[deliverable/linux.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/mmu_notifier.h>
#include <linux/page_idle.h>
#include <linux/kernel-page-flags.h>
#include <asm/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))
			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;

	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);

	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>
33c3fc71 VD	13	#include <linux/mmu_notifier.h>
33c3fc71 VD	14	#include <linux/page_idle.h>
1a9b5b7f	15	#include <linux/kernel-page-flags.h>
6d80e53f AD	16	#include <asm/uaccess.h>
	17	#include "internal.h"
	18
	19	#define KPMSIZE sizeof(u64)
	20	#define KPMMASK (KPMSIZE - 1)
33c3fc71	21	#define KPMBITS (KPMSIZE * BITS_PER_BYTE)
ed7ce0f1	22
6d80e53f AD	23	/* /proc/kpagecount - an array exposing page counts
	24	*
	25	* Each entry is a u64 representing the corresponding
	26	* physical page count.
	27	*/
	28	static ssize_t kpagecount_read(struct file file, char __user buf,
	29	size_t count, loff_t *ppos)
	30	{
	31	u64 __user out = (u64 __user )buf;
	32	struct page *ppage;
	33	unsigned long src = *ppos;
	34	unsigned long pfn;
	35	ssize_t ret = 0;
	36	u64 pcount;
	37
	38	pfn = src / KPMSIZE;
	39	count = min_t(size_t, count, (max_pfn * KPMSIZE) - src);
	40	if (src & KPMMASK \|\| count & KPMMASK)
	41	return -EINVAL;
	42
	43	while (count > 0) {
6d80e53f AD	44	if (pfn_valid(pfn))
6d80e53f AD	45	ppage = pfn_to_page(pfn);
ed7ce0f1 WF	46	else
ed7ce0f1 WF	47	ppage = NULL;
a6fc86d2	48	if (!ppage \|\| PageSlab(ppage))
6d80e53f AD	49	pcount = 0;
	50	else
	51	pcount = page_mapcount(ppage);
	52
ed7ce0f1	53	if (put_user(pcount, out)) {
6d80e53f AD	54	ret = -EFAULT;
	55	break;
	56	}
	57
ed7ce0f1 WF	58	pfn++;
ed7ce0f1 WF	59	out++;
6d80e53f AD	60	count -= KPMSIZE;
	61	}
	62
	63	ppos += (char __user )out - buf;
	64	if (!ret)
	65	ret = (char __user *)out - buf;
	66	return ret;
	67	}
	68
	69	static const struct file_operations proc_kpagecount_operations = {
	70	.llseek = mem_lseek,
	71	.read = kpagecount_read,
	72	};
	73
	74	/* /proc/kpageflags - an array exposing page flags
	75	*
	76	* Each entry is a u64 representing the corresponding
	77	* physical page flags.
	78	*/
	79
17797549 WF	80	static inline u64 kpf_copy_bit(u64 kflags, int ubit, int kbit)
	81	{
	82	return ((kflags >> kbit) & 1) << ubit;
	83	}
	84
1a9b5b7f	85	u64 stable_page_flags(struct page *page)
17797549 WF	86	{
	87	u64 k;
	88	u64 u;
	89
	90	/*
	91	* pseudo flag: KPF_NOPAGE
	92	* it differentiates a memory hole from a page with no flags
	93	*/
	94	if (!page)
	95	return 1 << KPF_NOPAGE;
	96
	97	k = page->flags;
	98	u = 0;
	99
	100	/*
	101	* pseudo flags for the well known (anonymous) memory mapped pages
	102	*
	103	* Note that page->_mapcount is overloaded in SLOB/SLUB/SLQB, so the
	104	* simple test in page_mapped() is not enough.
