aboutsummaryrefslogtreecommitdiffstats
path: root/include/asm-sparc64/page.h
blob: b87dbbd64bc9ca723e3077521cb5cd87af63906e (plain) (blame)
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
/* $Id: page.h,v 1.39 2002/02/09 19:49:31 davem Exp $ */

#ifndef _SPARC64_PAGE_H
#define _SPARC64_PAGE_H

#include <linux/config.h>
#include <asm/const.h>

#if defined(CONFIG_SPARC64_PAGE_SIZE_8KB)
#define PAGE_SHIFT   13
#elif defined(CONFIG_SPARC64_PAGE_SIZE_64KB)
#define PAGE_SHIFT   16
#elif defined(CONFIG_SPARC64_PAGE_SIZE_512KB)
#define PAGE_SHIFT   19
#elif defined(CONFIG_SPARC64_PAGE_SIZE_4MB)
#define PAGE_SHIFT   22
#else
#error No page size specified in kernel configuration
#endif

#define PAGE_SIZE    (_AC(1,UL) << PAGE_SHIFT)
#define PAGE_MASK    (~(PAGE_SIZE-1))

#ifdef __KERNEL__

#ifndef __ASSEMBLY__

extern void _clear_page(void *page);
#define clear_page(X)	_clear_page((void *)(X))
struct page;
extern void clear_user_page(void *addr, unsigned long vaddr, struct page *page);
#define copy_page(X,Y)	memcpy((void *)(X), (void *)(Y), PAGE_SIZE)
extern void copy_user_page(void *to, void *from, unsigned long vaddr, struct page *topage);

/* Unlike sparc32, sparc64's parameter passing API is more
 * sane in that structures which as small enough are passed
 * in registers instead of on the stack.  Thus, setting
 * STRICT_MM_TYPECHECKS does not generate worse code so
 * let's enable it to get the type checking.
 */

#define STRICT_MM_TYPECHECKS

#ifdef STRICT_MM_TYPECHECKS
/* These are used to make use of C type-checking.. */
typedef struct { unsigned long pte; } pte_t;
typedef struct { unsigned long iopte; } iopte_t;
typedef struct { unsigned int pmd; } pmd_t;
typedef struct { unsigned int pgd; } pgd_t;
typedef struct { unsigned long pgprot; } pgprot_t;

#define pte_val(x)	((x).pte)
#define iopte_val(x)	((x).iopte)
#define pmd_val(x)      ((x).pmd)
#define pgd_val(x)	((x).pgd)
#define pgprot_val(x)	((x).pgprot)

#define __pte(x)	((pte_t) { (x) } )
#define __iopte(x)	((iopte_t) { (x) } )
#define __pmd(x)        ((pmd_t) { (x) } )
#define __pgd(x)	((pgd_t) { (x) } )
#define __pgprot(x)	((pgprot_t) { (x) } )

#else
/* .. while these make it easier on the compiler */
typedef unsigned long pte_t;
typedef unsigned long iopte_t;
typedef unsigned int pmd_t;
typedef unsigned int pgd_t;
typedef unsigned long pgprot_t;

#define pte_val(x)	(x)
#define iopte_val(x)	(x)
#define pmd_val(x)      (x)
#define pgd_val(x)	(x)
#define pgprot_val(x)	(x)

#define __pte(x)	(x)
#define __iopte(x)	(x)
#define __pmd(x)        (x)
#define __pgd(x)	(x)
#define __pgprot(x)	(x)

#endif /* (STRICT_MM_TYPECHECKS) */

#if defined(CONFIG_HUGETLB_PAGE_SIZE_4MB)
#define HPAGE_SHIFT		22
#elif defined(CONFIG_HUGETLB_PAGE_SIZE_512K)
#define HPAGE_SHIFT		19
#elif defined(CONFIG_HUGETLB_PAGE_SIZE_64K)
#define HPAGE_SHIFT		16
#endif

#ifdef CONFIG_HUGETLB_PAGE
#define HPAGE_SIZE		(_AC(1,UL) << HPAGE_SHIFT)
#define HPAGE_MASK		(~(HPAGE_SIZE - 1UL))
#define HUGETLB_PAGE_ORDER	(HPAGE_SHIFT - PAGE_SHIFT)
#define ARCH_HAS_SETCLEAR_HUGE_PTE
#define ARCH_HAS_HUGETLB_PREFAULT_HOOK
#endif

#define TASK_UNMAPPED_BASE	(test_thread_flag(TIF_32BIT) ? \
				 (_AC(0x0000000070000000,UL)) : (PAGE_OFFSET))

#endif /* !(__ASSEMBLY__) */

/* to align the pointer to the (next) page boundary */
#define PAGE_ALIGN(addr)	(((addr)+PAGE_SIZE-1)&PAGE_MASK)

/* We used to stick this into a hard-coded global register (%g4)
 * but that does not make sense anymore.
 */
#define PAGE_OFFSET		_AC(0xFFFFF80000000000,UL)

#ifndef __ASSEMBLY__

#define __pa(x)			((unsigned long)(x) - PAGE_OFFSET)
#define __va(x)			((void *)((unsigned long) (x) + PAGE_OFFSET))

/* PFNs are real physical page numbers.  However, mem_map only begins to record
 * per-page information starting at pfn_base.  This is to handle systems where
 * the first physical page in the machine is at some huge physical address,
 * such as 4GB.   This is common on a partitioned E10000, for example.
 */
extern struct page *pfn_to_page(unsigned long pfn);
extern unsigned long page_to_pfn(struct page *);

