summaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel/irq_32.c
blob: 8d525765a6c409922e45bd65a7dcc296edd4f0b3 (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
/*
 *	Copyright (C) 1992, 1998 Linus Torvalds, Ingo Molnar
 *
 * This file contains the lowest level x86-specific interrupt
 * entry, irq-stacks and irq statistics code. All the remaining
 * irq logic is done by the generic kernel/irq/ code and
 * by the x86-specific irq controller code. (e.g. i8259.c and
 * io_apic.c.)
 */

#include <linux/module.h>
#include <linux/seq_file.h>
#include <linux/interrupt.h>
#include <linux/kernel_stat.h>
#include <linux/notifier.h>
#include <linux/cpu.h>
#include <linux/delay.h>

#include <asm/apic.h>
#include <asm/uaccess.h>

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

DEFINE_PER_CPU(struct pt_regs *, irq_regs);
EXPORT_PER_CPU_SYMBOL(irq_regs);

/*
 * 'what should we do if we get a hw irq event on an illegal vector'.
 * each architecture has to answer this themselves.
 */
void ack_bad_irq(unsigned int irq)
{
	printk(KERN_ERR "unexpected IRQ trap at vector %02x\n", irq);

#ifdef CONFIG_X86_LOCAL_APIC
	/*
	 * Currently unexpected vectors happen only on SMP and APIC.
	 * We _must_ ack these because every local APIC has only N
	 * irq slots per priority level, and a 'hanging, unacked' IRQ
	 * holds up an irq slot - in excessive cases (when multiple
	 * unexpected vectors occur) that might lock up the APIC
	 * completely.
	 * But only ack when the APIC is enabled -AK
	 */
	if (cpu_has_apic)
		ack_APIC_irq();
#endif
}

#ifdef CONFIG_DEBUG_STACKOVERFLOW
/* Debugging check for stack overflow: is there less than 1KB free? */
static int check_stack_overflow(void)
{
	long sp;

	__asm__ __volatile__("andl %%esp,%0" :
			     "=r" (sp) : "0" (THREAD_SIZE - 1));

	return sp < (sizeof(struct thread_info) + STACK_WARN);
}

static void print_stack_overflow(void)
{
	printk(KERN_WARNING "low stack detected by irq handler\n");
	dump_stack();
}

#else
static inline int check_stack_overflow(void) { return 0; }
static inline void print_stack_overflow(void) { }
#endif

#ifdef CONFIG_4KSTACKS
/*
 * per-CPU IRQ handling contexts (thread information and stack)
 */
union irq_ctx {
	struct thread_info      tinfo;
	u32                     stack[THREAD_SIZE/sizeof(u32)];
};

static union irq_ctx *hardirq_ctx[NR_CPUS] __read_mostly;
static union irq_ctx *softirq_ctx[NR_CPUS] __read_mostly;

static char softirq_stack[NR_CPUS * THREAD_SIZE] __page_aligned_bss;
static char hardirq_stack[NR_CPUS * THREAD_SIZE] __page_aligned_bss;

static void call_on_stack(void *func, void *stack)
{
	asm volatile("xchgl	%%ebx,%%esp	\n"
		     "call	*%%edi		\n"
		     "movl	%%ebx,%%esp	\n"
		     : "=b" (stack)
		     : "0" (stack),
		       "D"(func)
		     : "memory", "cc", "edx", "ecx", "eax");
}

static inline int
execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq)
{
	union irq_ctx *curctx, *irqctx;
	u32 *isp, arg1, arg2;

	curctx = (union irq_ctx *) current_thread_info();
	irqctx = hardirq_ctx[smp_processor_id()];

	/*
	 * this is where we switch to the IRQ stack. However, if we are
	 * already using the IRQ stack (because we interrupted a hardirq
	 * handler) we can't do that and just have to keep using the
	 * current stack (which is the irq stack already after all)
	 */
	if (unlikely(curctx == irqctx))
		return 0;

	/* build the stack frame on the IRQ stack */
	isp = (u32 *) ((char*)irqctx + sizeof(*irqctx));
	irqctx->tinfo.task = curctx->tinfo.task;
	irqctx->tinfo.previous_esp = current_stack_pointer;

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

	if (unlikely(overflow))
		call_on_stack(print_stack_overflow, isp);

	asm volatile("xchgl	%%ebx,%%esp	\n"
		     "call	*%%edi		\n"
		     "movl	%%ebx,%%esp	\n"
		     : "=a" (arg1), "=d" (arg2), "=b" (isp)
		     :  "0" (irq),   "1" (desc),  "2" (isp),
			"D" (desc->handle_irq)
		     : "memory", "cc", "ecx");
	return 1;
}

