[linux.git] / fs / proc / page.c

// 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/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)

/* /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)
{
	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;
	count = min_t(size_t, count, (max_pfn * KPMSIZE) - src);
	if (src & KPMMASK || count & KPMMASK)
		return -EINVAL;

	while (count > 0) {
		if (pfn_valid(pfn))
			ppage = pfn_to_page(pfn);
		else
			ppage = NULL;
		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 file_operations proc_kpagecount_operations = {
	.llseek = mem_lseek,
	.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);

	return u;
};

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

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

	while (count > 0) {
		if (pfn_valid(pfn))
			ppage = pfn_to_page(pfn);
		else
			ppage = NULL;

		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 file_operations proc_kpageflags_operations = {
	.llseek = mem_lseek,
	.read = kpageflags_read,
};

#ifdef CONFIG_MEMCG
static ssize_t kpagecgroup_read(struct file *file, char __user *buf,
				size_t count, loff_t *ppos)
{
	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;
	count = min_t(unsigned long, count, (max_pfn * KPMSIZE) - src);
	if (src & KPMMASK || count & KPMMASK)
		return -EINVAL;

	while (count > 0) {
		if (pfn_valid(pfn))
			ppage = pfn_to_page(pfn);
		else
			ppage = NULL;

		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 file_operations proc_kpagecgroup_operations = {
	.llseek = mem_lseek,
	.read = kpagecgroup_read,
};
#endif /* CONFIG_MEMCG */

