summaryrefslogtreecommitdiff
path: root/arch/x86/mm/tlb.c
blob: 4dbe65622810208182bfe363efdd477a84abb040 (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
#include <linux/init.h>

#include <linux/mm.h>
#include <linux/spinlock.h>
#include <linux/smp.h>
#include <linux/interrupt.h>
#include <linux/export.h>
#include <linux/cpu.h>

#include <asm/tlbflush.h>
#include <asm/mmu_context.h>
#include <asm/cache.h>
#include <asm/apic.h>
#include <asm/uv/uv.h>
#include <linux/debugfs.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
 *
 *	Implement flush IPI by CALL_FUNCTION_VECTOR, Alex Shi
 */

#ifdef CONFIG_SMP

struct flush_tlb_info {
	struct mm_struct *flush_mm;
	unsigned long flush_start;
	unsigned long flush_end;
};

/*
 * We cannot call mmdrop() because we are in interrupt context,
 * instead update mm->cpu_vm_mask.
 */
void leave_mm(int cpu)
{
	struct mm_struct *active_mm = this_cpu_read(cpu_tlbstate.active_mm);
	if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK)
		BUG();
	if (cpumask_test_cpu(cpu, mm_cpumask(active_mm))) {
		cpumask_clear_cpu(cpu, mm_cpumask(active_mm));
		load_cr3(swapper_pg_dir);
		/*
		 * This gets called in the idle path where RCU
		 * functions differently.  Tracing normally
		 * uses RCU, so we have to call the tracepoint
		 * specially here.
		 */
		trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
	}
}
EXPORT_SYMBOL_GPL(leave_mm);

#endif /* CONFIG_SMP */

void switch_mm(struct mm_struct *prev, struct mm_struct *next,
	       struct task_struct *tsk)
{
	unsigned long flags;

	local_irq_save(flags);
	switch_mm_irqs_off(prev, next, tsk);
	local_irq_restore(flags);
}

void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
			struct task_struct *tsk)
{
	unsigned cpu = smp_processor_id();

	if (likely(prev != next)) {
#ifdef CONFIG_SMP
		this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK);
		this_cpu_write(cpu_tlbstate.active_mm, next);
#endif
		cpumask_set_cpu(cpu, mm_cpumask(next));

		/*
		 * Re-load page tables.
		 *
		 * This logic has an ordering constraint:
		 *
		 *  CPU 0: Write to a PTE for 'next'
		 *  CPU 0: load bit 1 in mm_cpumask.  if nonzero, send IPI.
		 *  CPU 1: set bit 1 in next's mm_cpumask
		 *  CPU 1: load from the PTE that CPU 0 writes (implicit)
		 *
		 * We need to prevent an outcome in which CPU 1 observes
		 * the new PTE value and CPU 0 observes bit 1 clear in
		 * mm_cpumask.  (If that occurs, then the IPI will never
		 * be sent, and CPU 0's TLB will contain a stale entry.)
		 *
		 * The bad outcome can occur if either CPU's load is
		 * reordered before that CPU's store, so both CPUs must
		 * execute full barriers to prevent this from happening.
		 *
		 * Thus, switch_mm needs a full barrier between the
		 * store to mm_cpumask and any operation that could load
		 * from next->pgd.  TLB fills are special and can happen
		 * due to instruction fetches or for no reason at all,
		 * and neither LOCK nor MFENCE orders them.
		 * Fortunately, load_cr3() is serializing and gives the
		 * ordering guarantee we need.
		 *
		 */
		load_cr3(next->pgd);

		trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);

		/* Stop flush ipis for the previous mm */
		cpumask_clear_cpu(cpu, mm_cpumask(prev));

		/* Load per-mm CR4 state */
		load_mm_cr4(next);

#ifdef CONFIG_MODIFY_LDT_SYSCALL
		/*
		 * Load the LDT, if the LDT is different.
		 *
		 * It's possible that prev->context.ldt doesn't match
		 * the LDT register.  This can happen if leave_mm(prev)
		 * was called and then modify_ldt changed
		 * prev->context.ldt but suppressed an IPI to this CPU.
		 * In this case, prev->context.ldt != NULL, because we
		 * never set context.ldt to NULL while the mm still
		 * exists.  That means that next->context.ldt !=
		 * prev->context.ldt, because mms never share an LDT.
		 */
		if (unlikely(prev->context.ldt != next->context.ldt))
			load_mm_ldt(next);
#endif
	}
#ifdef CONFIG_SMP
	  else {
		this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK);
		BUG_ON(this_cpu_read(cpu_tlbstate.active_mm) != next);

		if (!cpumask_test_cpu(cpu, mm_cpumask(next))) {
			/*
			 * On established mms, the mm_cpumask is only changed
			 * from irq context, from ptep_clear_flush() while in
			 * lazy tlb mode, and here. Irqs are blocked during
			 * schedule, protecting us from simultaneous changes.
			 */
			cpumask_set_cpu(cpu, mm_cpumask(next));

