summaryrefslogtreecommitdiffstats
path: root/arch/i386/kernel/irq.c
blob: ea218fe4521470a92aa68dc818074ec73cbfb881 (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
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
/*
 *	linux/arch/i386/kernel/irq.c
 *
 *	Copyright (C) 1992, 1998 Linus Torvalds, Ingo Molnar
 *
 * This file contains the code used by various IRQ handling routines:
 * asking for different IRQ's should be done through these routines
 * instead of just grabbing them. Thus setups with different IRQ numbers
 * shouldn't result in any weird surprises, and installing new handlers
 * should be easier.
 */

/*
 * IRQs are in fact implemented a bit like signal handlers for the kernel.
 * Naturally it's not a 1:1 relation, but there are similarities.
 */

#include <linux/config.h>
#include <linux/ptrace.h>
#include <linux/errno.h>
#include <linux/kernel_stat.h>
#include <linux/signal.h>
#include <linux/sched.h>
#include <linux/ioport.h>
#include <linux/interrupt.h>
#include <linux/timex.h>
#include <linux/malloc.h>
#include <linux/random.h>
#include <linux/smp.h>
#include <linux/tasks.h>
#include <linux/smp_lock.h>
#include <linux/init.h>

#include <asm/system.h>
#include <asm/io.h>
#include <asm/irq.h>
#include <asm/bitops.h>
#include <asm/smp.h>
#include <asm/pgtable.h>
#include <asm/delay.h>
#include <asm/desc.h>

#include "irq.h"

unsigned int local_bh_count[NR_CPUS];
unsigned int local_irq_count[NR_CPUS];

atomic_t nmi_counter;

/*
 * Linux has a controller-independent x86 interrupt architecture.
 * every controller has a 'controller-template', that is used
 * by the main code to do the right thing. Each driver-visible
 * interrupt source is transparently wired to the apropriate
 * controller. Thus drivers need not be aware of the
 * interrupt-controller.
 *
 * Various interrupt controllers we handle: 8259 PIC, SMP IO-APIC,
 * PIIX4's internal 8259 PIC and SGI's Visual Workstation Cobalt (IO-)APIC.
 * (IO-APICs assumed to be messaging to Pentium local-APICs)
 *
 * the code is designed to be easily extended with new/different
 * interrupt controllers, without having to do assembly magic.
 */

/*
 * Micro-access to controllers is serialized over the whole
 * system. We never hold this lock when we call the actual
 * IRQ handler.
 */
spinlock_t irq_controller_lock;

/*
 * Dummy controller type for unused interrupts
 */
static void do_none(unsigned int irq, struct pt_regs * regs)
{
	/*
	 * we are careful. While for ISA irqs it's common to happen
	 * outside of any driver (think autodetection), this is not
	 * at all nice for PCI interrupts. So we are stricter and
	 * print a warning when such spurious interrupts happen.
	 * Spurious interrupts can confuse other drivers if the PCI
	 * IRQ line is shared.
	 *
	 * Such spurious interrupts are either driver bugs, or
	 * sometimes hw (chipset) bugs.
	 */
	printk("unexpected IRQ vector %d on CPU#%d!\n",irq, smp_processor_id());

#ifdef __SMP__
	/*
	 * [currently unexpected vectors happen only on SMP and APIC.
	 *  if we want to have non-APIC and non-8259A controllers
	 *  in the future with unexpected vectors, this ack should
	 *  probably be made controller-specific.]
	 */
	ack_APIC_irq();
#endif
}
static void enable_none(unsigned int irq) { }
static void disable_none(unsigned int irq) { }

/* startup is the same as "enable", shutdown is same as "disable" */
#define startup_none	enable_none
#define shutdown_none	disable_none

struct hw_interrupt_type no_irq_type = {
	"none",
	startup_none,
	shutdown_none,
	do_none,
	enable_none,
	disable_none
};

/*
 * This is the 'legacy' 8259A Programmable Interrupt Controller,
 * present in the majority of PC/AT boxes.
 */

static void do_8259A_IRQ(unsigned int irq, struct pt_regs * regs);
static void enable_8259A_irq(unsigned int irq);
void disable_8259A_irq(unsigned int irq);

