summaryrefslogtreecommitdiff
path: root/arch/loongarch/kernel/smp.c
blob: fbf747447f13fd356edb056cc3f5dea502e813b7 (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
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
 *
 * Derived from MIPS:
 * Copyright (C) 2000, 2001 Kanoj Sarcar
 * Copyright (C) 2000, 2001 Ralf Baechle
 * Copyright (C) 2000, 2001 Silicon Graphics, Inc.
 * Copyright (C) 2000, 2001, 2003 Broadcom Corporation
 */
#include <linux/acpi.h>
#include <linux/cpu.h>
#include <linux/cpumask.h>
#include <linux/init.h>
#include <linux/interrupt.h>
#include <linux/irq_work.h>
#include <linux/profile.h>
#include <linux/seq_file.h>
#include <linux/smp.h>
#include <linux/threads.h>
#include <linux/export.h>
#include <linux/syscore_ops.h>
#include <linux/time.h>
#include <linux/tracepoint.h>
#include <linux/sched/hotplug.h>
#include <linux/sched/task_stack.h>

#include <asm/cpu.h>
#include <asm/idle.h>
#include <asm/loongson.h>
#include <asm/mmu_context.h>
#include <asm/numa.h>
#include <asm/paravirt.h>
#include <asm/processor.h>
#include <asm/setup.h>
#include <asm/time.h>

int __cpu_number_map[NR_CPUS];   /* Map physical to logical */
EXPORT_SYMBOL(__cpu_number_map);

int __cpu_logical_map[NR_CPUS];		/* Map logical to physical */
EXPORT_SYMBOL(__cpu_logical_map);

/* Representing the threads (siblings) of each logical CPU */
cpumask_t cpu_sibling_map[NR_CPUS] __read_mostly;
EXPORT_SYMBOL(cpu_sibling_map);

/* Representing the core map of multi-core chips of each logical CPU */
cpumask_t cpu_core_map[NR_CPUS] __read_mostly;
EXPORT_SYMBOL(cpu_core_map);

static DECLARE_COMPLETION(cpu_starting);
static DECLARE_COMPLETION(cpu_running);

/*
 * A logcal cpu mask containing only one VPE per core to
 * reduce the number of IPIs on large MT systems.
 */
cpumask_t cpu_foreign_map[NR_CPUS] __read_mostly;
EXPORT_SYMBOL(cpu_foreign_map);

/* representing cpus for which sibling maps can be computed */
static cpumask_t cpu_sibling_setup_map;

/* representing cpus for which core maps can be computed */
static cpumask_t cpu_core_setup_map;

struct secondary_data cpuboot_data;
static DEFINE_PER_CPU(int, cpu_state);

static const char *ipi_types[NR_IPI] __tracepoint_string = {
	[IPI_RESCHEDULE] = "Rescheduling interrupts",
	[IPI_CALL_FUNCTION] = "Function call interrupts",
	[IPI_IRQ_WORK] = "IRQ work interrupts",
	[IPI_CLEAR_VECTOR] = "Clear vector interrupts",
};

void show_ipi_list(struct seq_file *p, int prec)
{
	unsigned int cpu, i;

	for (i = 0; i < NR_IPI; i++) {
		seq_printf(p, "%*s%u:%s", prec - 1, "IPI", i, prec >= 4 ? " " : "");
		for_each_online_cpu(cpu)
			seq_put_decimal_ull_width(p, " ", per_cpu(irq_stat, cpu).ipi_irqs[i], 10);
		seq_printf(p, " LoongArch  %d  %s\n", i + 1, ipi_types[i]);
	}
}

static inline void set_cpu_core_map(int cpu)
{
	int i;

	cpumask_set_cpu(cpu, &cpu_core_setup_map);

	for_each_cpu(i, &cpu_core_setup_map) {
		if (cpu_data[cpu].package == cpu_data[i].package) {
			cpumask_set_cpu(i, &cpu_core_map[cpu]);
			cpumask_set_cpu(cpu, &cpu_core_map[i]);
		}
	}
}

