summaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel/smp_64.c
blob: 03fa6ed559c637f5bf3b240184db97c16642aa65 (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
/*
 *	Intel SMP support routines.
 *
 *	(c) 1995 Alan Cox, Building #3 <alan@redhat.com>
 *	(c) 1998-99, 2000 Ingo Molnar <mingo@redhat.com>
 *      (c) 2002,2003 Andi Kleen, SuSE Labs.
 *
 *	This code is released under the GNU General Public License version 2 or
 *	later.
 */

#include <linux/init.h>

#include <linux/mm.h>
#include <linux/delay.h>
#include <linux/spinlock.h>
#include <linux/smp.h>
#include <linux/kernel_stat.h>
#include <linux/mc146818rtc.h>
#include <linux/interrupt.h>

#include <asm/mtrr.h>
#include <asm/pgalloc.h>
#include <asm/tlbflush.h>
#include <asm/mach_apic.h>
#include <asm/mmu_context.h>
#include <asm/proto.h>
#include <asm/apicdef.h>
#include <asm/idle.h>

/*
 *	Smarter SMP flushing macros. 
 *		c/o Linus Torvalds.
 *
 *	These mean you can really definitely utterly forget about
 *	writing to user space from interrupts. (Its not allowed anyway).
 *
 *	Optimizations Manfred Spraul <manfred@colorfullife.com>
 *
 * 	More scalable flush, from Andi Kleen
 *
 * 	To avoid global state use 8 different call vectors.
 * 	Each CPU uses a specific vector to trigger flushes on other
 * 	CPUs. Depending on the received vector the target CPUs look into
 *	the right per cpu variable for the flush data.
 *
 * 	With more than 8 CPUs they are hashed to the 8 available
 * 	vectors. The limited global vector space forces us to this right now.
 *	In future when interrupts are split into per CPU domains this could be
 *	fixed, at the cost of triggering multiple IPIs in some cases.
 */

union smp_flush_state {
	struct {
		cpumask_t flush_cpumask;
		struct mm_struct *flush_mm;
		unsigned long flush_va;
#define FLUSH_ALL	-1ULL
		spinlock_t tlbstate_lock;
	};
	char pad[SMP_CACHE_BYTES];
} ____cacheline_aligned;

/* State is put into the per CPU data section, but padded
   to a full cache line because other CPUs can access it and we don't
   want false sharing in the per cpu data segment. */
static DEFINE_PER_CPU(union smp_flush_state, flush_state);

/*
 * We cannot call mmdrop() because we are in interrupt context, 
 * instead update mm->cpu_vm_mask.
 */
static inline void leave_mm(int cpu)
{
	if (read_pda(mmu_state) == TLBSTATE_OK)
		BUG();
	cpu_clear(cpu, read_pda(active_mm)->cpu_vm_mask);
	load_cr3(swapper_pg_dir);
}

/*
 *
 * The flush IPI assumes that a thread switch happens in this order:
 * [cpu0: the cpu that switches]
 * 1) switch_mm() either 1a) or 1b)
 * 1a) thread switch to a different mm
 * 1a1) cpu_clear(cpu, old_mm->cpu_vm_mask);
 * 	Stop ipi delivery for the old mm. This is not synchronized with
 * 	the other cpus, but smp_invalidate_interrupt ignore flush ipis
 * 	for the wrong mm, and in the worst case we perform a superfluous
 * 	tlb flush.
 * 1a2) set cpu mmu_state to TLBSTATE_OK
 * 	Now the smp_invalidate_interrupt won't call leave_mm if cpu0
 *	was in lazy tlb mode.
 * 1a3) update cpu active_mm
 * 	Now cpu0 accepts tlb flushes for the new mm.
 * 1a4) cpu_set(cpu, new_mm->cpu_vm_mask);
 * 	Now the other cpus will send tlb flush ipis.
 * 1a4) change cr3.
 * 1b) thread switch without mm change
 *	cpu active_mm is correct, cpu0 already handles
 *	flush ipis.
 * 1b1) set cpu mmu_state to TLBSTATE_OK
 * 1b2) test_and_set the cpu bit in cpu_vm_mask.
 * 	Atomically set the bit [other cpus will start sending flush ipis],
 * 	and test the bit.
 * 1b3) if the bit was 0: leave_mm was called, flush the tlb.
 * 2) switch %%esp, ie current
 *
 * The interrupt must handle 2 special cases:
 * - cr3 is changed before %%esp, ie. it cannot use current->{active_,}mm.
 * - the cpu performs speculative tlb reads, i.e. even if the cpu only
 *   runs in kernel space, the cpu could load tlb entries for user space
 *   pages.
 *
 * The good news is that cpu mmu_state is local to each cpu, no
 * write/read ordering problems.
 */

