summaryrefslogtreecommitdiffstats
path: root/arch/s390/mm/fault.c
blob: cca73881e6721a3ab19cf3918c6661370a9c0e1c (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
/*
 *  S390 version
 *    Copyright IBM Corp. 1999
 *    Author(s): Hartmut Penner (hp@de.ibm.com)
 *               Ulrich Weigand (uweigand@de.ibm.com)
 *
 *  Derived from "arch/i386/mm/fault.c"
 *    Copyright (C) 1995  Linus Torvalds
 */

#include <linux/kernel_stat.h>
#include <linux/perf_event.h>
#include <linux/signal.h>
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/string.h>
#include <linux/types.h>
#include <linux/ptrace.h>
#include <linux/mman.h>
#include <linux/mm.h>
#include <linux/compat.h>
#include <linux/smp.h>
#include <linux/kdebug.h>
#include <linux/init.h>
#include <linux/console.h>
#include <linux/extable.h>
#include <linux/hardirq.h>
#include <linux/kprobes.h>
#include <linux/uaccess.h>
#include <linux/hugetlb.h>
#include <asm/asm-offsets.h>
#include <asm/diag.h>
#include <asm/pgtable.h>
#include <asm/gmap.h>
#include <asm/irq.h>
#include <asm/mmu_context.h>
#include <asm/facility.h>
#include "../kernel/entry.h"

#define __FAIL_ADDR_MASK -4096L
#define __SUBCODE_MASK 0x0600
#define __PF_RES_FIELD 0x8000000000000000ULL

#define VM_FAULT_BADCONTEXT	0x010000
#define VM_FAULT_BADMAP		0x020000
#define VM_FAULT_BADACCESS	0x040000
#define VM_FAULT_SIGNAL		0x080000
#define VM_FAULT_PFAULT		0x100000

static unsigned long store_indication __read_mostly;

static int __init fault_init(void)
{
	if (test_facility(75))
		store_indication = 0xc00;
	return 0;
}
early_initcall(fault_init);

static inline int notify_page_fault(struct pt_regs *regs)
{
	int ret = 0;

	/* kprobe_running() needs smp_processor_id() */
	if (kprobes_built_in() && !user_mode(regs)) {
		preempt_disable();
		if (kprobe_running() && kprobe_fault_handler(regs, 14))
			ret = 1;
		preempt_enable();
	}
	return ret;
}


/*
 * Unlock any spinlocks which will prevent us from getting the
 * message out.
 */
void bust_spinlocks(int yes)
{
	if (yes) {
		oops_in_progress = 1;
	} else {
		int loglevel_save = console_loglevel;
		console_unblank();
		oops_in_progress = 0;
		/*
		 * OK, the message is on the console.  Now we call printk()
		 * without oops_in_progress set so that printk will give klogd
		 * a poke.  Hold onto your hats...
		 */
		console_loglevel = 15;
		printk(" ");
		console_loglevel = loglevel_save;
	}
}

/*
 * Returns the address space associated with the fault.
 * Returns 0 for kernel space and 1 for user space.
 */
static inline int user_space_fault(struct pt_regs *regs)
{
	unsigned long trans_exc_code;

	/*
	 * The lowest two bits of the translation exception
	 * identification indicate which paging table was used.
	 */
	trans_exc_code = regs->int_parm_long & 3;
	if (trans_exc_code == 3) /* home space -> kernel */
		return 0;
	if (user_mode(regs))
		return 1;
	if (trans_exc_code == 2) /* secondary space -> set_fs */
		return current->thread.mm_segment.ar4;
	if (current->flags & PF_VCPU)
		return 1;
	return 0;
}

static int bad_address(void *p)
{
	unsigned long dummy;

	return probe_kernel_address((unsigned long *)p, dummy);
}

static void dump_pagetable(unsigned long asce, unsigned long address)
{
	unsigned long *table = __va(asce & PAGE_MASK);

