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

#include <linux/bootmem.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/kernel-page-flags.h>
#include <asm/uaccess.h>
#include "internal.h"

#define KPMSIZE sizeof(u64)
#define KPMMASK (KPMSIZE - 1)

/* /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))
			pcount = 0;
		else
			pcount = page_mapcount(ppage);

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

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

	*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->_count 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;

	if (PageBalloon(page))
		u |= 1 << KPF_BALLOON;

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

	u |= kpf_copy_bit(k, KPF_SLAB,		PG_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);

	u |= kpf_copy_bit(k, KPF_SWAPCACHE,	PG_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;
	}

	*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;
	}

	*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
6d80e53f AD	1	#include <linux/bootmem.h>
	2	#include <linux/compiler.h>
	3	#include <linux/fs.h>
	4	#include <linux/init.h>
9a840895	5	#include <linux/ksm.h>
6d80e53f AD	6	#include <linux/mm.h>
6d80e53f AD	7	#include <linux/mmzone.h>
56873f43	8	#include <linux/huge_mm.h>
6d80e53f AD	9	#include <linux/proc_fs.h>
6d80e53f AD	10	#include <linux/seq_file.h>
20a0307c	11	#include <linux/hugetlb.h>
80ae2fdc	12	#include <linux/memcontrol.h>
1a9b5b7f	13	#include <linux/kernel-page-flags.h>
6d80e53f AD	14	#include <asm/uaccess.h>
	15	#include "internal.h"
	16
	17	#define KPMSIZE sizeof(u64)
	18	#define KPMMASK (KPMSIZE - 1)
ed7ce0f1	19
6d80e53f AD	20	/* /proc/kpagecount - an array exposing page counts
	21	*
	22	* Each entry is a u64 representing the corresponding
	23	* physical page count.
	24	*/
	25	static ssize_t kpagecount_read(struct file file, char __user buf,
	26	size_t count, loff_t *ppos)
	27	{
	28	u64 __user out = (u64 __user )buf;
	29	struct page *ppage;
	30	unsigned long src = *ppos;
	31	unsigned long pfn;
	32	ssize_t ret = 0;
	33	u64 pcount;
	34
	35	pfn = src / KPMSIZE;
	36	count = min_t(size_t, count, (max_pfn * KPMSIZE) - src);
	37	if (src & KPMMASK \|\| count & KPMMASK)
	38	return -EINVAL;
	39
	40	while (count > 0) {
6d80e53f AD	41	if (pfn_valid(pfn))
6d80e53f AD	42	ppage = pfn_to_page(pfn);
ed7ce0f1 WF	43	else
ed7ce0f1 WF	44	ppage = NULL;
a6fc86d2	45	if (!ppage \|\| PageSlab(ppage))
6d80e53f AD	46	pcount = 0;
	47	else
	48	pcount = page_mapcount(ppage);
	49
ed7ce0f1	50	if (put_user(pcount, out)) {
6d80e53f AD	51	ret = -EFAULT;
	52	break;
	53	}
	54
ed7ce0f1 WF	55	pfn++;
ed7ce0f1 WF	56	out++;
6d80e53f AD	57	count -= KPMSIZE;
	58	}
	59
	60	ppos += (char __user )out - buf;
	61	if (!ret)
	62	ret = (char __user *)out - buf;
	63	return ret;
	64	}
	65
	66	static const struct file_operations proc_kpagecount_operations = {
	67	.llseek = mem_lseek,
	68	.read = kpagecount_read,
	69	};
	70
	71	/* /proc/kpageflags - an array exposing page flags
	72	*
	73	* Each entry is a u64 representing the corresponding
	74	* physical page flags.
	75	*/
	76
17797549 WF	77	static inline u64 kpf_copy_bit(u64 kflags, int ubit, int kbit)