	105	*/
	106	if (!PageSlab(page) && page_mapped(page))
	107	u \|= 1 << KPF_MMAP;
	108	if (PageAnon(page))
	109	u \|= 1 << KPF_ANON;
9a840895 HD	110	if (PageKsm(page))
9a840895 HD	111	u \|= 1 << KPF_KSM;
17797549 WF	112
	113	/*
	114	* compound pages: export both head/tail info
	115	* they together define a compound page's start/end pos and order
	116	*/
	117	if (PageHead(page))
	118	u \|= 1 << KPF_COMPOUND_HEAD;
	119	if (PageTail(page))
	120	u \|= 1 << KPF_COMPOUND_TAIL;
	121	if (PageHuge(page))
	122	u \|= 1 << KPF_HUGE;
7a71932d NH	123	/*
	124	* PageTransCompound can be true for non-huge compound pages (slab
	125	* pages or pages allocated by drivers with __GFP_COMP) because it
e3bba3c3 NH	126	* just checks PG_head/PG_tail, so we need to check PageLRU/PageAnon
e3bba3c3 NH	127	* to make sure a given page is a thp, not a non-huge compound page.
7a71932d	128	*/
56873f43 WY	129	else if (PageTransCompound(page)) {
	130	struct page *head = compound_head(page);
	131
	132	if (PageLRU(head) \|\| PageAnon(head))
	133	u \|= 1 << KPF_THP;
	134	else if (is_huge_zero_page(head)) {
	135	u \|= 1 << KPF_ZERO_PAGE;
	136	u \|= 1 << KPF_THP;
	137	}
	138	} else if (is_zero_pfn(page_to_pfn(page)))
	139	u \|= 1 << KPF_ZERO_PAGE;
	140
17797549	141
17797549	142	/*
5f24ce5f AA	143	* Caveats on high order pages: page->_count will only be set
	144	* -1 on the head page; SLUB/SLQB do the same for PG_slab;
	145	* SLOB won't set PG_slab at all on compound pages.
17797549	146	*/
5f24ce5f AA	147	if (PageBuddy(page))
	148	u \|= 1 << KPF_BUDDY;
	149
09316c09 KK	150	if (PageBalloon(page))
	151	u \|= 1 << KPF_BALLOON;
	152
f074a8f4 VD	153	if (page_is_idle(page))
	154	u \|= 1 << KPF_IDLE;
	155
5f24ce5f AA	156	u \|= kpf_copy_bit(k, KPF_LOCKED, PG_locked);
5f24ce5f AA	157
17797549	158	u \|= kpf_copy_bit(k, KPF_SLAB, PG_slab);
17797549 WF	159
	160	u \|= kpf_copy_bit(k, KPF_ERROR, PG_error);
	161	u \|= kpf_copy_bit(k, KPF_DIRTY, PG_dirty);
	162	u \|= kpf_copy_bit(k, KPF_UPTODATE, PG_uptodate);
	163	u \|= kpf_copy_bit(k, KPF_WRITEBACK, PG_writeback);
	164
	165	u \|= kpf_copy_bit(k, KPF_LRU, PG_lru);
	166	u \|= kpf_copy_bit(k, KPF_REFERENCED, PG_referenced);
	167	u \|= kpf_copy_bit(k, KPF_ACTIVE, PG_active);
	168	u \|= kpf_copy_bit(k, KPF_RECLAIM, PG_reclaim);
	169
	170	u \|= kpf_copy_bit(k, KPF_SWAPCACHE, PG_swapcache);
	171	u \|= kpf_copy_bit(k, KPF_SWAPBACKED, PG_swapbacked);
	172
17797549 WF	173	u \|= kpf_copy_bit(k, KPF_UNEVICTABLE, PG_unevictable);
17797549 WF	174	u \|= kpf_copy_bit(k, KPF_MLOCKED, PG_mlocked);
17797549	175
253fb02d WF	176	#ifdef CONFIG_MEMORY_FAILURE
	177	u \|= kpf_copy_bit(k, KPF_HWPOISON, PG_hwpoison);
	178	#endif
	179
ed430fec	180	#ifdef CONFIG_ARCH_USES_PG_UNCACHED
17797549 WF	181	u \|= kpf_copy_bit(k, KPF_UNCACHED, PG_uncached);
	182	#endif
	183
	184	u \|= kpf_copy_bit(k, KPF_RESERVED, PG_reserved);
	185	u \|= kpf_copy_bit(k, KPF_MAPPEDTODISK, PG_mappedtodisk);
