summaryrefslogtreecommitdiffstats
path: root/arch/x86/xen/p2m.c
blob: fd12d7ce7ff93265ed620ac9ef96db2c676a6c94 (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
/*
 * Xen leaves the responsibility for maintaining p2m mappings to the
 * guests themselves, but it must also access and update the p2m array
 * during suspend/resume when all the pages are reallocated.
 *
 * The p2m table is logically a flat array, but we implement it as a
 * three-level tree to allow the address space to be sparse.
 *
 *                               Xen
 *                                |
 *     p2m_top              p2m_top_mfn
 *       /  \                   /   \
 * p2m_mid p2m_mid	p2m_mid_mfn p2m_mid_mfn
 *    / \      / \         /           /
 *  p2m p2m p2m p2m p2m p2m p2m ...
 *
 * The p2m_mid_mfn pages are mapped by p2m_top_mfn_p.
 *
 * The p2m_top and p2m_top_mfn levels are limited to 1 page, so the
 * maximum representable pseudo-physical address space is:
 *  P2M_TOP_PER_PAGE * P2M_MID_PER_PAGE * P2M_PER_PAGE pages
 *
 * P2M_PER_PAGE depends on the architecture, as a mfn is always
 * unsigned long (8 bytes on 64-bit, 4 bytes on 32), leading to
 * 512 and 1024 entries respectively. 
 */

#include <linux/init.h>
#include <linux/module.h>
#include <linux/list.h>
#include <linux/hash.h>
#include <linux/sched.h>

#include <asm/cache.h>
#include <asm/setup.h>

#include <asm/xen/page.h>
#include <asm/xen/hypercall.h>
#include <asm/xen/hypervisor.h>

#include "xen-ops.h"

static void __init m2p_override_init(void);

unsigned long xen_max_p2m_pfn __read_mostly;

#define P2M_PER_PAGE		(PAGE_SIZE / sizeof(unsigned long))
#define P2M_MID_PER_PAGE	(PAGE_SIZE / sizeof(unsigned long *))
#define P2M_TOP_PER_PAGE	(PAGE_SIZE / sizeof(unsigned long **))

#define MAX_P2M_PFN		(P2M_TOP_PER_PAGE * P2M_MID_PER_PAGE * P2M_PER_PAGE)

/* Placeholders for holes in the address space */
static RESERVE_BRK_ARRAY(unsigned long, p2m_missing, P2M_PER_PAGE);
static RESERVE_BRK_ARRAY(unsigned long *, p2m_mid_missing, P2M_MID_PER_PAGE);
static RESERVE_BRK_ARRAY(unsigned long, p2m_mid_missing_mfn, P2M_MID_PER_PAGE);

static RESERVE_BRK_ARRAY(unsigned long **, p2m_top, P2M_TOP_PER_PAGE);
static RESERVE_BRK_ARRAY(unsigned long, p2m_top_mfn, P2M_TOP_PER_PAGE);
static RESERVE_BRK_ARRAY(unsigned long *, p2m_top_mfn_p, P2M_TOP_PER_PAGE);

RESERVE_BRK(p2m_mid, PAGE_SIZE * (MAX_DOMAIN_PAGES / (P2M_PER_PAGE * P2M_MID_PER_PAGE)));
RESERVE_BRK(p2m_mid_mfn, PAGE_SIZE * (MAX_DOMAIN_PAGES / (P2M_PER_PAGE * P2M_MID_PER_PAGE)));

static inline unsigned p2m_top_index(unsigned long pfn)
{
	BUG_ON(pfn >= MAX_P2M_PFN);
	return pfn / (P2M_MID_PER_PAGE * P2M_PER_PAGE);
}

static inline unsigned p2m_mid_index(unsigned long pfn)
{
	return (pfn / P2M_PER_PAGE) % P2M_MID_PER_PAGE;
}

static inline unsigned p2m_index(unsigned long pfn)
{
	return pfn % P2M_PER_PAGE;
}

static void p2m_top_init(unsigned long ***top)
{
	unsigned i;

	for (i = 0; i < P2M_TOP_PER_PAGE; i++)
		top[i] = p2m_mid_missing;
}

static void p2m_top_mfn_init(unsigned long *top)
{
	unsigned i;

	for (i = 0; i < P2M_TOP_PER_PAGE; i++)
		top[i] = virt_to_mfn(p2m_mid_missing_mfn);
}

static void p2m_top_mfn_p_init(unsigned long **top)
{
	unsigned i;

	for (i = 0; i < P2M_TOP_PER_PAGE; i++)
		top[i] = p2m_mid_missing_mfn;
}

static void p2m_mid_init(unsigned long **mid)
{
	unsigned i;

