summaryrefslogtreecommitdiffstats
path: root/arch/ia64/kernel/smp.c
blob: 983296f1c813a3baeb34435258b9ff8af737a172 (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
/*
 * SMP Support
 *
 * Copyright (C) 1999 Walt Drummond <drummond@valinux.com>
 * Copyright (C) 1999, 2001, 2003 David Mosberger-Tang <davidm@hpl.hp.com>
 *
 * Lots of stuff stolen from arch/alpha/kernel/smp.c
 *
 * 01/05/16 Rohit Seth <rohit.seth@intel.com>  IA64-SMP functions. Reorganized
 * the existing code (on the lines of x86 port).
 * 00/09/11 David Mosberger <davidm@hpl.hp.com> Do loops_per_jiffy
 * calibration on each CPU.
 * 00/08/23 Asit Mallick <asit.k.mallick@intel.com> fixed logical processor id
 * 00/03/31 Rohit Seth <rohit.seth@intel.com>	Fixes for Bootstrap Processor
 * & cpu_online_map now gets done here (instead of setup.c)
 * 99/10/05 davidm	Update to bring it in sync with new command-line processing
 *  scheme.
 * 10/13/00 Goutham Rao <goutham.rao@intel.com> Updated smp_call_function and
 *		smp_call_function_single to resend IPI on timeouts
 */
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/init.h>
#include <linux/interrupt.h>
#include <linux/smp.h>
#include <linux/kernel_stat.h>
#include <linux/mm.h>
#include <linux/cache.h>
#include <linux/delay.h>
#include <linux/efi.h>
#include <linux/bitops.h>
#include <linux/kexec.h>

#include <asm/atomic.h>
#include <asm/current.h>
#include <asm/delay.h>
#include <asm/machvec.h>
#include <asm/io.h>
#include <asm/irq.h>
#include <asm/page.h>
#include <asm/pgalloc.h>
#include <asm/pgtable.h>
#include <asm/processor.h>
#include <asm/ptrace.h>
#include <asm/sal.h>
#include <asm/system.h>
#include <asm/tlbflush.h>
#include <asm/unistd.h>
#include <asm/mca.h>

/*
 * Note: alignment of 4 entries/cacheline was empirically determined
 * to be a good tradeoff between hot cachelines & spreading the array
 * across too many cacheline.
 */
static struct local_tlb_flush_counts {
	unsigned int count;
} __attribute__((__aligned__(32))) local_tlb_flush_counts[NR_CPUS];

static DEFINE_PER_CPU(unsigned int, shadow_flush_counts[NR_CPUS]) ____cacheline_aligned;


/*
 * Structure and data for smp_call_function(). This is designed to minimise static memory
 * requirements. It also looks cleaner.
 */
static  __cacheline_aligned DEFINE_SPINLOCK(call_lock);

struct call_data_struct {
	void (*func) (void *info);
	void *info;
	long wait;
	atomic_t started;
	atomic_t finished;
};

static volatile struct call_data_struct *call_data;

#define IPI_CALL_FUNC		0
#define IPI_CPU_STOP		1
#define IPI_KDUMP_CPU_STOP	3

/* This needs to be cacheline aligned because it is written to by *other* CPUs.  */
static DEFINE_PER_CPU_SHARED_ALIGNED(u64, ipi_operation);

extern void cpu_halt (void);

void
lock_ipi_calllock(void)
{
	spin_lock_irq(&call_lock);
}

void
unlock_ipi_calllock(void)
{
	spin_unlock_irq(&call_lock);
}

static inline void
handle_call_data(void)
{
	struct call_data_struct *data;
	void (*func)(void *info);
	void *info;
	int wait;

	/* release the 'pointer lock' */
	data = (struct call_data_struct *)call_data;
	func = data->func;
	info = data->info;
	wait = data->wait;

	mb();
	atomic_inc(&data->started);
	/* At this point the structure may be gone unless wait is true. */
	(*func)(info);