	78	{
	79	return ((kflags >> kbit) & 1) << ubit;
	80	}
	81
1a9b5b7f	82	u64 stable_page_flags(struct page *page)
17797549 WF	83	{
	84	u64 k;
	85	u64 u;
	86
	87	/*
	88	* pseudo flag: KPF_NOPAGE
	89	* it differentiates a memory hole from a page with no flags
	90	*/
	91	if (!page)
	92	return 1 << KPF_NOPAGE;
	93
	94	k = page->flags;
	95	u = 0;
	96
	97	/*
	98	* pseudo flags for the well known (anonymous) memory mapped pages
	99	*
	100	* Note that page->_mapcount is overloaded in SLOB/SLUB/SLQB, so the
	101	* simple test in page_mapped() is not enough.
	102	*/
	103	if (!PageSlab(page) && page_mapped(page))
	104	u \|= 1 << KPF_MMAP;
	105	if (PageAnon(page))
	106	u \|= 1 << KPF_ANON;
9a840895 HD	107	if (PageKsm(page))
9a840895 HD	108	u \|= 1 << KPF_KSM;
17797549 WF	109
	110	/*
	111	* compound pages: export both head/tail info
	112	* they together define a compound page's start/end pos and order
	113	*/
	114	if (PageHead(page))
	115	u \|= 1 << KPF_COMPOUND_HEAD;
	116	if (PageTail(page))
	117	u \|= 1 << KPF_COMPOUND_TAIL;
	118	if (PageHuge(page))
	119	u \|= 1 << KPF_HUGE;
7a71932d NH	120	/*
	121	* PageTransCompound can be true for non-huge compound pages (slab
	122	* pages or pages allocated by drivers with __GFP_COMP) because it
e3bba3c3 NH	123	* just checks PG_head/PG_tail, so we need to check PageLRU/PageAnon
e3bba3c3 NH	124	* to make sure a given page is a thp, not a non-huge compound page.
7a71932d	125	*/
56873f43 WY	126	else if (PageTransCompound(page)) {
	127	struct page *head = compound_head(page);
	128
	129	if (PageLRU(head) \|\| PageAnon(head))
	130	u \|= 1 << KPF_THP;
	131	else if (is_huge_zero_page(head)) {
	132	u \|= 1 << KPF_ZERO_PAGE;
	133	u \|= 1 << KPF_THP;
	134	}
	135	} else if (is_zero_pfn(page_to_pfn(page)))
	136	u \|= 1 << KPF_ZERO_PAGE;
	137
17797549	138
17797549	139	/*
5f24ce5f AA	140	* Caveats on high order pages: page->_count will only be set
	141	* -1 on the head page; SLUB/SLQB do the same for PG_slab;
	142	* SLOB won't set PG_slab at all on compound pages.
17797549	143	*/
5f24ce5f AA	144	if (PageBuddy(page))
	145	u \|= 1 << KPF_BUDDY;
	146
09316c09 KK	147	if (PageBalloon(page))
	148	u \|= 1 << KPF_BALLOON;
	149
5f24ce5f AA	150	u \|= kpf_copy_bit(k, KPF_LOCKED, PG_locked);
5f24ce5f AA	151
17797549	152	u \|= kpf_copy_bit(k, KPF_SLAB, PG_slab);
17797549 WF	153
	154	u \|= kpf_copy_bit(k, KPF_ERROR, PG_error);
	155	u \|= kpf_copy_bit(k, KPF_DIRTY, PG_dirty);
	156	u \|= kpf_copy_bit(k, KPF_UPTODATE, PG_uptodate);
	157	u \|= kpf_copy_bit(k, KPF_WRITEBACK, PG_writeback);
	158
	159	u \|= kpf_copy_bit(k, KPF_LRU, PG_lru);
	160	u \|= kpf_copy_bit(k, KPF_REFERENCED, PG_referenced);
	161	u \|= kpf_copy_bit(k, KPF_ACTIVE, PG_active);
	162	u \|= kpf_copy_bit(k, KPF_RECLAIM, PG_reclaim);
	163
	164	u \|= kpf_copy_bit(k, KPF_SWAPCACHE, PG_swapcache);
	165	u \|= kpf_copy_bit(k, KPF_SWAPBACKED, PG_swapbacked);
	166
17797549 WF	167	u \|= kpf_copy_bit(k, KPF_UNEVICTABLE, PG_unevictable);
17797549 WF	168	u \|= kpf_copy_bit(k, KPF_MLOCKED, PG_mlocked);
17797549	169
253fb02d WF	170	#ifdef CONFIG_MEMORY_FAILURE
	171	u \|= kpf_copy_bit(k, KPF_HWPOISON, PG_hwpoison);