static inline void set_cpu_sibling_map(int cpu)
{
	int i;

	cpumask_set_cpu(cpu, &cpu_sibling_setup_map);

	for_each_cpu(i, &cpu_sibling_setup_map) {
		if (cpus_are_siblings(cpu, i)) {
			cpumask_set_cpu(i, &cpu_sibling_map[cpu]);
			cpumask_set_cpu(cpu, &cpu_sibling_map[i]);
		}
	}
}

static inline void clear_cpu_sibling_map(int cpu)
{
	int i;

	for_each_cpu(i, &cpu_sibling_setup_map) {
		if (cpus_are_siblings(cpu, i)) {
			cpumask_clear_cpu(i, &cpu_sibling_map[cpu]);
			cpumask_clear_cpu(cpu, &cpu_sibling_map[i]);
		}
	}

	cpumask_clear_cpu(cpu, &cpu_sibling_setup_map);
}

/*
 * Calculate a new cpu_foreign_map mask whenever a
 * new cpu appears or disappears.
 */
void calculate_cpu_foreign_map(void)
{
	int i, k, core_present;
	cpumask_t temp_foreign_map;

	/* Re-calculate the mask */
	cpumask_clear(&temp_foreign_map);
	for_each_online_cpu(i) {
		core_present = 0;
		for_each_cpu(k, &temp_foreign_map)
			if (cpus_are_siblings(i, k))
				core_present = 1;
		if (!core_present)
			cpumask_set_cpu(i, &temp_foreign_map);
	}

	for_each_online_cpu(i)
		cpumask_andnot(&cpu_foreign_map[i],
			       &temp_foreign_map, &cpu_sibling_map[i]);
}

/* Send mailbox buffer via Mail_Send */
static void csr_mail_send(uint64_t data, int cpu, int mailbox)
{
	uint64_t val;

	/* Send high 32 bits */
	val = IOCSR_MBUF_SEND_BLOCKING;
	val |= (IOCSR_MBUF_SEND_BOX_HI(mailbox) << IOCSR_MBUF_SEND_BOX_SHIFT);
	val |= (cpu << IOCSR_MBUF_SEND_CPU_SHIFT);
	val |= (data & IOCSR_MBUF_SEND_H32_MASK);
	iocsr_write64(val, LOONGARCH_IOCSR_MBUF_SEND);

	/* Send low 32 bits */
	val = IOCSR_MBUF_SEND_BLOCKING;
	val |= (IOCSR_MBUF_SEND_BOX_LO(mailbox) << IOCSR_MBUF_SEND_BOX_SHIFT);
	val |= (cpu << IOCSR_MBUF_SEND_CPU_SHIFT);
	val |= (data << IOCSR_MBUF_SEND_BUF_SHIFT);
	iocsr_write64(val, LOONGARCH_IOCSR_MBUF_SEND);
};

static u32 ipi_read_clear(int cpu)
{
	u32 action;

	/* Load the ipi register to figure out what we're supposed to do */
	action = iocsr_read32(LOONGARCH_IOCSR_IPI_STATUS);
	/* Clear the ipi register to clear the interrupt */
	iocsr_write32(action, LOONGARCH_IOCSR_IPI_CLEAR);
	wbflush();

	return action;
}

static void ipi_write_action(int cpu, u32 action)
{
	uint32_t val;

	val = IOCSR_IPI_SEND_BLOCKING | action;
	val |= (cpu << IOCSR_IPI_SEND_CPU_SHIFT);
	iocsr_write32(val, LOONGARCH_IOCSR_IPI_SEND);
}

static void loongson_send_ipi_single(int cpu, unsigned int action)
{
	ipi_write_action(cpu_logical_map(cpu), (u32)action);
}

static void loongson_send_ipi_mask(const struct cpumask *mask, unsigned int action)
{
	unsigned int i;

	for_each_cpu(i, mask)
		ipi_write_action(cpu_logical_map(i), (u32)action);
}

/*
 * This function sends a 'reschedule' IPI to another CPU.
 * it goes straight through and wastes no time serializing
 * anything. Worst case is that we lose a reschedule ...
 */
void arch_smp_send_reschedule(int cpu)
{
	mp_ops.send_ipi_single(cpu, ACTION_RESCHEDULE);
}
EXPORT_SYMBOL_GPL(arch_smp_send_reschedule);

