summaryrefslogtreecommitdiffstats
path: root/arch/powerpc/kernel/irq.c
blob: bdfb3eee3e6f6d58daee601eaa6e3aca3851957c (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
/*
 *  Derived from arch/i386/kernel/irq.c
 *    Copyright (C) 1992 Linus Torvalds
 *  Adapted from arch/i386 by Gary Thomas
 *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
 *  Updated and modified by Cort Dougan <cort@fsmlabs.com>
 *    Copyright (C) 1996-2001 Cort Dougan
 *  Adapted for Power Macintosh by Paul Mackerras
 *    Copyright (C) 1996 Paul Mackerras (paulus@cs.anu.edu.au)
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License
 * as published by the Free Software Foundation; either version
 * 2 of the License, or (at your option) any later version.
 *
 * 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.
 *
 * The MPC8xx has an interrupt mask in the SIU.  If a bit is set, the
 * interrupt is _enabled_.  As expected, IRQ0 is bit 0 in the 32-bit
 * mask register (of which only 16 are defined), hence the weird shifting
 * and complement of the cached_irq_mask.  I want to be able to stuff
 * this right into the SIU SMASK register.
 * Many of the prep/chrp functions are conditional compiled on CONFIG_8xx
 * to reduce code space and undefined function references.
 */

#undef DEBUG

#include <linux/export.h>
#include <linux/threads.h>
#include <linux/kernel_stat.h>
#include <linux/signal.h>
#include <linux/sched.h>
#include <linux/ptrace.h>
#include <linux/ioport.h>
#include <linux/interrupt.h>
#include <linux/timex.h>
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/delay.h>
#include <linux/irq.h>
#include <linux/seq_file.h>
#include <linux/cpumask.h>
#include <linux/profile.h>
#include <linux/bitops.h>
#include <linux/list.h>
#include <linux/radix-tree.h>
#include <linux/mutex.h>
#include <linux/bootmem.h>
#include <linux/pci.h>
#include <linux/debugfs.h>
#include <linux/of.h>
#include <linux/of_irq.h>

#include <asm/uaccess.h>
#include <asm/system.h>
#include <asm/io.h>
#include <asm/pgtable.h>
#include <asm/irq.h>
#include <asm/cache.h>
#include <asm/prom.h>
#include <asm/ptrace.h>
#include <asm/machdep.h>
#include <asm/udbg.h>
#include <asm/smp.h>

#ifdef CONFIG_PPC64
#include <asm/paca.h>
#include <asm/firmware.h>
#include <asm/lv1call.h>
#endif
#define CREATE_TRACE_POINTS
#include <asm/trace.h>

DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
EXPORT_PER_CPU_SYMBOL(irq_stat);

int __irq_offset_value;

#ifdef CONFIG_PPC32
EXPORT_SYMBOL(__irq_offset_value);
atomic_t ppc_n_lost_interrupts;

#ifdef CONFIG_TAU_INT
extern int tau_initialized;
extern int tau_interrupts(int);
#endif
#endif /* CONFIG_PPC32 */

#ifdef CONFIG_PPC64

#ifndef CONFIG_SPARSE_IRQ
EXPORT_SYMBOL(irq_desc);
#endif

int distribute_irqs = 1;

static inline notrace unsigned long get_hard_enabled(void)
{
	unsigned long enabled;

	__asm__ __volatile__("lbz %0,%1(13)"
	: "=r" (enabled) : "i" (offsetof(struct paca_struct, hard_enabled)));

	return enabled;
}

static inline notrace void set_soft_enabled(unsigned long enable)
{
	__asm__ __volatile__("stb %0,%1(13)"
	: : "r" (enable), "i" (offsetof(struct paca_struct, soft_enabled)));
}

static inline notrace void decrementer_check_overflow(void)
{
	u64 now = get_tb_or_rtc();
	u64 *next_tb;

	preempt_disable();
	next_tb = &__get_cpu_var(decrementers_next_tb);

	if (now >= *next_tb)
		set_dec(1);
	preempt_enable();
}

notrace void arch_local_irq_restore(unsigned long en)
{
	/*
	 * get_paca()->soft_enabled = en;
	 * Is it ever valid to use local_irq_restore(0) when soft_enabled is 1?
	 * That was allowed before, and in such a case we do need to take care
	 * that gcc will set soft_enabled directly via r13, not choose to use
	 * an intermediate register, lest we're preempted to a different cpu.
	 */
	set_soft_enabled(en);
	if (!en)
		return;

