aboutsummaryrefslogtreecommitdiff
path: root/arch/x86/kernel/irq.c
blob: 22d0687e7fda15163b04b771ac1a0e2170e1bf46 (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
/*
 * Common interrupt code for 32 and 64 bit
 */
#include <linux/cpu.h>
#include <linux/interrupt.h>
#include <linux/kernel_stat.h>
#include <linux/of.h>
#include <linux/seq_file.h>
#include <linux/smp.h>
#include <linux/ftrace.h>
#include <linux/delay.h>
#include <linux/export.h>

#include <asm/apic.h>
#include <asm/io_apic.h>
#include <asm/irq.h>
#include <asm/idle.h>
#include <asm/mce.h>
#include <asm/hw_irq.h>

#define CREATE_TRACE_POINTS
#include <asm/trace/irq_vectors.h>

atomic_t irq_err_count;

/* Function pointer for generic interrupt vector handling */
void (*x86_platform_ipi_callback)(void) = NULL;

/*
 * '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)
{
	if (printk_ratelimit())
		pr_err("unexpected IRQ trap at vector %02x\n", irq);

	/*
	 * 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
	 */
	ack_APIC_irq();
}

#define irq_stats(x)		(&per_cpu(irq_stat, x))
/*
 * /proc/interrupts printing for arch specific interrupts
 */
int arch_show_interrupts(struct seq_file *p, int prec)
{
	int j;

	seq_printf(p, "%*s: ", prec, "NMI");
	for_each_online_cpu(j)
		seq_printf(p, "%10u ", irq_stats(j)->__nmi_count);
	seq_printf(p, "  Non-maskable interrupts\n");
#ifdef CONFIG_X86_LOCAL_APIC
	seq_printf(p, "%*s: ", prec, "LOC");
	for_each_online_cpu(j)
		seq_printf(p, "%10u ", irq_stats(j)->apic_timer_irqs);
	seq_printf(p, "  Local timer interrupts\n");

	seq_printf(p, "%*s: ", prec, "SPU");
	for_each_online_cpu(j)
		seq_printf(p, "%10u ", irq_stats(j)->irq_spurious_count);
	seq_printf(p, "  Spurious interrupts\n");
	seq_printf(p, "%*s: ", prec, "PMI");
	for_each_online_cpu(j)
		seq_printf(p, "%10u ", irq_stats(j)->apic_perf_irqs);
	seq_printf(p, "  Performance monitoring interrupts\n");
	seq_printf(p, "%*s: ", prec, "IWI");
	for_each_online_cpu(j)
		seq_printf(p, "%10u ", irq_stats(j)->apic_irq_work_irqs);
	seq_printf(p, "  IRQ work interrupts\n");
	seq_printf(p, "%*s: ", prec, "RTR");
	for_each_online_cpu(j)
		seq_printf(p, "%10u ", irq_stats(j)->icr_read_retry_count);
	seq_printf(p, "  APIC ICR read retries\n");
#endif
	if (x86_platform_ipi_callback) {
		seq_printf(p, "%*s: ", prec, "PLT");
		for_each_online_cpu(j)
			seq_printf(p, "%10u ", irq_stats(j)->x86_platform_ipis);
		seq_printf(p, "  Platform interrupts\n");
	}
#ifdef CONFIG_SMP
	seq_printf(p, "%*s: ", prec, "RES");
	for_each_online_cpu(j)
		seq_printf(p, "%10u ", irq_stats(j)->irq_resched_count);
	seq_printf(p, "  Rescheduling interrupts\n");
	seq_printf(p, "%*s: ", prec, "CAL");
	for_each_online_cpu(j)
		seq_printf(p, "%10u ", irq_stats(j)->irq_call_count -
					irq_stats(j)->irq_tlb_count);
	seq_printf(p, "  Function call interrupts\n");
	seq_printf(p, "%*s: ", prec, "TLB");
	for_each_online_cpu(j)
		seq_printf(p, "%10u ", irq_stats(j)->irq_tlb_count);
	seq_printf(p, "  TLB shootdowns\n");
#endif
#ifdef CONFIG_X86_THERMAL_VECTOR
	seq_printf(p, "%*s: ", prec, "TRM");
	for_each_online_cpu(j)
		seq_printf(p, "%10u ", irq_stats(j)->irq_thermal_count);
	seq_printf(p, "  Thermal event interrupts\n");
#endif
#ifdef CONFIG_X86_MCE_THRESHOLD
	seq_printf(p, "%*s: ", prec, "THR");
	for_each_online_cpu(j)
		seq_printf(p, "%10u ", irq_stats(j)->irq_threshold_count);
	seq_printf(p, "  Threshold APIC interrupts\n");
#endif
#ifdef CONFIG_X86_MCE
	seq_printf(p, "%*s: ", prec, "MCE");
	for_each_online_cpu(j)
		seq_printf(p, "%10u ", per_cpu(mce_exception_count, j));
	seq_printf(p, "  Machine check exceptions\n");
	seq_printf(p, "%*s: ", prec, "MCP");
	for_each_online_cpu(j)
		seq_printf(p, "%10u ", per_cpu(mce_poll_count, j));
	seq_printf(p, "  Machine check polls\n");
#endif
	seq_printf(p, "%*s: %10u\n", prec, "ERR", atomic_read(&irq_err_count));
#if defined(CONFIG_X86_IO_APIC)
	seq_printf(p, "%*s: %10u\n", prec, "MIS", atomic_read(&irq_mis_count));
#endif
	return 0;
}