#ifdef CONFIG_IRQ_WORK
void arch_irq_work_raise(void)
{
	mp_ops.send_ipi_single(smp_processor_id(), ACTION_IRQ_WORK);
}
#endif

static irqreturn_t loongson_ipi_interrupt(int irq, void *dev)
{
	unsigned int action;
	unsigned int cpu = smp_processor_id();

	action = ipi_read_clear(cpu_logical_map(cpu));

	if (action & SMP_RESCHEDULE) {
		scheduler_ipi();
		per_cpu(irq_stat, cpu).ipi_irqs[IPI_RESCHEDULE]++;
	}

	if (action & SMP_CALL_FUNCTION) {
		generic_smp_call_function_interrupt();
		per_cpu(irq_stat, cpu).ipi_irqs[IPI_CALL_FUNCTION]++;
	}

	if (action & SMP_IRQ_WORK) {
		irq_work_run();
		per_cpu(irq_stat, cpu).ipi_irqs[IPI_IRQ_WORK]++;
	}

	if (action & SMP_CLEAR_VECTOR) {
		complete_irq_moving();
		per_cpu(irq_stat, cpu).ipi_irqs[IPI_CLEAR_VECTOR]++;
	}

	return IRQ_HANDLED;
}

static void loongson_init_ipi(void)
{
	int r, ipi_irq;

	ipi_irq = get_percpu_irq(INT_IPI);
	if (ipi_irq < 0)
		panic("IPI IRQ mapping failed\n");

	irq_set_percpu_devid(ipi_irq);
	r = request_percpu_irq(ipi_irq, loongson_ipi_interrupt, "IPI", &irq_stat);
	if (r < 0)
		panic("IPI IRQ request failed\n");
}

struct smp_ops mp_ops = {
	.init_ipi		= loongson_init_ipi,
	.send_ipi_single	= loongson_send_ipi_single,
	.send_ipi_mask		= loongson_send_ipi_mask,
};

static void __init fdt_smp_setup(void)
{
#ifdef CONFIG_OF
	unsigned int cpu, cpuid;
	struct device_node *node = NULL;

	for_each_of_cpu_node(node) {
		if (!of_device_is_available(node))
			continue;

		cpuid = of_get_cpu_hwid(node, 0);
		if (cpuid >= nr_cpu_ids)
			continue;

		if (cpuid == loongson_sysconf.boot_cpu_id)
			cpu = 0;
		else
			cpu = find_first_zero_bit(cpumask_bits(cpu_present_mask), NR_CPUS);

		num_processors++;
		set_cpu_possible(cpu, true);
		set_cpu_present(cpu, true);
		__cpu_number_map[cpuid] = cpu;
		__cpu_logical_map[cpu] = cpuid;

		early_numa_add_cpu(cpuid, 0);
		set_cpuid_to_node(cpuid, 0);
	}

	loongson_sysconf.nr_cpus = num_processors;
	set_bit(0, loongson_sysconf.cores_io_master);
#endif
}

void __init loongson_smp_setup(void)
{
	fdt_smp_setup();

	if (loongson_sysconf.cores_per_package == 0)
		loongson_sysconf.cores_per_package = num_processors;

	cpu_data[0].core = cpu_logical_map(0) % loongson_sysconf.cores_per_package;
	cpu_data[0].package = cpu_logical_map(0) / loongson_sysconf.cores_per_package;

	pv_ipi_init();
	iocsr_write32(0xffffffff, LOONGARCH_IOCSR_IPI_EN);
	pr_info("Detected %i available CPU(s)\n", loongson_sysconf.nr_cpus);
}

void __init loongson_prepare_cpus(unsigned int max_cpus)
{
	int i = 0;

	parse_acpi_topology();
	cpu_data[0].global_id = cpu_logical_map(0);