#define virt_to_page(kaddr)	pfn_to_page(__pa(kaddr)>>PAGE_SHIFT)

#define pfn_valid(pfn)		(((pfn)-(pfn_base)) < max_mapnr)
#define virt_addr_valid(kaddr)	pfn_valid(__pa(kaddr) >> PAGE_SHIFT)

#define virt_to_phys __pa
#define phys_to_virt __va

/* The following structure is used to hold the physical
 * memory configuration of the machine.  This is filled in
 * probe_memory() and is later used by mem_init() to set up
 * mem_map[].  We statically allocate SPARC_PHYS_BANKS of
 * these structs, this is arbitrary.  The entry after the
 * last valid one has num_bytes==0.
 */

struct sparc_phys_banks {
	unsigned long base_addr;
	unsigned long num_bytes;
};

#define SPARC_PHYS_BANKS 32

extern struct sparc_phys_banks sp_banks[SPARC_PHYS_BANKS];

/* Pure 2^n version of get_order */
static __inline__ int get_order(unsigned long size)
{
	int order;

	size = (size-1) >> (PAGE_SHIFT-1);
	order = -1;
	do {
		size >>= 1;
		order++;
	} while (size);
	return order;
}

#endif /* !(__ASSEMBLY__) */

#define VM_DATA_DEFAULT_FLAGS	(VM_READ | VM_WRITE | VM_EXEC | \
				 VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)

#endif /* !(__KERNEL__) */

#endif /* !(_SPARC64_PAGE_H) */
52'>552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307
#ifndef _LINUX_MM_H
#define _LINUX_MM_H

#include <linux/errno.h>

#ifdef __KERNEL__

#include <linux/gfp.h>
#include <linux/list.h>
#include <linux/mmzone.h>
#include <linux/rbtree.h>
#include <linux/prio_tree.h>
#include <linux/debug_locks.h>
#include <linux/mm_types.h>

struct mempolicy;
struct anon_vma;
struct file_ra_state;
struct user_struct;
struct writeback_control;
struct rlimit;

#ifndef CONFIG_DISCONTIGMEM          /* Don't use mapnrs, do it properly */
extern unsigned long max_mapnr;
#endif

extern unsigned long num_physpages;
extern void * high_memory;
extern int page_cluster;

#ifdef CONFIG_SYSCTL
extern int sysctl_legacy_va_layout;
#else
#define sysctl_legacy_va_layout 0
#endif

#include <asm/page.h>
#include <asm/pgtable.h>
#include <asm/processor.h>

#define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n))

/* to align the pointer to the (next) page boundary */
#define PAGE_ALIGN(addr) ALIGN(addr, PAGE_SIZE)

/*
 * Linux kernel virtual memory manager primitives.
 * The idea being to have a "virtual" mm in the same way
 * we have a virtual fs - giving a cleaner interface to the
 * mm details, and allowing different kinds of memory mappings
 * (from shared memory to executable loading to arbitrary
 * mmap() functions).
 */

extern struct kmem_cache *vm_area_cachep;

#ifndef CONFIG_MMU
extern struct rb_root nommu_region_tree;
extern struct rw_semaphore nommu_region_sem;

extern unsigned int kobjsize(const void *objp);
#endif

/*
 * vm_flags in vm_area_struct, see mm_types.h.
 */
#define VM_READ		0x00000001	/* currently active flags */
#define VM_WRITE	0x00000002
#define VM_EXEC		0x00000004
#define VM_SHARED	0x00000008

/* mprotect() hardcodes VM_MAYREAD >> 4 == VM_READ, and so for r/w/x bits. */
#define VM_MAYREAD	0x00000010	/* limits for mprotect() etc */
#define VM_MAYWRITE	0x00000020
#define VM_MAYEXEC	0x00000040
#define VM_MAYSHARE	0x00000080

#define VM_GROWSDOWN	0x00000100	/* general info on the segment */
#define VM_GROWSUP	0x00000200
#define VM_PFNMAP	0x00000400	/* Page-ranges managed without "struct page", just pure PFN */
#define VM_DENYWRITE	0x00000800	/* ETXTBSY on write attempts.. */

#define VM_EXECUTABLE	0x00001000
#define VM_LOCKED	0x00002000
#define VM_IO           0x00004000	/* Memory mapped I/O or similar */

					/* Used by sys_madvise() */
#define VM_SEQ_READ	0x00008000	/* App will access data sequentially */
#define VM_RAND_READ	0x00010000	/* App will not benefit from clustered reads */

#define VM_DONTCOPY	0x00020000      /* Do not copy this vma on fork */
#define VM_DONTEXPAND	0x00040000	/* Cannot expand with mremap() */
#define VM_RESERVED	0x00080000	/* Count as reserved_vm like IO */
#define VM_ACCOUNT	0x00100000	/* Is a VM accounted object */
#define VM_NORESERVE	0x00200000	/* should the VM suppress accounting */
#define VM_HUGETLB	0x00400000	/* Huge TLB Page VM */
#define VM_NONLINEAR	0x00800000	/* Is non-linear (remap_file_pages) */
#define VM_MAPPED_COPY	0x01000000	/* T if mapped copy of data (nommu mmap) */
#define VM_INSERTPAGE	0x02000000	/* The vma has had "vm_insert_page()" done on it */
#define VM_ALWAYSDUMP	0x04000000	/* Always include in core dumps */