	for (i = 0; i < P2M_MID_PER_PAGE; i++)
		mid[i] = p2m_missing;
}

static void p2m_mid_mfn_init(unsigned long *mid)
{
	unsigned i;

	for (i = 0; i < P2M_MID_PER_PAGE; i++)
		mid[i] = virt_to_mfn(p2m_missing);
}

static void p2m_init(unsigned long *p2m)
{
	unsigned i;

	for (i = 0; i < P2M_MID_PER_PAGE; i++)
		p2m[i] = INVALID_P2M_ENTRY;
}

/*
 * Build the parallel p2m_top_mfn and p2m_mid_mfn structures
 *
 * This is called both at boot time, and after resuming from suspend:
 * - At boot time we're called very early, and must use extend_brk()
 *   to allocate memory.
 *
 * - After resume we're called from within stop_machine, but the mfn
 *   tree should alreay be completely allocated.
 */
void xen_build_mfn_list_list(void)
{
	unsigned long pfn;

	/* Pre-initialize p2m_top_mfn to be completely missing */
	if (p2m_top_mfn == NULL) {
		p2m_mid_missing_mfn = extend_brk(PAGE_SIZE, PAGE_SIZE);
		p2m_mid_mfn_init(p2m_mid_missing_mfn);

		p2m_top_mfn_p = extend_brk(PAGE_SIZE, PAGE_SIZE);
		p2m_top_mfn_p_init(p2m_top_mfn_p);

		p2m_top_mfn = extend_brk(PAGE_SIZE, PAGE_SIZE);
		p2m_top_mfn_init(p2m_top_mfn);
	} else {
		/* Reinitialise, mfn's all change after migration */
		p2m_mid_mfn_init(p2m_mid_missing_mfn);
	}

	for (pfn = 0; pfn < xen_max_p2m_pfn; pfn += P2M_PER_PAGE) {
		unsigned topidx = p2m_top_index(pfn);
		unsigned mididx = p2m_mid_index(pfn);
		unsigned long **mid;
		unsigned long *mid_mfn_p;

		mid = p2m_top[topidx];
		mid_mfn_p = p2m_top_mfn_p[topidx];

		/* Don't bother allocating any mfn mid levels if
		 * they're just missing, just update the stored mfn,
		 * since all could have changed over a migrate.
		 */
		if (mid == p2m_mid_missing) {
			BUG_ON(mididx);
			BUG_ON(mid_mfn_p != p2m_mid_missing_mfn);
			p2m_top_mfn[topidx] = virt_to_mfn(p2m_mid_missing_mfn);
			pfn += (P2M_MID_PER_PAGE - 1) * P2M_PER_PAGE;
			continue;
		}

		if (mid_mfn_p == p2m_mid_missing_mfn) {
			/*
			 * XXX boot-time only!  We should never find
			 * missing parts of the mfn tree after
			 * runtime.  extend_brk() will BUG if we call
			 * it too late.
			 */
			mid_mfn_p = extend_brk(PAGE_SIZE, PAGE_SIZE);
			p2m_mid_mfn_init(mid_mfn_p);

			p2m_top_mfn_p[topidx] = mid_mfn_p;
		}

		p2m_top_mfn[topidx] = virt_to_mfn(mid_mfn_p);
		mid_mfn_p[mididx] = virt_to_mfn(mid[mididx]);
	}
}

void xen_setup_mfn_list_list(void)
{
	BUG_ON(HYPERVISOR_shared_info == &xen_dummy_shared_info);

	HYPERVISOR_shared_info->arch.pfn_to_mfn_frame_list_list =
		virt_to_mfn(p2m_top_mfn);
	HYPERVISOR_shared_info->arch.max_pfn = xen_max_p2m_pfn;
}

/* Set up p2m_top to point to the domain-builder provided p2m pages */
void __init xen_build_dynamic_phys_to_machine(void)
{
	unsigned long *mfn_list = (unsigned long *)xen_start_info->mfn_list;
	unsigned long max_pfn = min(MAX_DOMAIN_PAGES, xen_start_info->nr_pages);
	unsigned long pfn;

	xen_max_p2m_pfn = max_pfn;

	p2m_missing = extend_brk(PAGE_SIZE, PAGE_SIZE);
	p2m_init(p2m_missing);

	p2m_mid_missing = extend_brk(PAGE_SIZE, PAGE_SIZE);
	p2m_mid_init(p2m_mid_missing);

	p2m_top = extend_brk(PAGE_SIZE, PAGE_SIZE);
	p2m_top_init(p2m_top);

