aboutsummaryrefslogtreecommitdiffstats
path: root/extras/mini-os/arch/x86/mm.c
blob: 8bc90eddea6d1463b1b92868c3e8ab9eabca0285 (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
/* 
 ****************************************************************************
 * (C) 2003 - Rolf Neugebauer - Intel Research Cambridge
 * (C) 2005 - Grzegorz Milos - Intel Research Cambridge
 ****************************************************************************
 *
 *        File: mm.c
 *      Author: Rolf Neugebauer (neugebar@dcs.gla.ac.uk)
 *     Changes: Grzegorz Milos
 *              
 *        Date: Aug 2003, chages Aug 2005
 * 
 * Environment: Xen Minimal OS
 * Description: memory management related functions
 *              contains buddy page allocator from Xen.
 *
 ****************************************************************************
 * Permission is hereby granted, free of charge, to any person obtaining a copy
 * of this software and associated documentation files (the "Software"), to
 * deal in the Software without restriction, including without limitation the
 * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
 * sell copies of the Software, and to permit persons to whom the Software is
 * furnished to do so, subject to the following conditions:
 * 
 * The above copyright notice and this permission notice shall be included in
 * all copies or substantial portions of the Software.
 * 
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE 
 * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
 * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
 * DEALINGS IN THE SOFTWARE.
 */

#include <os.h>
#include <hypervisor.h>
#include <mm.h>
#include <types.h>
#include <lib.h>
#include <xmalloc.h>
#include <xen/memory.h>

#ifdef MM_DEBUG
#define DEBUG(_f, _a...) \
    printk("MINI_OS(file=mm.c, line=%d) " _f "\n", __LINE__, ## _a)
#else
#define DEBUG(_f, _a...)    ((void)0)
#endif

unsigned long *phys_to_machine_mapping;
unsigned long mfn_zero;
extern char stack[];
extern void page_walk(unsigned long virt_addr);

void new_pt_frame(unsigned long *pt_pfn, unsigned long prev_l_mfn, 
                                unsigned long offset, unsigned long level)
{   
    pgentry_t *tab = (pgentry_t *)start_info.pt_base;
    unsigned long pt_page = (unsigned long)pfn_to_virt(*pt_pfn); 
    unsigned long prot_e, prot_t, pincmd;
    mmu_update_t mmu_updates[1];
    struct mmuext_op pin_request;
    
    prot_e = prot_t = pincmd = 0;
    DEBUG("Allocating new L%d pt frame for pt_pfn=%lx, "
           "prev_l_mfn=%lx, offset=%lx", 
           level, *pt_pfn, prev_l_mfn, offset);

    /* We need to clear the page, otherwise we might fail to map it
       as a page table page */
    memset((unsigned long*)pfn_to_virt(*pt_pfn), 0, PAGE_SIZE);  
 
    switch ( level )
    {
    case L1_FRAME:
         prot_e = L1_PROT;
         prot_t = L2_PROT;
         pincmd = MMUEXT_PIN_L1_TABLE;
         break;
#if defined(__x86_64__) || defined(CONFIG_X86_PAE)
    case L2_FRAME:
         prot_e = L2_PROT;
         prot_t = L3_PROT;
         pincmd = MMUEXT_PIN_L2_TABLE;
         break;
#endif
#if defined(__x86_64__)
    case L3_FRAME:
         prot_e = L3_PROT;
         prot_t = L4_PROT;
         pincmd = MMUEXT_PIN_L3_TABLE;
         break;
#endif
    default:
         printk("new_pt_frame() called with invalid level number %d\n", level);
         do_exit();
         break;
    }

    /* Update the entry */
#if defined(__x86_64__)
    tab = pte_to_virt(tab[l4_table_offset(pt_page)]);
    tab = pte_to_virt(tab[l3_table_offset(pt_page)]);
#endif
#if defined(CONFIG_X86_PAE)
    tab = pte_to_virt(tab[l3_table_offset(pt_page)]);
#endif

    mmu_updates[0].ptr = ((pgentry_t)tab[l2_table_offset(pt_page)] & PAGE_MASK) + 
                         sizeof(pgentry_t) * l1_table_offset(pt_page);
    mmu_updates[0].val = (pgentry_t)pfn_to_mfn(*pt_pfn) << PAGE_SHIFT | 
                         (prot_e & ~_PAGE_RW);
    if(HYPERVISOR_mmu_update(mmu_updates, 1, NULL, DOMID_SELF) < 0)
    {
         printk("PTE for new page table page could not be updated\n");
         do_exit();
    }
                        