/* startup is the same as "enable", shutdown is same as "disable" */
#define startup_8259A_irq	enable_8259A_irq
#define shutdown_8259A_irq	disable_8259A_irq

static struct hw_interrupt_type i8259A_irq_type = {
	"XT-PIC",
	startup_8259A_irq,
	shutdown_8259A_irq,
	do_8259A_IRQ,
	enable_8259A_irq,
	disable_8259A_irq
};

/*
 * Controller mappings for all interrupt sources:
 */
irq_desc_t irq_desc[NR_IRQS] = { [0 ... NR_IRQS-1] = { 0, &no_irq_type, }};


/*
 * 8259A PIC functions to handle ISA devices:
 */

/*
 * This contains the irq mask for both 8259A irq controllers,
 */
static unsigned int cached_irq_mask = 0xffff;

#define __byte(x,y) 	(((unsigned char *)&(y))[x])
#define cached_21	(__byte(0,cached_irq_mask))
#define cached_A1	(__byte(1,cached_irq_mask))

/*
 * Not all IRQs can be routed through the IO-APIC, eg. on certain (older)
 * boards the timer interrupt is not connected to any IO-APIC pin, it's
 * fed to the CPU IRQ line directly.
 *
 * Any '1' bit in this mask means the IRQ is routed through the IO-APIC.
 * this 'mixed mode' IRQ handling costs nothing because it's only used
 * at IRQ setup time.
 */
unsigned long io_apic_irqs = 0;

/*
 * These have to be protected by the irq controller spinlock
 * before being called.
 */
void disable_8259A_irq(unsigned int irq)
{
	unsigned int mask = 1 << irq;
	cached_irq_mask |= mask;
	if (irq & 8) {
		outb(cached_A1,0xA1);
	} else {
		outb(cached_21,0x21);
	}
}

static void enable_8259A_irq(unsigned int irq)
{
	unsigned int mask = ~(1 << irq);
	cached_irq_mask &= mask;
	if (irq & 8) {
		outb(cached_A1,0xA1);
	} else {
		outb(cached_21,0x21);
	}
}

int i8259A_irq_pending(unsigned int irq)
{
	unsigned int mask = 1<<irq;

	if (irq < 8)
                return (inb(0x20) & mask);
        return (inb(0xA0) & (mask >> 8));
}

void make_8259A_irq(unsigned int irq)
{
	disable_irq_nosync(irq);
	io_apic_irqs &= ~(1<<irq);
	irq_desc[irq].handler = &i8259A_irq_type;
	enable_irq(irq);
}

/*
 * Careful! The 8259A is a fragile beast, it pretty
 * much _has_ to be done exactly like this (mask it
 * first, _then_ send the EOI, and the order of EOI
 * to the two 8259s is important!
 */
static inline void mask_and_ack_8259A(unsigned int irq)
{
	cached_irq_mask |= 1 << irq;
	if (irq & 8) {
		inb(0xA1);	/* DUMMY */
		outb(cached_A1,0xA1);
		outb(0x62,0x20);	/* Specific EOI to cascade */
		outb(0x20,0xA0);
	} else {
		inb(0x21);	/* DUMMY */
		outb(cached_21,0x21);
		outb(0x20,0x20);
	}
}

static void do_8259A_IRQ(unsigned int irq, struct pt_regs * regs)
{
	struct irqaction * action;
	irq_desc_t *desc = irq_desc + irq;

	spin_lock(&irq_controller_lock);
	{
		unsigned int status;
		mask_and_ack_8259A(irq);
		status = desc->status & ~(IRQ_REPLAY | IRQ_WAITING);
		action = NULL;
		if (!(status & (IRQ_DISABLED | IRQ_INPROGRESS))) {
			action = desc->action;
			status |= IRQ_INPROGRESS;
		}
		desc->status = status;
	}
	spin_unlock(&irq_controller_lock);

	/* Exit early if we had no action or it was disabled */
	if (!action)
		return;

	handle_IRQ_event(irq, regs, action);

	spin_lock(&irq_controller_lock);
	{
		unsigned int status = desc->status & ~IRQ_INPROGRESS;
		desc->status = status;
		if (!(status & IRQ_DISABLED))
			enable_8259A_irq(irq);
	}
	spin_unlock(&irq_controller_lock);
}

/*
 * This builds up the IRQ handler stubs using some ugly macros in irq.h
 *
 * These macros create the low-level assembly IRQ routines that save
 * register context and call do_IRQ(). do_IRQ() then does all the
 * operations that are needed to keep the AT (or SMP IOAPIC)
 * interrupt-controller happy.
 */