#ifdef CONFIG_PPC_STD_MMU_64
	if (firmware_has_feature(FW_FEATURE_ISERIES)) {
		/*
		 * Do we need to disable preemption here?  Not really: in the
		 * unlikely event that we're preempted to a different cpu in
		 * between getting r13, loading its lppaca_ptr, and loading
		 * its any_int, we might call iseries_handle_interrupts without
		 * an interrupt pending on the new cpu, but that's no disaster,
		 * is it?  And the business of preempting us off the old cpu
		 * would itself involve a local_irq_restore which handles the
		 * interrupt to that cpu.
		 *
		 * But use "local_paca->lppaca_ptr" instead of "get_lppaca()"
		 * to avoid any preemption checking added into get_paca().
		 */
		if (local_paca->lppaca_ptr->int_dword.any_int)
			iseries_handle_interrupts();
	}
#endif /* CONFIG_PPC_STD_MMU_64 */

	/*
	 * if (get_paca()->hard_enabled) return;
	 * But again we need to take care that gcc gets hard_enabled directly
	 * via r13, not choose to use an intermediate register, lest we're
	 * preempted to a different cpu in between the two instructions.
	 */
	if (get_hard_enabled())
		return;

	/*
	 * Need to hard-enable interrupts here.  Since currently disabled,
	 * no need to take further asm precautions against preemption; but
	 * use local_paca instead of get_paca() to avoid preemption checking.
	 */
	local_paca->hard_enabled = en;

	/*
	 * Trigger the decrementer if we have a pending event. Some processors
	 * only trigger on edge transitions of the sign bit. We might also
	 * have disabled interrupts long enough that the decrementer wrapped
	 * to positive.
	 */
	decrementer_check_overflow();

	/*
	 * Force the delivery of pending soft-disabled interrupts on PS3.
	 * Any HV call will have this side effect.
	 */
	if (firmware_has_feature(FW_FEATURE_PS3_LV1)) {
		u64 tmp, tmp2;
		lv1_get_version_info(&tmp, &tmp2);
	}

	__hard_irq_enable();
}
EXPORT_SYMBOL(arch_local_irq_restore);
#endif /* CONFIG_PPC64 */

int arch_show_interrupts(struct seq_file *p, int prec)
{
	int j;

#if defined(CONFIG_PPC32) && defined(CONFIG_TAU_INT)
	if (tau_initialized) {
		seq_printf(p, "%*s: ", prec, "TAU");
		for_each_online_cpu(j)
			seq_printf(p, "%10u ", tau_interrupts(j));
		seq_puts(p, "  PowerPC             Thermal Assist (cpu temp)\n");
	}
#endif /* CONFIG_PPC32 && CONFIG_TAU_INT */

	seq_printf(p, "%*s: ", prec, "LOC");
	for_each_online_cpu(j)
		seq_printf(p, "%10u ", per_cpu(irq_stat, j).timer_irqs);
        seq_printf(p, "  Local timer interrupts\n");

	seq_printf(p, "%*s: ", prec, "SPU");
	for_each_online_cpu(j)
		seq_printf(p, "%10u ", per_cpu(irq_stat, j).spurious_irqs);
	seq_printf(p, "  Spurious interrupts\n");

	seq_printf(p, "%*s: ", prec, "CNT");
	for_each_online_cpu(j)
		seq_printf(p, "%10u ", per_cpu(irq_stat, j).pmu_irqs);
	seq_printf(p, "  Performance monitoring interrupts\n");

	seq_printf(p, "%*s: ", prec, "MCE");
	for_each_online_cpu(j)
		seq_printf(p, "%10u ", per_cpu(irq_stat, j).mce_exceptions);
	seq_printf(p, "  Machine check exceptions\n");

	return 0;
}

/*
 * /proc/stat helpers
 */
u64 arch_irq_stat_cpu(unsigned int cpu)
{
	u64 sum = per_cpu(irq_stat, cpu).timer_irqs;

	sum += per_cpu(irq_stat, cpu).pmu_irqs;
	sum += per_cpu(irq_stat, cpu).mce_exceptions;
	sum += per_cpu(irq_stat, cpu).spurious_irqs;

	return sum;
}

#ifdef CONFIG_HOTPLUG_CPU
void migrate_irqs(void)
{
	struct irq_desc *desc;
	unsigned int irq;
	static int warned;
	cpumask_var_t mask;
	const struct cpumask *map = cpu_online_mask;