			/*
			 * We were in lazy tlb mode and leave_mm disabled
			 * tlb flush IPI delivery. We must reload CR3
			 * to make sure to use no freed page tables.
			 *
			 * As above, load_cr3() is serializing and orders TLB
			 * fills with respect to the mm_cpumask write.
			 */
			load_cr3(next->pgd);
			trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
			load_mm_cr4(next);
			load_mm_ldt(next);
		}
	}
#endif
}

#ifdef CONFIG_SMP

/*
 * 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) set cpu_tlbstate to TLBSTATE_OK
 *	Now the tlb flush NMI handler flush_tlb_func won't call leave_mm
 *	if cpu0 was in lazy tlb mode.
 * 1a2) update cpu active_mm
 *	Now cpu0 accepts tlb flushes for the new mm.
 * 1a3) cpu_set(cpu, new_mm->cpu_vm_mask);
 *	Now the other cpus will send tlb flush ipis.
 * 1a4) change cr3.
 * 1a5) cpu_clear(cpu, old_mm->cpu_vm_mask);
 *	Stop ipi delivery for the old mm. This is not synchronized with
 *	the other cpus, but flush_tlb_func ignore flush ipis for the wrong
 *	mm, and in the worst case we perform a superfluous tlb flush.
 * 1b) thread switch without mm change
 *	cpu active_mm is correct, cpu0 already handles flush ipis.
 * 1b1) set cpu_tlbstate 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_tlbstate is local to each cpu, no
 * write/read ordering problems.
 */

/*
 * TLB flush funcation:
 * 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.
 */
static void flush_tlb_func(void *info)
{
	struct flush_tlb_info *f = info;

	inc_irq_stat(irq_tlb_count);

	if (f->flush_mm && f->flush_mm != this_cpu_read(cpu_tlbstate.active_mm))
		return;

	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
	if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK) {
		if (f->flush_end == TLB_FLUSH_ALL) {
			local_flush_tlb();
			trace_tlb_flush(TLB_REMOTE_SHOOTDOWN, TLB_FLUSH_ALL);
		} else {
			unsigned long addr;
			unsigned long nr_pages =
				(f->flush_end - f->flush_start) / PAGE_SIZE;
			addr = f->flush_start;
			while (addr < f->flush_end) {
				__flush_tlb_single(addr);
				addr += PAGE_SIZE;
			}
			trace_tlb_flush(TLB_REMOTE_SHOOTDOWN, nr_pages);
		}
	} else
		leave_mm(smp_processor_id());

}

void native_flush_tlb_others(const struct cpumask *cpumask,
				 struct mm_struct *mm, unsigned long start,
				 unsigned long end)
{
	struct flush_tlb_info info;

	if (end == 0)
		end = start + PAGE_SIZE;
	info.flush_mm = mm;
	info.flush_start = start;
	info.flush_end = end;

	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH);
	if (end == TLB_FLUSH_ALL)
		trace_tlb_flush(TLB_REMOTE_SEND_IPI, TLB_FLUSH_ALL);
	else
		trace_tlb_flush(TLB_REMOTE_SEND_IPI,
				(end - start) >> PAGE_SHIFT);

	if (is_uv_system()) {
		unsigned int cpu;

		cpu = smp_processor_id();
		cpumask = uv_flush_tlb_others(cpumask, mm, start, end, cpu);
		if (cpumask)
			smp_call_function_many(cpumask, flush_tlb_func,
								&info, 1);
		return;
	}
	smp_call_function_many(cpumask, flush_tlb_func, &info, 1);
}

void flush_tlb_current_task(void)
{
	struct mm_struct *mm = current->mm;

	preempt_disable();

	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);

	/* This is an implicit full barrier that synchronizes with switch_mm. */
	local_flush_tlb();

	trace_tlb_flush(TLB_LOCAL_SHOOTDOWN, TLB_FLUSH_ALL);
	if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids)
		flush_tlb_others(mm_cpumask(mm), mm, 0UL, TLB_FLUSH_ALL);
	preempt_enable();
}