BUILD_COMMON_IRQ()

#define BI(x,y) \
	BUILD_IRQ(##x##y)

#define BUILD_16_IRQS(x) \
	BI(x,0) BI(x,1) BI(x,2) BI(x,3) \
	BI(x,4) BI(x,5) BI(x,6) BI(x,7) \
	BI(x,8) BI(x,9) BI(x,a) BI(x,b) \
	BI(x,c) BI(x,d) BI(x,e) BI(x,f)

/*
 * ISA PIC or low IO-APIC triggered (INTA-cycle or APIC) interrupts:
 * (these are usually mapped to vectors 0x20-0x30)
 */
BUILD_16_IRQS(0x0)

#ifdef CONFIG_X86_IO_APIC
/*
 * The IO-APIC gives us many more interrupt sources. Most of these 
 * are unused but an SMP system is supposed to have enough memory ...
 * sometimes (mostly wrt. hw bugs) we get corrupted vectors all
 * across the spectrum, so we really want to be prepared to get all
 * of these. Plus, more powerful systems might have more than 64
 * IO-APIC registers.
 *
 * (these are usually mapped into the 0x30-0xff vector range)
 */
                   BUILD_16_IRQS(0x1) BUILD_16_IRQS(0x2) BUILD_16_IRQS(0x3)
BUILD_16_IRQS(0x4) BUILD_16_IRQS(0x5) BUILD_16_IRQS(0x6) BUILD_16_IRQS(0x7)
BUILD_16_IRQS(0x8) BUILD_16_IRQS(0x9) BUILD_16_IRQS(0xa) BUILD_16_IRQS(0xb)
BUILD_16_IRQS(0xc) BUILD_16_IRQS(0xd)
#endif

#undef BUILD_16_IRQS
#undef BI


#ifdef __SMP__
/*
 * The following vectors are part of the Linux architecture, there
 * is no hardware IRQ pin equivalent for them, they are triggered
 * through the ICC by us (IPIs)
 */
BUILD_SMP_INTERRUPT(reschedule_interrupt)
BUILD_SMP_INTERRUPT(invalidate_interrupt)
BUILD_SMP_INTERRUPT(stop_cpu_interrupt)
BUILD_SMP_INTERRUPT(call_function_interrupt)
BUILD_SMP_INTERRUPT(spurious_interrupt)

/*
 * every pentium local APIC has two 'local interrupts', with a
 * soft-definable vector attached to both interrupts, one of
 * which is a timer interrupt, the other one is error counter
 * overflow. Linux uses the local APIC timer interrupt to get
 * a much simpler SMP time architecture:
 */
BUILD_SMP_TIMER_INTERRUPT(apic_timer_interrupt)

#endif

#define IRQ(x,y) \
	IRQ##x##y##_interrupt

#define IRQLIST_16(x) \
	IRQ(x,0), IRQ(x,1), IRQ(x,2), IRQ(x,3), \
	IRQ(x,4), IRQ(x,5), IRQ(x,6), IRQ(x,7), \
	IRQ(x,8), IRQ(x,9), IRQ(x,a), IRQ(x,b), \
	IRQ(x,c), IRQ(x,d), IRQ(x,e), IRQ(x,f)

static void (*interrupt[NR_IRQS])(void) = {
	IRQLIST_16(0x0),

#ifdef CONFIG_X86_IO_APIC
	                 IRQLIST_16(0x1), IRQLIST_16(0x2), IRQLIST_16(0x3),
	IRQLIST_16(0x4), IRQLIST_16(0x5), IRQLIST_16(0x6), IRQLIST_16(0x7),
	IRQLIST_16(0x8), IRQLIST_16(0x9), IRQLIST_16(0xa), IRQLIST_16(0xb),
	IRQLIST_16(0xc), IRQLIST_16(0xd)
#endif
};

#undef IRQ
#undef IRQLIST_16


/*
 * Special irq handlers.
 */

void no_action(int cpl, void *dev_id, struct pt_regs *regs) { }

#ifndef CONFIG_VISWS
/*
 * Note that on a 486, we don't want to do a SIGFPE on an irq13
 * as the irq is unreliable, and exception 16 works correctly
 * (ie as explained in the intel literature). On a 386, you
 * can't use exception 16 due to bad IBM design, so we have to
 * rely on the less exact irq13.
 *
 * Careful.. Not only is IRQ13 unreliable, but it is also
 * leads to races. IBM designers who came up with it should
 * be shot.
 */
 
static void math_error_irq(int cpl, void *dev_id, struct pt_regs *regs)
{
	outb(0,0xF0);
	if (ignore_irq13 || !boot_cpu_data.hard_math)
		return;
	math_error();
}

static struct irqaction irq13 = { math_error_irq, 0, 0, "fpu", NULL, NULL };