	pr_alert("AS:%016lx ", asce);
	switch (asce & _ASCE_TYPE_MASK) {
	case _ASCE_TYPE_REGION1:
		table = table + ((address >> 53) & 0x7ff);
		if (bad_address(table))
			goto bad;
		pr_cont("R1:%016lx ", *table);
		if (*table & _REGION_ENTRY_INVALID)
			goto out;
		table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
		/* fallthrough */
	case _ASCE_TYPE_REGION2:
		table = table + ((address >> 42) & 0x7ff);
		if (bad_address(table))
			goto bad;
		pr_cont("R2:%016lx ", *table);
		if (*table & _REGION_ENTRY_INVALID)
			goto out;
		table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
		/* fallthrough */
	case _ASCE_TYPE_REGION3:
		table = table + ((address >> 31) & 0x7ff);
		if (bad_address(table))
			goto bad;
		pr_cont("R3:%016lx ", *table);
		if (*table & (_REGION_ENTRY_INVALID | _REGION3_ENTRY_LARGE))
			goto out;
		table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
		/* fallthrough */
	case _ASCE_TYPE_SEGMENT:
		table = table + ((address >> 20) & 0x7ff);
		if (bad_address(table))
			goto bad;
		pr_cont("S:%016lx ", *table);
		if (*table & (_SEGMENT_ENTRY_INVALID | _SEGMENT_ENTRY_LARGE))
			goto out;
		table = (unsigned long *)(*table & _SEGMENT_ENTRY_ORIGIN);
	}
	table = table + ((address >> 12) & 0xff);
	if (bad_address(table))
		goto bad;
	pr_cont("P:%016lx ", *table);
out:
	pr_cont("\n");
	return;
bad:
	pr_cont("BAD\n");
}

static void dump_fault_info(struct pt_regs *regs)
{
	unsigned long asce;

	pr_alert("Failing address: %016lx TEID: %016lx\n",
		 regs->int_parm_long & __FAIL_ADDR_MASK, regs->int_parm_long);
	pr_alert("Fault in ");
	switch (regs->int_parm_long & 3) {
	case 3:
		pr_cont("home space ");
		break;
	case 2:
		pr_cont("secondary space ");
		break;
	case 1:
		pr_cont("access register ");
		break;
	case 0:
		pr_cont("primary space ");
		break;
	}
	pr_cont("mode while using ");
	if (!user_space_fault(regs)) {
		asce = S390_lowcore.kernel_asce;
		pr_cont("kernel ");
	}
#ifdef CONFIG_PGSTE
	else if ((current->flags & PF_VCPU) && S390_lowcore.gmap) {
		struct gmap *gmap = (struct gmap *)S390_lowcore.gmap;
		asce = gmap->asce;
		pr_cont("gmap ");
	}
#endif
	else {
		asce = S390_lowcore.user_asce;
		pr_cont("user ");
	}
	pr_cont("ASCE.\n");
	dump_pagetable(asce, regs->int_parm_long & __FAIL_ADDR_MASK);
}

int show_unhandled_signals = 1;

void report_user_fault(struct pt_regs *regs, long signr, int is_mm_fault)
{
	if ((task_pid_nr(current) > 1) && !show_unhandled_signals)
		return;
	if (!unhandled_signal(current, signr))
		return;
	if (!printk_ratelimit())
		return;
	printk(KERN_ALERT "User process fault: interruption code %04x ilc:%d ",
	       regs->int_code & 0xffff, regs->int_code >> 17);
	print_vma_addr(KERN_CONT "in ", regs->psw.addr);
	printk(KERN_CONT "\n");
	if (is_mm_fault)
		dump_fault_info(regs);
	show_regs(regs);
}

/*
 * Send SIGSEGV to task.  This is an external routine
 * to keep the stack usage of do_page_fault small.
 */
static noinline void do_sigsegv(struct pt_regs *regs, int si_code)
{
	struct siginfo si;

	report_user_fault(regs, SIGSEGV, 1);
	si.si_signo = SIGSEGV;
	si.si_errno = 0;
	si.si_code = si_code;
	si.si_addr = (void __user *)(regs->int_parm_long & __FAIL_ADDR_MASK);
	force_sig_info(SIGSEGV, &si, current);
}

static noinline void do_no_context(struct pt_regs *regs)
{
	const struct exception_table_entry *fixup;

	/* Are we prepared to handle this kernel fault?  */
	fixup = search_exception_tables(regs->psw.addr);
	if (fixup) {
		regs->psw.addr = extable_fixup(fixup);
		return;
	}