	172	#endif
	173
ed430fec	174	#ifdef CONFIG_ARCH_USES_PG_UNCACHED
17797549 WF	175	u \|= kpf_copy_bit(k, KPF_UNCACHED, PG_uncached);
	176	#endif
	177
	178	u \|= kpf_copy_bit(k, KPF_RESERVED, PG_reserved);
	179	u \|= kpf_copy_bit(k, KPF_MAPPEDTODISK, PG_mappedtodisk);
	180	u \|= kpf_copy_bit(k, KPF_PRIVATE, PG_private);
	181	u \|= kpf_copy_bit(k, KPF_PRIVATE_2, PG_private_2);
	182	u \|= kpf_copy_bit(k, KPF_OWNER_PRIVATE, PG_owner_priv_1);
	183	u \|= kpf_copy_bit(k, KPF_ARCH, PG_arch_1);
	184
	185	return u;
	186	};
6d80e53f AD	187
	188	static ssize_t kpageflags_read(struct file file, char __user buf,
	189	size_t count, loff_t *ppos)
	190	{
	191	u64 __user out = (u64 __user )buf;
	192	struct page *ppage;
	193	unsigned long src = *ppos;
	194	unsigned long pfn;
	195	ssize_t ret = 0;
6d80e53f AD	196
	197	pfn = src / KPMSIZE;
	198	count = min_t(unsigned long, count, (max_pfn * KPMSIZE) - src);
	199	if (src & KPMMASK \|\| count & KPMMASK)
	200	return -EINVAL;
	201
	202	while (count > 0) {
6d80e53f AD	203	if (pfn_valid(pfn))
6d80e53f AD	204	ppage = pfn_to_page(pfn);
ed7ce0f1 WF	205	else
ed7ce0f1 WF	206	ppage = NULL;
17797549	207
1a9b5b7f	208	if (put_user(stable_page_flags(ppage), out)) {
6d80e53f AD	209	ret = -EFAULT;
	210	break;
	211	}
	212
ed7ce0f1 WF	213	pfn++;
ed7ce0f1 WF	214	out++;
6d80e53f AD	215	count -= KPMSIZE;
	216	}
	217
	218	ppos += (char __user )out - buf;
	219	if (!ret)
	220	ret = (char __user *)out - buf;
	221	return ret;
	222	}
	223
	224	static const struct file_operations proc_kpageflags_operations = {
	225	.llseek = mem_lseek,
	226	.read = kpageflags_read,
	227	};
	228
80ae2fdc VD	229	#ifdef CONFIG_MEMCG
	230	static ssize_t kpagecgroup_read(struct file file, char __user buf,
	231	size_t count, loff_t *ppos)
	232	{
	233	u64 __user out = (u64 __user )buf;
	234	struct page *ppage;
	235	unsigned long src = *ppos;
	236	unsigned long pfn;
	237	ssize_t ret = 0;
	238	u64 ino;
	239
	240	pfn = src / KPMSIZE;
	241	count = min_t(unsigned long, count, (max_pfn * KPMSIZE) - src);
	242	if (src & KPMMASK \|\| count & KPMMASK)
	243	return -EINVAL;
	244
	245	while (count > 0) {
	246	if (pfn_valid(pfn))
	247	ppage = pfn_to_page(pfn);
	248	else
	249	ppage = NULL;
	250
	251	if (ppage)
	252	ino = page_cgroup_ino(ppage);
	253	else
	254	ino = 0;
	255
	256	if (put_user(ino, out)) {
	257	ret = -EFAULT;
	258	break;
	259	}
	260
	261	pfn++;
	262	out++;
	263	count -= KPMSIZE;
	264	}
	265
	266	ppos += (char __user )out - buf;
	267	if (!ret)
	268	ret = (char __user *)out - buf;
	269	return ret;
	270	}
	271
	272	static const struct file_operations proc_kpagecgroup_operations = {
	273	.llseek = mem_lseek,
	274	.read = kpagecgroup_read,
	275	};
	276	#endif /* CONFIG_MEMCG */
	277
6d80e53f AD	278	static int __init proc_page_init(void)
	279	{
	280	proc_create("kpagecount", S_IRUSR, NULL, &proc_kpagecount_operations);
	281	proc_create("kpageflags", S_IRUSR, NULL, &proc_kpageflags_operations);
80ae2fdc VD	282	#ifdef CONFIG_MEMCG
	283	proc_create("kpagecgroup", S_IRUSR, NULL, &proc_kpagecgroup_operations);
	284	#endif
6d80e53f AD	285	return 0;
6d80e53f AD	286	}
abaf3787	287	fs_initcall(proc_page_init);