/*
 * IRQ2 is cascade interrupt to second interrupt controller
 */

static struct irqaction irq2  = { no_action, 0, 0, "cascade", NULL, NULL};
#endif

/*
 * Generic, controller-independent functions:
 */

int get_irq_list(char *buf)
{
	int i, j;
	struct irqaction * action;
	char *p = buf;

	p += sprintf(p, "           ");
	for (j=0; j<smp_num_cpus; j++)
		p += sprintf(p, "CPU%d       ",j);
	*p++ = '\n';

	for (i = 0 ; i < NR_IRQS ; i++) {
		action = irq_desc[i].action;
		if (!action) 
			continue;
		p += sprintf(p, "%3d: ",i);
#ifndef __SMP__
		p += sprintf(p, "%10u ", kstat_irqs(i));
#else
		for (j=0; j<smp_num_cpus; j++)
			p += sprintf(p, "%10u ",
				kstat.irqs[cpu_logical_map(j)][i]);
#endif
		p += sprintf(p, " %14s", irq_desc[i].handler->typename);
		p += sprintf(p, "  %s", action->name);

		for (action=action->next; action; action = action->next) {
			p += sprintf(p, ", %s", action->name);
		}
		*p++ = '\n';
	}
	p += sprintf(p, "NMI: %10u\n", atomic_read(&nmi_counter));
#ifdef __SMP__
	p += sprintf(p, "ERR: %10lu\n", ipi_count);
#endif		
	return p - buf;
}

/*
 * Global interrupt locks for SMP. Allow interrupts to come in on any
 * CPU, yet make cli/sti act globally to protect critical regions..
 */
#ifdef __SMP__
unsigned char global_irq_holder = NO_PROC_ID;
unsigned volatile int global_irq_lock;
atomic_t global_irq_count;

atomic_t global_bh_count;
atomic_t global_bh_lock;

/*
 * "global_cli()" is a special case, in that it can hold the
 * interrupts disabled for a longish time, and also because
 * we may be doing TLB invalidates when holding the global
 * IRQ lock for historical reasons. Thus we may need to check
 * SMP invalidate events specially by hand here (but not in
 * any normal spinlocks)
 */
static inline void check_smp_invalidate(int cpu)
{
	if (test_bit(cpu, &smp_invalidate_needed)) {
		clear_bit(cpu, &smp_invalidate_needed);
		local_flush_tlb();
	}
}

static void show(char * str)
{
	int i;
	unsigned long *stack;
	int cpu = smp_processor_id();
	extern char *get_options(char *str, int *ints);

	printk("\n%s, CPU %d:\n", str, cpu);
	printk("irq:  %d [%d %d]\n",
		atomic_read(&global_irq_count), local_irq_count[0], local_irq_count[1]);
	printk("bh:   %d [%d %d]\n",
		atomic_read(&global_bh_count), local_bh_count[0], local_bh_count[1]);
	stack = (unsigned long *) &stack;
	for (i = 40; i ; i--) {
		unsigned long x = *++stack;
		if (x > (unsigned long) &get_options && x < (unsigned long) &vsprintf) {
			printk("<[%08lx]> ", x);
		}
	}
}
	
#define MAXCOUNT 100000000

static inline void wait_on_bh(void)
{
	int count = MAXCOUNT;
	do {
		if (!--count) {
			show("wait_on_bh");
			count = ~0;
		}
		/* nothing .. wait for the other bh's to go away */
	} while (atomic_read(&global_bh_count) != 0);
}

