1pagemap, 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 15 * Bits 0-54 page frame number (PFN) if present 16 * Bits 0-4 swap type if swapped 17 * Bits 5-54 swap offset if swapped 18 * Bit 55 pte is soft-dirty (see Documentation/vm/soft-dirty.txt) 19 * Bits 56-60 zero 20 * Bit 61 page is file-page or shared-anon 21 * 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 40 The flags are (from fs/proc/page.c, above kpageflags_read): 41 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 53 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 61 19. HWPOISON 62 20. NOPAGE 63 21. KSM 64 22. THP 65 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 9319. HWPOISON 94 hardware detected memory corruption on this page: don't touch the data! 95 9620. NOPAGE 97 no page frame exists at the requested address 98 9921. KSM 100 identical memory pages dynamically shared between one or more processes 101 10222. THP 103 contiguous pages which construct transparent hugepages 104 105 [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. 127 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 151the read on an 8-byte boundary (e.g., if you sought an odd number of bytes 152into the file), or if the size of the read is not a multiple of 8 bytes. 153