/*
 * TLB flush IPI:
 *
 * 1) Flush the tlb entries if the cpu uses the mm that's being flushed.
 * 2) Leave the mm if we are in the lazy tlb mode.
 *
 * Interrupts are disabled.
 */

asmlinkage void smp_invalidate_interrupt(struct pt_regs *regs)
{
	int cpu;
	int sender;
	union smp_flush_state *f;

	cpu = smp_processor_id();
	/*
	 * orig_rax contains the negated interrupt vector.
	 * Use that to determine where the sender put the data.
	 */
	sender = ~regs->orig_rax - INVALIDATE_TLB_VECTOR_START;
	f = &per_cpu(flush_state, sender);

	if (!cpu_isset(cpu, f->flush_cpumask))
		goto out;
		/* 
		 * This was a BUG() but until someone can quote me the
		 * line from the intel manual that guarantees an IPI to
		 * multiple CPUs is retried _only_ on the erroring CPUs
		 * its staying as a return
		 *
		 * BUG();
		 */
		 
	if (f->flush_mm == read_pda(active_mm)) {
		if (read_pda(mmu_state) == TLBSTATE_OK) {
			if (f->flush_va == FLUSH_ALL)
				local_flush_tlb();
			else
				__flush_tlb_one(f->flush_va);
		} else
			leave_mm(cpu);
	}
out:
	ack_APIC_irq();
	cpu_clear(cpu, f->flush_cpumask);
	add_pda(irq_tlb_count, 1);
}

static void flush_tlb_others(cpumask_t cpumask, struct mm_struct *mm,
						unsigned long va)
{
	int sender;
	union smp_flush_state *f;

	/* Caller has disabled preemption */
	sender = smp_processor_id() % NUM_INVALIDATE_TLB_VECTORS;
	f = &per_cpu(flush_state, sender);

	/* Could avoid this lock when
	   num_online_cpus() <= NUM_INVALIDATE_TLB_VECTORS, but it is
	   probably not worth checking this for a cache-hot lock. */
	spin_lock(&f->tlbstate_lock);

	f->flush_mm = mm;
	f->flush_va = va;
	cpus_or(f->flush_cpumask, cpumask, f->flush_cpumask);

	/*
	 * We have to send the IPI only to
	 * CPUs affected.
	 */
	send_IPI_mask(cpumask, INVALIDATE_TLB_VECTOR_START + sender);

	while (!cpus_empty(f->flush_cpumask))
		cpu_relax();

	f->flush_mm = NULL;
	f->flush_va = 0;
	spin_unlock(&f->tlbstate_lock);
}

int __cpuinit init_smp_flush(void)
{
	int i;
	for_each_cpu_mask(i, cpu_possible_map) {
		spin_lock_init(&per_cpu(flush_state, i).tlbstate_lock);
	}
	return 0;
}

core_initcall(init_smp_flush);
	
void flush_tlb_current_task(void)
{
	struct mm_struct *mm = current->mm;
	cpumask_t cpu_mask;

	preempt_disable();
	cpu_mask = mm->cpu_vm_mask;
	cpu_clear(smp_processor_id(), cpu_mask);

	local_flush_tlb();
	if (!cpus_empty(cpu_mask))
		flush_tlb_others(cpu_mask, mm, FLUSH_ALL);
	preempt_enable();
}
EXPORT_SYMBOL(flush_tlb_current_task);

void flush_tlb_mm (struct mm_struct * mm)
{
	cpumask_t cpu_mask;

	preempt_disable();
	cpu_mask = mm->cpu_vm_mask;
	cpu_clear(smp_processor_id(), cpu_mask);

	if (current->active_mm == mm) {
		if (current->mm)
			local_flush_tlb();
		else
			leave_mm(smp_processor_id());
	}
	if (!cpus_empty(cpu_mask))
		flush_tlb_others(cpu_mask, mm, FLUSH_ALL);

	preempt_enable();
}
EXPORT_SYMBOL(flush_tlb_mm);