/*
 * I had a lockup scenario where a tight loop doing
 * spin_unlock()/spin_lock() on CPU#1 was racing with
 * spin_lock() on CPU#0. CPU#0 should have noticed spin_unlock(), but
 * apparently the spin_unlock() information did not make it
 * through to CPU#0 ... nasty, is this by design, do we have to limit
 * 'memory update oscillation frequency' artificially like here?
 *
 * Such 'high frequency update' races can be avoided by careful design, but
 * some of our major constructs like spinlocks use similar techniques,
 * it would be nice to clarify this issue. Set this define to 0 if you
 * want to check whether your system freezes.  I suspect the delay done
 * by SYNC_OTHER_CORES() is in correlation with 'snooping latency', but
 * i thought that such things are guaranteed by design, since we use
 * the 'LOCK' prefix.
 */
#define SUSPECTED_CPU_OR_CHIPSET_BUG_WORKAROUND 1

#if SUSPECTED_CPU_OR_CHIPSET_BUG_WORKAROUND
# define SYNC_OTHER_CORES(x) udelay(x+1)
#else
/*
 * We have to allow irqs to arrive between __sti and __cli
 */
# define SYNC_OTHER_CORES(x) __asm__ __volatile__ ("nop")
#endif

static inline void wait_on_irq(int cpu)
{
	int count = MAXCOUNT;

	for (;;) {

		/*
		 * Wait until all interrupts are gone. Wait
		 * for bottom half handlers unless we're
		 * already executing in one..
		 */
		if (!atomic_read(&global_irq_count)) {
			if (local_bh_count[cpu] || !atomic_read(&global_bh_count))
				break;
		}

		/* Duh, we have to loop. Release the lock to avoid deadlocks */
		clear_bit(0,&global_irq_lock);

		for (;;) {
			if (!--count) {
				show("wait_on_irq");
				count = ~0;
			}
			__sti();
			SYNC_OTHER_CORES(cpu);
			__cli();
			check_smp_invalidate(cpu);
			if (atomic_read(&global_irq_count))
				continue;
			if (global_irq_lock)
				continue;
			if (!local_bh_count[cpu] && atomic_read(&global_bh_count))
				continue;
			if (!test_and_set_bit(0,&global_irq_lock))
				break;
		}
	}
}

/*
 * This is called when we want to synchronize with
 * bottom half handlers. We need to wait until
 * no other CPU is executing any bottom half handler.
 *
 * Don't wait if we're already running in an interrupt
 * context or are inside a bh handler. 
 */
void synchronize_bh(void)
{
	if (atomic_read(&global_bh_count) && !in_interrupt())
		wait_on_bh();
}

/*
 * This is called when we want to synchronize with
 * interrupts. We may for example tell a device to
 * stop sending interrupts: but to make sure there
 * are no interrupts that are executing on another
 * CPU we need to call this function.
 */
void synchronize_irq(void)
{
	if (atomic_read(&global_irq_count)) {
		/* Stupid approach */
		cli();
		sti();
	}
}

static inline void get_irqlock(int cpu)
{
	if (test_and_set_bit(0,&global_irq_lock)) {
		/* do we already hold the lock? */
		if ((unsigned char) cpu == global_irq_holder)
			return;
		/* Uhhuh.. Somebody else got it. Wait.. */
		do {
			do {
				check_smp_invalidate(cpu);
			} while (test_bit(0,&global_irq_lock));
		} while (test_and_set_bit(0,&global_irq_lock));		
	}
	/* 
	 * We also to make sure that nobody else is running
	 * in an interrupt context. 
	 */
	wait_on_irq(cpu);

	/*
	 * Ok, finally..
	 */
	global_irq_holder = cpu;
}

#define EFLAGS_IF_SHIFT 9

/*
 * A global "cli()" while in an interrupt context
 * turns into just a local cli(). Interrupts
 * should use spinlocks for the (very unlikely)
 * case that they ever want to protect against
 * each other.
 *
 * If we already have local interrupts disabled,
 * this will not turn a local disable into a
 * global one (problems with spinlocks: this makes
 * save_flags+cli+sti usable inside a spinlock).
 */
void __global_cli(void)
{
	unsigned int flags;

	__save_flags(flags);
	if (flags & (1 << EFLAGS_IF_SHIFT)) {
		int cpu = smp_processor_id();
		__cli();
		if (!local_irq_count[cpu])
			get_irqlock(cpu);
	}
}

void __global_sti(void)
{
	int cpu = smp_processor_id();

	if (!local_irq_count[cpu])
		release_irqlock(cpu);
	__sti();
}

/*
 * SMP flags value to restore to:
 * 0 - global cli
 * 1 - global sti
 * 2 - local cli
 * 3 - local sti
 */
unsigned long __global_save_flags(void)
{
	int retval;
	int local_enabled;
	unsigned long flags;