	for (i = 0; i < loongson_sysconf.nr_cpus; i++) {
		set_cpu_present(i, true);
		csr_mail_send(0, __cpu_logical_map[i], 0);
	}

	per_cpu(cpu_state, smp_processor_id()) = CPU_ONLINE;
}

/*
 * Setup the PC, SP, and TP of a secondary processor and start it running!
 */
void loongson_boot_secondary(int cpu, struct task_struct *idle)
{
	unsigned long entry;

	pr_info("Booting CPU#%d...\n", cpu);

	entry = __pa_symbol((unsigned long)&smpboot_entry);
	cpuboot_data.stack = (unsigned long)__KSTK_TOS(idle);
	cpuboot_data.thread_info = (unsigned long)task_thread_info(idle);

	csr_mail_send(entry, cpu_logical_map(cpu), 0);

	loongson_send_ipi_single(cpu, ACTION_BOOT_CPU);
}

/*
 * SMP init and finish on secondary CPUs
 */
void loongson_init_secondary(void)
{
	unsigned int cpu = smp_processor_id();
	unsigned int imask = ECFGF_IP0 | ECFGF_IP1 | ECFGF_IP2 |
			     ECFGF_IPI | ECFGF_PMC | ECFGF_TIMER | ECFGF_SIP0;

	change_csr_ecfg(ECFG0_IM, imask);

	iocsr_write32(0xffffffff, LOONGARCH_IOCSR_IPI_EN);

#ifdef CONFIG_NUMA
	numa_add_cpu(cpu);
#endif
	per_cpu(cpu_state, cpu) = CPU_ONLINE;
	cpu_data[cpu].package =
		     cpu_logical_map(cpu) / loongson_sysconf.cores_per_package;
	cpu_data[cpu].core = pptt_enabled ? cpu_data[cpu].core :
		     cpu_logical_map(cpu) % loongson_sysconf.cores_per_package;
	cpu_data[cpu].global_id = cpu_logical_map(cpu);
}

void loongson_smp_finish(void)
{
	local_irq_enable();
	iocsr_write64(0, LOONGARCH_IOCSR_MBUF0);
	pr_info("CPU#%d finished\n", smp_processor_id());
}

#ifdef CONFIG_HOTPLUG_CPU

int loongson_cpu_disable(void)
{
	unsigned long flags;
	unsigned int cpu = smp_processor_id();

	if (io_master(cpu))
		return -EBUSY;

#ifdef CONFIG_NUMA
	numa_remove_cpu(cpu);
#endif
	set_cpu_online(cpu, false);
	clear_cpu_sibling_map(cpu);
	calculate_cpu_foreign_map();
	local_irq_save(flags);
	irq_migrate_all_off_this_cpu();
	clear_csr_ecfg(ECFG0_IM);
	local_irq_restore(flags);
	local_flush_tlb_all();

	return 0;
}

void loongson_cpu_die(unsigned int cpu)
{
	while (per_cpu(cpu_state, cpu) != CPU_DEAD)
		cpu_relax();

	mb();
}

void __noreturn arch_cpu_idle_dead(void)
{
	register uint64_t addr;
	register void (*init_fn)(void);

	idle_task_exit();
	local_irq_enable();
	set_csr_ecfg(ECFGF_IPI);
	__this_cpu_write(cpu_state, CPU_DEAD);

	__smp_mb();
	do {
		__asm__ __volatile__("idle 0\n\t");
		addr = iocsr_read64(LOONGARCH_IOCSR_MBUF0);
	} while (addr == 0);

	local_irq_disable();
	init_fn = (void *)TO_CACHE(addr);
	iocsr_write32(0xffffffff, LOONGARCH_IOCSR_IPI_CLEAR);

	init_fn();
	BUG();
}

#endif

/*
 * Power management
 */
#ifdef CONFIG_PM

static int loongson_ipi_suspend(void)
{
	return 0;
}

static void loongson_ipi_resume(void)
{
	iocsr_write32(0xffffffff, LOONGARCH_IOCSR_IPI_EN);
}

static struct syscore_ops loongson_ipi_syscore_ops = {
	.resume         = loongson_ipi_resume,
	.suspend        = loongson_ipi_suspend,
};