#define VM_CAN_NONLINEAR 0x08000000	/* Has ->fault & does nonlinear pages */
#define VM_MIXEDMAP	0x10000000	/* Can contain "struct page" and pure PFN pages */
#define VM_SAO		0x20000000	/* Strong Access Ordering (powerpc) */
#define VM_PFN_AT_MMAP	0x40000000	/* PFNMAP vma that is fully mapped at mmap time */

#ifndef VM_STACK_DEFAULT_FLAGS		/* arch can override this */
#define VM_STACK_DEFAULT_FLAGS VM_DATA_DEFAULT_FLAGS
#endif

#ifdef CONFIG_STACK_GROWSUP
#define VM_STACK_FLAGS	(VM_GROWSUP | VM_STACK_DEFAULT_FLAGS | VM_ACCOUNT)
#else
#define VM_STACK_FLAGS	(VM_GROWSDOWN | VM_STACK_DEFAULT_FLAGS | VM_ACCOUNT)
#endif

#define VM_READHINTMASK			(VM_SEQ_READ | VM_RAND_READ)
#define VM_ClearReadHint(v)		(v)->vm_flags &= ~VM_READHINTMASK
#define VM_NormalReadHint(v)		(!((v)->vm_flags & VM_READHINTMASK))
#define VM_SequentialReadHint(v)	((v)->vm_flags & VM_SEQ_READ)
#define VM_RandomReadHint(v)		((v)->vm_flags & VM_RAND_READ)

/*
 * special vmas that are non-mergable, non-mlock()able
 */
#define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_RESERVED | VM_PFNMAP)

/*
 * mapping from the currently active vm_flags protection bits (the
 * low four bits) to a page protection mask..
 */
extern pgprot_t protection_map[16];

#define FAULT_FLAG_WRITE	0x01	/* Fault was a write access */
#define FAULT_FLAG_NONLINEAR	0x02	/* Fault was via a nonlinear mapping */
#define FAULT_FLAG_MKWRITE	0x04	/* Fault was mkwrite of existing pte */

/*
 * This interface is used by x86 PAT code to identify a pfn mapping that is
 * linear over entire vma. This is to optimize PAT code that deals with
 * marking the physical region with a particular prot. This is not for generic
 * mm use. Note also that this check will not work if the pfn mapping is
 * linear for a vma starting at physical address 0. In which case PAT code
 * falls back to slow path of reserving physical range page by page.
 */
static inline int is_linear_pfn_mapping(struct vm_area_struct *vma)
{
	return (vma->vm_flags & VM_PFN_AT_MMAP);
}

static inline int is_pfn_mapping(struct vm_area_struct *vma)
{
	return (vma->vm_flags & VM_PFNMAP);
}

/*
 * vm_fault is filled by the the pagefault handler and passed to the vma's
 * ->fault function. The vma's ->fault is responsible for returning a bitmask
 * of VM_FAULT_xxx flags that give details about how the fault was handled.
 *
 * pgoff should be used in favour of virtual_address, if possible. If pgoff
 * is used, one may set VM_CAN_NONLINEAR in the vma->vm_flags to get nonlinear
 * mapping support.
 */
struct vm_fault {
	unsigned int flags;		/* FAULT_FLAG_xxx flags */
	pgoff_t pgoff;			/* Logical page offset based on vma */
	void __user *virtual_address;	/* Faulting virtual address */

	struct page *page;		/* ->fault handlers should return a
					 * page here, unless VM_FAULT_NOPAGE
					 * is set (which is also implied by
					 * VM_FAULT_ERROR).
					 */
};

/*
 * These are the virtual MM functions - opening of an area, closing and
 * unmapping it (needed to keep files on disk up-to-date etc), pointer
 * to the functions called when a no-page or a wp-page exception occurs. 
 */
struct vm_operations_struct {
	void (*open)(struct vm_area_struct * area);
	void (*close)(struct vm_area_struct * area);
	int (*fault)(struct vm_area_struct *vma, struct vm_fault *vmf);

	/* notification that a previously read-only page is about to become
	 * writable, if an error is returned it will cause a SIGBUS */
	int (*page_mkwrite)(struct vm_area_struct *vma, struct vm_fault *vmf);

	/* called by access_process_vm when get_user_pages() fails, typically
	 * for use by special VMAs that can switch between memory and hardware
	 */
	int (*access)(struct vm_area_struct *vma, unsigned long addr,
		      void *buf, int len, int write);
#ifdef CONFIG_NUMA
	/*
	 * set_policy() op must add a reference to any non-NULL @new mempolicy
	 * to hold the policy upon return.  Caller should pass NULL @new to
	 * remove a policy and fall back to surrounding context--i.e. do not
	 * install a MPOL_DEFAULT policy, nor the task or system default
	 * mempolicy.
	 */
	int (*set_policy)(struct vm_area_struct *vma, struct mempolicy *new);

	/*
	 * get_policy() op must add reference [mpol_get()] to any policy at
	 * (vma,addr) marked as MPOL_SHARED.  The shared policy infrastructure
	 * in mm/mempolicy.c will do this automatically.
	 * get_policy() must NOT add a ref if the policy at (vma,addr) is not
	 * marked as MPOL_SHARED. vma policies are protected by the mmap_sem.
	 * If no [shared/vma] mempolicy exists at the addr, get_policy() op
	 * must return NULL--i.e., do not "fallback" to task or system default
	 * policy.
	 */
	struct mempolicy *(*get_policy)(struct vm_area_struct *vma,
					unsigned long addr);
	int (*migrate)(struct vm_area_struct *vma, const nodemask_t *from,
		const nodemask_t *to, unsigned long flags);
#endif
};

struct mmu_gather;
struct inode;

