aboutsummaryrefslogtreecommitdiff
path: root/fs/proc/task_mmu.c
blob: 2d45889931f630899efd571df62d67af4e06d6c0 (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
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
#include <linux/mm.h>
#include <linux/hugetlb.h>
#include <linux/mount.h>
#include <linux/seq_file.h>
#include <linux/highmem.h>
#include <linux/ptrace.h>
#include <linux/slab.h>
#include <linux/pagemap.h>
#include <linux/mempolicy.h>
#include <linux/swap.h>
#include <linux/swapops.h>

#include <asm/elf.h>
#include <asm/uaccess.h>
#include <asm/tlbflush.h>
#include "internal.h"

void task_mem(struct seq_file *m, struct mm_struct *mm)
{
	unsigned long data, text, lib, swap;
	unsigned long hiwater_vm, total_vm, hiwater_rss, total_rss;

	/*
	 * Note: to minimize their overhead, mm maintains hiwater_vm and
	 * hiwater_rss only when about to *lower* total_vm or rss.  Any
	 * collector of these hiwater stats must therefore get total_vm
	 * and rss too, which will usually be the higher.  Barriers? not
	 * worth the effort, such snapshots can always be inconsistent.
	 */
	hiwater_vm = total_vm = mm->total_vm;
	if (hiwater_vm < mm->hiwater_vm)
		hiwater_vm = mm->hiwater_vm;
	hiwater_rss = total_rss = get_mm_rss(mm);
	if (hiwater_rss < mm->hiwater_rss)
		hiwater_rss = mm->hiwater_rss;

	data = mm->total_vm - mm->shared_vm - mm->stack_vm;
	text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK)) >> 10;
	lib = (mm->exec_vm << (PAGE_SHIFT-10)) - text;
	swap = get_mm_counter(mm, MM_SWAPENTS);
	seq_printf(m,
		"VmPeak:\t%8lu kB\n"
		"VmSize:\t%8lu kB\n"
		"VmLck:\t%8lu kB\n"
		"VmHWM:\t%8lu kB\n"
		"VmRSS:\t%8lu kB\n"
		"VmData:\t%8lu kB\n"
		"VmStk:\t%8lu kB\n"
		"VmExe:\t%8lu kB\n"
		"VmLib:\t%8lu kB\n"
		"VmPTE:\t%8lu kB\n"
		"VmSwap:\t%8lu kB\n",
		hiwater_vm << (PAGE_SHIFT-10),
		(total_vm - mm->reserved_vm) << (PAGE_SHIFT-10),
		mm->locked_vm << (PAGE_SHIFT-10),
		hiwater_rss << (PAGE_SHIFT-10),
		total_rss << (PAGE_SHIFT-10),
		data << (PAGE_SHIFT-10),
		mm->stack_vm << (PAGE_SHIFT-10), text, lib,
		(PTRS_PER_PTE*sizeof(pte_t)*mm->nr_ptes) >> 10,
		swap << (PAGE_SHIFT-10));
}

unsigned long task_vsize(struct mm_struct *mm)
{
	return PAGE_SIZE * mm->total_vm;
}

int task_statm(struct mm_struct *mm, int *shared, int *text,
	       int *data, int *resident)
{
	*shared = get_mm_counter(mm, MM_FILEPAGES);
	*text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK))
								>> PAGE_SHIFT;
	*data = mm->total_vm - mm->shared_vm;
	*resident = *shared + get_mm_counter(mm, MM_ANONPAGES);
	return mm->total_vm;
}

static void pad_len_spaces(struct seq_file *m, int len)
{
	len = 25 + sizeof(void*) * 6 - len;
	if (len < 1)
		len = 1;
	seq_printf(m, "%*c", len, ' ');
}

static void vma_stop(struct proc_maps_private *priv, struct vm_area_struct *vma)
{
	if (vma && vma != priv->tail_vma) {
		struct mm_struct *mm = vma->vm_mm;
		up_read(&mm->mmap_sem);
		mmput(mm);
	}
}

static void *m_start(struct seq_file *m, loff_t *pos)
{
	struct proc_maps_private *priv = m->private;
	unsigned long last_addr = m->version;
	struct mm_struct *mm;
	struct vm_area_struct *vma, *tail_vma = NULL;
	loff_t l = *pos;