/*
 * Enable boot cpu ipi before enabling nonboot cpus
 * during syscore_resume.
 */
static int __init ipi_pm_init(void)
{
	register_syscore_ops(&loongson_ipi_syscore_ops);
	return 0;
}

core_initcall(ipi_pm_init);
#endif

/* Preload SMP state for boot cpu */
void __init smp_prepare_boot_cpu(void)
{
	unsigned int cpu, node, rr_node;

	set_cpu_possible(0, true);
	set_cpu_online(0, true);
	set_my_cpu_offset(per_cpu_offset(0));
	numa_add_cpu(0);

	rr_node = first_node(node_online_map);
	for_each_possible_cpu(cpu) {
		node = early_cpu_to_node(cpu);

		/*
		 * The mapping between present cpus and nodes has been
		 * built during MADT and SRAT parsing.
		 *
		 * If possible cpus = present cpus here, early_cpu_to_node
		 * will return valid node.
		 *
		 * If possible cpus > present cpus here (e.g. some possible
		 * cpus will be added by cpu-hotplug later), for possible but
		 * not present cpus, early_cpu_to_node will return NUMA_NO_NODE,
		 * and we just map them to online nodes in round-robin way.
		 * Once hotplugged, new correct mapping will be built for them.
		 */
		if (node != NUMA_NO_NODE)
			set_cpu_numa_node(cpu, node);
		else {
			set_cpu_numa_node(cpu, rr_node);
			rr_node = next_node_in(rr_node, node_online_map);
		}
	}

	pv_spinlock_init();
}

/* called from main before smp_init() */
void __init smp_prepare_cpus(unsigned int max_cpus)
{
	init_new_context(current, &init_mm);
	current_thread_info()->cpu = 0;
	loongson_prepare_cpus(max_cpus);
	set_cpu_sibling_map(0);
	set_cpu_core_map(0);
	calculate_cpu_foreign_map();
#ifndef CONFIG_HOTPLUG_CPU
	init_cpu_present(cpu_possible_mask);
#endif
}

int __cpu_up(unsigned int cpu, struct task_struct *tidle)
{
	loongson_boot_secondary(cpu, tidle);

	/* Wait for CPU to start and be ready to sync counters */
	if (!wait_for_completion_timeout(&cpu_starting,
					 msecs_to_jiffies(5000))) {
		pr_crit("CPU%u: failed to start\n", cpu);
		return -EIO;
	}

	/* Wait for CPU to finish startup & mark itself online before return */
	wait_for_completion(&cpu_running);

	return 0;
}

/*
 * First C code run on the secondary CPUs after being started up by
 * the master.
 */
asmlinkage void start_secondary(void)
{
	unsigned int cpu;

	sync_counter();
	cpu = raw_smp_processor_id();
	set_my_cpu_offset(per_cpu_offset(cpu));

	cpu_probe();
	constant_clockevent_init();
	loongson_init_secondary();

	set_cpu_sibling_map(cpu);
	set_cpu_core_map(cpu);

	notify_cpu_starting(cpu);

	/* Notify boot CPU that we're starting */
	complete(&cpu_starting);

	/* The CPU is running, now mark it online */
	set_cpu_online(cpu, true);

	calculate_cpu_foreign_map();

	/*
	 * Notify boot CPU that we're up & online and it can safely return
	 * from __cpu_up()
	 */
	complete(&cpu_running);

	/*
	 * irq will be enabled in loongson_smp_finish(), enabling it too
	 * early is dangerous.
	 */
	WARN_ON_ONCE(!irqs_disabled());
	loongson_smp_finish();