static int __init proc_page_init(void)
{
	proc_create("kpagecount", S_IRUSR, NULL, &proc_kpagecount_operations);
	proc_create("kpageflags", S_IRUSR, NULL, &proc_kpageflags_operations);
#ifdef CONFIG_MEMCG
	proc_create("kpagecgroup", S_IRUSR, NULL, &proc_kpagecgroup_operations);
#endif
	return 0;
}
fs_initcall(proc_page_init);
Commit	Line	Data
b2441318	1	// SPDX-License-Identifier: GPL-2.0
57c8a661	2	#include <linux/memblock.h>
6d80e53f AD	3	#include <linux/compiler.h>
	4	#include <linux/fs.h>
	5	#include <linux/init.h>
9a840895	6	#include <linux/ksm.h>
6d80e53f AD	7	#include <linux/mm.h>
6d80e53f AD	8	#include <linux/mmzone.h>
56873f43	9	#include <linux/huge_mm.h>
6d80e53f AD	10	#include <linux/proc_fs.h>
6d80e53f AD	11	#include <linux/seq_file.h>
20a0307c	12	#include <linux/hugetlb.h>
80ae2fdc	13	#include <linux/memcontrol.h>
33c3fc71 VD	14	#include <linux/mmu_notifier.h>
33c3fc71 VD	15	#include <linux/page_idle.h>
1a9b5b7f	16	#include <linux/kernel-page-flags.h>
7c0f6ba6	17	#include <linux/uaccess.h>
6d80e53f AD	18	#include "internal.h"
	19
	20	#define KPMSIZE sizeof(u64)
	21	#define KPMMASK (KPMSIZE - 1)
33c3fc71	22	#define KPMBITS (KPMSIZE * BITS_PER_BYTE)
ed7ce0f1	23
6d80e53f AD	24	/* /proc/kpagecount - an array exposing page counts
	25	*
	26	* Each entry is a u64 representing the corresponding
	27	* physical page count.
	28	*/
	29	static ssize_t kpagecount_read(struct file file, char __user buf,
	30	size_t count, loff_t *ppos)
	31	{
	32	u64 __user out = (u64 __user )buf;
	33	struct page *ppage;
	34	unsigned long src = *ppos;
	35	unsigned long pfn;
	36	ssize_t ret = 0;
	37	u64 pcount;
	38
	39	pfn = src / KPMSIZE;
	40	count = min_t(size_t, count, (max_pfn * KPMSIZE) - src);
	41	if (src & KPMMASK \|\| count & KPMMASK)
	42	return -EINVAL;
	43
	44	while (count > 0) {
6d80e53f AD	45	if (pfn_valid(pfn))
6d80e53f AD	46	ppage = pfn_to_page(pfn);
ed7ce0f1 WF	47	else
ed7ce0f1 WF	48	ppage = NULL;
144552ff	49	if (!ppage \|\| PageSlab(ppage) \|\| page_has_type(ppage))
6d80e53f AD	50	pcount = 0;
	51	else
	52	pcount = page_mapcount(ppage);
	53
ed7ce0f1	54	if (put_user(pcount, out)) {
6d80e53f AD	55	ret = -EFAULT;
	56	break;
	57	}
	58
ed7ce0f1 WF	59	pfn++;
ed7ce0f1 WF	60	out++;
6d80e53f	61	count -= KPMSIZE;
d3691d2c VD	62
d3691d2c VD	63	cond_resched();
6d80e53f AD	64	}
	65
	66	ppos += (char __user )out - buf;
	67	if (!ret)
	68	ret = (char __user *)out - buf;
	69	return ret;
	70	}
	71
	72	static const struct file_operations proc_kpagecount_operations = {
	73	.llseek = mem_lseek,
	74	.read = kpagecount_read,
	75	};
	76
	77	/* /proc/kpageflags - an array exposing page flags
	78	*
	79	* Each entry is a u64 representing the corresponding
	80	* physical page flags.
	81	*/
	82
17797549 WF	83	static inline u64 kpf_copy_bit(u64 kflags, int ubit, int kbit)
	84	{
	85	return ((kflags >> kbit) & 1) << ubit;
	86	}
	87
1a9b5b7f	88	u64 stable_page_flags(struct page *page)
17797549 WF	89	{
	90	u64 k;
	91	u64 u;
	92
	93	/*
	94	* pseudo flag: KPF_NOPAGE
	95	* it differentiates a memory hole from a page with no flags
	96	*/
	97	if (!page)
	98	return 1 << KPF_NOPAGE;
	99
	100	k = page->flags;
	101	u = 0;
	102
	103	/*
	104	* pseudo flags for the well known (anonymous) memory mapped pages
	105	*