	/*
	 * The domain builder gives us a pre-constructed p2m array in
	 * mfn_list for all the pages initially given to us, so we just
	 * need to graft that into our tree structure.
	 */
	for (pfn = 0; pfn < max_pfn; pfn += P2M_PER_PAGE) {
		unsigned topidx = p2m_top_index(pfn);
		unsigned mididx = p2m_mid_index(pfn);

		if (p2m_top[topidx] == p2m_mid_missing) {
			unsigned long **mid = extend_brk(PAGE_SIZE, PAGE_SIZE);
			p2m_mid_init(mid);

			p2m_top[topidx] = mid;
		}

		/*
		 * As long as the mfn_list has enough entries to completely
		 * fill a p2m page, pointing into the array is ok. But if
		 * not the entries beyond the last pfn will be undefined.
		 */
		if (unlikely(pfn + P2M_PER_PAGE > max_pfn)) {
			unsigned long p2midx;

			p2midx = max_pfn % P2M_PER_PAGE;
			for ( ; p2midx < P2M_PER_PAGE; p2midx++)
				mfn_list[pfn + p2midx] = INVALID_P2M_ENTRY;
		}
		p2m_top[topidx][mididx] = &mfn_list[pfn];
	}

	m2p_override_init();
}

unsigned long get_phys_to_machine(unsigned long pfn)
{
	unsigned topidx, mididx, idx;

	if (unlikely(pfn >= MAX_P2M_PFN))
		return INVALID_P2M_ENTRY;

	topidx = p2m_top_index(pfn);
	mididx = p2m_mid_index(pfn);
	idx = p2m_index(pfn);

	return p2m_top[topidx][mididx][idx];
}
EXPORT_SYMBOL_GPL(get_phys_to_machine);

static void *alloc_p2m_page(void)
{
	return (void *)__get_free_page(GFP_KERNEL | __GFP_REPEAT);
}

static void free_p2m_page(void *p)
{
	free_page((unsigned long)p);
}

/* 
 * Fully allocate the p2m structure for a given pfn.  We need to check
 * that both the top and mid levels are allocated, and make sure the
 * parallel mfn tree is kept in sync.  We may race with other cpus, so
 * the new pages are installed with cmpxchg; if we lose the race then
 * simply free the page we allocated and use the one that's there.
 */
static bool alloc_p2m(unsigned long pfn)
{
	unsigned topidx, mididx;
	unsigned long ***top_p, **mid;
	unsigned long *top_mfn_p, *mid_mfn;

	topidx = p2m_top_index(pfn);
	mididx = p2m_mid_index(pfn);

	top_p = &p2m_top[topidx];
	mid = *top_p;

	if (mid == p2m_mid_missing) {
		/* Mid level is missing, allocate a new one */
		mid = alloc_p2m_page();
		if (!mid)
			return false;

		p2m_mid_init(mid);

		if (cmpxchg(top_p, p2m_mid_missing, mid) != p2m_mid_missing)
			free_p2m_page(mid);
	}

	top_mfn_p = &p2m_top_mfn[topidx];
	mid_mfn = p2m_top_mfn_p[topidx];

	BUG_ON(virt_to_mfn(mid_mfn) != *top_mfn_p);

	if (mid_mfn == p2m_mid_missing_mfn) {
		/* Separately check the mid mfn level */
		unsigned long missing_mfn;
		unsigned long mid_mfn_mfn;

		mid_mfn = alloc_p2m_page();
		if (!mid_mfn)
			return false;

		p2m_mid_mfn_init(mid_mfn);

		missing_mfn = virt_to_mfn(p2m_mid_missing_mfn);
		mid_mfn_mfn = virt_to_mfn(mid_mfn);
		if (cmpxchg(top_mfn_p, missing_mfn, mid_mfn_mfn) != missing_mfn)
			free_p2m_page(mid_mfn);
		else
			p2m_top_mfn_p[topidx] = mid_mfn;
	}

	if (p2m_top[topidx][mididx] == p2m_missing) {
		/* p2m leaf page is missing */
		unsigned long *p2m;

		p2m = alloc_p2m_page();
		if (!p2m)
			return false;

		p2m_init(p2m);

		if (cmpxchg(&mid[mididx], p2m_missing, p2m) != p2m_missing)
			free_p2m_page(p2m);
		else
			mid_mfn[mididx] = virt_to_mfn(p2m);
	}

	return true;
}

/* Try to install p2m mapping; fail if intermediate bits missing */
bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn)
{
	unsigned topidx, mididx, idx;

	if (unlikely(pfn >= MAX_P2M_PFN)) {
		BUG_ON(mfn != INVALID_P2M_ENTRY);
		return true;
	}

	topidx = p2m_top_index(pfn);
	mididx = p2m_mid_index(pfn);
	idx = p2m_index(pfn);

	if (p2m_top[topidx][mididx] == p2m_missing)
		return mfn == INVALID_P2M_ENTRY;