    /* Pin the page to provide correct protection */
    pin_request.cmd = pincmd;
    pin_request.arg1.mfn = pfn_to_mfn(*pt_pfn);
    if(HYPERVISOR_mmuext_op(&pin_request, 1, NULL, DOMID_SELF) < 0)
    {
        printk("ERROR: pinning failed\n");
        do_exit();
    }

    /* Now fill the new page table page with entries.
       Update the page directory as well. */
    mmu_updates[0].ptr = ((pgentry_t)prev_l_mfn << PAGE_SHIFT) + sizeof(pgentry_t) * offset;
    mmu_updates[0].val = (pgentry_t)pfn_to_mfn(*pt_pfn) << PAGE_SHIFT | prot_t;
    if(HYPERVISOR_mmu_update(mmu_updates, 1, NULL, DOMID_SELF) < 0) 
    {
       printk("ERROR: mmu_update failed\n");
       do_exit();
    }

    *pt_pfn += 1;
}

/* Checks if a pagetable frame is needed (if weren't allocated by Xen) */
static int need_pt_frame(unsigned long virt_address, int level)
{
    unsigned long hyp_virt_start = HYPERVISOR_VIRT_START;
#if defined(__x86_64__)
    unsigned long hyp_virt_end = HYPERVISOR_VIRT_END;
#else
    unsigned long hyp_virt_end = 0xffffffff;
#endif

    /* In general frames will _not_ be needed if they were already
       allocated to map the hypervisor into our VA space */
#if defined(__x86_64__)
    if(level == L3_FRAME)
    {
        if(l4_table_offset(virt_address) >= 
           l4_table_offset(hyp_virt_start) &&
           l4_table_offset(virt_address) <= 
           l4_table_offset(hyp_virt_end))
            return 0;
        return 1;
    } else
#endif

#if defined(__x86_64__) || defined(CONFIG_X86_PAE)
    if(level == L2_FRAME)
    {
#if defined(__x86_64__)
        if(l4_table_offset(virt_address) >= 
           l4_table_offset(hyp_virt_start) &&
           l4_table_offset(virt_address) <= 
           l4_table_offset(hyp_virt_end))
#endif
            if(l3_table_offset(virt_address) >= 
               l3_table_offset(hyp_virt_start) &&
               l3_table_offset(virt_address) <= 
               l3_table_offset(hyp_virt_end))
                return 0;

        return 1;
    } else 
#endif /* defined(__x86_64__) || defined(CONFIG_X86_PAE) */

    /* Always need l1 frames */
    if(level == L1_FRAME)
        return 1;

    printk("ERROR: Unknown frame level %d, hypervisor %llx,%llx\n", 
        level, hyp_virt_start, hyp_virt_end);
    return -1;
}

void build_pagetable(unsigned long *start_pfn, unsigned long *max_pfn)
{
    unsigned long start_address, end_address;
    unsigned long pfn_to_map, pt_pfn = *start_pfn;
    static mmu_update_t mmu_updates[L1_PAGETABLE_ENTRIES + 1];
    pgentry_t *tab = (pgentry_t *)start_info.pt_base, page;
    unsigned long mfn = pfn_to_mfn(virt_to_pfn(start_info.pt_base));
    unsigned long offset;
    int count = 0;

    pfn_to_map = (start_info.nr_pt_frames - NOT_L1_FRAMES) * L1_PAGETABLE_ENTRIES;

    if (*max_pfn >= virt_to_pfn(HYPERVISOR_VIRT_START))
    {
        printk("WARNING: Mini-OS trying to use Xen virtual space. "
               "Truncating memory from %dMB to ",
               ((unsigned long)pfn_to_virt(*max_pfn) - (unsigned long)&_text)>>20);
        *max_pfn = virt_to_pfn(HYPERVISOR_VIRT_START - PAGE_SIZE);
        printk("%dMB\n",
               ((unsigned long)pfn_to_virt(*max_pfn) - (unsigned long)&_text)>>20);
    }

    start_address = (unsigned long)pfn_to_virt(pfn_to_map);
    end_address = (unsigned long)pfn_to_virt(*max_pfn);