	/*
	 * Oops. The kernel tried to access some bad page. We'll have to
	 * terminate things with extreme prejudice.
	 */
	if (!user_space_fault(regs))
		printk(KERN_ALERT "Unable to handle kernel pointer dereference"
		       " in virtual kernel address space\n");
	else
		printk(KERN_ALERT "Unable to handle kernel paging request"
		       " in virtual user address space\n");
	dump_fault_info(regs);
	die(regs, "Oops");
	do_exit(SIGKILL);
}

static noinline void do_low_address(struct pt_regs *regs)
{
	/* Low-address protection hit in kernel mode means
	   NULL pointer write access in kernel mode.  */
	if (regs->psw.mask & PSW_MASK_PSTATE) {
		/* Low-address protection hit in user mode 'cannot happen'. */
		die (regs, "Low-address protection");
		do_exit(SIGKILL);
	}

	do_no_context(regs);
}

static noinline void do_sigbus(struct pt_regs *regs)
{
	struct task_struct *tsk = current;
	struct siginfo si;

	/*
	 * Send a sigbus, regardless of whether we were in kernel
	 * or user mode.
	 */
	si.si_signo = SIGBUS;
	si.si_errno = 0;
	si.si_code = BUS_ADRERR;
	si.si_addr = (void __user *)(regs->int_parm_long & __FAIL_ADDR_MASK);
	force_sig_info(SIGBUS, &si, tsk);
}

static noinline void do_fault_error(struct pt_regs *regs, int fault)
{
	int si_code;

	switch (fault) {
	case VM_FAULT_BADACCESS:
	case VM_FAULT_BADMAP:
		/* Bad memory access. Check if it is kernel or user space. */
		if (user_mode(regs)) {
			/* User mode accesses just cause a SIGSEGV */
			si_code = (fault == VM_FAULT_BADMAP) ?
				SEGV_MAPERR : SEGV_ACCERR;
			do_sigsegv(regs, si_code);
			return;
		}
	case VM_FAULT_BADCONTEXT:
	case VM_FAULT_PFAULT:
		do_no_context(regs);
		break;
	case VM_FAULT_SIGNAL:
		if (!user_mode(regs))
			do_no_context(regs);
		break;
	default: /* fault & VM_FAULT_ERROR */
		if (fault & VM_FAULT_OOM) {
			if (!user_mode(regs))
				do_no_context(regs);
			else
				pagefault_out_of_memory();
		} else if (fault & VM_FAULT_SIGSEGV) {
			/* Kernel mode? Handle exceptions or die */
			if (!user_mode(regs))
				do_no_context(regs);
			else
				do_sigsegv(regs, SEGV_MAPERR);
		} else if (fault & VM_FAULT_SIGBUS) {
			/* Kernel mode? Handle exceptions or die */
			if (!user_mode(regs))
				do_no_context(regs);
			else
				do_sigbus(regs);
		} else
			BUG();
		break;
	}
}

/*
 * This routine handles page faults.  It determines the address,
 * and the problem, and then passes it off to one of the appropriate
 * routines.
 *
 * interruption code (int_code):
 *   04       Protection           ->  Write-Protection  (suprression)
 *   10       Segment translation  ->  Not present       (nullification)
 *   11       Page translation     ->  Not present       (nullification)
 *   3b       Region third trans.  ->  Not present       (nullification)
 */
static inline int do_exception(struct pt_regs *regs, int access)
{
#ifdef CONFIG_PGSTE
	struct gmap *gmap;
#endif
	struct task_struct *tsk;
	struct mm_struct *mm;
	struct vm_area_struct *vma;
	unsigned long trans_exc_code;
	unsigned long address;
	unsigned int flags;
	int fault;

	tsk = current;
	/*
	 * The instruction that caused the program check has
	 * been nullified. Don't signal single step via SIGTRAP.
	 */
	clear_pt_regs_flag(regs, PIF_PER_TRAP);

	if (notify_page_fault(regs))
		return 0;

	mm = tsk->mm;
	trans_exc_code = regs->int_parm_long;