	alloc_cpumask_var(&mask, GFP_KERNEL);

	for_each_irq(irq) {
		struct irq_data *data;
		struct irq_chip *chip;

		desc = irq_to_desc(irq);
		if (!desc)
			continue;

		data = irq_desc_get_irq_data(desc);
		if (irqd_is_per_cpu(data))
			continue;

		chip = irq_data_get_irq_chip(data);

		cpumask_and(mask, data->affinity, map);
		if (cpumask_any(mask) >= nr_cpu_ids) {
			printk("Breaking affinity for irq %i\n", irq);
			cpumask_copy(mask, map);
		}
		if (chip->irq_set_affinity)
			chip->irq_set_affinity(data, mask, true);
		else if (desc->action && !(warned++))
			printk("Cannot set affinity for irq %i\n", irq);
	}

	free_cpumask_var(mask);

	local_irq_enable();
	mdelay(1);
	local_irq_disable();
}
#endif

static inline void handle_one_irq(unsigned int irq)
{
	struct thread_info *curtp, *irqtp;
	unsigned long saved_sp_limit;
	struct irq_desc *desc;

	desc = irq_to_desc(irq);
	if (!desc)
		return;

	/* Switch to the irq stack to handle this */
	curtp = current_thread_info();
	irqtp = hardirq_ctx[smp_processor_id()];

	if (curtp == irqtp) {
		/* We're already on the irq stack, just handle it */
		desc->handle_irq(irq, desc);
		return;
	}

	saved_sp_limit = current->thread.ksp_limit;

	irqtp->task = curtp->task;
	irqtp->flags = 0;

	/* Copy the softirq bits in preempt_count so that the
	 * softirq checks work in the hardirq context. */
	irqtp->preempt_count = (irqtp->preempt_count & ~SOFTIRQ_MASK) |
			       (curtp->preempt_count & SOFTIRQ_MASK);

	current->thread.ksp_limit = (unsigned long)irqtp +
		_ALIGN_UP(sizeof(struct thread_info), 16);

	call_handle_irq(irq, desc, irqtp, desc->handle_irq);
	current->thread.ksp_limit = saved_sp_limit;
	irqtp->task = NULL;

	/* Set any flag that may have been set on the
	 * alternate stack
	 */
	if (irqtp->flags)
		set_bits(irqtp->flags, &curtp->flags);
}

static inline void check_stack_overflow(void)
{
#ifdef CONFIG_DEBUG_STACKOVERFLOW
	long sp;

	sp = __get_SP() & (THREAD_SIZE-1);

	/* check for stack overflow: is there less than 2KB free? */
	if (unlikely(sp < (sizeof(struct thread_info) + 2048))) {
		printk("do_IRQ: stack overflow: %ld\n",
			sp - sizeof(struct thread_info));
		dump_stack();
	}
#endif
}

void do_IRQ(struct pt_regs *regs)
{
	struct pt_regs *old_regs = set_irq_regs(regs);
	unsigned int irq;

	trace_irq_entry(regs);

	irq_enter();

	check_stack_overflow();

	irq = ppc_md.get_irq();

	if (irq != NO_IRQ && irq != NO_IRQ_IGNORE)
		handle_one_irq(irq);
	else if (irq != NO_IRQ_IGNORE)
		__get_cpu_var(irq_stat).spurious_irqs++;

	irq_exit();
	set_irq_regs(old_regs);

#ifdef CONFIG_PPC_ISERIES
	if (firmware_has_feature(FW_FEATURE_ISERIES) &&
			get_lppaca()->int_dword.fields.decr_int) {
		get_lppaca()->int_dword.fields.decr_int = 0;
		/* Signal a fake decrementer interrupt */
		timer_interrupt(regs);
	}
#endif

	trace_irq_exit(regs);
}

void __init init_IRQ(void)
{
	if (ppc_md.init_IRQ)
		ppc_md.init_IRQ();

	exc_lvl_ctx_init();

	irq_ctx_init();
}

#if defined(CONFIG_BOOKE) || defined(CONFIG_40x)
struct thread_info   *critirq_ctx[NR_CPUS] __read_mostly;
struct thread_info    *dbgirq_ctx[NR_CPUS] __read_mostly;
struct thread_info *mcheckirq_ctx[NR_CPUS] __read_mostly;

void exc_lvl_ctx_init(void)
{
	struct thread_info *tp;
	int i, cpu_nr;

	for_each_possible_cpu(i) {
#ifdef CONFIG_PPC64
		cpu_nr = i;
#else
		cpu_nr = get_hard_smp_processor_id(i);
#endif
		memset((void *)critirq_ctx[cpu_nr], 0, THREAD_SIZE);
		tp = critirq_ctx[cpu_nr];
		tp->cpu = cpu_nr;
		tp->preempt_count = 0;