    /* We worked out the virtual memory range to map, now mapping loop */
    printk("Mapping memory range 0x%lx - 0x%lx\n", start_address, end_address);

    while(start_address < end_address)
    {
        tab = (pgentry_t *)start_info.pt_base;
        mfn = pfn_to_mfn(virt_to_pfn(start_info.pt_base));

#if defined(__x86_64__)
        offset = l4_table_offset(start_address);
        /* Need new L3 pt frame */
        if(!(start_address & L3_MASK)) 
            if(need_pt_frame(start_address, L3_FRAME)) 
                new_pt_frame(&pt_pfn, mfn, offset, L3_FRAME);

        page = tab[offset];
        mfn = pte_to_mfn(page);
        tab = to_virt(mfn_to_pfn(mfn) << PAGE_SHIFT);
#endif
#if defined(__x86_64__) || defined(CONFIG_X86_PAE)
        offset = l3_table_offset(start_address);
        /* Need new L2 pt frame */
        if(!(start_address & L2_MASK))
            if(need_pt_frame(start_address, L2_FRAME))
                new_pt_frame(&pt_pfn, mfn, offset, L2_FRAME);

        page = tab[offset];
        mfn = pte_to_mfn(page);
        tab = to_virt(mfn_to_pfn(mfn) << PAGE_SHIFT);
#endif
        offset = l2_table_offset(start_address);        
        /* Need new L1 pt frame */
        if(!(start_address & L1_MASK))
            if(need_pt_frame(start_address, L1_FRAME)) 
                new_pt_frame(&pt_pfn, mfn, offset, L1_FRAME);

        page = tab[offset];
        mfn = pte_to_mfn(page);
        offset = l1_table_offset(start_address);

        mmu_updates[count].ptr = ((pgentry_t)mfn << PAGE_SHIFT) + sizeof(pgentry_t) * offset;
        mmu_updates[count].val = (pgentry_t)pfn_to_mfn(pfn_to_map++) << PAGE_SHIFT | L1_PROT;
        count++;
        if (count == L1_PAGETABLE_ENTRIES || pfn_to_map == *max_pfn)
        {
            if(HYPERVISOR_mmu_update(mmu_updates, count, NULL, DOMID_SELF) < 0)
            {
                printk("PTE could not be updated\n");
                do_exit();
            }
            count = 0;
        }
        start_address += PAGE_SIZE;
    }

    *start_pfn = pt_pfn;
}

extern void shared_info;
static void set_readonly(void *text, void *etext)
{
    unsigned long start_address = ((unsigned long) text + PAGE_SIZE - 1) & PAGE_MASK;
    unsigned long end_address = (unsigned long) etext;
    static mmu_update_t mmu_updates[L1_PAGETABLE_ENTRIES + 1];
    pgentry_t *tab = (pgentry_t *)start_info.pt_base, page;
    unsigned long mfn = pfn_to_mfn(virt_to_pfn(start_info.pt_base));
    unsigned long offset;
    int count = 0;

    printk("setting %p-%p readonly\n", text, etext);

    while (start_address + PAGE_SIZE <= end_address) {
        tab = (pgentry_t *)start_info.pt_base;
        mfn = pfn_to_mfn(virt_to_pfn(start_info.pt_base));

#if defined(__x86_64__)
        offset = l4_table_offset(start_address);
        page = tab[offset];
        mfn = pte_to_mfn(page);
        tab = to_virt(mfn_to_pfn(mfn) << PAGE_SHIFT);
#endif
#if defined(__x86_64__) || defined(CONFIG_X86_PAE)
        offset = l3_table_offset(start_address);
        page = tab[offset];
        mfn = pte_to_mfn(page);
        tab = to_virt(mfn_to_pfn(mfn) << PAGE_SHIFT);
#endif
        offset = l2_table_offset(start_address);        
        page = tab[offset];
        mfn = pte_to_mfn(page);
        tab = to_virt(mfn_to_pfn(mfn) << PAGE_SHIFT);