	/*
	 * Verify that the fault happened in user space, that
	 * we are not in an interrupt and that there is a 
	 * user context.
	 */
	fault = VM_FAULT_BADCONTEXT;
	if (unlikely(!user_space_fault(regs) || faulthandler_disabled() || !mm))
		goto out;

	address = trans_exc_code & __FAIL_ADDR_MASK;
	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
	flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
	if (user_mode(regs))
		flags |= FAULT_FLAG_USER;
	if (access == VM_WRITE || (trans_exc_code & store_indication) == 0x400)
		flags |= FAULT_FLAG_WRITE;
	down_read(&mm->mmap_sem);

#ifdef CONFIG_PGSTE
	gmap = (current->flags & PF_VCPU) ?
		(struct gmap *) S390_lowcore.gmap : NULL;
	if (gmap) {
		current->thread.gmap_addr = address;
		current->thread.gmap_write_flag = !!(flags & FAULT_FLAG_WRITE);
		current->thread.gmap_int_code = regs->int_code & 0xffff;
		address = __gmap_translate(gmap, address);
		if (address == -EFAULT) {
			fault = VM_FAULT_BADMAP;
			goto out_up;
		}
		if (gmap->pfault_enabled)
			flags |= FAULT_FLAG_RETRY_NOWAIT;
	}
#endif

retry:
	fault = VM_FAULT_BADMAP;
	vma = find_vma(mm, address);
	if (!vma)
		goto out_up;

	if (unlikely(vma->vm_start > address)) {
		if (!(vma->vm_flags & VM_GROWSDOWN))
			goto out_up;
		if (expand_stack(vma, address))
			goto out_up;
	}

	/*
	 * Ok, we have a good vm_area for this memory access, so
	 * we can handle it..
	 */
	fault = VM_FAULT_BADACCESS;
	if (unlikely(!(vma->vm_flags & access)))
		goto out_up;

	if (is_vm_hugetlb_page(vma))
		address &= HPAGE_MASK;
	/*
	 * If for any reason at all we couldn't handle the fault,
	 * make sure we exit gracefully rather than endlessly redo
	 * the fault.
	 */
	fault = handle_mm_fault(vma, address, flags);
	/* No reason to continue if interrupted by SIGKILL. */
	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) {
		fault = VM_FAULT_SIGNAL;
		goto out;
	}
	if (unlikely(fault & VM_FAULT_ERROR))
		goto out_up;

	/*
	 * Major/minor page fault accounting is only done on the
	 * initial attempt. If we go through a retry, it is extremely
	 * likely that the page will be found in page cache at that point.
	 */
	if (flags & FAULT_FLAG_ALLOW_RETRY) {
		if (fault & VM_FAULT_MAJOR) {
			tsk->maj_flt++;
			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1,
				      regs, address);
		} else {
			tsk->min_flt++;
			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1,
				      regs, address);
		}
		if (fault & VM_FAULT_RETRY) {
#ifdef CONFIG_PGSTE
			if (gmap && (flags & FAULT_FLAG_RETRY_NOWAIT)) {
				/* FAULT_FLAG_RETRY_NOWAIT has been set,
				 * mmap_sem has not been released */
				current->thread.gmap_pfault = 1;
				fault = VM_FAULT_PFAULT;
				goto out_up;
			}
#endif
			/* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk
			 * of starvation. */
			flags &= ~(FAULT_FLAG_ALLOW_RETRY |
				   FAULT_FLAG_RETRY_NOWAIT);
			flags |= FAULT_FLAG_TRIED;
			down_read(&mm->mmap_sem);
			goto retry;
		}
	}
#ifdef CONFIG_PGSTE
	if (gmap) {
		address =  __gmap_link(gmap, current->thread.gmap_addr,
				       address);
		if (address == -EFAULT) {
			fault = VM_FAULT_BADMAP;
			goto out_up;
		}
		if (address == -ENOMEM) {
			fault = VM_FAULT_OOM;
			goto out_up;
		}
	}
#endif
	fault = 0;
out_up:
	up_read(&mm->mmap_sem);
out:
	return fault;
}

void do_protection_exception(struct pt_regs *regs)
{
	unsigned long trans_exc_code;
	int fault;