	/* Clear the per syscall fields in priv */
	priv->task = NULL;
	priv->tail_vma = NULL;

	/*
	 * We remember last_addr rather than next_addr to hit with
	 * mmap_cache most of the time. We have zero last_addr at
	 * the beginning and also after lseek. We will have -1 last_addr
	 * after the end of the vmas.
	 */

	if (last_addr == -1UL)
		return NULL;

	priv->task = get_pid_task(priv->pid, PIDTYPE_PID);
	if (!priv->task)
		return NULL;

	mm = mm_for_maps(priv->task);
	if (!mm)
		return NULL;
	down_read(&mm->mmap_sem);

	tail_vma = get_gate_vma(priv->task);
	priv->tail_vma = tail_vma;

	/* Start with last addr hint */
	vma = find_vma(mm, last_addr);
	if (last_addr && vma) {
		vma = vma->vm_next;
		goto out;
	}

	/*
	 * Check the vma index is within the range and do
	 * sequential scan until m_index.
	 */
	vma = NULL;
	if ((unsigned long)l < mm->map_count) {
		vma = mm->mmap;
		while (l-- && vma)
			vma = vma->vm_next;
		goto out;
	}

	if (l != mm->map_count)
		tail_vma = NULL; /* After gate vma */

out:
	if (vma)
		return vma;

	/* End of vmas has been reached */
	m->version = (tail_vma != NULL)? 0: -1UL;
	up_read(&mm->mmap_sem);
	mmput(mm);
	return tail_vma;
}

static void *m_next(struct seq_file *m, void *v, loff_t *pos)
{
	struct proc_maps_private *priv = m->private;
	struct vm_area_struct *vma = v;
	struct vm_area_struct *tail_vma = priv->tail_vma;

	(*pos)++;
	if (vma && (vma != tail_vma) && vma->vm_next)
		return vma->vm_next;
	vma_stop(priv, vma);
	return (vma != tail_vma)? tail_vma: NULL;
}

static void m_stop(struct seq_file *m, void *v)
{
	struct proc_maps_private *priv = m->private;
	struct vm_area_struct *vma = v;

	vma_stop(priv, vma);
	if (priv->task)
		put_task_struct(priv->task);
}

static int do_maps_open(struct inode *inode, struct file *file,
			const struct seq_operations *ops)
{
	struct proc_maps_private *priv;
	int ret = -ENOMEM;
	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
	if (priv) {
		priv->pid = proc_pid(inode);
		ret = seq_open(file, ops);
		if (!ret) {
			struct seq_file *m = file->private_data;
			m->private = priv;
		} else {
			kfree(priv);
		}
	}
	return ret;
}

static void show_map_vma(struct seq_file *m, struct vm_area_struct *vma)
{
	struct mm_struct *mm = vma->vm_mm;
	struct file *file = vma->vm_file;
	int flags = vma->vm_flags;
	unsigned long ino = 0;
	unsigned long long pgoff = 0;
	dev_t dev = 0;
	int len;

	if (file) {
		struct inode *inode = vma->vm_file->f_path.dentry->d_inode;
		dev = inode->i_sb->s_dev;
		ino = inode->i_ino;
		pgoff = ((loff_t)vma->vm_pgoff) << PAGE_SHIFT;
	}

	seq_printf(m, "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu %n",
			vma->vm_start,
			vma->vm_end,
			flags & VM_READ ? 'r' : '-',
			flags & VM_WRITE ? 'w' : '-',
			flags & VM_EXEC ? 'x' : '-',
			flags & VM_MAYSHARE ? 's' : 'p',
			pgoff,
			MAJOR(dev), MINOR(dev), ino, &len);