#define page_private(page)		((page)->private)
#define set_page_private(page, v)	((page)->private = (v))

/*
 * FIXME: take this include out, include page-flags.h in
 * files which need it (119 of them)
 */
#include <linux/page-flags.h>

/*
 * Methods to modify the page usage count.
 *
 * What counts for a page usage:
 * - cache mapping   (page->mapping)
 * - private data    (page->private)
 * - page mapped in a task's page tables, each mapping
 *   is counted separately
 *
 * Also, many kernel routines increase the page count before a critical
 * routine so they can be sure the page doesn't go away from under them.
 */

/*
 * Drop a ref, return true if the refcount fell to zero (the page has no users)
 */
static inline int put_page_testzero(struct page *page)
{
	VM_BUG_ON(atomic_read(&page->_count) == 0);
	return atomic_dec_and_test(&page->_count);
}

/*
 * Try to grab a ref unless the page has a refcount of zero, return false if
 * that is the case.
 */
static inline int get_page_unless_zero(struct page *page)
{
	return atomic_inc_not_zero(&page->_count);
}

/* Support for virtually mapped pages */
struct page *vmalloc_to_page(const void *addr);
unsigned long vmalloc_to_pfn(const void *addr);

/*
 * Determine if an address is within the vmalloc range
 *
 * On nommu, vmalloc/vfree wrap through kmalloc/kfree directly, so there
 * is no special casing required.
 */
static inline int is_vmalloc_addr(const void *x)
{
#ifdef CONFIG_MMU
	unsigned long addr = (unsigned long)x;

	return addr >= VMALLOC_START && addr < VMALLOC_END;
#else
	return 0;
#endif
}

static inline struct page *compound_head(struct page *page)
{
	if (unlikely(PageTail(page)))
		return page->first_page;
	return page;
}

static inline int page_count(struct page *page)
{
	return atomic_read(&compound_head(page)->_count);
}

static inline void get_page(struct page *page)
{
	page = compound_head(page);
	VM_BUG_ON(atomic_read(&page->_count) == 0);
	atomic_inc(&page->_count);
}

static inline struct page *virt_to_head_page(const void *x)
{
	struct page *page = virt_to_page(x);
	return compound_head(page);
}

/*
 * Setup the page count before being freed into the page allocator for
 * the first time (boot or memory hotplug)
 */
static inline void init_page_count(struct page *page)
{
	atomic_set(&page->_count, 1);
}

void put_page(struct page *page);
void put_pages_list(struct list_head *pages);

void split_page(struct page *page, unsigned int order);

/*
 * Compound pages have a destructor function.  Provide a
 * prototype for that function and accessor functions.
 * These are _only_ valid on the head of a PG_compound page.
 */
typedef void compound_page_dtor(struct page *);

static inline void set_compound_page_dtor(struct page *page,
						compound_page_dtor *dtor)
{
	page[1].lru.next = (void *)dtor;
}

static inline compound_page_dtor *get_compound_page_dtor(struct page *page)
{
	return (compound_page_dtor *)page[1].lru.next;
}

static inline int compound_order(struct page *page)
{
	if (!PageHead(page))
		return 0;
	return (unsigned long)page[1].lru.prev;
}

static inline void set_compound_order(struct page *page, unsigned long order)
{
	page[1].lru.prev = (void *)order;
}

/*
 * Multiple processes may "see" the same page. E.g. for untouched
 * mappings of /dev/null, all processes see the same page full of
 * zeroes, and text pages of executables and shared libraries have
 * only one copy in memory, at most, normally.
 *
 * For the non-reserved pages, page_count(page) denotes a reference count.
 *   page_count() == 0 means the page is free. page->lru is then used for
 *   freelist management in the buddy allocator.
 *   page_count() > 0  means the page has been allocated.
 *
 * Pages are allocated by the slab allocator in order to provide memory
 * to kmalloc and kmem_cache_alloc. In this case, the management of the
 * page, and the fields in 'struct page' are the responsibility of mm/slab.c
 * unless a particular usage is carefully commented. (the responsibility of
 * freeing the kmalloc memory is the caller's, of course).
 *
 * A page may be used by anyone else who does a __get_free_page().
 * In this case, page_count still tracks the references, and should only
 * be used through the normal accessor functions. The top bits of page->flags
 * and page->virtual store page management information, but all other fields
 * are unused and could be used privately, carefully. The management of this
 * page is the responsibility of the one who allocated it, and those who have
 * subsequently been given references to it.
 *
 * The other pages (we may call them "pagecache pages") are completely
 * managed by the Linux memory manager: I/O, buffers, swapping etc.
 * The following discussion applies only to them.
 *
 * A pagecache page contains an opaque `private' member, which belongs to the
 * page's address_space. Usually, this is the address of a circular list of
 * the page's disk buffers. PG_private must be set to tell the VM to call
 * into the filesystem to release these pages.
 *
 * A page may belong to an inode's memory mapping. In this case, page->mapping
 * is the pointer to the inode, and page->index is the file offset of the page,
 * in units of PAGE_CACHE_SIZE.
 *
 * If pagecache pages are not associated with an inode, they are said to be
 * anonymous pages. These may become associated with the swapcache, and in that
 * case PG_swapcache is set, and page->private is an offset into the swapcache.
 *
 * In either case (swapcache or inode backed), the pagecache itself holds one
 * reference to the page. Setting PG_private should also increment the
 * refcount. The each user mapping also has a reference to the page.
 *
 * The pagecache pages are stored in a per-mapping radix tree, which is
 * rooted at mapping->page_tree, and indexed by offset.
 * Where 2.4 and early 2.6 kernels kept dirty/clean pages in per-address_space
 * lists, we instead now tag pages as dirty/writeback in the radix tree.
 *
 * All pagecache pages may be subject to I/O:
 * - inode pages may need to be read from disk,
 * - inode pages which have been modified and are MAP_SHARED may need
 *   to be written back to the inode on disk,
 * - anonymous pages (including MAP_PRIVATE file mappings) which have been
 *   modified may need to be swapped out to swap space and (later) to be read
 *   back into memory.
 */