	trans_exc_code = regs->int_parm_long;
	/*
	 * Protection exceptions are suppressing, decrement psw address.
	 * The exception to this rule are aborted transactions, for these
	 * the PSW already points to the correct location.
	 */
	if (!(regs->int_code & 0x200))
		regs->psw.addr = __rewind_psw(regs->psw, regs->int_code >> 16);
	/*
	 * Check for low-address protection.  This needs to be treated
	 * as a special case because the translation exception code
	 * field is not guaranteed to contain valid data in this case.
	 */
	if (unlikely(!(trans_exc_code & 4))) {
		do_low_address(regs);
		return;
	}
	fault = do_exception(regs, VM_WRITE);
	if (unlikely(fault))
		do_fault_error(regs, fault);
}
NOKPROBE_SYMBOL(do_protection_exception);

void do_dat_exception(struct pt_regs *regs)
{
	int access, fault;

	access = VM_READ | VM_EXEC | VM_WRITE;
	fault = do_exception(regs, access);
	if (unlikely(fault))
		do_fault_error(regs, fault);
}
NOKPROBE_SYMBOL(do_dat_exception);

#ifdef CONFIG_PFAULT 
/*
 * 'pfault' pseudo page faults routines.
 */
static int pfault_disable;

static int __init nopfault(char *str)
{
	pfault_disable = 1;
	return 1;
}

__setup("nopfault", nopfault);

struct pfault_refbk {
	u16 refdiagc;
	u16 reffcode;
	u16 refdwlen;
	u16 refversn;
	u64 refgaddr;
	u64 refselmk;
	u64 refcmpmk;
	u64 reserved;
} __attribute__ ((packed, aligned(8)));

int pfault_init(void)
{
	struct pfault_refbk refbk = {
		.refdiagc = 0x258,
		.reffcode = 0,
		.refdwlen = 5,
		.refversn = 2,
		.refgaddr = __LC_LPP,
		.refselmk = 1ULL << 48,
		.refcmpmk = 1ULL << 48,
		.reserved = __PF_RES_FIELD };
        int rc;

	if (pfault_disable)
		return -1;
	diag_stat_inc(DIAG_STAT_X258);
	asm volatile(
		"	diag	%1,%0,0x258\n"
		"0:	j	2f\n"
		"1:	la	%0,8\n"
		"2:\n"
		EX_TABLE(0b,1b)
		: "=d" (rc) : "a" (&refbk), "m" (refbk) : "cc");
        return rc;
}

void pfault_fini(void)
{
	struct pfault_refbk refbk = {
		.refdiagc = 0x258,
		.reffcode = 1,
		.refdwlen = 5,
		.refversn = 2,
	};

	if (pfault_disable)
		return;
	diag_stat_inc(DIAG_STAT_X258);
	asm volatile(
		"	diag	%0,0,0x258\n"
		"0:	nopr	%%r7\n"
		EX_TABLE(0b,0b)
		: : "a" (&refbk), "m" (refbk) : "cc");
}

static DEFINE_SPINLOCK(pfault_lock);
static LIST_HEAD(pfault_list);

#define PF_COMPLETE	0x0080

/*
 * The mechanism of our pfault code: if Linux is running as guest, runs a user
 * space process and the user space process accesses a page that the host has
 * paged out we get a pfault interrupt.
 *
 * This allows us, within the guest, to schedule a different process. Without
 * this mechanism the host would have to suspend the whole virtual cpu until
 * the page has been paged in.
 *
 * So when we get such an interrupt then we set the state of the current task
 * to uninterruptible and also set the need_resched flag. Both happens within
 * interrupt context(!). If we later on want to return to user space we
 * recognize the need_resched flag and then call schedule().  It's not very
 * obvious how this works...
 *
 * Of course we have a lot of additional fun with the completion interrupt (->
 * host signals that a page of a process has been paged in and the process can
 * continue to run). This interrupt can arrive on any cpu and, since we have
 * virtual cpus, actually appear before the interrupt that signals that a page
 * is missing.
 */
static void pfault_interrupt(struct ext_code ext_code,
			     unsigned int param32, unsigned long param64)
{
	struct task_struct *tsk;
	__u16 subcode;
	pid_t pid;

