blob: 5948e455c4d24346c29bb245551571258991d37f [file] [log] [blame]
Thomas Tuttleef421be2008-06-05 22:46:59 -07001pagemap, from the userspace perspective
2---------------------------------------
3
4pagemap is a new (as of 2.6.25) set of interfaces in the kernel that allow
5userspace programs to examine the page tables and related information by
6reading files in /proc.
7
8There are three components to pagemap:
9
10 * /proc/pid/pagemap. This file lets a userspace process find out which
11 physical frame each virtual page is mapped to. It contains one 64-bit
12 value for each virtual page, containing the following data (from
13 fs/proc/task_mmu.c, above pagemap_read):
14
Wu Fengguangc9ba78e2009-06-16 15:32:25 -070015 * Bits 0-54 page frame number (PFN) if present
Thomas Tuttleef421be2008-06-05 22:46:59 -070016 * Bits 0-4 swap type if swapped
Wu Fengguangc9ba78e2009-06-16 15:32:25 -070017 * Bits 5-54 swap offset if swapped
Pavel Emelyanov541c2372013-07-03 15:01:22 -070018 * Bit 55 pte is soft-dirty (see Documentation/vm/soft-dirty.txt)
19 * Bits 56-60 zero
Konstantin Khlebnikov052fb0d2012-05-31 16:26:19 -070020 * Bit 61 page is file-page or shared-anon
Thomas Tuttleef421be2008-06-05 22:46:59 -070021 * Bit 62 page swapped
22 * Bit 63 page present
23
24 If the page is not present but in swap, then the PFN contains an
25 encoding of the swap file number and the page's offset into the
26 swap. Unmapped pages return a null PFN. This allows determining
27 precisely which pages are mapped (or in swap) and comparing mapped
28 pages between processes.
29
30 Efficient users of this interface will use /proc/pid/maps to
31 determine which areas of memory are actually mapped and llseek to
32 skip over unmapped regions.
33
34 * /proc/kpagecount. This file contains a 64-bit count of the number of
35 times each page is mapped, indexed by PFN.
36
37 * /proc/kpageflags. This file contains a 64-bit set of flags for each
38 page, indexed by PFN.
39
Wu Fengguangc9ba78e2009-06-16 15:32:25 -070040 The flags are (from fs/proc/page.c, above kpageflags_read):
Thomas Tuttleef421be2008-06-05 22:46:59 -070041
42 0. LOCKED
43 1. ERROR
44 2. REFERENCED
45 3. UPTODATE
46 4. DIRTY
47 5. LRU
48 6. ACTIVE
49 7. SLAB
50 8. WRITEBACK
51 9. RECLAIM
52 10. BUDDY
Wu Fengguang17e89502009-06-16 15:32:26 -070053 11. MMAP
54 12. ANON
55 13. SWAPCACHE
56 14. SWAPBACKED
57 15. COMPOUND_HEAD
58 16. COMPOUND_TAIL
59 16. HUGE
60 18. UNEVICTABLE
Wu Fengguang253fb022009-10-07 16:32:27 -070061 19. HWPOISON
Wu Fengguang17e89502009-06-16 15:32:26 -070062 20. NOPAGE
Wu Fengguanga1bbb5e2009-10-07 16:32:28 -070063 21. KSM
Naoya Horiguchi807f0cc2012-03-21 16:33:58 -070064 22. THP
Wu Fengguang17e89502009-06-16 15:32:26 -070065
66Short descriptions to the page flags:
67
68 0. LOCKED
69 page is being locked for exclusive access, eg. by undergoing read/write IO
70
71 7. SLAB
72 page is managed by the SLAB/SLOB/SLUB/SLQB kernel memory allocator
73 When compound page is used, SLUB/SLQB will only set this flag on the head
74 page; SLOB will not flag it at all.
75
7610. BUDDY
77 a free memory block managed by the buddy system allocator
78 The buddy system organizes free memory in blocks of various orders.
79 An order N block has 2^N physically contiguous pages, with the BUDDY flag
80 set for and _only_ for the first page.
81
8215. COMPOUND_HEAD
8316. COMPOUND_TAIL
84 A compound page with order N consists of 2^N physically contiguous pages.
85 A compound page with order 2 takes the form of "HTTT", where H donates its
86 head page and T donates its tail page(s). The major consumers of compound
87 pages are hugeTLB pages (Documentation/vm/hugetlbpage.txt), the SLUB etc.
88 memory allocators and various device drivers. However in this interface,
89 only huge/giga pages are made visible to end users.
9017. HUGE
91 this is an integral part of a HugeTLB page
92
Wu Fengguang253fb022009-10-07 16:32:27 -07009319. HWPOISON
94 hardware detected memory corruption on this page: don't touch the data!
95
Wu Fengguang17e89502009-06-16 15:32:26 -07009620. NOPAGE
97 no page frame exists at the requested address
98
Wu Fengguanga1bbb5e2009-10-07 16:32:28 -07009921. KSM
100 identical memory pages dynamically shared between one or more processes
101
Naoya Horiguchi807f0cc2012-03-21 16:33:58 -070010222. THP
103 contiguous pages which construct transparent hugepages
104
Wu Fengguang17e89502009-06-16 15:32:26 -0700105 [IO related page flags]
106 1. ERROR IO error occurred
107 3. UPTODATE page has up-to-date data
108 ie. for file backed page: (in-memory data revision >= on-disk one)
109 4. DIRTY page has been written to, hence contains new data
110 ie. for file backed page: (in-memory data revision > on-disk one)
111 8. WRITEBACK page is being synced to disk
112
113 [LRU related page flags]
114 5. LRU page is in one of the LRU lists
115 6. ACTIVE page is in the active LRU list
11618. UNEVICTABLE page is in the unevictable (non-)LRU list
117 It is somehow pinned and not a candidate for LRU page reclaims,
118 eg. ramfs pages, shmctl(SHM_LOCK) and mlock() memory segments
119 2. REFERENCED page has been referenced since last LRU list enqueue/requeue
120 9. RECLAIM page will be reclaimed soon after its pageout IO completed
12111. MMAP a memory mapped page
12212. ANON a memory mapped page that is not part of a file
12313. SWAPCACHE page is mapped to swap space, ie. has an associated swap entry
12414. SWAPBACKED page is backed by swap/RAM
125
126The page-types tool in this directory can be used to query the above flags.
Thomas Tuttleef421be2008-06-05 22:46:59 -0700127
128Using pagemap to do something useful:
129
130The general procedure for using pagemap to find out about a process' memory
131usage goes like this:
132
133 1. Read /proc/pid/maps to determine which parts of the memory space are
134 mapped to what.
135 2. Select the maps you are interested in -- all of them, or a particular
136 library, or the stack or the heap, etc.
137 3. Open /proc/pid/pagemap and seek to the pages you would like to examine.
138 4. Read a u64 for each page from pagemap.
139 5. Open /proc/kpagecount and/or /proc/kpageflags. For each PFN you just
140 read, seek to that entry in the file, and read the data you want.
141
142For example, to find the "unique set size" (USS), which is the amount of
143memory that a process is using that is not shared with any other process,
144you can go through every map in the process, find the PFNs, look those up
145in kpagecount, and tally up the number of pages that are only referenced
146once.
147
148Other notes:
149
150Reading from any of the files will return -EINVAL if you are not starting
Anatol Pomozovf884ab12013-05-08 16:56:16 -0700151the read on an 8-byte boundary (e.g., if you sought an odd number of bytes
Thomas Tuttleef421be2008-06-05 22:46:59 -0700152into the file), or if the size of the read is not a multiple of 8 bytes.