void flush_tlb_page(struct vm_area_struct * vma, unsigned long va)
{
	struct mm_struct *mm = vma->vm_mm;
	cpumask_t cpu_mask;

	preempt_disable();
	cpu_mask = mm->cpu_vm_mask;
	cpu_clear(smp_processor_id(), cpu_mask);

	if (current->active_mm == mm) {
		if(current->mm)
			__flush_tlb_one(va);
		 else
		 	leave_mm(smp_processor_id());
	}

	if (!cpus_empty(cpu_mask))
		flush_tlb_others(cpu_mask, mm, va);

	preempt_enable();
}
EXPORT_SYMBOL(flush_tlb_page);

static void do_flush_tlb_all(void* info)
{
	unsigned long cpu = smp_processor_id();

	__flush_tlb_all();
	if (read_pda(mmu_state) == TLBSTATE_LAZY)
		leave_mm(cpu);
}

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

/*
 * 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 smp_send_reschedule(int cpu)
{
	send_IPI_mask(cpumask_of_cpu(cpu), RESCHEDULE_VECTOR);
}

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

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

static struct call_data_struct * call_data;

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

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

/*
 * this function sends a 'generic call function' IPI to all other CPU
 * of the system defined in the mask.
 */

static 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;

	allbutself = cpu_online_map;
	cpu_clear(smp_processor_id(), allbutself);

	cpus_and(mask, mask, allbutself);
	cpus = cpus_weight(mask);

	if (!cpus)
		return 0;

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

	call_data = &data;
	wmb();

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

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

	if (!wait)
		return 0;

	while (atomic_read(&data.finished) != cpus)
		cpu_relax();

	return 0;
}
/**
 * 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)
{
	int ret;

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

	spin_lock(&call_lock);
	ret = __smp_call_function_mask(mask, func, info, wait);
	spin_unlock(&call_lock);
	return ret;
}
EXPORT_SYMBOL(smp_call_function_mask);

/*
 * smp_call_function_single - 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.
 *
 * Retrurns 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 cpu, void (*func) (void *info), void *info,
	int nonatomic, int wait)
{
	/* prevent preemption and reschedule on another processor */
	int ret;
	int me = get_cpu();

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

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

	ret = smp_call_function_mask(cpumask_of_cpu(cpu), func, info, wait);

	put_cpu();
	return ret;
}
EXPORT_SYMBOL(smp_call_function_single);

/*
 * smp_call_function - 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.
 * Actually there are a few legal cases, like panic.
 */
int smp_call_function (void (*func) (void *info), void *info, int nonatomic,
			int wait)
{
	return smp_call_function_mask(cpu_online_map, func, info, wait);
}
EXPORT_SYMBOL(smp_call_function);

static void stop_this_cpu(void *dummy)
{
	local_irq_disable();
	/*
	 * Remove this CPU:
	 */
	cpu_clear(smp_processor_id(), cpu_online_map);
	disable_local_APIC();
	for (;;) 
		halt();
} 

void smp_send_stop(void)
{
	int nolock;
	unsigned long flags;

	if (reboot_force)
		return;

	/* Don't deadlock on the call lock in panic */
	nolock = !spin_trylock(&call_lock);
	local_irq_save(flags);
	__smp_call_function_mask(cpu_online_map, stop_this_cpu, NULL, 0);
	if (!nolock)
		spin_unlock(&call_lock);
	disable_local_APIC();
	local_irq_restore(flags);
}

/*
 * Reschedule call back. Nothing to do,
 * all the work is done automatically when
 * we return from the interrupt.
 */
asmlinkage void smp_reschedule_interrupt(void)
{
	ack_APIC_irq();
	add_pda(irq_resched_count, 1);
}

asmlinkage void smp_call_function_interrupt(void)
{
	void (*func) (void *info) = call_data->func;
	void *info = call_data->info;
	int wait = call_data->wait;

	ack_APIC_irq();
	/*
	 * Notify initiating CPU that I've grabbed the data and am
	 * about to execute the function
	 */
	mb();
	atomic_inc(&call_data->started);
	/*
	 * At this point the info structure may be out of scope unless wait==1
	 */
	exit_idle();
	irq_enter();
	(*func)(info);
	add_pda(irq_call_count, 1);
	irq_exit();
	if (wait) {
		mb();
		atomic_inc(&call_data->finished);
	}
}