/*
 * The zone field is never updated after free_area_init_core()
 * sets it, so none of the operations on it need to be atomic.
 */


/*
 * page->flags layout:
 *
 * There are three possibilities for how page->flags get
 * laid out.  The first is for the normal case, without
 * sparsemem.  The second is for sparsemem when there is
 * plenty of space for node and section.  The last is when
 * we have run out of space and have to fall back to an
 * alternate (slower) way of determining the node.
 *
 * No sparsemem or sparsemem vmemmap: |       NODE     | ZONE | ... | FLAGS |
 * classic sparse with space for node:| SECTION | NODE | ZONE | ... | FLAGS |
 * classic sparse no space for node:  | SECTION |     ZONE    | ... | FLAGS |
 */
#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP)
#define SECTIONS_WIDTH		SECTIONS_SHIFT
#else
#define SECTIONS_WIDTH		0
#endif

#define ZONES_WIDTH		ZONES_SHIFT

#if SECTIONS_WIDTH+ZONES_WIDTH+NODES_SHIFT <= BITS_PER_LONG - NR_PAGEFLAGS
#define NODES_WIDTH		NODES_SHIFT
#else
#ifdef CONFIG_SPARSEMEM_VMEMMAP
#error "Vmemmap: No space for nodes field in page flags"
#endif
#define NODES_WIDTH		0
#endif

/* Page flags: | [SECTION] | [NODE] | ZONE | ... | FLAGS | */
#define SECTIONS_PGOFF		((sizeof(unsigned long)*8) - SECTIONS_WIDTH)
#define NODES_PGOFF		(SECTIONS_PGOFF - NODES_WIDTH)
#define ZONES_PGOFF		(NODES_PGOFF - ZONES_WIDTH)

/*
 * We are going to use the flags for the page to node mapping if its in
 * there.  This includes the case where there is no node, so it is implicit.
 */
#if !(NODES_WIDTH > 0 || NODES_SHIFT == 0)
#define NODE_NOT_IN_PAGE_FLAGS
#endif

#ifndef PFN_SECTION_SHIFT
#define PFN_SECTION_SHIFT 0
#endif

/*
 * Define the bit shifts to access each section.  For non-existant
 * sections we define the shift as 0; that plus a 0 mask ensures
 * the compiler will optimise away reference to them.
 */
#define SECTIONS_PGSHIFT	(SECTIONS_PGOFF * (SECTIONS_WIDTH != 0))
#define NODES_PGSHIFT		(NODES_PGOFF * (NODES_WIDTH != 0))
#define ZONES_PGSHIFT		(ZONES_PGOFF * (ZONES_WIDTH != 0))

/* NODE:ZONE or SECTION:ZONE is used to ID a zone for the buddy allcator */
#ifdef NODE_NOT_IN_PAGEFLAGS
#define ZONEID_SHIFT		(SECTIONS_SHIFT + ZONES_SHIFT)
#define ZONEID_PGOFF		((SECTIONS_PGOFF < ZONES_PGOFF)? \
						SECTIONS_PGOFF : ZONES_PGOFF)
#else
#define ZONEID_SHIFT		(NODES_SHIFT + ZONES_SHIFT)
#define ZONEID_PGOFF		((NODES_PGOFF < ZONES_PGOFF)? \
						NODES_PGOFF : ZONES_PGOFF)
#endif

#define ZONEID_PGSHIFT		(ZONEID_PGOFF * (ZONEID_SHIFT != 0))

#if SECTIONS_WIDTH+NODES_WIDTH+ZONES_WIDTH > BITS_PER_LONG - NR_PAGEFLAGS
#error SECTIONS_WIDTH+NODES_WIDTH+ZONES_WIDTH > BITS_PER_LONG - NR_PAGEFLAGS
#endif

#define ZONES_MASK		((1UL << ZONES_WIDTH) - 1)
#define NODES_MASK		((1UL << NODES_WIDTH) - 1)
#define SECTIONS_MASK		((1UL << SECTIONS_WIDTH) - 1)
#define ZONEID_MASK		((1UL << ZONEID_SHIFT) - 1)

static inline enum zone_type page_zonenum(struct page *page)
{
	return (page->flags >> ZONES_PGSHIFT) & ZONES_MASK;
}