	106	* Note that page->_mapcount is overloaded in SLOB/SLUB/SLQB, so the
832fc1de	107	* simple test in page_mapped() is not enough.
17797549	108	*/
832fc1de	109	if (!PageSlab(page) && page_mapped(page))
17797549 WF	110	u \|= 1 << KPF_MMAP;
	111	if (PageAnon(page))
	112	u \|= 1 << KPF_ANON;
9a840895 HD	113	if (PageKsm(page))
9a840895 HD	114	u \|= 1 << KPF_KSM;
17797549 WF	115
	116	/*
	117	* compound pages: export both head/tail info
	118	* they together define a compound page's start/end pos and order
	119	*/
	120	if (PageHead(page))
	121	u \|= 1 << KPF_COMPOUND_HEAD;
	122	if (PageTail(page))
	123	u \|= 1 << KPF_COMPOUND_TAIL;
	124	if (PageHuge(page))
	125	u \|= 1 << KPF_HUGE;
7a71932d NH	126	/*
	127	* PageTransCompound can be true for non-huge compound pages (slab
	128	* pages or pages allocated by drivers with __GFP_COMP) because it
e3bba3c3 NH	129	* just checks PG_head/PG_tail, so we need to check PageLRU/PageAnon
e3bba3c3 NH	130	* to make sure a given page is a thp, not a non-huge compound page.
7a71932d	131	*/
56873f43 WY	132	else if (PageTransCompound(page)) {
	133	struct page *head = compound_head(page);
	134
	135	if (PageLRU(head) \|\| PageAnon(head))
	136	u \|= 1 << KPF_THP;
	137	else if (is_huge_zero_page(head)) {
	138	u \|= 1 << KPF_ZERO_PAGE;
	139	u \|= 1 << KPF_THP;
	140	}
	141	} else if (is_zero_pfn(page_to_pfn(page)))
	142	u \|= 1 << KPF_ZERO_PAGE;
	143
17797549	144
17797549	145	/*
0139aa7b	146	* Caveats on high order pages: page->_refcount will only be set
5f24ce5f AA	147	* -1 on the head page; SLUB/SLQB do the same for PG_slab;
5f24ce5f AA	148	* SLOB won't set PG_slab at all on compound pages.
17797549	149	*/
5f24ce5f AA	150	if (PageBuddy(page))
5f24ce5f AA	151	u \|= 1 << KPF_BUDDY;
832fc1de NH	152	else if (page_count(page) == 0 && is_free_buddy_page(page))
832fc1de NH	153	u \|= 1 << KPF_BUDDY;
5f24ce5f	154
ca215086 DH	155	if (PageOffline(page))
ca215086 DH	156	u \|= 1 << KPF_OFFLINE;
1d40a5ea MW	157	if (PageTable(page))
1d40a5ea MW	158	u \|= 1 << KPF_PGTABLE;
09316c09	159
f074a8f4 VD	160	if (page_is_idle(page))
	161	u \|= 1 << KPF_IDLE;
	162
5f24ce5f AA	163	u \|= kpf_copy_bit(k, KPF_LOCKED, PG_locked);
5f24ce5f AA	164
17797549	165	u \|= kpf_copy_bit(k, KPF_SLAB, PG_slab);
0a71649c NH	166	if (PageTail(page) && PageSlab(compound_head(page)))
0a71649c NH	167	u \|= 1 << KPF_SLAB;
17797549 WF	168
	169	u \|= kpf_copy_bit(k, KPF_ERROR, PG_error);
	170	u \|= kpf_copy_bit(k, KPF_DIRTY, PG_dirty);
	171	u \|= kpf_copy_bit(k, KPF_UPTODATE, PG_uptodate);
	172	u \|= kpf_copy_bit(k, KPF_WRITEBACK, PG_writeback);
	173
	174	u \|= kpf_copy_bit(k, KPF_LRU, PG_lru);
	175	u \|= kpf_copy_bit(k, KPF_REFERENCED, PG_referenced);
	176	u \|= kpf_copy_bit(k, KPF_ACTIVE, PG_active);
	177	u \|= kpf_copy_bit(k, KPF_RECLAIM, PG_reclaim);
	178
b6789123 HD	179	if (PageSwapCache(page))
b6789123 HD	180	u \|= 1 << KPF_SWAPCACHE;
17797549 WF	181	u \|= kpf_copy_bit(k, KPF_SWAPBACKED, PG_swapbacked);
17797549 WF	182
17797549 WF	183	u \|= kpf_copy_bit(k, KPF_UNEVICTABLE, PG_unevictable);
17797549 WF	184	u \|= kpf_copy_bit(k, KPF_MLOCKED, PG_mlocked);
17797549	185
253fb02d WF	186	#ifdef CONFIG_MEMORY_FAILURE
	187	u \|= kpf_copy_bit(k, KPF_HWPOISON, PG_hwpoison);
	188	#endif
	189
