summaryrefslogtreecommitdiffstats
path: root/fs/proc/task_mmu.c
blob: 8952ce70315e43499046e2e2966d6667881d4c95 (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
#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/pagemap.h>
#include <linux/mempolicy.h>

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

char *task_mem(struct mm_struct *mm, char *buffer)
{
	unsigned long data, text, lib;
	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;
	buffer += sprintf(buffer,
		"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",
		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);
	return buffer;
}

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, file_rss);
	*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, anon_rss);
	return mm->total_vm;
}

int proc_exe_link(struct inode *inode, struct dentry **dentry, struct vfsmount **mnt)
{
	struct vm_area_struct * vma;
	int result = -ENOENT;
	struct task_struct *task = get_proc_task(inode);
	struct mm_struct * mm = NULL;

	if (task) {
		mm = get_task_mm(task);
		put_task_struct(task);
	}
	if (!mm)
		goto out;
	down_read(&mm->mmap_sem);

	vma = mm->mmap;
	while (vma) {
		if ((vma->vm_flags & VM_EXECUTABLE) && vma->vm_file)
			break;
		vma = vma->vm_next;
	}

	if (vma) {
		*mnt = mntget(vma->vm_file->f_path.mnt);
		*dentry = dget(vma->vm_file->f_path.dentry);
		result = 0;
	}

	up_read(&mm->mmap_sem);
	mmput(mm);
out:
	return result;
}

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, ' ');
}

/*
 * 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

struct mem_size_stats
{
	unsigned long resident;
	unsigned long shared_clean;
	unsigned long shared_dirty;
	unsigned long private_clean;
	unsigned long private_dirty;
	unsigned long referenced;
	u64 pss;
};

struct pmd_walker {
	struct vm_area_struct *vma;
	void *private;
	void (*action)(struct vm_area_struct *, pmd_t *, unsigned long,
		       unsigned long, void *);
};

static int show_map_internal(struct seq_file *m, void *v, struct mem_size_stats *mss)
{
	struct proc_maps_private *priv = m->private;
	struct task_struct *task = priv->task;
	struct vm_area_struct *vma = v;
	struct mm_struct *mm = vma->vm_mm;
	struct file *file = vma->vm_file;
	int flags = vma->vm_flags;
	unsigned long ino = 0;
	dev_t dev = 0;
	int len;

	if (maps_protect && !ptrace_may_attach(task))
		return -EACCES;

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

	seq_printf(m, "%08lx-%08lx %c%c%c%c %08lx %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',
			vma->vm_pgoff << PAGE_SHIFT,
			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.mnt, file->f_path.dentry, "\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 {
				name = "[vdso]";
			}
		}
		if (name) {
			pad_len_spaces(m, len);
			seq_puts(m, name);
		}
	}
	seq_putc(m, '\n');

	if (mss)
		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",
			   (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);

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

static int show_map(struct seq_file *m, void *v)
{
	return show_map_internal(m, v, NULL);
}

static void smaps_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
			    unsigned long addr, unsigned long end,
			    void *private)
{
	struct mem_size_stats *mss = private;
	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 (!pte_present(ptent))
			continue;

		mss->resident += PAGE_SIZE;

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

		/* 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();
}

static void clear_refs_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
				 unsigned long addr, unsigned long end,
				 void *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();
}

static inline void walk_pmd_range(struct pmd_walker *walker, pud_t *pud,
				  unsigned long addr, unsigned long end)
{
	pmd_t *pmd;
	unsigned long next;

	for (pmd = pmd_offset(pud, addr); addr != end;
	     pmd++, addr = next) {
		next = pmd_addr_end(addr, end);
		if (pmd_none_or_clear_bad(pmd))
			continue;
		walker->action(walker->vma, pmd, addr, next, walker->private);
	}
}

static inline void walk_pud_range(struct pmd_walker *walker, pgd_t *pgd,
				  unsigned long addr, unsigned long end)
{
	pud_t *pud;
	unsigned long next;

	for (pud = pud_offset(pgd, addr); addr != end;
	     pud++, addr = next) {
		next = pud_addr_end(addr, end);
		if (pud_none_or_clear_bad(pud))
			continue;
		walk_pmd_range(walker, pud, addr, next);
	}
}

/*
 * walk_page_range - walk the page tables of a VMA with a callback
 * @vma - VMA to walk
 * @action - callback invoked for every bottom-level (PTE) page table
 * @private - private data passed to the callback function
 *
 * Recursively walk the page table for the memory area in a VMA, calling
 * a callback for every bottom-level (PTE) page table.
 */
static inline void walk_page_range(struct vm_area_struct *vma,
				   void (*action)(struct vm_area_struct *,
						  pmd_t *, unsigned long,
						  unsigned long, void *),
				   void *private)
{
	unsigned long addr = vma->vm_start;
	unsigned long end = vma->vm_end;
	struct pmd_walker walker = {
		.vma		= vma,
		.private	= private,
		.action		= action,
	};
	pgd_t *pgd;
	unsigned long next;

	for (pgd = pgd_offset(vma->vm_mm, addr); addr != end;
	     pgd++, addr = next) {
		next = pgd_addr_end(addr, end);
		if (pgd_none_or_clear_bad(pgd))
			continue;
		walk_pud_range(&walker, pgd, addr, next);
	}
}

static int show_smap(struct seq_file *m, void *v)
{
	struct vm_area_struct *vma = v;
	struct mem_size_stats mss;

	memset(&mss, 0, sizeof mss);
	if (vma->vm_mm && !is_vm_hugetlb_page(vma))
		walk_page_range(vma, smaps_pte_range, &mss);
	return show_map_internal(m, v, &mss);
}

void clear_refs_smap(struct mm_struct *mm)
{
	struct vm_area_struct *vma;

	down_read(&mm->mmap_sem);
	for (vma = mm->mmap; vma; vma = vma->vm_next)
		if (vma->vm_mm && !is_vm_hugetlb_page(vma))
			walk_page_range(vma, clear_refs_pte_range, NULL);
	flush_tlb_mm(mm);
	up_read(&mm->mmap_sem);
}

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;

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

	/* Start with last addr hint */
	if (last_addr && (vma = find_vma(mm, last_addr))) {
		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 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_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 struct seq_operations proc_pid_maps_op = {
	.start	= m_start,
	.next	= m_next,
	.stop	= m_stop,
	.show	= show_map
};

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

static int do_maps_open(struct inode *inode, struct file *file,
			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 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,
};

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

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

	if (maps_protect && !ptrace_may_attach(task))
		return -EACCES;

	return show_numa_map(m, v);
}

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

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

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,
};
OpenPOWER on IntegriCloud