	p2m_top[topidx][mididx][idx] = mfn;

	return true;
}

bool set_phys_to_machine(unsigned long pfn, unsigned long mfn)
{
	if (unlikely(xen_feature(XENFEAT_auto_translated_physmap))) {
		BUG_ON(pfn != mfn && mfn != INVALID_P2M_ENTRY);
		return true;
	}

	if (unlikely(!__set_phys_to_machine(pfn, mfn)))  {
		if (!alloc_p2m(pfn))
			return false;

		if (!__set_phys_to_machine(pfn, mfn))
			return false;
	}

	return true;
}

#define M2P_OVERRIDE_HASH_SHIFT	10
#define M2P_OVERRIDE_HASH	(1 << M2P_OVERRIDE_HASH_SHIFT)

static RESERVE_BRK_ARRAY(struct list_head, m2p_overrides, M2P_OVERRIDE_HASH);
static DEFINE_SPINLOCK(m2p_override_lock);

static void __init m2p_override_init(void)
{
	unsigned i;

	m2p_overrides = extend_brk(sizeof(*m2p_overrides) * M2P_OVERRIDE_HASH,
				   sizeof(unsigned long));

	for (i = 0; i < M2P_OVERRIDE_HASH; i++)
		INIT_LIST_HEAD(&m2p_overrides[i]);
}

static unsigned long mfn_hash(unsigned long mfn)
{
	return hash_long(mfn, M2P_OVERRIDE_HASH_SHIFT);
}

/* Add an MFN override for a particular page */
int m2p_add_override(unsigned long mfn, struct page *page)
{
	unsigned long flags;
	unsigned long pfn;
	unsigned long address;
	unsigned level;
	pte_t *ptep = NULL;

	pfn = page_to_pfn(page);
	if (!PageHighMem(page)) {
		address = (unsigned long)__va(pfn << PAGE_SHIFT);
		ptep = lookup_address(address, &level);

		if (WARN(ptep == NULL || level != PG_LEVEL_4K,
					"m2p_add_override: pfn %lx not mapped", pfn))
			return -EINVAL;
	}

	page->private = mfn;
	page->index = pfn_to_mfn(pfn);

	__set_phys_to_machine(pfn, FOREIGN_FRAME(mfn));
	if (!PageHighMem(page))
		/* Just zap old mapping for now */
		pte_clear(&init_mm, address, ptep);

	spin_lock_irqsave(&m2p_override_lock, flags);
	list_add(&page->lru,  &m2p_overrides[mfn_hash(mfn)]);
	spin_unlock_irqrestore(&m2p_override_lock, flags);

	return 0;
}

int m2p_remove_override(struct page *page)
{
	unsigned long flags;
	unsigned long mfn;
	unsigned long pfn;
	unsigned long address;
	unsigned level;
	pte_t *ptep = NULL;

	pfn = page_to_pfn(page);
	mfn = get_phys_to_machine(pfn);
	if (mfn == INVALID_P2M_ENTRY || !(mfn & FOREIGN_FRAME_BIT))
		return -EINVAL;

	if (!PageHighMem(page)) {
		address = (unsigned long)__va(pfn << PAGE_SHIFT);
		ptep = lookup_address(address, &level);

		if (WARN(ptep == NULL || level != PG_LEVEL_4K,
					"m2p_remove_override: pfn %lx not mapped", pfn))
			return -EINVAL;
	}

	spin_lock_irqsave(&m2p_override_lock, flags);
	list_del(&page->lru);
	spin_unlock_irqrestore(&m2p_override_lock, flags);
	__set_phys_to_machine(pfn, page->index);

	if (!PageHighMem(page))
		set_pte_at(&init_mm, address, ptep,
				pfn_pte(pfn, PAGE_KERNEL));
		/* No tlb flush necessary because the caller already
		 * left the pte unmapped. */

	return 0;
}

struct page *m2p_find_override(unsigned long mfn)
{
	unsigned long flags;
	struct list_head *bucket = &m2p_overrides[mfn_hash(mfn)];
	struct page *p, *ret;

	ret = NULL;

	spin_lock_irqsave(&m2p_override_lock, flags);

	list_for_each_entry(p, bucket, lru) {
		if (p->private == mfn) {
			ret = p;
			break;
		}
	}

	spin_unlock_irqrestore(&m2p_override_lock, flags);

	return ret;
}

unsigned long m2p_find_override_pfn(unsigned long mfn, unsigned long pfn)
{
	struct page *p = m2p_find_override(mfn);
	unsigned long ret = pfn;

	if (p)
		ret = page_to_pfn(p);

	return ret;
}
EXPORT_SYMBOL_GPL(m2p_find_override_pfn);