/*
 * allocate per-cpu stacks for hardirq and for softirq processing
 */
void __cpuinit irq_ctx_init(int cpu)
{
	union irq_ctx *irqctx;

	if (hardirq_ctx[cpu])
		return;

	irqctx = (union irq_ctx*) &hardirq_stack[cpu*THREAD_SIZE];
	irqctx->tinfo.task		= NULL;
	irqctx->tinfo.exec_domain	= NULL;
	irqctx->tinfo.cpu		= cpu;
	irqctx->tinfo.preempt_count	= HARDIRQ_OFFSET;
	irqctx->tinfo.addr_limit	= MAKE_MM_SEG(0);

	hardirq_ctx[cpu] = irqctx;

	irqctx = (union irq_ctx*) &softirq_stack[cpu*THREAD_SIZE];
	irqctx->tinfo.task		= NULL;
	irqctx->tinfo.exec_domain	= NULL;
	irqctx->tinfo.cpu		= cpu;
	irqctx->tinfo.preempt_count	= 0;
	irqctx->tinfo.addr_limit	= MAKE_MM_SEG(0);

	softirq_ctx[cpu] = irqctx;

	printk(KERN_DEBUG "CPU %u irqstacks, hard=%p soft=%p\n",
	       cpu,hardirq_ctx[cpu],softirq_ctx[cpu]);
}

void irq_ctx_exit(int cpu)
{
	hardirq_ctx[cpu] = NULL;
}

asmlinkage void do_softirq(void)
{
	unsigned long flags;
	struct thread_info *curctx;
	union irq_ctx *irqctx;
	u32 *isp;

	if (in_interrupt())
		return;

	local_irq_save(flags);

	if (local_softirq_pending()) {
		curctx = current_thread_info();
		irqctx = softirq_ctx[smp_processor_id()];
		irqctx->tinfo.task = curctx->task;
		irqctx->tinfo.previous_esp = current_stack_pointer;

		/* build the stack frame on the softirq stack */
		isp = (u32*) ((char*)irqctx + sizeof(*irqctx));

		call_on_stack(__do_softirq, isp);
		/*
		 * Shouldnt happen, we returned above if in_interrupt():
		 */
		WARN_ON_ONCE(softirq_count());
	}

	local_irq_restore(flags);
}

#else
static inline int
execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq) { return 0; }
#endif

/*
 * do_IRQ handles all normal device IRQ's (the special
 * SMP cross-CPU interrupts have their own specific
 * handlers).
 */
unsigned int do_IRQ(struct pt_regs *regs)
{
	struct pt_regs *old_regs;
	/* high bit used in ret_from_ code */
	int overflow;
	unsigned vector = ~regs->orig_ax;
	struct irq_desc *desc;
	unsigned irq;


	old_regs = set_irq_regs(regs);
	irq_enter();
	irq = __get_cpu_var(vector_irq)[vector];

	overflow = check_stack_overflow();

	desc = irq_to_desc(irq);
	if (unlikely(!desc)) {
		printk(KERN_EMERG "%s: cannot handle IRQ %d vector %#x cpu %d\n",
					__func__, irq, vector, smp_processor_id());
		BUG();
	}

	if (!execute_on_irq_stack(overflow, desc, irq)) {
		if (unlikely(overflow))
			print_stack_overflow();
		desc->handle_irq(irq, desc);
	}

	irq_exit();
	set_irq_regs(old_regs);
	return 1;
}

/*
 * Interrupt statistics:
 */

atomic_t irq_err_count;

/*
 * /proc/interrupts printing:
 */

static int show_other_interrupts(struct seq_file *p)
{
	int j;

	seq_printf(p, "NMI: ");
	for_each_online_cpu(j)
		seq_printf(p, "%10u ", nmi_count(j));
	seq_printf(p, "  Non-maskable interrupts\n");
#ifdef CONFIG_X86_LOCAL_APIC
	seq_printf(p, "LOC: ");
	for_each_online_cpu(j)
		seq_printf(p, "%10u ", per_cpu(irq_stat,j).apic_timer_irqs);
	seq_printf(p, "  Local timer interrupts\n");
#endif
#ifdef CONFIG_SMP
	seq_printf(p, "RES: ");
	for_each_online_cpu(j)
		seq_printf(p, "%10u ", per_cpu(irq_stat,j).irq_resched_count);
	seq_printf(p, "  Rescheduling interrupts\n");
	seq_printf(p, "CAL: ");
	for_each_online_cpu(j)
		seq_printf(p, "%10u ", per_cpu(irq_stat,j).irq_call_count);
	seq_printf(p, "  Function call interrupts\n");
	seq_printf(p, "TLB: ");
	for_each_online_cpu(j)
		seq_printf(p, "%10u ", per_cpu(irq_stat,j).irq_tlb_count);
	seq_printf(p, "  TLB shootdowns\n");
#endif
#ifdef CONFIG_X86_MCE
	seq_printf(p, "TRM: ");
	for_each_online_cpu(j)
		seq_printf(p, "%10u ", per_cpu(irq_stat,j).irq_thermal_count);
	seq_printf(p, "  Thermal event interrupts\n");
#endif
#ifdef CONFIG_X86_LOCAL_APIC
	seq_printf(p, "SPU: ");
	for_each_online_cpu(j)
		seq_printf(p, "%10u ", per_cpu(irq_stat,j).irq_spurious_count);
	seq_printf(p, "  Spurious interrupts\n");
#endif
	seq_printf(p, "ERR: %10u\n", atomic_read(&irq_err_count));
#if defined(CONFIG_X86_IO_APIC)
	seq_printf(p, "MIS: %10u\n", atomic_read(&irq_mis_count));
#endif
	return 0;
}

