summaryrefslogtreecommitdiff
path: root/fs/proc/page.c
blob: a2873a617ae86232c12376064cbc8ffc4df59ab8 (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
// SPDX-License-Identifier: GPL-2.0
#include <linux/memblock.h>
#include <linux/compiler.h>
#include <linux/fs.h>
#include <linux/init.h>
#include <linux/ksm.h>
#include <linux/mm.h>
#include <linux/mmzone.h>
#include <linux/huge_mm.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/hugetlb.h>
#include <linux/memremap.h>
#include <linux/memcontrol.h>
#include <linux/mmu_notifier.h>
#include <linux/page_idle.h>
#include <linux/kernel-page-flags.h>
#include <linux/uaccess.h>
#include "internal.h"

#define KPMSIZE sizeof(u64)
#define KPMMASK (KPMSIZE - 1)
#define KPMBITS (KPMSIZE * BITS_PER_BYTE)

static inline unsigned long get_max_dump_pfn(void)
{
#ifdef CONFIG_SPARSEMEM
	/*
	 * The memmap of early sections is completely populated and marked
	 * online even if max_pfn does not fall on a section boundary -
	 * pfn_to_online_page() will succeed on all pages. Allow inspecting
	 * these memmaps.
	 */
	return round_up(max_pfn, PAGES_PER_SECTION);
#else
	return max_pfn;
#endif
}

/* /proc/kpagecount - an array exposing page counts
 *
 * Each entry is a u64 representing the corresponding
 * physical page count.
 */
static ssize_t kpagecount_read(struct file *file, char __user *buf,
			     size_t count, loff_t *ppos)
{
	const unsigned long max_dump_pfn = get_max_dump_pfn();
	u64 __user *out = (u64 __user *)buf;
	struct page *ppage;
	unsigned long src = *ppos;
	unsigned long pfn;
	ssize_t ret = 0;
	u64 pcount;

	pfn = src / KPMSIZE;
	if (src & KPMMASK || count & KPMMASK)
		return -EINVAL;
	if (src >= max_dump_pfn * KPMSIZE)
		return 0;
	count = min_t(unsigned long, count, (max_dump_pfn * KPMSIZE) - src);

	while (count > 0) {
		/*
		 * TODO: ZONE_DEVICE support requires to identify
		 * memmaps that were actually initialized.
		 */
		ppage = pfn_to_online_page(pfn);

		if (!ppage || PageSlab(ppage) || page_has_type(ppage))
			pcount = 0;
		else
			pcount = page_mapcount(ppage);

		if (put_user(pcount, out)) {
			ret = -EFAULT;
			break;
		}

		pfn++;
		out++;
		count -= KPMSIZE;

		cond_resched();
	}

	*ppos += (char __user *)out - buf;
	if (!ret)
		ret = (char __user *)out - buf;
	return ret;
}

static const struct proc_ops kpagecount_proc_ops = {
	.proc_lseek	= mem_lseek,
	.proc_read	= kpagecount_read,
};

/* /proc/kpageflags - an array exposing page flags
 *
 * Each entry is a u64 representing the corresponding
 * physical page flags.
 */

static inline u64 kpf_copy_bit(u64 kflags, int ubit, int kbit)
{
	return ((kflags >> kbit) & 1) << ubit;
}

u64 stable_page_flags(struct page *page)
{
	u64 k;
	u64 u;

	/*
	 * pseudo flag: KPF_NOPAGE
	 * it differentiates a memory hole from a page with no flags
	 */
	if (!page)
		return 1 << KPF_NOPAGE;

	k = page->flags;
	u = 0;

	/*
	 * pseudo flags for the well known (anonymous) memory mapped pages
	 *
	 * Note that page->_mapcount is overloaded in SLOB/SLUB/SLQB, so the
	 * simple test in page_mapped() is not enough.
	 */
	if (!PageSlab(page) && page_mapped(page))
		u |= 1 << KPF_MMAP;
	if (PageAnon(page))
		u |= 1 << KPF_ANON;
	if (PageKsm(page))
		u |= 1 << KPF_KSM;

	/*
	 * compound pages: export both head/tail info
	 * they together define a compound page's start/end pos and order
	 */
	if (PageHead(page))
		u |= 1 << KPF_COMPOUND_HEAD;
	if (PageTail(page))
		u |= 1 << KPF_COMPOUND_TAIL;
	if (PageHuge(page))
		u |= 1 << KPF_HUGE;
	/*
	 * PageTransCompound can be true for non-huge compound pages (slab
	 * pages or pages allocated by drivers with __GFP_COMP) because it
	 * just checks PG_head/PG_tail, so we need to check PageLRU/PageAnon
	 * to make sure a given page is a thp, not a non-huge compound page.
	 */
	else if (PageTransCompound(page)) {
		struct page *head = compound_head(page);

		if (PageLRU(head) || PageAnon(head))
			u |= 1 << KPF_THP;
		else if (is_huge_zero_page(head)) {
			u |= 1 << KPF_ZERO_PAGE;
			u |= 1 << KPF_THP;
		}
	} else if (is_zero_pfn(page_to_pfn(page)))
		u |= 1 << KPF_ZERO_PAGE;