	/*
	 * Print the dentry name for named mappings, and a
	 * special [heap] marker for the heap:
	 */
	if (file) {
		pad_len_spaces(m, len);
		seq_path(m, &file->f_path, "\n");
	} else {
		const char *name = arch_vma_name(vma);
		if (!name) {
			if (mm) {
				if (vma->vm_start <= mm->start_brk &&
						vma->vm_end >= mm->brk) {
					name = "[heap]";
				} else if (vma->vm_start <= mm->start_stack &&
					   vma->vm_end >= mm->start_stack) {
					name = "[stack]";
				} else {
					unsigned long stack_start;
					struct proc_maps_private *pmp;

					pmp = m->private;
					stack_start = pmp->task->stack_start;

					if (vma->vm_start <= stack_start &&
					    vma->vm_end >= stack_start) {
						pad_len_spaces(m, len);
						seq_printf(m,
						 "[threadstack:%08lx]",
#ifdef CONFIG_STACK_GROWSUP
						 vma->vm_end - stack_start
#else
						 stack_start - vma->vm_start
#endif
						);
					}
				}
			} else {
				name = "[vdso]";
			}
		}
		if (name) {
			pad_len_spaces(m, len);
			seq_puts(m, name);
		}
	}
	seq_putc(m, '\n');
}

static int show_map(struct seq_file *m, void *v)
{
	struct vm_area_struct *vma = v;
	struct proc_maps_private *priv = m->private;
	struct task_struct *task = priv->task;

	show_map_vma(m, vma);

	if (m->count < m->size)  /* vma is copied successfully */
		m->version = (vma != get_gate_vma(task))? vma->vm_start: 0;
	return 0;
}

static const struct seq_operations proc_pid_maps_op = {
	.start	= m_start,
	.next	= m_next,
	.stop	= m_stop,
	.show	= show_map
};

static int maps_open(struct inode *inode, struct file *file)
{
	return do_maps_open(inode, file, &proc_pid_maps_op);
}

const struct file_operations proc_maps_operations = {
	.open		= maps_open,
	.read		= seq_read,
	.llseek		= seq_lseek,
	.release	= seq_release_private,
};

/*
 * Proportional Set Size(PSS): my share of RSS.
 *
 * PSS of a process is the count of pages it has in memory, where each
 * page is divided by the number of processes sharing it.  So if a
 * process has 1000 pages all to itself, and 1000 shared with one other
 * process, its PSS will be 1500.
 *
 * To keep (accumulated) division errors low, we adopt a 64bit
 * fixed-point pss counter to minimize division errors. So (pss >>
 * PSS_SHIFT) would be the real byte count.
 *
 * A shift of 12 before division means (assuming 4K page size):
 * 	- 1M 3-user-pages add up to 8KB errors;
 * 	- supports mapcount up to 2^24, or 16M;
 * 	- supports PSS up to 2^52 bytes, or 4PB.
 */
#define PSS_SHIFT 12

#ifdef CONFIG_PROC_PAGE_MONITOR
struct mem_size_stats {
	struct vm_area_struct *vma;
	unsigned long resident;
	unsigned long shared_clean;
	unsigned long shared_dirty;
	unsigned long private_clean;
	unsigned long private_dirty;
	unsigned long referenced;
	unsigned long swap;
	u64 pss;
};

static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
			   struct mm_walk *walk)
{
	struct mem_size_stats *mss = walk->private;
	struct vm_area_struct *vma = mss->vma;
	pte_t *pte, ptent;
	spinlock_t *ptl;
	struct page *page;
	int mapcount;

	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
	for (; addr != end; pte++, addr += PAGE_SIZE) {
		ptent = *pte;

		if (is_swap_pte(ptent)) {
			mss->swap += PAGE_SIZE;
			continue;
		}

		if (!pte_present(ptent))
			continue;

		page = vm_normal_page(vma, addr, ptent);
		if (!page)
			continue;