        offset = l1_table_offset(start_address);

	if (start_address != (unsigned long)&shared_info) {
	    mmu_updates[count].ptr = ((pgentry_t)mfn << PAGE_SHIFT) + sizeof(pgentry_t) * offset;
	    mmu_updates[count].val = tab[offset] & ~_PAGE_RW;
	    count++;
	} else
	    printk("skipped %p\n", start_address);

        start_address += PAGE_SIZE;

        if (count == L1_PAGETABLE_ENTRIES || start_address + PAGE_SIZE > end_address)
        {
            if(HYPERVISOR_mmu_update(mmu_updates, count, NULL, DOMID_SELF) < 0)
            {
                printk("PTE could not be updated\n");
                do_exit();
            }
            count = 0;
        }
    }

    {
	mmuext_op_t op = {
	    .cmd = MMUEXT_TLB_FLUSH_ALL,
	};
	int count;
	HYPERVISOR_mmuext_op(&op, 1, &count, DOMID_SELF);
    }
}

void mem_test(unsigned long *start_add, unsigned long *end_add)
{
    unsigned long mask = 0x10000;
    unsigned long *pointer;

    for(pointer = start_add; pointer < end_add; pointer++)
    {
        if(!(((unsigned long)pointer) & 0xfffff))
        {
            printk("Writing to %lx\n", pointer);
            page_walk((unsigned long)pointer);
        }
        *pointer = (unsigned long)pointer & ~mask;
    }

    for(pointer = start_add; pointer < end_add; pointer++)
    {
        if(((unsigned long)pointer & ~mask) != *pointer)
            printk("Read error at 0x%lx. Read: 0x%lx, should read 0x%lx\n",
                (unsigned long)pointer, 
                *pointer, 
                ((unsigned long)pointer & ~mask));
    }

}

static pgentry_t *get_pgt(unsigned long addr)
{
    unsigned long mfn;
    pgentry_t *tab;
    unsigned offset;

    tab = (pgentry_t *)start_info.pt_base;
    mfn = virt_to_mfn(start_info.pt_base);

#if defined(__x86_64__)
    offset = l4_table_offset(addr);
    if (!(tab[offset] & _PAGE_PRESENT))
        return NULL;
    mfn = pte_to_mfn(tab[offset]);
    tab = mfn_to_virt(mfn);
#endif
#if defined(__x86_64__) || defined(CONFIG_X86_PAE)
    offset = l3_table_offset(addr);
    if (!(tab[offset] & _PAGE_PRESENT))
        return NULL;
    mfn = pte_to_mfn(tab[offset]);
    tab = mfn_to_virt(mfn);
#endif
    offset = l2_table_offset(addr);
    if (!(tab[offset] & _PAGE_PRESENT))
        return NULL;
    mfn = pte_to_mfn(tab[offset]);
    tab = mfn_to_virt(mfn);
    offset = l1_table_offset(addr);
    return &tab[offset];
}

static pgentry_t *need_pgt(unsigned long addr)
{
    unsigned long mfn;
    pgentry_t *tab;
    unsigned long pt_pfn;
    unsigned offset;

    tab = (pgentry_t *)start_info.pt_base;
    mfn = virt_to_mfn(start_info.pt_base);

#if defined(__x86_64__)
    offset = l4_table_offset(addr);
    if (!(tab[offset] & _PAGE_PRESENT)) {
        pt_pfn = virt_to_pfn(alloc_page());
        new_pt_frame(&pt_pfn, mfn, offset, L3_FRAME);
    }
    ASSERT(tab[offset] & _PAGE_PRESENT);
    mfn = pte_to_mfn(tab[offset]);
    tab = mfn_to_virt(mfn);
#endif
#if defined(__x86_64__) || defined(CONFIG_X86_PAE)
    offset = l3_table_offset(addr);
    if (!(tab[offset] & _PAGE_PRESENT)) {
        pt_pfn = virt_to_pfn(alloc_page());
        new_pt_frame(&pt_pfn, mfn, offset, L2_FRAME);
    }
    ASSERT(tab[offset] & _PAGE_PRESENT);
    mfn = pte_to_mfn(tab[offset]);
    tab = mfn_to_virt(mfn);
#endif
    offset = l2_table_offset(addr);
    if (!(tab[offset] & _PAGE_PRESENT)) {
        pt_pfn = virt_to_pfn(alloc_page());
	new_pt_frame(&pt_pfn, mfn, offset, L1_FRAME);
    }
    ASSERT(tab[offset] & _PAGE_PRESENT);
    mfn = pte_to_mfn(tab[offset]);
    tab = mfn_to_virt(mfn);