	/*
	 * Caveats on high order pages: page->_refcount will only be set
	 * -1 on the head page; SLUB/SLQB do the same for PG_slab;
	 * SLOB won't set PG_slab at all on compound pages.
	 */
	if (PageBuddy(page))
		u |= 1 << KPF_BUDDY;
	else if (page_count(page) == 0 && is_free_buddy_page(page))
		u |= 1 << KPF_BUDDY;

	if (PageOffline(page))
		u |= 1 << KPF_OFFLINE;
	if (PageTable(page))
		u |= 1 << KPF_PGTABLE;

	if (page_is_idle(page))
		u |= 1 << KPF_IDLE;

	u |= kpf_copy_bit(k, KPF_LOCKED,	PG_locked);

	u |= kpf_copy_bit(k, KPF_SLAB,		PG_slab);
	if (PageTail(page) && PageSlab(compound_head(page)))
		u |= 1 << KPF_SLAB;

	u |= kpf_copy_bit(k, KPF_ERROR,		PG_error);
	u |= kpf_copy_bit(k, KPF_DIRTY,		PG_dirty);
	u |= kpf_copy_bit(k, KPF_UPTODATE,	PG_uptodate);
	u |= kpf_copy_bit(k, KPF_WRITEBACK,	PG_writeback);

	u |= kpf_copy_bit(k, KPF_LRU,		PG_lru);
	u |= kpf_copy_bit(k, KPF_REFERENCED,	PG_referenced);
	u |= kpf_copy_bit(k, KPF_ACTIVE,	PG_active);
	u |= kpf_copy_bit(k, KPF_RECLAIM,	PG_reclaim);

	if (PageSwapCache(page))
		u |= 1 << KPF_SWAPCACHE;
	u |= kpf_copy_bit(k, KPF_SWAPBACKED,	PG_swapbacked);

	u |= kpf_copy_bit(k, KPF_UNEVICTABLE,	PG_unevictable);
	u |= kpf_copy_bit(k, KPF_MLOCKED,	PG_mlocked);

#ifdef CONFIG_MEMORY_FAILURE
	u |= kpf_copy_bit(k, KPF_HWPOISON,	PG_hwpoison);
#endif

#ifdef CONFIG_ARCH_USES_PG_UNCACHED
	u |= kpf_copy_bit(k, KPF_UNCACHED,	PG_uncached);
#endif

	u |= kpf_copy_bit(k, KPF_RESERVED,	PG_reserved);
	u |= kpf_copy_bit(k, KPF_MAPPEDTODISK,	PG_mappedtodisk);
	u |= kpf_copy_bit(k, KPF_PRIVATE,	PG_private);
	u |= kpf_copy_bit(k, KPF_PRIVATE_2,	PG_private_2);
	u |= kpf_copy_bit(k, KPF_OWNER_PRIVATE,	PG_owner_priv_1);
	u |= kpf_copy_bit(k, KPF_ARCH,		PG_arch_1);
#ifdef CONFIG_64BIT
	u |= kpf_copy_bit(k, KPF_ARCH_2,	PG_arch_2);
#endif

	return u;
};

static ssize_t kpageflags_read(struct file *file, char __user *buf,
			     size_t count, loff_t *ppos)
{
	const unsigned long max_dump_pfn = get_max_dump_pfn();
	u64 __user *out = (u64 __user *)buf;
	struct page *ppage;
	unsigned long src = *ppos;
	unsigned long pfn;
	ssize_t ret = 0;

	pfn = src / KPMSIZE;
	if (src & KPMMASK || count & KPMMASK)
		return -EINVAL;
	if (src >= max_dump_pfn * KPMSIZE)
		return 0;
	count = min_t(unsigned long, count, (max_dump_pfn * KPMSIZE) - src);

	while (count > 0) {
		/*
		 * TODO: ZONE_DEVICE support requires to identify
		 * memmaps that were actually initialized.
		 */
		ppage = pfn_to_online_page(pfn);

		if (put_user(stable_page_flags(ppage), out)) {
			ret = -EFAULT;
			break;
		}

		pfn++;
		out++;
		count -= KPMSIZE;

		cond_resched();
	}

	*ppos += (char __user *)out - buf;
	if (!ret)
		ret = (char __user *)out - buf;
	return ret;
}

static const struct proc_ops kpageflags_proc_ops = {
	.proc_lseek	= mem_lseek,
	.proc_read	= kpageflags_read,
};

#ifdef CONFIG_MEMCG
static ssize_t kpagecgroup_read(struct file *file, char __user *buf,
				size_t count, loff_t *ppos)
{
	const unsigned long max_dump_pfn = get_max_dump_pfn();
	u64 __user *out = (u64 __user *)buf;
	struct page *ppage;
	unsigned long src = *ppos;
	unsigned long pfn;
	ssize_t ret = 0;
	u64 ino;

	pfn = src / KPMSIZE;
	if (src & KPMMASK || count & KPMMASK)
		return -EINVAL;
	if (src >= max_dump_pfn * KPMSIZE)
		return 0;
	count = min_t(unsigned long, count, (max_dump_pfn * KPMSIZE) - src);

	while (count > 0) {
		/*
		 * TODO: ZONE_DEVICE support requires to identify
		 * memmaps that were actually initialized.
		 */
		ppage = pfn_to_online_page(pfn);

		if (ppage)
			ino = page_cgroup_ino(ppage);
		else
			ino = 0;

		if (put_user(ino, out)) {
			ret = -EFAULT;
			break;
		}

		pfn++;
		out++;
		count -= KPMSIZE;

		cond_resched();
	}

	*ppos += (char __user *)out - buf;
	if (!ret)
		ret = (char __user *)out - buf;
	return ret;
}

static const struct proc_ops kpagecgroup_proc_ops = {
	.proc_lseek	= mem_lseek,
	.proc_read	= kpagecgroup_read,
};
#endif /* CONFIG_MEMCG */

static int __init proc_page_init(void)
{
	proc_create("kpagecount", S_IRUSR, NULL, &kpagecount_proc_ops);
	proc_create("kpageflags", S_IRUSR, NULL, &kpageflags_proc_ops);
#ifdef CONFIG_MEMCG
	proc_create("kpagecgroup", S_IRUSR, NULL, &kpagecgroup_proc_ops);
#endif
	return 0;
}
fs_initcall(proc_page_init);