		mss->resident += PAGE_SIZE;
		/* Accumulate the size in pages that have been accessed. */
		if (pte_young(ptent) || PageReferenced(page))
			mss->referenced += PAGE_SIZE;
		mapcount = page_mapcount(page);
		if (mapcount >= 2) {
			if (pte_dirty(ptent))
				mss->shared_dirty += PAGE_SIZE;
			else
				mss->shared_clean += PAGE_SIZE;
			mss->pss += (PAGE_SIZE << PSS_SHIFT) / mapcount;
		} else {
			if (pte_dirty(ptent))
				mss->private_dirty += PAGE_SIZE;
			else
				mss->private_clean += PAGE_SIZE;
			mss->pss += (PAGE_SIZE << PSS_SHIFT);
		}
	}
	pte_unmap_unlock(pte - 1, ptl);
	cond_resched();
	return 0;
}

static int show_smap(struct seq_file *m, void *v)
{
	struct proc_maps_private *priv = m->private;
	struct task_struct *task = priv->task;
	struct vm_area_struct *vma = v;
	struct mem_size_stats mss;
	struct mm_walk smaps_walk = {
		.pmd_entry = smaps_pte_range,
		.mm = vma->vm_mm,
		.private = &mss,
	};

	memset(&mss, 0, sizeof mss);
	mss.vma = vma;
	if (vma->vm_mm && !is_vm_hugetlb_page(vma))
		walk_page_range(vma->vm_start, vma->vm_end, &smaps_walk);

	show_map_vma(m, vma);

	seq_printf(m,
		   "Size:           %8lu kB\n"
		   "Rss:            %8lu kB\n"
		   "Pss:            %8lu kB\n"
		   "Shared_Clean:   %8lu kB\n"
		   "Shared_Dirty:   %8lu kB\n"
		   "Private_Clean:  %8lu kB\n"
		   "Private_Dirty:  %8lu kB\n"
		   "Referenced:     %8lu kB\n"
		   "Swap:           %8lu kB\n"
		   "KernelPageSize: %8lu kB\n"
		   "MMUPageSize:    %8lu kB\n",
		   (vma->vm_end - vma->vm_start) >> 10,
		   mss.resident >> 10,
		   (unsigned long)(mss.pss >> (10 + PSS_SHIFT)),
		   mss.shared_clean  >> 10,
		   mss.shared_dirty  >> 10,
		   mss.private_clean >> 10,
		   mss.private_dirty >> 10,
		   mss.referenced >> 10,
		   mss.swap >> 10,
		   vma_kernel_pagesize(vma) >> 10,
		   vma_mmu_pagesize(vma) >> 10);

	if (m->count < m->size)  /* vma is copied successfully */
		m->version = (vma != get_gate_vma(task)) ? vma->vm_start : 0;
	return 0;
}

static const struct seq_operations proc_pid_smaps_op = {
	.start	= m_start,
	.next	= m_next,
	.stop	= m_stop,
	.show	= show_smap
};

static int smaps_open(struct inode *inode, struct file *file)
{
	return do_maps_open(inode, file, &proc_pid_smaps_op);
}

const struct file_operations proc_smaps_operations = {
	.open		= smaps_open,
	.read		= seq_read,
	.llseek		= seq_lseek,
	.release	= seq_release_private,
};

static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
				unsigned long end, struct mm_walk *walk)
{
	struct vm_area_struct *vma = walk->private;
	pte_t *pte, ptent;
	spinlock_t *ptl;
	struct page *page;

	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
	for (; addr != end; pte++, addr += PAGE_SIZE) {
		ptent = *pte;
		if (!pte_present(ptent))
			continue;

		page = vm_normal_page(vma, addr, ptent);
		if (!page)
			continue;

		/* Clear accessed and referenced bits. */
		ptep_test_and_clear_young(vma, addr, pte);
		ClearPageReferenced(page);
	}
	pte_unmap_unlock(pte - 1, ptl);
	cond_resched();
	return 0;
}