	__save_flags(flags);
	local_enabled = (flags >> EFLAGS_IF_SHIFT) & 1;
	/* default to local */
	retval = 2 + local_enabled;

	/* check for global flags if we're not in an interrupt */
	if (!local_irq_count[smp_processor_id()]) {
		if (local_enabled)
			retval = 1;
		if (global_irq_holder == (unsigned char) smp_processor_id())
			retval = 0;
	}
	return retval;
}

void __global_restore_flags(unsigned long flags)
{
	switch (flags) {
	case 0:
		__global_cli();
		break;
	case 1:
		__global_sti();
		break;
	case 2:
		__cli();
		break;
	case 3:
		__sti();
		break;
	default:
		printk("global_restore_flags: %08lx (%08lx)\n",
			flags, (&flags)[-1]);
	}
}

#endif

/*
 * This should really return information about whether
 * we should do bottom half handling etc. Right now we
 * end up _always_ checking the bottom half, which is a
 * waste of time and is not what some drivers would
 * prefer.
 */
int handle_IRQ_event(unsigned int irq, struct pt_regs * regs, struct irqaction * action)
{
	int status;
	int cpu = smp_processor_id();

	irq_enter(cpu, irq);

	status = 1;	/* Force the "do bottom halves" bit */

	if (!(action->flags & SA_INTERRUPT))
		__sti();

	do {
		status |= action->flags;
		action->handler(irq, action->dev_id, regs);
		action = action->next;
	} while (action);
	if (status & SA_SAMPLE_RANDOM)
		add_interrupt_randomness(irq);
	__cli();

	irq_exit(cpu, irq);

	return status;
}

/*
 * Generic enable/disable code: this just calls
 * down into the PIC-specific version for the actual
 * hardware disable after having gotten the irq
 * controller lock. 
 */
void disable_irq_nosync(unsigned int irq)
{
	unsigned long flags;

	spin_lock_irqsave(&irq_controller_lock, flags);
	if (!irq_desc[irq].depth++) {
		irq_desc[irq].status |= IRQ_DISABLED;
		irq_desc[irq].handler->disable(irq);
	}
	spin_unlock_irqrestore(&irq_controller_lock, flags);
}

/*
 * Synchronous version of the above, making sure the IRQ is
 * no longer running on any other IRQ..
 */
void disable_irq(unsigned int irq)
{
	disable_irq_nosync(irq);

	if (!local_irq_count[smp_processor_id()]) {
		do {
			barrier();
		} while (irq_desc[irq].status & IRQ_INPROGRESS);
	}
}

void enable_irq(unsigned int irq)
{
	unsigned long flags;

	spin_lock_irqsave(&irq_controller_lock, flags);
	switch (irq_desc[irq].depth) {
	case 1:
		irq_desc[irq].status &= ~IRQ_DISABLED;
		irq_desc[irq].handler->enable(irq);
		/* fall throught */
	default:
		irq_desc[irq].depth--;
		break;
	case 0:
		printk("enable_irq() unbalanced from %p\n",
		       __builtin_return_address(0));
	}
	spin_unlock_irqrestore(&irq_controller_lock, flags);
}

/*
 * do_IRQ handles all normal device IRQ's (the special
 * SMP cross-CPU interrupts have their own specific
 * handlers).
 */
asmlinkage void do_IRQ(struct pt_regs regs)
{	
	/* 
	 * We ack quickly, we don't want the irq controller
	 * thinking we're snobs just because some other CPU has
	 * disabled global interrupts (we have already done the
	 * INT_ACK cycles, it's too late to try to pretend to the
	 * controller that we aren't taking the interrupt).
	 *
	 * 0 return value means that this irq is already being
	 * handled by some other CPU. (or is disabled)
	 */
	int irq = regs.orig_eax & 0xff; /* subtle, see irq.h */
	int cpu = smp_processor_id();

	kstat.irqs[cpu][irq]++;
	irq_desc[irq].handler->handle(irq, &regs);

	/*
	 * This should be conditional: we should really get
	 * a return code from the irq handler to tell us
	 * whether the handler wants us to do software bottom
	 * half handling or not..
	 */
	if (1) {
		if (bh_active & bh_mask)
			do_bottom_half();
	}
}

int setup_x86_irq(unsigned int irq, struct irqaction * new)
{
	int shared = 0;
	struct irqaction *old, **p;
	unsigned long flags;