	/* Notify the sending CPU that the task is done. */
	mb();
	if (wait)
		atomic_inc(&data->finished);
}

static void
stop_this_cpu(void)
{
	/*
	 * Remove this CPU:
	 */
	cpu_clear(smp_processor_id(), cpu_online_map);
	max_xtp();
	local_irq_disable();
	cpu_halt();
}

void
cpu_die(void)
{
	max_xtp();
	local_irq_disable();
	cpu_halt();
	/* Should never be here */
	BUG();
	for (;;);
}

irqreturn_t
handle_IPI (int irq, void *dev_id)
{
	int this_cpu = get_cpu();
	unsigned long *pending_ipis = &__ia64_per_cpu_var(ipi_operation);
	unsigned long ops;

	mb();	/* Order interrupt and bit testing. */
	while ((ops = xchg(pending_ipis, 0)) != 0) {
		mb();	/* Order bit clearing and data access. */
		do {
			unsigned long which;

			which = ffz(~ops);
			ops &= ~(1 << which);

			switch (which) {
			case IPI_CALL_FUNC:
				handle_call_data();
				break;

			case IPI_CPU_STOP:
				stop_this_cpu();
				break;
#ifdef CONFIG_KEXEC
			case IPI_KDUMP_CPU_STOP:
				unw_init_running(kdump_cpu_freeze, NULL);
				break;
#endif
			default:
				printk(KERN_CRIT "Unknown IPI on CPU %d: %lu\n",
						this_cpu, which);
				break;
			}
		} while (ops);
		mb();	/* Order data access and bit testing. */
	}
	put_cpu();
	return IRQ_HANDLED;
}

/*
 * Called with preemption disabled.
 */
static inline void
send_IPI_single (int dest_cpu, int op)
{
	set_bit(op, &per_cpu(ipi_operation, dest_cpu));
	platform_send_ipi(dest_cpu, IA64_IPI_VECTOR, IA64_IPI_DM_INT, 0);
}

/*
 * Called with preemption disabled.
 */
static inline void
send_IPI_allbutself (int op)
{
	unsigned int i;

	for_each_online_cpu(i) {
		if (i != smp_processor_id())
			send_IPI_single(i, op);
	}
}

/*
 * Called with preemption disabled.
 */
static inline void
send_IPI_mask(cpumask_t mask, int op)
{
	unsigned int cpu;

	for_each_cpu_mask(cpu, mask) {
			send_IPI_single(cpu, op);
	}
}

/*
 * Called with preemption disabled.
 */
static inline void
send_IPI_all (int op)
{
	int i;

	for_each_online_cpu(i) {
		send_IPI_single(i, op);
	}
}

/*
 * Called with preemption disabled.
 */
static inline void
send_IPI_self (int op)
{
	send_IPI_single(smp_processor_id(), op);
}

#ifdef CONFIG_KEXEC
void
kdump_smp_send_stop(void)
{
 	send_IPI_allbutself(IPI_KDUMP_CPU_STOP);
}

void
kdump_smp_send_init(void)
{
	unsigned int cpu, self_cpu;
	self_cpu = smp_processor_id();
	for_each_online_cpu(cpu) {
		if (cpu != self_cpu) {
			if(kdump_status[cpu] == 0)
				platform_send_ipi(cpu, 0, IA64_IPI_DM_INIT, 0);
		}
	}
}
#endif
/*
 * Called with preemption disabled.
 */
void
smp_send_reschedule (int cpu)
{
	platform_send_ipi(cpu, IA64_IPI_RESCHEDULE, IA64_IPI_DM_INT, 0);
}

/*
 * Called with preemption disabled.
 */
static void
smp_send_local_flush_tlb (int cpu)
{
	platform_send_ipi(cpu, IA64_IPI_LOCAL_TLB_FLUSH, IA64_IPI_DM_INT, 0);
}

void
smp_local_flush_tlb(void)
{
	/*
	 * Use atomic ops. Otherwise, the load/increment/store sequence from
	 * a "++" operation can have the line stolen between the load & store.
	 * The overhead of the atomic op in negligible in this case & offers
	 * significant benefit for the brief periods where lots of cpus
	 * are simultaneously flushing TLBs.
	 */
	ia64_fetchadd(1, &local_tlb_flush_counts[smp_processor_id()].count, acq);
	local_flush_tlb_all();
}

