because
	 * %fs and %gs may be cleared by load_TLS().
	 *
	 * (e.g. xen_load_tls())
	 */
	save_fsgs(prev_p);

	/*
	 * Load TLS before restoring any segments so that segment loads
	 * reference the correct GDT entries.
	 */
	load_TLS(next, cpu);

	/*
	 * Leave lazy mode, flushing any hypercalls made here.  This
	 * must be done after loading TLS entries in the GDT but before
	 * loading segments that might reference them.
	 */
	arch_end_context_switch(next_p);

	/* Switch DS and ES.
	 *
	 * Reading them only returns the selectors, but writing them (if
	 * nonzero) loads the full descriptor from the GDT or LDT.  The
	 * LDT for next is loaded in switch_mm, and the GDT is loaded
	 * above.
	 *
	 * We therefore need to write new values to the segment
	 * registers on every context switch unless both the new and old
	 * values are zero.
	 *
	 * Note that we don't need to do anything for CS and SS, as
	 * those are saved and restored as part of pt_regs.
	 */
	savesegment(es, prev->es);
	if (unlikely(next->es | prev->es))
		loadsegment(es, next->es);

	savesegment(ds, prev->ds);
	if (unlikely(next->ds | prev->ds))
		loadsegment(ds, next->ds);

	x86_fsgsbase_load(prev, next);

	x86_pkru_load(prev, next);

	/*
	 * Switch the PDA and FPU contexts.
	 */
	this_cpu_write(current_task, next_p);
	this_cpu_write(cpu_current_top_of_stack, task_top_of_stack(next_p));

	switch_fpu_finish();

	/* Reload sp0. */
	update_task_stack(next_p);

	switch_to_extra(prev_p, next_p);

	if (static_cpu_has_bug(X86_BUG_SYSRET_SS_ATTRS)) {
		/*
		 * AMD CPUs have a misfeature: SYSRET sets the SS selector but
		 * does not update the cached descriptor.  As a result, if we
		 * do SYSRET while SS is NULL, we'll end up in user mode with
		 * SS apparently equal to __USER_DS but actually unusable.
		 *
		 * The straightforward workaround would be to fix it up just
		 * before SYSRET, but that would slow down the system call
		 * fast paths.  Instead, we ensure that SS is never NULL in
		 * system call context.  We do this by replacing NULL SS
		 * selectors at every context switch.  SYSCALL sets up a valid
		 * SS, so the only way to get NULL is to re-enter the kernel
		 * from CPL 3 through an interrupt.  Since that can't happen
		 * in the same task as a running syscall, we are guaranteed to
		 * context switch between every interrupt vector entry and a
		 * subsequent SYSRET.
		 *
		 * We read SS first because SS reads are much faster than
		 * writes.  Out of caution, we force SS to __KERNEL_DS even if
		 * it previously had a different non-NULL value.
		 */
		unsigned short ss_sel;
		savesegment(ss, ss_sel);
		if (ss_sel != __KERNEL_DS)
			loadsegment(ss, __KERNEL_DS);
	}

	/* Load the Intel cache allocation PQR MSR. */
	resctrl_sched_in(next_p);

	return prev_p;
}

void set_personality_64bit(void)
{
	/* inherit personality from parent */

	/* Make sure to be in 64bit mode */
	clear_thread_flag(TIF_ADDR32);
	/* Pretend that this comes from a 64bit execve */
	task_pt_regs(current)->orig_ax = __NR_execve;
	current_thread_info()->status &= ~TS_COMPAT;
	if (current->mm)
		current->mm->context.flags = MM_CONTEXT_HAS_VSYSCALL;

	/* TBD: overwrites user setup. Should have two bits.
	   But 64bit processes have always behaved this way,
	   so it's not too bad. The main problem is just that
	   32bit children are affected again. */
	current->personality &= ~READ_IMPLIES_EXEC;
}

static void __set_personality_x32(void)
{
#ifdef CONFIG_X86_X32_ABI
	if (current->mm)
		current->mm->context.flags = 0;

	current->personality &= ~READ_IMPLIES_EXEC;
	/*
	 * in_32bit_syscall() uses the presence of the x32 syscall bit
	 * flag to determine compat status.  The x86 mmap() code relies on
	 * the syscall bitness so set x32 syscall bit right here to make
	 * in_32bit_syscall() work during exec().
	 *
	 * Pretend to come from a x32 execve.
	 */
	task_pt_regs(current)->orig_ax = __NR_x32_execve | __X32_SYSCALL_BIT;
	current_thread_info()->status &= ~TS_COMPAT;
#endif
}