/*
 * The identification function is only used by the buddy allocator for
 * determining if two pages could be buddies. We are not really
 * identifying a zone since we could be using a the section number
 * id if we have not node id available in page flags.
 * We guarantee only that it will return the same value for two
 * combinable pages in a zone.
 */
static inline int page_zone_id(struct page *page)
{
	return (page->flags >> ZONEID_PGSHIFT) & ZONEID_MASK;
}

static inline int zone_to_nid(struct zone *zone)
{
#ifdef CONFIG_NUMA
	return zone->node;
#else
	return 0;
#endif
}

#ifdef NODE_NOT_IN_PAGE_FLAGS
extern int page_to_nid(struct page *page);
#else
static inline int page_to_nid(struct page *page)
{
	return (page->flags >> NODES_PGSHIFT) & NODES_MASK;
}
#endif

static inline struct zone *page_zone(struct page *page)
{
	return &NODE_DATA(page_to_nid(page))->node_zones[page_zonenum(page)];
}

#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP)
static inline unsigned long page_to_section(struct page *page)
{
	return (page->flags >> SECTIONS_PGSHIFT) & SECTIONS_MASK;
}
#endif

static inline void set_page_zone(struct page *page, enum zone_type zone)
{
	page->flags &= ~(ZONES_MASK << ZONES_PGSHIFT);
	page->flags |= (zone & ZONES_MASK) << ZONES_PGSHIFT;
}

static inline void set_page_node(struct page *page, unsigned long node)
{
	page->flags &= ~(NODES_MASK << NODES_PGSHIFT);
	page->flags |= (node & NODES_MASK) << NODES_PGSHIFT;
}

static inline void set_page_section(struct page *page, unsigned long section)
{
	page->flags &= ~(SECTIONS_MASK << SECTIONS_PGSHIFT);
	page->flags |= (section & SECTIONS_MASK) << SECTIONS_PGSHIFT;
}

static inline void set_page_links(struct page *page, enum zone_type zone,
	unsigned long node, unsigned long pfn)
{
	set_page_zone(page, zone);
	set_page_node(page, node);
	set_page_section(page, pfn_to_section_nr(pfn));
}

/*
 * Some inline functions in vmstat.h depend on page_zone()
 */
#include <linux/vmstat.h>

static __always_inline void *lowmem_page_address(struct page *page)
{
	return __va(page_to_pfn(page) << PAGE_SHIFT);
}

#if defined(CONFIG_HIGHMEM) && !defined(WANT_PAGE_VIRTUAL)
#define HASHED_PAGE_VIRTUAL
#endif

#if defined(WANT_PAGE_VIRTUAL)
#define page_address(page) ((page)->virtual)
#define set_page_address(page, address)			\
	do {						\
		(page)->virtual = (address);		\
	} while(0)
#define page_address_init()  do { } while(0)
#endif

#if defined(HASHED_PAGE_VIRTUAL)
void *page_address(struct page *page);
void set_page_address(struct page *page, void *virtual);
void page_address_init(void);
#endif

#if !defined(HASHED_PAGE_VIRTUAL) && !defined(WANT_PAGE_VIRTUAL)
#define page_address(page) lowmem_page_address(page)
#define set_page_address(page, address)  do { } while(0)
#define page_address_init()  do { } while(0)
#endif

/*
 * On an anonymous page mapped into a user virtual memory area,
 * page->mapping points to its anon_vma, not to a struct address_space;
 * with the PAGE_MAPPING_ANON bit set to distinguish it.
 *
 * Please note that, confusingly, "page_mapping" refers to the inode
 * address_space which maps the page from disk; whereas "page_mapped"
 * refers to user virtual address space into which the page is mapped.
 */
#define PAGE_MAPPING_ANON	1

extern struct address_space swapper_space;
static inline struct address_space *page_mapping(struct page *page)
{
	struct address_space *mapping = page->mapping;

	VM_BUG_ON(PageSlab(page));
#ifdef CONFIG_SWAP
	if (unlikely(PageSwapCache(page)))
		mapping = &swapper_space;
	else
#endif
	if (unlikely((unsigned long)mapping & PAGE_MAPPING_ANON))
		mapping = NULL;
	return mapping;
}

static inline int PageAnon(struct page *page)
{
	return ((unsigned long)page->mapping & PAGE_MAPPING_ANON) != 0;
}

/*
 * Return the pagecache index of the passed page.  Regular pagecache pages
 * use ->index whereas swapcache pages use ->private
 */
static inline pgoff_t page_index(struct page *page)
{
	if (unlikely(PageSwapCache(page)))
		return page_private(page);
	return page->index;
}

/*
 * The atomic page->_mapcount, like _count, starts from -1:
 * so that transitions both from it and to it can be tracked,
 * using atomic_inc_and_test and atomic_add_negative(-1).
 */
static inline void reset_page_mapcount(struct page *page)
{
	atomic_set(&(page)->_mapcount, -1);
}

static inline int page_mapcount(struct page *page)
{
	return atomic_read(&(page)->_mapcount) + 1;
}

/*
 * Return true if this page is mapped into pagetables.
 */
static inline int page_mapped(struct page *page)
{
	return atomic_read(&(page)->_mapcount) >= 0;
}

/*
 * Different kinds of faults, as returned by handle_mm_fault().
 * Used to decide whether a process gets delivered SIGBUS or
 * just gets major/minor fault counters bumped up.
 */