	186	u \|= kpf_copy_bit(k, KPF_PRIVATE, PG_private);
	187	u \|= kpf_copy_bit(k, KPF_PRIVATE_2, PG_private_2);
	188	u \|= kpf_copy_bit(k, KPF_OWNER_PRIVATE, PG_owner_priv_1);
	189	u \|= kpf_copy_bit(k, KPF_ARCH, PG_arch_1);
	190
	191	return u;
	192	};
6d80e53f AD	193
	194	static ssize_t kpageflags_read(struct file file, char __user buf,
	195	size_t count, loff_t *ppos)
	196	{
	197	u64 __user out = (u64 __user )buf;
	198	struct page *ppage;
	199	unsigned long src = *ppos;
	200	unsigned long pfn;
	201	ssize_t ret = 0;
6d80e53f AD	202
	203	pfn = src / KPMSIZE;
	204	count = min_t(unsigned long, count, (max_pfn * KPMSIZE) - src);
	205	if (src & KPMMASK \|\| count & KPMMASK)
	206	return -EINVAL;
	207
	208	while (count > 0) {
6d80e53f AD	209	if (pfn_valid(pfn))
6d80e53f AD	210	ppage = pfn_to_page(pfn);
ed7ce0f1 WF	211	else
ed7ce0f1 WF	212	ppage = NULL;
17797549	213
1a9b5b7f	214	if (put_user(stable_page_flags(ppage), out)) {
6d80e53f AD	215	ret = -EFAULT;
	216	break;
	217	}
	218
ed7ce0f1 WF	219	pfn++;
ed7ce0f1 WF	220	out++;
6d80e53f AD	221	count -= KPMSIZE;
	222	}
	223
	224	ppos += (char __user )out - buf;
	225	if (!ret)
	226	ret = (char __user *)out - buf;
	227	return ret;
	228	}
	229
	230	static const struct file_operations proc_kpageflags_operations = {
	231	.llseek = mem_lseek,
	232	.read = kpageflags_read,
	233	};
	234
80ae2fdc VD	235	#ifdef CONFIG_MEMCG
	236	static ssize_t kpagecgroup_read(struct file file, char __user buf,
	237	size_t count, loff_t *ppos)
	238	{
	239	u64 __user out = (u64 __user )buf;
	240	struct page *ppage;
	241	unsigned long src = *ppos;
	242	unsigned long pfn;
	243	ssize_t ret = 0;
	244	u64 ino;
	245
	246	pfn = src / KPMSIZE;
	247	count = min_t(unsigned long, count, (max_pfn * KPMSIZE) - src);
	248	if (src & KPMMASK \|\| count & KPMMASK)
	249	return -EINVAL;
	250
	251	while (count > 0) {
	252	if (pfn_valid(pfn))
	253	ppage = pfn_to_page(pfn);
	254	else
	255	ppage = NULL;
	256
	257	if (ppage)
	258	ino = page_cgroup_ino(ppage);
	259	else
	260	ino = 0;
	261
	262	if (put_user(ino, out)) {
	263	ret = -EFAULT;
	264	break;
	265	}
	266
	267	pfn++;
	268	out++;
	269	count -= KPMSIZE;
	270	}
	271
	272	ppos += (char __user )out - buf;
	273	if (!ret)
	274	ret = (char __user *)out - buf;
	275	return ret;
	276	}
	277
	278	static const struct file_operations proc_kpagecgroup_operations = {
	279	.llseek = mem_lseek,
	280	.read = kpagecgroup_read,
	281	};
	282	#endif /* CONFIG_MEMCG */
	283
6d80e53f AD	284	static int __init proc_page_init(void)
	285	{
	286	proc_create("kpagecount", S_IRUSR, NULL, &proc_kpagecount_operations);
	287	proc_create("kpageflags", S_IRUSR, NULL, &proc_kpageflags_operations);
80ae2fdc VD	288	#ifdef CONFIG_MEMCG
	289	proc_create("kpagecgroup", S_IRUSR, NULL, &proc_kpagecgroup_operations);
	290	#endif
6d80e53f AD	291	return 0;
6d80e53f AD	292	}
abaf3787	293	fs_initcall(proc_page_init);