/*
 * /proc/stat helpers
 */
u64 arch_irq_stat_cpu(unsigned int cpu)
{
	u64 sum = irq_stats(cpu)->__nmi_count;

#ifdef CONFIG_X86_LOCAL_APIC
	sum += irq_stats(cpu)->apic_timer_irqs;
	sum += irq_stats(cpu)->irq_spurious_count;
	sum += irq_stats(cpu)->apic_perf_irqs;
	sum += irq_stats(cpu)->apic_irq_work_irqs;
	sum += irq_stats(cpu)->icr_read_retry_count;
#endif
	if (x86_platform_ipi_callback)
		sum += irq_stats(cpu)->x86_platform_ipis;
#ifdef CONFIG_SMP
	sum += irq_stats(cpu)->irq_resched_count;
	sum += irq_stats(cpu)->irq_call_count;
#endif
#ifdef CONFIG_X86_THERMAL_VECTOR
	sum += irq_stats(cpu)->irq_thermal_count;
#endif
#ifdef CONFIG_X86_MCE_THRESHOLD
	sum += irq_stats(cpu)->irq_threshold_count;
#endif
#ifdef CONFIG_X86_MCE
	sum += per_cpu(mce_exception_count, cpu);
	sum += per_cpu(mce_poll_count, cpu);
#endif
	return sum;
}

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


/*
 * do_IRQ handles all normal device IRQ's (the special
 * SMP cross-CPU interrupts have their own specific
 * handlers).
 */
__visible unsigned int __irq_entry do_IRQ(struct pt_regs *regs)
{
	struct pt_regs *old_regs = set_irq_regs(regs);

	/* high bit used in ret_from_ code  */
	unsigned vector = ~regs->orig_ax;
	unsigned irq;

	irq_enter();
	exit_idle();

	irq = __this_cpu_read(vector_irq[vector]);

	if (!handle_irq(irq, regs)) {
		ack_APIC_irq();

		if (printk_ratelimit())
			pr_emerg("%s: %d.%d No irq handler for vector (irq %d)\n",
				__func__, smp_processor_id(), vector, irq);
	}

	irq_exit();

	set_irq_regs(old_regs);
	return 1;
}

/*
 * Handler for X86_PLATFORM_IPI_VECTOR.
 */
void __smp_x86_platform_ipi(void)
{
	inc_irq_stat(x86_platform_ipis);

	if (x86_platform_ipi_callback)
		x86_platform_ipi_callback();
}

__visible void smp_x86_platform_ipi(struct pt_regs *regs)
{
	struct pt_regs *old_regs = set_irq_regs(regs);

	entering_ack_irq();
	__smp_x86_platform_ipi();
	exiting_irq();
	set_irq_regs(old_regs);
}