#define CLEAR_REFS_ALL 1
#define CLEAR_REFS_ANON 2
#define CLEAR_REFS_MAPPED 3

static ssize_t clear_refs_write(struct file *file, const char __user *buf,
				size_t count, loff_t *ppos)
{
	struct task_struct *task;
	char buffer[PROC_NUMBUF];
	struct mm_struct *mm;
	struct vm_area_struct *vma;
	long type;

	memset(buffer, 0, sizeof(buffer));
	if (count > sizeof(buffer) - 1)
		count = sizeof(buffer) - 1;
	if (copy_from_user(buffer, buf, count))
		return -EFAULT;
	if (strict_strtol(strstrip(buffer), 10, &type))
		return -EINVAL;
	if (type < CLEAR_REFS_ALL || type > CLEAR_REFS_MAPPED)
		return -EINVAL;
	task = get_proc_task(file->f_path.dentry->d_inode);
	if (!task)
		return -ESRCH;
	mm = get_task_mm(task);
	if (mm) {
		struct mm_walk clear_refs_walk = {
			.pmd_entry = clear_refs_pte_range,
			.mm = mm,
		};
		down_read(&mm->mmap_sem);
		for (vma = mm->mmap; vma; vma = vma->vm_next) {
			clear_refs_walk.private = vma;
			if (is_vm_hugetlb_page(vma))
				continue;
			/*
			 * Writing 1 to /proc/pid/clear_refs affects all pages.
			 *
			 * Writing 2 to /proc/pid/clear_refs only affects
			 * Anonymous pages.
			 *
			 * Writing 3 to /proc/pid/clear_refs only affects file
			 * mapped pages.
			 */
			if (type == CLEAR_REFS_ANON && vma->vm_file)
				continue;
			if (type == CLEAR_REFS_MAPPED && !vma->vm_file)
				continue;
			walk_page_range(vma->vm_start, vma->vm_end,
					&clear_refs_walk);
		}
		flush_tlb_mm(mm);
		up_read(&mm->mmap_sem);
		mmput(mm);
	}
	put_task_struct(task);

	return count;
}

const struct file_operations proc_clear_refs_operations = {
	.write		= clear_refs_write,
};

struct pagemapread {
	u64 __user *out, *end;
};

#define PM_ENTRY_BYTES      sizeof(u64)
#define PM_STATUS_BITS      3
#define PM_STATUS_OFFSET    (64 - PM_STATUS_BITS)
#define PM_STATUS_MASK      (((1LL << PM_STATUS_BITS) - 1) << PM_STATUS_OFFSET)
#define PM_STATUS(nr)       (((nr) << PM_STATUS_OFFSET) & PM_STATUS_MASK)
#define PM_PSHIFT_BITS      6
#define PM_PSHIFT_OFFSET    (PM_STATUS_OFFSET - PM_PSHIFT_BITS)
#define PM_PSHIFT_MASK      (((1LL << PM_PSHIFT_BITS) - 1) << PM_PSHIFT_OFFSET)
#define PM_PSHIFT(x)        (((u64) (x) << PM_PSHIFT_OFFSET) & PM_PSHIFT_MASK)
#define PM_PFRAME_MASK      ((1LL << PM_PSHIFT_OFFSET) - 1)
#define PM_PFRAME(x)        ((x) & PM_PFRAME_MASK)

#define PM_PRESENT          PM_STATUS(4LL)
#define PM_SWAP             PM_STATUS(2LL)
#define PM_NOT_PRESENT      PM_PSHIFT(PAGE_SHIFT)
#define PM_END_OF_BUFFER    1

static int add_to_pagemap(unsigned long addr, u64 pfn,
			  struct pagemapread *pm)
{
	if (put_user(pfn, pm->out))
		return -EFAULT;
	pm->out++;
	if (pm->out >= pm->end)
		return PM_END_OF_BUFFER;
	return 0;
}

static int pagemap_pte_hole(unsigned long start, unsigned long end,
				struct mm_walk *walk)
{
	struct pagemapread *pm = walk->private;
	unsigned long addr;
	int err = 0;
	for (addr = start; addr < end; addr += PAGE_SIZE) {
		err = add_to_pagemap(addr, PM_NOT_PRESENT, pm);
		if (err)
			break;
	}
	return err;
}

static u64 swap_pte_to_pagemap_entry(pte_t pte)
{
	swp_entry_t e = pte_to_swp_entry(pte);
	return swp_type(e) | (swp_offset(e) << MAX_SWAPFILES_SHIFT);
}

static u64 pte_to_pagemap_entry(pte_t pte)
{
	u64 pme = 0;
	if (is_swap_pte(pte))
		pme = PM_PFRAME(swap_pte_to_pagemap_entry(pte))
			| PM_PSHIFT(PAGE_SHIFT) | PM_SWAP;
	else if (pte_present(pte))
		pme = PM_PFRAME(pte_pfn(pte))
			| PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT;
	return pme;
}

static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
			     struct mm_walk *walk)
{
	struct vm_area_struct *vma;
	struct pagemapread *pm = walk->private;
	pte_t *pte;
	int err = 0;