/*
 * See Documentation/x86/tlb.txt for details.  We choose 33
 * because it is large enough to cover the vast majority (at
 * least 95%) of allocations, and is small enough that we are
 * confident it will not cause too much overhead.  Each single
 * flush is about 100 ns, so this caps the maximum overhead at
 * _about_ 3,000 ns.
 *
 * This is in units of pages.
 */
static unsigned long tlb_single_page_flush_ceiling __read_mostly = 33;

void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
				unsigned long end, unsigned long vmflag)
{
	unsigned long addr;
	/* do a global flush by default */
	unsigned long base_pages_to_flush = TLB_FLUSH_ALL;

	preempt_disable();
	if (current->active_mm != mm) {
		/* Synchronize with switch_mm. */
		smp_mb();

		goto out;
	}

	if (!current->mm) {
		leave_mm(smp_processor_id());

		/* Synchronize with switch_mm. */
		smp_mb();

		goto out;
	}

	if ((end != TLB_FLUSH_ALL) && !(vmflag & VM_HUGETLB))
		base_pages_to_flush = (end - start) >> PAGE_SHIFT;

	/*
	 * Both branches below are implicit full barriers (MOV to CR or
	 * INVLPG) that synchronize with switch_mm.
	 */
	if (base_pages_to_flush > tlb_single_page_flush_ceiling) {
		base_pages_to_flush = TLB_FLUSH_ALL;
		count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
		local_flush_tlb();
	} else {
		/* flush range by one by one 'invlpg' */
		for (addr = start; addr < end;	addr += PAGE_SIZE) {
			count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE);
			__flush_tlb_single(addr);
		}
	}
	trace_tlb_flush(TLB_LOCAL_MM_SHOOTDOWN, base_pages_to_flush);
out:
	if (base_pages_to_flush == TLB_FLUSH_ALL) {
		start = 0UL;
		end = TLB_FLUSH_ALL;
	}
	if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids)
		flush_tlb_others(mm_cpumask(mm), mm, start, end);
	preempt_enable();
}

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

	preempt_disable();

	if (current->active_mm == mm) {
		if (current->mm) {
			/*
			 * Implicit full barrier (INVLPG) that synchronizes
			 * with switch_mm.
			 */
			__flush_tlb_one(start);
		} else {
			leave_mm(smp_processor_id());

			/* Synchronize with switch_mm. */
			smp_mb();
		}
	}

	if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids)
		flush_tlb_others(mm_cpumask(mm), mm, start, 0UL);

	preempt_enable();
}

static void do_flush_tlb_all(void *info)
{
	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
	__flush_tlb_all();
	if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_LAZY)
		leave_mm(smp_processor_id());
}

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

static void do_kernel_range_flush(void *info)
{
	struct flush_tlb_info *f = info;
	unsigned long addr;

	/* flush range by one by one 'invlpg' */
	for (addr = f->flush_start; addr < f->flush_end; addr += PAGE_SIZE)
		__flush_tlb_single(addr);
}

void flush_tlb_kernel_range(unsigned long start, unsigned long end)
{

	/* Balance as user space task's flush, a bit conservative */
	if (end == TLB_FLUSH_ALL ||
	    (end - start) > tlb_single_page_flush_ceiling * PAGE_SIZE) {
		on_each_cpu(do_flush_tlb_all, NULL, 1);
	} else {
		struct flush_tlb_info info;
		info.flush_start = start;
		info.flush_end = end;
		on_each_cpu(do_kernel_range_flush, &info, 1);
	}
}

static ssize_t tlbflush_read_file(struct file *file, char __user *user_buf,
			     size_t count, loff_t *ppos)
{
	char buf[32];
	unsigned int len;

	len = sprintf(buf, "%ld\n", tlb_single_page_flush_ceiling);
	return simple_read_from_buffer(user_buf, count, ppos, buf, len);
}

static ssize_t tlbflush_write_file(struct file *file,
		 const char __user *user_buf, size_t count, loff_t *ppos)
{
	char buf[32];
	ssize_t len;
	int ceiling;

	len = min(count, sizeof(buf) - 1);
	if (copy_from_user(buf, user_buf, len))
		return -EFAULT;

	buf[len] = '\0';
	if (kstrtoint(buf, 0, &ceiling))
		return -EINVAL;

	if (ceiling < 0)
		return -EINVAL;

	tlb_single_page_flush_ceiling = ceiling;
	return count;
}

static const struct file_operations fops_tlbflush = {
	.read = tlbflush_read_file,
	.write = tlbflush_write_file,
	.llseek = default_llseek,
};

static int __init create_tlb_single_page_flush_ceiling(void)
{
	debugfs_create_file("tlb_single_page_flush_ceiling", S_IRUSR | S_IWUSR,
			    arch_debugfs_dir, NULL, &fops_tlbflush);
	return 0;
}
late_initcall(create_tlb_single_page_flush_ceiling);

#endif /* CONFIG_SMP */