    offset = l1_table_offset(addr);
    return &tab[offset];
}

static unsigned long demand_map_area_start;
#ifdef __x86_64__
#define DEMAND_MAP_PAGES ((128ULL << 30) / PAGE_SIZE)
#else
#define DEMAND_MAP_PAGES ((2ULL << 30) / PAGE_SIZE)
#endif

#ifdef HAVE_LIBC
unsigned long heap, brk, heap_mapped, heap_end;
#ifdef __x86_64__
#define HEAP_PAGES ((128ULL << 30) / PAGE_SIZE)
#else
#define HEAP_PAGES ((1ULL << 30) / PAGE_SIZE)
#endif
#endif

void arch_init_demand_mapping_area(unsigned long cur_pfn)
{
    cur_pfn++;

    demand_map_area_start = (unsigned long) pfn_to_virt(cur_pfn);
    cur_pfn += DEMAND_MAP_PAGES;
    printk("Demand map pfns at %lx-%lx.\n", demand_map_area_start, pfn_to_virt(cur_pfn));

#ifdef HAVE_LIBC
    cur_pfn++;
    heap_mapped = brk = heap = (unsigned long) pfn_to_virt(cur_pfn);
    cur_pfn += HEAP_PAGES;
    heap_end = (unsigned long) pfn_to_virt(cur_pfn);
    printk("Heap resides at %lx-%lx.\n", brk, heap_end);
#endif
}

#define MAP_BATCH ((STACK_SIZE / 2) / sizeof(mmu_update_t))
void do_map_frames(unsigned long addr,
        unsigned long *f, unsigned long n, unsigned long stride,
	unsigned long increment, domid_t id, int may_fail, unsigned long prot)
{
    pgentry_t *pgt = NULL;
    unsigned long done = 0;
    unsigned long i;
    int rc;

    while (done < n) {
	unsigned long todo;

	if (may_fail)
	    todo = 1;
	else
	    todo = n - done;

	if (todo > MAP_BATCH)
		todo = MAP_BATCH;

	{
	    mmu_update_t mmu_updates[todo];

	    for (i = 0; i < todo; i++, addr += PAGE_SIZE, pgt++) {
                if (!pgt || !(addr & L1_MASK))
                    pgt = need_pgt(addr);
		mmu_updates[i].ptr = virt_to_mach(pgt);
		mmu_updates[i].val = ((f[(done + i) * stride] + (done + i) * increment) << PAGE_SHIFT) | prot;
	    }

	    rc = HYPERVISOR_mmu_update(mmu_updates, todo, NULL, id);
	    if (rc < 0) {
		if (may_fail)
		    f[done * stride] |= 0xF0000000;
		else {
		    printk("Map %ld (%lx, ...) at %p failed: %d.\n", todo, f[done * stride] + done * increment, addr, rc);
                    do_exit();
		}
	    }
	}

	done += todo;
    }
}

void *map_frames_ex(unsigned long *f, unsigned long n, unsigned long stride,
	unsigned long increment, unsigned long alignment, domid_t id,
	int may_fail, unsigned long prot)
{
    unsigned long x;
    unsigned long y = 0;

    /* Find a properly aligned run of n contiguous frames */
    for (x = 0; x <= DEMAND_MAP_PAGES - n; x = (x + y + 1 + alignment - 1) & ~(alignment - 1)) {
        unsigned long addr = demand_map_area_start + x * PAGE_SIZE;
        pgentry_t *pgt = get_pgt(addr);
        for (y = 0; y < n; y++, addr += PAGE_SIZE) {
            if (!(addr & L1_MASK))
                pgt = get_pgt(addr);
            if (pgt) {
                if (*pgt & _PAGE_PRESENT)
                    break;
                pgt++;
            }
        }
        if (y == n)
            break;
    }
    if (y != n) {
        printk("Failed to find %ld frames!\n", n);
        return NULL;
    }