int show_interrupts(struct seq_file *p, void *v)
{
	unsigned long flags, any_count = 0;
	int i = *(loff_t *) v, j;
	struct irqaction *action;
	struct irq_desc *desc;

	if (i > nr_irqs)
		return 0;

	if (i == nr_irqs)
		return show_other_interrupts(p);

	/* print header */
	if (i == 0) {
		seq_printf(p, "           ");
		for_each_online_cpu(j)
			seq_printf(p, "CPU%-8d",j);
		seq_putc(p, '\n');
	}

	desc = irq_to_desc(i);
	spin_lock_irqsave(&desc->lock, flags);
#ifndef CONFIG_SMP
	any_count = kstat_irqs(i);
#else
	for_each_online_cpu(j)
		any_count |= kstat_irqs_cpu(i, j);
#endif
	action = desc->action;
	if (!action && !any_count)
		goto out;

	seq_printf(p, "%3d: ", i);
#ifndef CONFIG_SMP
	seq_printf(p, "%10u ", kstat_irqs(i));
#else
	for_each_online_cpu(j)
		seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
#endif
	seq_printf(p, " %8s", desc->chip->name);
	seq_printf(p, "-%-8s", desc->name);

	if (action) {
		seq_printf(p, "  %s", action->name);
		while ((action = action->next) != NULL)
			seq_printf(p, ", %s", action->name);
	}

	seq_putc(p, '\n');
out:
	spin_unlock_irqrestore(&desc->lock, flags);
	return 0;
}

/*
 * /proc/stat helpers
 */
u64 arch_irq_stat_cpu(unsigned int cpu)
{
	u64 sum = nmi_count(cpu);

#ifdef CONFIG_X86_LOCAL_APIC
	sum += per_cpu(irq_stat, cpu).apic_timer_irqs;
#endif
#ifdef CONFIG_SMP
	sum += per_cpu(irq_stat, cpu).irq_resched_count;
	sum += per_cpu(irq_stat, cpu).irq_call_count;
	sum += per_cpu(irq_stat, cpu).irq_tlb_count;
#endif
#ifdef CONFIG_X86_MCE
	sum += per_cpu(irq_stat, cpu).irq_thermal_count;
#endif
#ifdef CONFIG_X86_LOCAL_APIC
	sum += per_cpu(irq_stat, cpu).irq_spurious_count;
#endif
	return sum;
}

u64 arch_irq_stat(void)
{
	u64 sum = atomic_read(&irq_err_count);

#ifdef CONFIG_X86_IO_APIC
	sum += atomic_read(&irq_mis_count);
#endif
	return sum;
}

#ifdef CONFIG_HOTPLUG_CPU
#include <mach_apic.h>

void fixup_irqs(cpumask_t map)
{
	unsigned int irq;
	static int warned;
	struct irq_desc *desc;

	for_each_irq_desc(irq, desc) {
		cpumask_t mask;

		if (irq == 2)
			continue;

		cpus_and(mask, desc->affinity, map);
		if (any_online_cpu(mask) == NR_CPUS) {
			printk("Breaking affinity for irq %i\n", irq);
			mask = map;
		}
		if (desc->chip->set_affinity)
			desc->chip->set_affinity(irq, mask);
		else if (desc->action && !(warned++))
			printk("Cannot set affinity for irq %i\n", irq);
	}

#if 0
	barrier();
	/* Ingo Molnar says: "after the IO-APIC masks have been redirected
	   [note the nop - the interrupt-enable boundary on x86 is two
	   instructions from sti] - to flush out pending hardirqs and
	   IPIs. After this point nothing is supposed to reach this CPU." */
	__asm__ __volatile__("sti; nop; cli");
	barrier();
#else
	/* That doesn't seem sufficient.  Give it 1ms. */
	local_irq_enable();
	mdelay(1);
	local_irq_disable();
#endif
}
#endif