	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
}

void __init smp_cpus_done(unsigned int max_cpus)
{
}

static void stop_this_cpu(void *dummy)
{
	set_cpu_online(smp_processor_id(), false);
	calculate_cpu_foreign_map();
	local_irq_disable();
	while (true);
}

void smp_send_stop(void)
{
	smp_call_function(stop_this_cpu, NULL, 0);
}

#ifdef CONFIG_PROFILING
int setup_profiling_timer(unsigned int multiplier)
{
	return 0;
}
#endif

static void flush_tlb_all_ipi(void *info)
{
	local_flush_tlb_all();
}

void flush_tlb_all(void)
{
	on_each_cpu(flush_tlb_all_ipi, NULL, 1);
}

static void flush_tlb_mm_ipi(void *mm)
{
	local_flush_tlb_mm((struct mm_struct *)mm);
}

void flush_tlb_mm(struct mm_struct *mm)
{
	if (atomic_read(&mm->mm_users) == 0)
		return;		/* happens as a result of exit_mmap() */

	preempt_disable();

	if ((atomic_read(&mm->mm_users) != 1) || (current->mm != mm)) {
		on_each_cpu_mask(mm_cpumask(mm), flush_tlb_mm_ipi, mm, 1);
	} else {
		unsigned int cpu;

		for_each_online_cpu(cpu) {
			if (cpu != smp_processor_id() && cpu_context(cpu, mm))
				cpu_context(cpu, mm) = 0;
		}
		local_flush_tlb_mm(mm);
	}

	preempt_enable();
}

struct flush_tlb_data {
	struct vm_area_struct *vma;
	unsigned long addr1;
	unsigned long addr2;
};

static void flush_tlb_range_ipi(void *info)
{
	struct flush_tlb_data *fd = info;

	local_flush_tlb_range(fd->vma, fd->addr1, fd->addr2);
}

void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end)
{
	struct mm_struct *mm = vma->vm_mm;

	preempt_disable();
	if ((atomic_read(&mm->mm_users) != 1) || (current->mm != mm)) {
		struct flush_tlb_data fd = {
			.vma = vma,
			.addr1 = start,
			.addr2 = end,
		};

		on_each_cpu_mask(mm_cpumask(mm), flush_tlb_range_ipi, &fd, 1);
	} else {
		unsigned int cpu;

		for_each_online_cpu(cpu) {
			if (cpu != smp_processor_id() && cpu_context(cpu, mm))
				cpu_context(cpu, mm) = 0;
		}
		local_flush_tlb_range(vma, start, end);
	}
	preempt_enable();
}

static void flush_tlb_kernel_range_ipi(void *info)
{
	struct flush_tlb_data *fd = info;

	local_flush_tlb_kernel_range(fd->addr1, fd->addr2);
}

void flush_tlb_kernel_range(unsigned long start, unsigned long end)
{
	struct flush_tlb_data fd = {
		.addr1 = start,
		.addr2 = end,
	};

	on_each_cpu(flush_tlb_kernel_range_ipi, &fd, 1);
}

static void flush_tlb_page_ipi(void *info)
{
	struct flush_tlb_data *fd = info;

	local_flush_tlb_page(fd->vma, fd->addr1);
}

void flush_tlb_page(struct vm_area_struct *vma, unsigned long page)
{
	preempt_disable();
	if ((atomic_read(&vma->vm_mm->mm_users) != 1) || (current->mm != vma->vm_mm)) {
		struct flush_tlb_data fd = {
			.vma = vma,
			.addr1 = page,
		};

		on_each_cpu_mask(mm_cpumask(vma->vm_mm), flush_tlb_page_ipi, &fd, 1);
	} else {
		unsigned int cpu;

		for_each_online_cpu(cpu) {
			if (cpu != smp_processor_id() && cpu_context(cpu, vma->vm_mm))
				cpu_context(cpu, vma->vm_mm) = 0;
		}
		local_flush_tlb_page(vma, page);
	}
	preempt_enable();
}
EXPORT_SYMBOL(flush_tlb_page);

static void flush_tlb_one_ipi(void *info)
{
	unsigned long vaddr = (unsigned long) info;

	local_flush_tlb_one(vaddr);
}

void flush_tlb_one(unsigned long vaddr)
{
	on_each_cpu(flush_tlb_one_ipi, (void *)vaddr, 1);
}
EXPORT_SYMBOL(flush_tlb_one);