	/*
	 * Some drivers like serial.c use request_irq() heavily,
	 * so we have to be careful not to interfere with a
	 * running system.
	 */
	if (new->flags & SA_SAMPLE_RANDOM) {
		/*
		 * This function might sleep, we want to call it first,
		 * outside of the atomic block.
		 * Yes, this might clear the entropy pool if the wrong
		 * driver is attempted to be loaded, without actually
		 * installing a new handler, but is this really a problem,
		 * only the sysadmin is able to do this.
		 */
		rand_initialize_irq(irq);
	}

	/*
	 * The following block of code has to be executed atomically
	 */
	spin_lock_irqsave(&irq_controller_lock,flags);
	p = &irq_desc[irq].action;
	if ((old = *p) != NULL) {
		/* Can't share interrupts unless both agree to */
		if (!(old->flags & new->flags & SA_SHIRQ)) {
			spin_unlock_irqrestore(&irq_controller_lock,flags);
			return -EBUSY;
		}

		/* add new interrupt at end of irq queue */
		do {
			p = &old->next;
			old = *p;
		} while (old);
		shared = 1;
	}

	*p = new;

	if (!shared) {
		irq_desc[irq].depth = 0;
		irq_desc[irq].status &= ~IRQ_DISABLED;
		irq_desc[irq].handler->startup(irq);
	}
	spin_unlock_irqrestore(&irq_controller_lock,flags);
	return 0;
}

int request_irq(unsigned int irq, 
		void (*handler)(int, void *, struct pt_regs *),
		unsigned long irqflags, 
		const char * devname,
		void *dev_id)
{
	int retval;
	struct irqaction * action;

	if (irq >= NR_IRQS)
		return -EINVAL;
	if (!handler)
		return -EINVAL;

	action = (struct irqaction *)
			kmalloc(sizeof(struct irqaction), GFP_KERNEL);
	if (!action)
		return -ENOMEM;

	action->handler = handler;
	action->flags = irqflags;
	action->mask = 0;
	action->name = devname;
	action->next = NULL;
	action->dev_id = dev_id;

	retval = setup_x86_irq(irq, action);

	if (retval)
		kfree(action);
	return retval;
}
		
void free_irq(unsigned int irq, void *dev_id)
{
	struct irqaction * action, **p;
	unsigned long flags;

	if (irq >= NR_IRQS)
		return;

	spin_lock_irqsave(&irq_controller_lock,flags);
	for (p = &irq_desc[irq].action; (action = *p) != NULL; p = &action->next) {
		if (action->dev_id != dev_id)
			continue;

		/* Found it - now free it */
		*p = action->next;
		kfree(action);
		if (!irq_desc[irq].action) {
			irq_desc[irq].status |= IRQ_DISABLED;
			irq_desc[irq].handler->shutdown(irq);
		}
		goto out;
	}
	printk("Trying to free free IRQ%d\n",irq);
out:
	spin_unlock_irqrestore(&irq_controller_lock,flags);
}

/*
 * IRQ autodetection code..
 *
 * This depends on the fact that any interrupt that
 * comes in on to an unassigned handler will get stuck
 * with "IRQ_WAITING" cleared and the interrupt
 * disabled.
 */
unsigned long probe_irq_on(void)
{
	unsigned int i;
	unsigned long delay;

	/*
	 * first, enable any unassigned irqs
	 */
	spin_lock_irq(&irq_controller_lock);
	for (i = NR_IRQS-1; i > 0; i--) {
		if (!irq_desc[i].action) {
			irq_desc[i].status |= IRQ_AUTODETECT | IRQ_WAITING;
			irq_desc[i].handler->startup(i);
		}
	}
	spin_unlock_irq(&irq_controller_lock);

	/*
	 * Wait for spurious interrupts to trigger
	 */
	for (delay = jiffies + HZ/10; time_after(delay, jiffies); )
		/* about 100ms delay */ synchronize_irq();

	/*
	 * Now filter out any obviously spurious interrupts
	 */
	spin_lock_irq(&irq_controller_lock);
	for (i=0; i<NR_IRQS; i++) {
		unsigned int status = irq_desc[i].status;

		if (!(status & IRQ_AUTODETECT))
			continue;
		