	/* find the first VMA at or above 'addr' */
	vma = find_vma(walk->mm, addr);
	for (; addr != end; addr += PAGE_SIZE) {
		u64 pfn = PM_NOT_PRESENT;

		/* check to see if we've left 'vma' behind
		 * and need a new, higher one */
		if (vma && (addr >= vma->vm_end))
			vma = find_vma(walk->mm, addr);

		/* check that 'vma' actually covers this address,
		 * and that it isn't a huge page vma */
		if (vma && (vma->vm_start <= addr) &&
		    !is_vm_hugetlb_page(vma)) {
			pte = pte_offset_map(pmd, addr);
			pfn = pte_to_pagemap_entry(*pte);
			/* unmap before userspace copy */
			pte_unmap(pte);
		}
		err = add_to_pagemap(addr, pfn, pm);
		if (err)
			return err;
	}

	cond_resched();

	return err;
}

static u64 huge_pte_to_pagemap_entry(pte_t pte, int offset)
{
	u64 pme = 0;
	if (pte_present(pte))
		pme = PM_PFRAME(pte_pfn(pte) + offset)
			| PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT;
	return pme;
}

static int pagemap_hugetlb_range(pte_t *pte, unsigned long addr,
				 unsigned long end, struct mm_walk *walk)
{
	struct vm_area_struct *vma;
	struct pagemapread *pm = walk->private;
	struct hstate *hs = NULL;
	int err = 0;

	vma = find_vma(walk->mm, addr);
	if (vma)
		hs = hstate_vma(vma);
	for (; addr != end; addr += PAGE_SIZE) {
		u64 pfn = PM_NOT_PRESENT;

		if (vma && (addr >= vma->vm_end)) {
			vma = find_vma(walk->mm, addr);
			if (vma)
				hs = hstate_vma(vma);
		}

		if (vma && (vma->vm_start <= addr) && is_vm_hugetlb_page(vma)) {
			/* calculate pfn of the "raw" page in the hugepage. */
			int offset = (addr & ~huge_page_mask(hs)) >> PAGE_SHIFT;
			pfn = huge_pte_to_pagemap_entry(*pte, offset);
		}
		err = add_to_pagemap(addr, pfn, pm);
		if (err)
			return err;
	}

	cond_resched();

	return err;
}

/*
 * /proc/pid/pagemap - an array mapping virtual pages to pfns
 *
 * For each page in the address space, this file contains one 64-bit entry
 * consisting of the following:
 *
 * Bits 0-55  page frame number (PFN) if present
 * Bits 0-4   swap type if swapped
 * Bits 5-55  swap offset if swapped
 * Bits 55-60 page shift (page size = 1<<page shift)
 * Bit  61    reserved for future use
 * Bit  62    page swapped
 * Bit  63    page present
 *
 * If the page is not present but in swap, then the PFN contains an
 * encoding of the swap file number and the page's offset into the
 * swap. Unmapped pages return a null PFN. This allows determining
 * precisely which pages are mapped (or in swap) and comparing mapped
 * pages between processes.
 *
 * Efficient users of this interface will use /proc/pid/maps to
 * determine which areas of memory are actually mapped and llseek to
 * skip over unmapped regions.
 */
static ssize_t pagemap_read(struct file *file, char __user *buf,
			    size_t count, loff_t *ppos)
{
	struct task_struct *task = get_proc_task(file->f_path.dentry->d_inode);
	struct page **pages, *page;
	unsigned long uaddr, uend;
	struct mm_struct *mm;
	struct pagemapread pm;
	int pagecount;
	int ret = -ESRCH;
	struct mm_walk pagemap_walk = {};
	unsigned long src;
	unsigned long svpfn;
	unsigned long start_vaddr;
	unsigned long end_vaddr;