	/*
	 * Get the external interruption subcode & pfault initial/completion
	 * signal bit. VM stores this in the 'cpu address' field associated
	 * with the external interrupt.
	 */
	subcode = ext_code.subcode;
	if ((subcode & 0xff00) != __SUBCODE_MASK)
		return;
	inc_irq_stat(IRQEXT_PFL);
	/* Get the token (= pid of the affected task). */
	pid = param64 & LPP_PFAULT_PID_MASK;
	rcu_read_lock();
	tsk = find_task_by_pid_ns(pid, &init_pid_ns);
	if (tsk)
		get_task_struct(tsk);
	rcu_read_unlock();
	if (!tsk)
		return;
	spin_lock(&pfault_lock);
	if (subcode & PF_COMPLETE) {
		/* signal bit is set -> a page has been swapped in by VM */
		if (tsk->thread.pfault_wait == 1) {
			/* Initial interrupt was faster than the completion
			 * interrupt. pfault_wait is valid. Set pfault_wait
			 * back to zero and wake up the process. This can
			 * safely be done because the task is still sleeping
			 * and can't produce new pfaults. */
			tsk->thread.pfault_wait = 0;
			list_del(&tsk->thread.list);
			wake_up_process(tsk);
			put_task_struct(tsk);
		} else {
			/* Completion interrupt was faster than initial
			 * interrupt. Set pfault_wait to -1 so the initial
			 * interrupt doesn't put the task to sleep.
			 * If the task is not running, ignore the completion
			 * interrupt since it must be a leftover of a PFAULT
			 * CANCEL operation which didn't remove all pending
			 * completion interrupts. */
			if (tsk->state == TASK_RUNNING)
				tsk->thread.pfault_wait = -1;
		}
	} else {
		/* signal bit not set -> a real page is missing. */
		if (WARN_ON_ONCE(tsk != current))
			goto out;
		if (tsk->thread.pfault_wait == 1) {
			/* Already on the list with a reference: put to sleep */
			goto block;
		} else if (tsk->thread.pfault_wait == -1) {
			/* Completion interrupt was faster than the initial
			 * interrupt (pfault_wait == -1). Set pfault_wait
			 * back to zero and exit. */
			tsk->thread.pfault_wait = 0;
		} else {
			/* Initial interrupt arrived before completion
			 * interrupt. Let the task sleep.
			 * An extra task reference is needed since a different
			 * cpu may set the task state to TASK_RUNNING again
			 * before the scheduler is reached. */
			get_task_struct(tsk);
			tsk->thread.pfault_wait = 1;
			list_add(&tsk->thread.list, &pfault_list);
block:
			/* Since this must be a userspace fault, there
			 * is no kernel task state to trample. Rely on the
			 * return to userspace schedule() to block. */
			__set_current_state(TASK_UNINTERRUPTIBLE);
			set_tsk_need_resched(tsk);
		}
	}
out:
	spin_unlock(&pfault_lock);
	put_task_struct(tsk);
}

static int pfault_cpu_notify(struct notifier_block *self, unsigned long action,
			     void *hcpu)
{
	struct thread_struct *thread, *next;
	struct task_struct *tsk;

	switch (action & ~CPU_TASKS_FROZEN) {
	case CPU_DEAD:
		spin_lock_irq(&pfault_lock);
		list_for_each_entry_safe(thread, next, &pfault_list, list) {
			thread->pfault_wait = 0;
			list_del(&thread->list);
			tsk = container_of(thread, struct task_struct, thread);
			wake_up_process(tsk);
			put_task_struct(tsk);
		}
		spin_unlock_irq(&pfault_lock);
		break;
	default:
		break;
	}
	return NOTIFY_OK;
}

static int __init pfault_irq_init(void)
{
	int rc;

	rc = register_external_irq(EXT_IRQ_CP_SERVICE, pfault_interrupt);
	if (rc)
		goto out_extint;
	rc = pfault_init() == 0 ? 0 : -EOPNOTSUPP;
	if (rc)
		goto out_pfault;
	irq_subclass_register(IRQ_SUBCLASS_SERVICE_SIGNAL);
	hotcpu_notifier(pfault_cpu_notify, 0);
	return 0;

out_pfault:
	unregister_external_irq(EXT_IRQ_CP_SERVICE, pfault_interrupt);
out_extint:
	pfault_disable = 1;
	return rc;
}
early_initcall(pfault_irq_init);

#endif /* CONFIG_PFAULT */