		/* It triggered already - consider it spurious. */
		if (!(status & IRQ_WAITING)) {
			irq_desc[i].status = status & ~IRQ_AUTODETECT;
			irq_desc[i].handler->shutdown(i);
		}
	}
	spin_unlock_irq(&irq_controller_lock);

	return 0x12345678;
}

int probe_irq_off(unsigned long unused)
{
	int i, irq_found, nr_irqs;

	if (unused != 0x12345678)
		printk("Bad IRQ probe from %lx\n", (&unused)[-1]);

	nr_irqs = 0;
	irq_found = 0;
	spin_lock_irq(&irq_controller_lock);
	for (i=0; i<NR_IRQS; i++) {
		unsigned int status = irq_desc[i].status;

		if (!(status & IRQ_AUTODETECT))
			continue;

		if (!(status & IRQ_WAITING)) {
			if (!nr_irqs)
				irq_found = i;
			nr_irqs++;
		}
		irq_desc[i].status = status & ~IRQ_AUTODETECT;
		irq_desc[i].handler->shutdown(i);
	}
	spin_unlock_irq(&irq_controller_lock);

	if (nr_irqs > 1)
		irq_found = -irq_found;
	return irq_found;
}

void init_ISA_irqs (void)
{
	int i;

	for (i = 0; i < NR_IRQS; i++) {
		irq_desc[i].status = IRQ_DISABLED;
		irq_desc[i].action = 0;
		irq_desc[i].depth = 0;

		if (i < 16) {
			/*
			 * 16 old-style INTA-cycle interrupts:
			 */
			irq_desc[i].handler = &i8259A_irq_type;
		} else {
			/*
			 * 'high' PCI IRQs filled in on demand
			 */
			irq_desc[i].handler = &no_irq_type;
		}
	}
}

__initfunc(void init_IRQ(void))
{
	int i;

#ifndef CONFIG_X86_VISWS_APIC
	init_ISA_irqs();
#else
	init_VISWS_APIC_irqs();
#endif
	/*
	 * Cover the whole vector space, no vector can escape
	 * us. (some of these will be overridden and become
	 * 'special' SMP interrupts)
	 */
	for (i = 0; i < NR_IRQS; i++) {
		int vector = FIRST_EXTERNAL_VECTOR + i;
		if (vector != SYSCALL_VECTOR) 
			set_intr_gate(vector, interrupt[i]);
	}

#ifdef __SMP__	

	/*
	  IRQ0 must be given a fixed assignment and initialized
	  before init_IRQ_SMP.
	*/
	set_intr_gate(IRQ0_TRAP_VECTOR, interrupt[0]);

	/*
	 * The reschedule interrupt is a CPU-to-CPU reschedule-helper
	 * IPI, driven by wakeup.
	 */
	set_intr_gate(RESCHEDULE_VECTOR, reschedule_interrupt);

	/* IPI for invalidation */
	set_intr_gate(INVALIDATE_TLB_VECTOR, invalidate_interrupt);

	/* IPI for CPU halt */
	set_intr_gate(STOP_CPU_VECTOR, stop_cpu_interrupt);

	/* self generated IPI for local APIC timer */
	set_intr_gate(LOCAL_TIMER_VECTOR, apic_timer_interrupt);

	/* IPI for generic function call */
	set_intr_gate(CALL_FUNCTION_VECTOR, call_function_interrupt);

	/* IPI vector for APIC spurious interrupts */
	set_intr_gate(SPURIOUS_APIC_VECTOR, spurious_interrupt);
#endif	
	request_region(0x20,0x20,"pic1");
	request_region(0xa0,0x20,"pic2");

	/*
	 * Set the clock to 100 Hz, we already have a valid
	 * vector now:
	 */
	outb_p(0x34,0x43);		/* binary, mode 2, LSB/MSB, ch 0 */
	outb_p(LATCH & 0xff , 0x40);	/* LSB */
	outb(LATCH >> 8 , 0x40);	/* MSB */

#ifndef CONFIG_VISWS
	setup_x86_irq(2, &irq2);
	setup_x86_irq(13, &irq13);
#endif
}

#ifdef CONFIG_X86_IO_APIC
__initfunc(void init_IRQ_SMP(void))
{
	int i;
	for (i = 0; i < NR_IRQS ; i++)
		if (IO_APIC_VECTOR(i) > 0)
			set_intr_gate(IO_APIC_VECTOR(i), interrupt[i]);
}
#endif