#define VM_FAULT_MINOR	0 /* For backwards compat. Remove me quickly. */

#define VM_FAULT_OOM	0x0001
#define VM_FAULT_SIGBUS	0x0002
#define VM_FAULT_MAJOR	0x0004
#define VM_FAULT_WRITE	0x0008	/* Special case for get_user_pages */

#define VM_FAULT_NOPAGE	0x0100	/* ->fault installed the pte, not return page */
#define VM_FAULT_LOCKED	0x0200	/* ->fault locked the returned page */

#define VM_FAULT_ERROR	(VM_FAULT_OOM | VM_FAULT_SIGBUS)

/*
 * Can be called by the pagefault handler when it gets a VM_FAULT_OOM.
 */
extern void pagefault_out_of_memory(void);

#define offset_in_page(p)	((unsigned long)(p) & ~PAGE_MASK)

extern void show_free_areas(void);

#ifdef CONFIG_SHMEM
extern int shmem_lock(struct file *file, int lock, struct user_struct *user);
#else
static inline int shmem_lock(struct file *file, int lock,
			    struct user_struct *user)
{
	return 0;
}
#endif
struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags);

int shmem_zero_setup(struct vm_area_struct *);

#ifndef CONFIG_MMU
extern unsigned long shmem_get_unmapped_area(struct file *file,
					     unsigned long addr,
					     unsigned long len,
					     unsigned long pgoff,
					     unsigned long flags);
#endif

extern int can_do_mlock(void);
extern int user_shm_lock(size_t, struct user_struct *);
extern void user_shm_unlock(size_t, struct user_struct *);

/*
 * Parameter block passed down to zap_pte_range in exceptional cases.
 */
struct zap_details {
	struct vm_area_struct *nonlinear_vma;	/* Check page->index if set */
	struct address_space *check_mapping;	/* Check page->mapping if set */
	pgoff_t	first_index;			/* Lowest page->index to unmap */
	pgoff_t last_index;			/* Highest page->index to unmap */
	spinlock_t *i_mmap_lock;		/* For unmap_mapping_range: */
	unsigned long truncate_count;		/* Compare vm_truncate_count */
};

struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
		pte_t pte);

int zap_vma_ptes(struct vm_area_struct *vma, unsigned long address,
		unsigned long size);
unsigned long zap_page_range(struct vm_area_struct *vma, unsigned long address,
		unsigned long size, struct zap_details *);
unsigned long unmap_vmas(struct mmu_gather **tlb,
		struct vm_area_struct *start_vma, unsigned long start_addr,
		unsigned long end_addr, unsigned long *nr_accounted,
		struct zap_details *);

/**
 * mm_walk - callbacks for walk_page_range
 * @pgd_entry: if set, called for each non-empty PGD (top-level) entry
 * @pud_entry: if set, called for each non-empty PUD (2nd-level) entry
 * @pmd_entry: if set, called for each non-empty PMD (3rd-level) entry
 * @pte_entry: if set, called for each non-empty PTE (4th-level) entry
 * @pte_hole: if set, called for each hole at all levels
 *
 * (see walk_page_range for more details)
 */
struct mm_walk {
	int (*pgd_entry)(pgd_t *, unsigned long, unsigned long, struct mm_walk *);
	int (*pud_entry)(pud_t *, unsigned long, unsigned long, struct mm_walk *);
	int (*pmd_entry)(pmd_t *, unsigned long, unsigned long, struct mm_walk *);
	int (*pte_entry)(pte_t *, unsigned long, unsigned long, struct mm_walk *);
	int (*pte_hole)(unsigned long, unsigned long, struct mm_walk *);
	struct mm_struct *mm;
	void *private;
};

int walk_page_range(unsigned long addr, unsigned long end,
		struct mm_walk *walk);
void free_pgd_range(struct mmu_gather *tlb, unsigned long addr,
		unsigned long end, unsigned long floor, unsigned long ceiling);
int copy_page_range(struct mm_struct *dst, struct mm_struct *src,
			struct vm_area_struct *vma);
void unmap_mapping_range(struct address_space *mapping,
		loff_t const holebegin, loff_t const holelen, int even_cows);
int follow_pfn(struct vm_area_struct *vma, unsigned long address,
	unsigned long *pfn);
int follow_phys(struct vm_area_struct *vma, unsigned long address,
		unsigned int flags, unsigned long *prot, resource_size_t *phys);
int generic_access_phys(struct vm_area_struct *vma, unsigned long addr,
			void *buf, int len, int write);

static inline void unmap_shared_mapping_range(struct address_space *mapping,
		loff_t const holebegin, loff_t const holelen)
{
	unmap_mapping_range(mapping, holebegin, holelen, 0);
}

extern int vmtruncate(struct inode * inode, loff_t offset);
extern int vmtruncate_range(struct inode * inode, loff_t offset, loff_t end);