ed430fec	190	#ifdef CONFIG_ARCH_USES_PG_UNCACHED
17797549 WF	191	u \|= kpf_copy_bit(k, KPF_UNCACHED, PG_uncached);
	192	#endif
	193
	194	u \|= kpf_copy_bit(k, KPF_RESERVED, PG_reserved);
	195	u \|= kpf_copy_bit(k, KPF_MAPPEDTODISK, PG_mappedtodisk);
	196	u \|= kpf_copy_bit(k, KPF_PRIVATE, PG_private);
	197	u \|= kpf_copy_bit(k, KPF_PRIVATE_2, PG_private_2);
	198	u \|= kpf_copy_bit(k, KPF_OWNER_PRIVATE, PG_owner_priv_1);
	199	u \|= kpf_copy_bit(k, KPF_ARCH, PG_arch_1);
	200
	201	return u;
	202	};
6d80e53f AD	203
	204	static ssize_t kpageflags_read(struct file file, char __user buf,
	205	size_t count, loff_t *ppos)
	206	{
	207	u64 __user out = (u64 __user )buf;
	208	struct page *ppage;
	209	unsigned long src = *ppos;
	210	unsigned long pfn;
	211	ssize_t ret = 0;
6d80e53f AD	212
	213	pfn = src / KPMSIZE;
	214	count = min_t(unsigned long, count, (max_pfn * KPMSIZE) - src);
	215	if (src & KPMMASK \|\| count & KPMMASK)
	216	return -EINVAL;
	217
	218	while (count > 0) {
6d80e53f AD	219	if (pfn_valid(pfn))
6d80e53f AD	220	ppage = pfn_to_page(pfn);
ed7ce0f1 WF	221	else
ed7ce0f1 WF	222	ppage = NULL;
17797549	223
1a9b5b7f	224	if (put_user(stable_page_flags(ppage), out)) {
6d80e53f AD	225	ret = -EFAULT;
	226	break;
	227	}
	228
ed7ce0f1 WF	229	pfn++;
ed7ce0f1 WF	230	out++;
6d80e53f	231	count -= KPMSIZE;
d3691d2c VD	232
d3691d2c VD	233	cond_resched();
6d80e53f AD	234	}
	235
	236	ppos += (char __user )out - buf;
	237	if (!ret)
	238	ret = (char __user *)out - buf;
	239	return ret;
	240	}
	241
	242	static const struct file_operations proc_kpageflags_operations = {
	243	.llseek = mem_lseek,
	244	.read = kpageflags_read,
	245	};
	246
80ae2fdc VD	247	#ifdef CONFIG_MEMCG
	248	static ssize_t kpagecgroup_read(struct file file, char __user buf,
	249	size_t count, loff_t *ppos)
	250	{
	251	u64 __user out = (u64 __user )buf;
	252	struct page *ppage;
	253	unsigned long src = *ppos;
	254	unsigned long pfn;
	255	ssize_t ret = 0;
	256	u64 ino;
	257
	258	pfn = src / KPMSIZE;
	259	count = min_t(unsigned long, count, (max_pfn * KPMSIZE) - src);
	260	if (src & KPMMASK \|\| count & KPMMASK)
	261	return -EINVAL;
	262
	263	while (count > 0) {
	264	if (pfn_valid(pfn))
	265	ppage = pfn_to_page(pfn);
	266	else
	267	ppage = NULL;
	268
	269	if (ppage)
	270	ino = page_cgroup_ino(ppage);
	271	else
	272	ino = 0;
	273
	274	if (put_user(ino, out)) {
	275	ret = -EFAULT;
	276	break;
	277	}
	278
	279	pfn++;
	280	out++;
	281	count -= KPMSIZE;
d3691d2c VD	282
d3691d2c VD	283	cond_resched();
80ae2fdc VD	284	}
	285
	286	ppos += (char __user )out - buf;
	287	if (!ret)
	288	ret = (char __user *)out - buf;
	289	return ret;
	290	}
	291
	292	static const struct file_operations proc_kpagecgroup_operations = {
	293	.llseek = mem_lseek,
	294	.read = kpagecgroup_read,
	295	};
	296	#endif /* CONFIG_MEMCG */
	297
6d80e53f AD	298	static int __init proc_page_init(void)
	299	{
	300	proc_create("kpagecount", S_IRUSR, NULL, &proc_kpagecount_operations);
	301	proc_create("kpageflags", S_IRUSR, NULL, &proc_kpageflags_operations);
80ae2fdc VD	302	#ifdef CONFIG_MEMCG
	303	proc_create("kpagecgroup", S_IRUSR, NULL, &proc_kpagecgroup_operations);
	304	#endif
6d80e53f AD	305	return 0;
6d80e53f AD	306	}
abaf3787	307	fs_initcall(proc_page_init);