#ifdef CONFIG_BOOKE
		memset((void *)dbgirq_ctx[cpu_nr], 0, THREAD_SIZE);
		tp = dbgirq_ctx[cpu_nr];
		tp->cpu = cpu_nr;
		tp->preempt_count = 0;

		memset((void *)mcheckirq_ctx[cpu_nr], 0, THREAD_SIZE);
		tp = mcheckirq_ctx[cpu_nr];
		tp->cpu = cpu_nr;
		tp->preempt_count = HARDIRQ_OFFSET;
#endif
	}
}
#endif

struct thread_info *softirq_ctx[NR_CPUS] __read_mostly;
struct thread_info *hardirq_ctx[NR_CPUS] __read_mostly;

void irq_ctx_init(void)
{
	struct thread_info *tp;
	int i;

	for_each_possible_cpu(i) {
		memset((void *)softirq_ctx[i], 0, THREAD_SIZE);
		tp = softirq_ctx[i];
		tp->cpu = i;
		tp->preempt_count = 0;

		memset((void *)hardirq_ctx[i], 0, THREAD_SIZE);
		tp = hardirq_ctx[i];
		tp->cpu = i;
		tp->preempt_count = HARDIRQ_OFFSET;
	}
}

static inline void do_softirq_onstack(void)
{
	struct thread_info *curtp, *irqtp;
	unsigned long saved_sp_limit = current->thread.ksp_limit;

	curtp = current_thread_info();
	irqtp = softirq_ctx[smp_processor_id()];
	irqtp->task = curtp->task;
	irqtp->flags = 0;
	current->thread.ksp_limit = (unsigned long)irqtp +
				    _ALIGN_UP(sizeof(struct thread_info), 16);
	call_do_softirq(irqtp);
	current->thread.ksp_limit = saved_sp_limit;
	irqtp->task = NULL;

	/* Set any flag that may have been set on the
	 * alternate stack
	 */
	if (irqtp->flags)
		set_bits(irqtp->flags, &curtp->flags);
}

void do_softirq(void)
{
	unsigned long flags;

	if (in_interrupt())
		return;

	local_irq_save(flags);

	if (local_softirq_pending())
		do_softirq_onstack();

	local_irq_restore(flags);
}

irq_hw_number_t irqd_to_hwirq(struct irq_data *d)
{
	return d->hwirq;
}
EXPORT_SYMBOL_GPL(irqd_to_hwirq);

irq_hw_number_t virq_to_hw(unsigned int virq)
{
	struct irq_data *irq_data = irq_get_irq_data(virq);
	return WARN_ON(!irq_data) ? 0 : irq_data->hwirq;
}
EXPORT_SYMBOL_GPL(virq_to_hw);

#ifdef CONFIG_SMP
int irq_choose_cpu(const struct cpumask *mask)
{
	int cpuid;

	if (cpumask_equal(mask, cpu_all_mask)) {
		static int irq_rover;
		static DEFINE_RAW_SPINLOCK(irq_rover_lock);
		unsigned long flags;

		/* Round-robin distribution... */
do_round_robin:
		raw_spin_lock_irqsave(&irq_rover_lock, flags);

		irq_rover = cpumask_next(irq_rover, cpu_online_mask);
		if (irq_rover >= nr_cpu_ids)
			irq_rover = cpumask_first(cpu_online_mask);

		cpuid = irq_rover;

		raw_spin_unlock_irqrestore(&irq_rover_lock, flags);
	} else {
		cpuid = cpumask_first_and(mask, cpu_online_mask);
		if (cpuid >= nr_cpu_ids)
			goto do_round_robin;
	}

	return get_hard_smp_processor_id(cpuid);
}
#else
int irq_choose_cpu(const struct cpumask *mask)
{
	return hard_smp_processor_id();
}
#endif

int arch_early_irq_init(void)
{
	return 0;
}

#ifdef CONFIG_PPC64
static int __init setup_noirqdistrib(char *str)
{
	distribute_irqs = 0;
	return 1;
}

__setup("noirqdistrib", setup_noirqdistrib);
#endif /* CONFIG_PPC64 */