	if (!task)
		goto out;

	ret = -EACCES;
	if (!ptrace_may_access(task, PTRACE_MODE_READ))
		goto out_task;

	ret = -EINVAL;
	/* file position must be aligned */
	if ((*ppos % PM_ENTRY_BYTES) || (count % PM_ENTRY_BYTES))
		goto out_task;

	ret = 0;

	if (!count)
		goto out_task;

	mm = get_task_mm(task);
	if (!mm)
		goto out_task;


	uaddr = (unsigned long)buf & PAGE_MASK;
	uend = (unsigned long)(buf + count);
	pagecount = (PAGE_ALIGN(uend) - uaddr) / PAGE_SIZE;
	ret = 0;
	if (pagecount == 0)
		goto out_mm;
	pages = kcalloc(pagecount, sizeof(struct page *), GFP_KERNEL);
	ret = -ENOMEM;
	if (!pages)
		goto out_mm;

	down_read(&current->mm->mmap_sem);
	ret = get_user_pages(current, current->mm, uaddr, pagecount,
			     1, 0, pages, NULL);
	up_read(&current->mm->mmap_sem);

	if (ret < 0)
		goto out_free;

	if (ret != pagecount) {
		pagecount = ret;
		ret = -EFAULT;
		goto out_pages;
	}

	pm.out = (u64 __user *)buf;
	pm.end = (u64 __user *)(buf + count);

	pagemap_walk.pmd_entry = pagemap_pte_range;
	pagemap_walk.pte_hole = pagemap_pte_hole;
	pagemap_walk.hugetlb_entry = pagemap_hugetlb_range;
	pagemap_walk.mm = mm;
	pagemap_walk.private = &pm;

	src = *ppos;
	svpfn = src / PM_ENTRY_BYTES;
	start_vaddr = svpfn << PAGE_SHIFT;
	end_vaddr = TASK_SIZE_OF(task);

	/* watch out for wraparound */
	if (svpfn > TASK_SIZE_OF(task) >> PAGE_SHIFT)
		start_vaddr = end_vaddr;

	/*
	 * The odds are that this will stop walking way
	 * before end_vaddr, because the length of the
	 * user buffer is tracked in "pm", and the walk
	 * will stop when we hit the end of the buffer.
	 */
	ret = walk_page_range(start_vaddr, end_vaddr, &pagemap_walk);
	if (ret == PM_END_OF_BUFFER)
		ret = 0;
	/* don't need mmap_sem for these, but this looks cleaner */
	*ppos += (char __user *)pm.out - buf;
	if (!ret)
		ret = (char __user *)pm.out - buf;

out_pages:
	for (; pagecount; pagecount--) {
		page = pages[pagecount-1];
		if (!PageReserved(page))
			SetPageDirty(page);
		page_cache_release(page);
	}
out_free:
	kfree(pages);
out_mm:
	mmput(mm);
out_task:
	put_task_struct(task);
out:
	return ret;
}

const struct file_operations proc_pagemap_operations = {
	.llseek		= mem_lseek, /* borrow this */
	.read		= pagemap_read,
};
#endif /* CONFIG_PROC_PAGE_MONITOR */

#ifdef CONFIG_NUMA
extern int show_numa_map(struct seq_file *m, void *v);

static const struct seq_operations proc_pid_numa_maps_op = {
        .start  = m_start,
        .next   = m_next,
        .stop   = m_stop,
        .show   = show_numa_map,
};

static int numa_maps_open(struct inode *inode, struct file *file)
{
	return do_maps_open(inode, file, &proc_pid_numa_maps_op);
}

const struct file_operations proc_numa_maps_operations = {
	.open		= numa_maps_open,
	.read		= seq_read,
	.llseek		= seq_lseek,
	.release	= seq_release_private,
};
#endif