#define FLUSH_DELAY	5 /* Usec backoff to eliminate excessive cacheline bouncing */

void
smp_flush_tlb_cpumask(cpumask_t xcpumask)
{
	unsigned int *counts = __ia64_per_cpu_var(shadow_flush_counts);
	cpumask_t cpumask = xcpumask;
	int mycpu, cpu, flush_mycpu = 0;

	preempt_disable();
	mycpu = smp_processor_id();

	for_each_cpu_mask(cpu, cpumask)
		counts[cpu] = local_tlb_flush_counts[cpu].count;

	mb();
	for_each_cpu_mask(cpu, cpumask) {
		if (cpu == mycpu)
			flush_mycpu = 1;
		else
			smp_send_local_flush_tlb(cpu);
	}

	if (flush_mycpu)
		smp_local_flush_tlb();

	for_each_cpu_mask(cpu, cpumask)
		while(counts[cpu] == local_tlb_flush_counts[cpu].count)
			udelay(FLUSH_DELAY);

	preempt_enable();
}

void
smp_flush_tlb_all (void)
{
	on_each_cpu((void (*)(void *))local_flush_tlb_all, NULL, 1, 1);
}

void
smp_flush_tlb_mm (struct mm_struct *mm)
{
	preempt_disable();
	/* this happens for the common case of a single-threaded fork():  */
	if (likely(mm == current->active_mm && atomic_read(&mm->mm_users) == 1))
	{
		local_finish_flush_tlb_mm(mm);
		preempt_enable();
		return;
	}

	preempt_enable();
	/*
	 * We could optimize this further by using mm->cpu_vm_mask to track which CPUs
	 * have been running in the address space.  It's not clear that this is worth the
	 * trouble though: to avoid races, we have to raise the IPI on the target CPU
	 * anyhow, and once a CPU is interrupted, the cost of local_flush_tlb_all() is
	 * rather trivial.
	 */
	on_each_cpu((void (*)(void *))local_finish_flush_tlb_mm, mm, 1, 1);
}

/*
 * Run a function on a specific CPU
 *  <func>	The function to run. This must be fast and non-blocking.
 *  <info>	An arbitrary pointer to pass to the function.
 *  <nonatomic>	Currently unused.
 *  <wait>	If true, wait until function has completed on other CPUs.
 *  [RETURNS]   0 on success, else a negative status code.
 *
 * Does not return until the remote CPU is nearly ready to execute <func>
 * or is or has executed.
 */

int
smp_call_function_single (int cpuid, void (*func) (void *info), void *info, int nonatomic,
			  int wait)
{
	struct call_data_struct data;
	int cpus = 1;
	int me = get_cpu(); /* prevent preemption and reschedule on another processor */

	if (cpuid == me) {
		local_irq_disable();
		func(info);
		local_irq_enable();
		put_cpu();
		return 0;
	}

	data.func = func;
	data.info = info;
	atomic_set(&data.started, 0);
	data.wait = wait;
	if (wait)
		atomic_set(&data.finished, 0);

	spin_lock_bh(&call_lock);

	call_data = &data;
	mb();	/* ensure store to call_data precedes setting of IPI_CALL_FUNC */
  	send_IPI_single(cpuid, IPI_CALL_FUNC);

	/* Wait for response */
	while (atomic_read(&data.started) != cpus)
		cpu_relax();

	if (wait)
		while (atomic_read(&data.finished) != cpus)
			cpu_relax();
	call_data = NULL;

	spin_unlock_bh(&call_lock);
	put_cpu();
	return 0;
}
EXPORT_SYMBOL(smp_call_function_single);