static void __set_personality_ia32(void)
{
#ifdef CONFIG_IA32_EMULATION
	if (current->mm) {
		/*
		 * uprobes applied to this MM need to know this and
		 * cannot use user_64bit_mode() at that time.
		 */
		current->mm->context.flags = MM_CONTEXT_UPROBE_IA32;
	}

	current->personality |= force_personality32;
	/* Prepare the first "return" to user space */
	task_pt_regs(current)->orig_ax = __NR_ia32_execve;
	current_thread_info()->status |= TS_COMPAT;
#endif
}

void set_personality_ia32(bool x32)
{
	/* Make sure to be in 32bit mode */
	set_thread_flag(TIF_ADDR32);

	if (x32)
		__set_personality_x32();
	else
		__set_personality_ia32();
}
EXPORT_SYMBOL_GPL(set_personality_ia32);

#ifdef CONFIG_CHECKPOINT_RESTORE
static long prctl_map_vdso(const struct vdso_image *image, unsigned long addr)
{
	int ret;

	ret = map_vdso_once(image, addr);
	if (ret)
		return ret;

	return (long)image->size;
}
#endif

long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2)
{
	int ret = 0;

	switch (option) {
	case ARCH_SET_GS: {
		if (unlikely(arg2 >= TASK_SIZE_MAX))
			return -EPERM;

		preempt_disable();
		/*
		 * ARCH_SET_GS has always overwritten the index
		 * and the base. Zero is the most sensible value
		 * to put in the index, and is the only value that
		 * makes any sense if FSGSBASE is unavailable.
		 */
		if (task == current) {
			loadseg(GS, 0);
			x86_gsbase_write_cpu_inactive(arg2);

			/*
			 * On non-FSGSBASE systems, save_base_legacy() expects
			 * that we also fill in thread.gsbase.
			 */
			task->thread.gsbase = arg2;

		} else {
			task->thread.gsindex = 0;
			x86_gsbase_write_task(task, arg2);
		}
		preempt_enable();
		break;
	}
	case ARCH_SET_FS: {
		/*
		 * Not strictly needed for %fs, but do it for symmetry
		 * with %gs
		 */
		if (unlikely(arg2 >= TASK_SIZE_MAX))
			return -EPERM;

		preempt_disable();
		/*
		 * Set the selector to 0 for the same reason
		 * as %gs above.
		 */
		if (task == current) {
			loadseg(FS, 0);
			x86_fsbase_write_cpu(arg2);

			/*
			 * On non-FSGSBASE systems, save_base_legacy() expects
			 * that we also fill in thread.fsbase.
			 */
			task->thread.fsbase = arg2;
		} else {
			task->thread.fsindex = 0;
			x86_fsbase_write_task(task, arg2);
		}
		preempt_enable();
		break;
	}
	case ARCH_GET_FS: {
		unsigned long base = x86_fsbase_read_task(task);

		ret = put_user(base, (unsigned long __user *)arg2);
		break;
	}
	case ARCH_GET_GS: {
		unsigned long base = x86_gsbase_read_task(task);

		ret = put_user(base, (unsigned long __user *)arg2);
		break;
	}

#ifdef CONFIG_CHECKPOINT_RESTORE
# ifdef CONFIG_X86_X32_ABI
	case ARCH_MAP_VDSO_X32:
		return prctl_map_vdso(&vdso_image_x32, arg2);
# endif
# if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
	case ARCH_MAP_VDSO_32:
		return prctl_map_vdso(&vdso_image_32, arg2);
# endif
	case ARCH_MAP_VDSO_64:
		return prctl_map_vdso(&vdso_image_64, arg2);
#endif

	default:
		ret = -EINVAL;
		break;
	}

	return ret;
}

SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2)
{
	long ret;

	ret = do_arch_prctl_64(current, option, arg2);
	if (ret == -EINVAL)
		ret = do_arch_prctl_common(option, arg2);

	return ret;
}

#ifdef CONFIG_IA32_EMULATION
COMPAT_SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2)
{
	return do_arch_prctl_common(option, arg2);
}
#endif

unsigned long KSTK_ESP(struct task_struct *task)
{
	return task_pt_regs(task)->sp;
}