#ifdef CONFIG_HAVE_KVM
/*
 * Handler for POSTED_INTERRUPT_VECTOR.
 */
__visible void smp_kvm_posted_intr_ipi(struct pt_regs *regs)
{
	struct pt_regs *old_regs = set_irq_regs(regs);

	ack_APIC_irq();

	irq_enter();

	exit_idle();

	inc_irq_stat(kvm_posted_intr_ipis);

	irq_exit();

	set_irq_regs(old_regs);
}
#endif

__visible void smp_trace_x86_platform_ipi(struct pt_regs *regs)
{
	struct pt_regs *old_regs = set_irq_regs(regs);

	entering_ack_irq();
	trace_x86_platform_ipi_entry(X86_PLATFORM_IPI_VECTOR);
	__smp_x86_platform_ipi();
	trace_x86_platform_ipi_exit(X86_PLATFORM_IPI_VECTOR);
	exiting_irq();
	set_irq_regs(old_regs);
}

EXPORT_SYMBOL_GPL(vector_used_by_percpu_irq);

#ifdef CONFIG_HOTPLUG_CPU
/* A cpu has been removed from cpu_online_mask.  Reset irq affinities. */
void fixup_irqs(void)
{
	unsigned int irq, vector;
	static int warned;
	struct irq_desc *desc;
	struct irq_data *data;
	struct irq_chip *chip;

	for_each_irq_desc(irq, desc) {
		int break_affinity = 0;
		int set_affinity = 1;
		const struct cpumask *affinity;

		if (!desc)
			continue;
		if (irq == 2)
			continue;

		/* interrupt's are disabled at this point */
		raw_spin_lock(&desc->lock);

		data = irq_desc_get_irq_data(desc);
		affinity = data->affinity;
		if (!irq_has_action(irq) || irqd_is_per_cpu(data) ||
		    cpumask_subset(affinity, cpu_online_mask)) {
			raw_spin_unlock(&desc->lock);
			continue;
		}

		/*
		 * Complete the irq move. This cpu is going down and for
		 * non intr-remapping case, we can't wait till this interrupt
		 * arrives at this cpu before completing the irq move.
		 */
		irq_force_complete_move(irq);

		if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) {
			break_affinity = 1;
			affinity = cpu_online_mask;
		}

		chip = irq_data_get_irq_chip(data);
		if (!irqd_can_move_in_process_context(data) && chip->irq_mask)
			chip->irq_mask(data);

		if (chip->irq_set_affinity)
			chip->irq_set_affinity(data, affinity, true);
		else if (!(warned++))
			set_affinity = 0;

		/*
		 * We unmask if the irq was not marked masked by the
		 * core code. That respects the lazy irq disable
		 * behaviour.
		 */
		if (!irqd_can_move_in_process_context(data) &&
		    !irqd_irq_masked(data) && chip->irq_unmask)
			chip->irq_unmask(data);

		raw_spin_unlock(&desc->lock);

		if (break_affinity && set_affinity)
			pr_notice("Broke affinity for irq %i\n", irq);
		else if (!set_affinity)
			pr_notice("Cannot set affinity for irq %i\n", irq);
	}

	/*
	 * We can remove mdelay() and then send spuriuous interrupts to
	 * new cpu targets for all the irqs that were handled previously by
	 * this cpu. While it works, I have seen spurious interrupt messages
	 * (nothing wrong but still...).
	 *
	 * So for now, retain mdelay(1) and check the IRR and then send those
	 * interrupts to new targets as this cpu is already offlined...
	 */
	mdelay(1);

	for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) {
		unsigned int irr;

		if (__this_cpu_read(vector_irq[vector]) < 0)
			continue;

		irr = apic_read(APIC_IRR + (vector / 32 * 0x10));
		if (irr  & (1 << (vector % 32))) {
			irq = __this_cpu_read(vector_irq[vector]);

			desc = irq_to_desc(irq);
			data = irq_desc_get_irq_data(desc);
			chip = irq_data_get_irq_chip(data);
			raw_spin_lock(&desc->lock);
			if (chip->irq_retrigger)
				chip->irq_retrigger(data);
			raw_spin_unlock(&desc->lock);
		}
		__this_cpu_write(vector_irq[vector], -1);
	}
}
#endif