#ifdef CONFIG_MMU
extern int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
			unsigned long address, unsigned int flags);
#else
static inline int handle_mm_fault(struct mm_struct *mm,
			struct vm_area_struct *vma, unsigned long address,
			unsigned int flags)
{
	/* should never happen if there's no MMU */
	BUG();
	return VM_FAULT_SIGBUS;
}
#endif

extern int make_pages_present(unsigned long addr, unsigned long end);
extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, int write);

int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
			unsigned long start, int nr_pages, int write, int force,
			struct page **pages, struct vm_area_struct **vmas);
int get_user_pages_fast(unsigned long start, int nr_pages, int write,
			struct page **pages);

extern int try_to_release_page(struct page * page, gfp_t gfp_mask);
extern void do_invalidatepage(struct page *page, unsigned long offset);

int __set_page_dirty_nobuffers(struct page *page);
int __set_page_dirty_no_writeback(struct page *page);
int redirty_page_for_writepage(struct writeback_control *wbc,
				struct page *page);
void account_page_dirtied(struct page *page, struct address_space *mapping);
int set_page_dirty(struct page *page);
int set_page_dirty_lock(struct page *page);
int clear_page_dirty_for_io(struct page *page);

extern unsigned long move_page_tables(struct vm_area_struct *vma,
		unsigned long old_addr, struct vm_area_struct *new_vma,
		unsigned long new_addr, unsigned long len);
extern unsigned long do_mremap(unsigned long addr,
			       unsigned long old_len, unsigned long new_len,
			       unsigned long flags, unsigned long new_addr);
extern int mprotect_fixup(struct vm_area_struct *vma,
			  struct vm_area_struct **pprev, unsigned long start,
			  unsigned long end, unsigned long newflags);

/*
 * doesn't attempt to fault and will return short.
 */
int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
			  struct page **pages);

/*
 * A callback you can register to apply pressure to ageable caches.
 *
 * 'shrink' is passed a count 'nr_to_scan' and a 'gfpmask'.  It should
 * look through the least-recently-used 'nr_to_scan' entries and
 * attempt to free them up.  It should return the number of objects
 * which remain in the cache.  If it returns -1, it means it cannot do
 * any scanning at this time (eg. there is a risk of deadlock).
 *
 * The 'gfpmask' refers to the allocation we are currently trying to
 * fulfil.
 *
 * Note that 'shrink' will be passed nr_to_scan == 0 when the VM is
 * querying the cache size, so a fastpath for that case is appropriate.
 */
struct shrinker {
	int (*shrink)(int nr_to_scan, gfp_t gfp_mask);
	int seeks;	/* seeks to recreate an obj */

	/* These are for internal use */
	struct list_head list;
	long nr;	/* objs pending delete */
};
#define DEFAULT_SEEKS 2 /* A good number if you don't know better. */
extern void register_shrinker(struct shrinker *);
extern void unregister_shrinker(struct shrinker *);

int vma_wants_writenotify(struct vm_area_struct *vma);

extern pte_t *get_locked_pte(struct mm_struct *mm, unsigned long addr, spinlock_t **ptl);

#ifdef __PAGETABLE_PUD_FOLDED
static inline int __pud_alloc(struct mm_struct *mm, pgd_t *pgd,
						unsigned long address)
{
	return 0;
}
#else
int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address);
#endif

#ifdef __PAGETABLE_PMD_FOLDED
static inline int __pmd_alloc(struct mm_struct *mm, pud_t *pud,
						unsigned long address)
{
	return 0;
}
#else
int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address);
#endif

int __pte_alloc(struct mm_struct *mm, pmd_t *pmd, unsigned long address);
int __pte_alloc_kernel(pmd_t *pmd, unsigned long address);

/*
 * The following ifdef needed to get the 4level-fixup.h header to work.
 * Remove it when 4level-fixup.h has been removed.
 */
#if defined(CONFIG_MMU) && !defined(__ARCH_HAS_4LEVEL_HACK)
static inline pud_t *pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address)
{
	return (unlikely(pgd_none(*pgd)) && __pud_alloc(mm, pgd, address))?
		NULL: pud_offset(pgd, address);
}

static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address)
{
	return (unlikely(pud_none(*pud)) && __pmd_alloc(mm, pud, address))?
		NULL: pmd_offset(pud, address);
}
#endif /* CONFIG_MMU && !__ARCH_HAS_4LEVEL_HACK */

#if USE_SPLIT_PTLOCKS
/*
 * We tuck a spinlock to guard each pagetable page into its struct page,
 * at page->private, with BUILD_BUG_ON to make sure that this will not
 * overflow into the next struct page (as it might with DEBUG_SPINLOCK).
 * When freeing, reset page->mapping so free_pages_check won't complain.
 */
#define __pte_lockptr(page)	&((page)->ptl)
#define pte_lock_init(_page)	do {					\
	spin_lock_init(__pte_lockptr(_page));				\
} while (0)
#define pte_lock_deinit(page)	((page)->mapping = NULL)
#define pte_lockptr(mm, pmd)	({(void)(mm); __pte_lockptr(pmd_page(*(pmd)));})
#else	/* !USE_SPLIT_PTLOCKS */
/*
 * We use mm->page_table_lock to guard all pagetable pages of the mm.
 */
#define pte_lock_init(page)	do {} while (0)
#define pte_lock_deinit(page)	do {} while (0)
#define pte_lockptr(mm, pmd)	({(void)(pmd); &(mm)->page_table_lock;})
#endif /* USE_SPLIT_PTLOCKS */

static inline void pgtable_page_ctor(struct page *page)
{
	pte_lock_init(page);
	inc_zone_page_state(page, NR_PAGETABLE);
}

static inline void pgtable_page_dtor(struct page *page)
{
	pte_lock_deinit(page);
	dec_zone_page_state(page, NR_PAGETABLE);
}

#define pte_offset_map_lock(mm, pmd, address, ptlp)	\
({							\
	spinlock_t *__ptl = pte_lockptr(mm, pmd);	\
	pte_t *__pte = pte_offset_map(pmd, address);	\
	*(ptlp) = __ptl;				\