/**
 * smp_call_function_mask(): Run a function on a set of other CPUs.
 * <mask>	The set of cpus to run on.  Must not include the current cpu.
 * <func> 	The function to run. This must be fast and non-blocking.
 * <info>	An arbitrary pointer to pass to the function.
 * <wait>	If true, wait (atomically) until function
 *		has completed on other CPUs.
 *
 * Returns 0 on success, else a negative status code.
 *
 * If @wait is true, then returns once @func has returned; otherwise
 * it returns just before the target cpu calls @func.
 *
 * You must not call this function with disabled interrupts or from a
 * hardware interrupt handler or from a bottom half handler.
 */
int smp_call_function_mask(cpumask_t mask,
			   void (*func)(void *), void *info,
			   int wait)
{
	struct call_data_struct data;
	cpumask_t allbutself;
	int cpus;

	spin_lock(&call_lock);
	allbutself = cpu_online_map;
	cpu_clear(smp_processor_id(), allbutself);

	cpus_and(mask, mask, allbutself);
	cpus = cpus_weight(mask);
	if (!cpus) {
		spin_unlock(&call_lock);
		return 0;
	}

	/* Can deadlock when called with interrupts disabled */
	WARN_ON(irqs_disabled());

	data.func = func;
	data.info = info;
	atomic_set(&data.started, 0);
	data.wait = wait;
	if (wait)
		atomic_set(&data.finished, 0);

	call_data = &data;
	mb(); /* ensure store to call_data precedes setting of IPI_CALL_FUNC*/

	/* Send a message to other CPUs */
	if (cpus_equal(mask, allbutself))
		send_IPI_allbutself(IPI_CALL_FUNC);
	else
		send_IPI_mask(mask, IPI_CALL_FUNC);

	/* Wait for response */
	while (atomic_read(&data.started) != cpus)
		cpu_relax();

	if (wait)
		while (atomic_read(&data.finished) != cpus)
			cpu_relax();
	call_data = NULL;

	spin_unlock(&call_lock);
	return 0;

}
EXPORT_SYMBOL(smp_call_function_mask);

/*
 * this function sends a 'generic call function' IPI to all other CPUs
 * in the system.
 */

/*
 *  [SUMMARY]	Run a function on all other CPUs.
 *  <func>	The function to run. This must be fast and non-blocking.
 *  <info>	An arbitrary pointer to pass to the function.
 *  <nonatomic>	currently unused.
 *  <wait>	If true, wait (atomically) until function has completed on other CPUs.
 *  [RETURNS]   0 on success, else a negative status code.
 *
 * Does not return until remote CPUs are nearly ready to execute <func> or are or have
 * executed.
 *
 * You must not call this function with disabled interrupts or from a
 * hardware interrupt handler or from a bottom half handler.
 */
int
smp_call_function (void (*func) (void *info), void *info, int nonatomic, int wait)
{
	struct call_data_struct data;
	int cpus;

	spin_lock(&call_lock);
	cpus = num_online_cpus() - 1;
	if (!cpus) {
		spin_unlock(&call_lock);
		return 0;
	}

	/* Can deadlock when called with interrupts disabled */
	WARN_ON(irqs_disabled());

	data.func = func;
	data.info = info;
	atomic_set(&data.started, 0);
	data.wait = wait;
	if (wait)
		atomic_set(&data.finished, 0);

	call_data = &data;
	mb();	/* ensure store to call_data precedes setting of IPI_CALL_FUNC */
	send_IPI_allbutself(IPI_CALL_FUNC);

	/* Wait for response */
	while (atomic_read(&data.started) != cpus)
		cpu_relax();

	if (wait)
		while (atomic_read(&data.finished) != cpus)
			cpu_relax();
	call_data = NULL;

	spin_unlock(&call_lock);
	return 0;
}
EXPORT_SYMBOL(smp_call_function);

/*
 * this function calls the 'stop' function on all other CPUs in the system.
 */
void
smp_send_stop (void)
{
	send_IPI_allbutself(IPI_CPU_STOP);
}

int
setup_profiling_timer (unsigned int multiplier)
{
	return -EINVAL;
}