    /* Found it at x.  Map it in. */
    do_map_frames(demand_map_area_start + x * PAGE_SIZE, f, n, stride, increment, id, may_fail, prot);

    return (void *)(unsigned long)(demand_map_area_start + x * PAGE_SIZE);
}

static void clear_bootstrap(void)
{
    xen_pfn_t mfns[] = { virt_to_mfn(&shared_info) };
    int n = sizeof(mfns)/sizeof(*mfns);
    pte_t nullpte = { };

    /* Use first page as the CoW zero page */
    memset(&_text, 0, PAGE_SIZE);
    mfn_zero = pfn_to_mfn((unsigned long) &_text);
    if (HYPERVISOR_update_va_mapping((unsigned long) &_text, nullpte, UVMF_INVLPG))
	printk("Unable to unmap first page\n");

    if (free_physical_pages(mfns, n) != n)
	printk("Unable to free bootstrap pages\n");
}

void arch_init_p2m(unsigned long max_pfn)
{
#define L1_P2M_SHIFT    9
#define L2_P2M_SHIFT    18    
#define L3_P2M_SHIFT    27    
#define L1_P2M_ENTRIES  (1 << L1_P2M_SHIFT)    
#define L2_P2M_ENTRIES  (1 << (L2_P2M_SHIFT - L1_P2M_SHIFT))    
#define L3_P2M_ENTRIES  (1 << (L3_P2M_SHIFT - L2_P2M_SHIFT))    
#define L1_P2M_MASK     (L1_P2M_ENTRIES - 1)    
#define L2_P2M_MASK     (L2_P2M_ENTRIES - 1)    
#define L3_P2M_MASK     (L3_P2M_ENTRIES - 1)    
    
    unsigned long *l1_list, *l2_list, *l3_list;
    unsigned long pfn;
    
    l3_list = (unsigned long *)alloc_page(); 
    for(pfn=0; pfn<max_pfn; pfn++)
    {
        if(!(pfn % (L1_P2M_ENTRIES * L2_P2M_ENTRIES)))
        {
            l2_list = (unsigned long*)alloc_page();
            if((pfn >> L3_P2M_SHIFT) > 0)
            {
                printk("Error: Too many pfns.\n");
                do_exit();
            }
            l3_list[(pfn >> L2_P2M_SHIFT)] = virt_to_mfn(l2_list);  
        }
        if(!(pfn % (L1_P2M_ENTRIES)))
        {
            l1_list = (unsigned long*)alloc_page();
            l2_list[(pfn >> L1_P2M_SHIFT) & L2_P2M_MASK] = 
                virt_to_mfn(l1_list); 
        }

        l1_list[pfn & L1_P2M_MASK] = pfn_to_mfn(pfn); 
    }
    HYPERVISOR_shared_info->arch.pfn_to_mfn_frame_list_list = 
        virt_to_mfn(l3_list);
    HYPERVISOR_shared_info->arch.max_pfn = max_pfn;
}

void arch_init_mm(unsigned long* start_pfn_p, unsigned long* max_pfn_p)
{

    unsigned long start_pfn, max_pfn;

    printk("  _text:        %p\n", &_text);
    printk("  _etext:       %p\n", &_etext);
    printk("  _erodata:     %p\n", &_erodata);
    printk("  _edata:       %p\n", &_edata);
    printk("  stack start:  %p\n", stack);
    printk("  _end:         %p\n", &_end);

    /* First page follows page table pages and 3 more pages (store page etc) */
    start_pfn = PFN_UP(to_phys(start_info.pt_base)) + 
                start_info.nr_pt_frames + 3;
    max_pfn = start_info.nr_pages;
   
    printk("  start_pfn:    %lx\n", start_pfn);
    printk("  max_pfn:      %lx\n", max_pfn);

    build_pagetable(&start_pfn, &max_pfn);
    clear_bootstrap();
    set_readonly(&_text, &_erodata);

    *start_pfn_p = start_pfn;
    *max_pfn_p = max_pfn;
}