Root/Documentation/vm/highmem.txt

1
2                 ====================
3                 HIGH MEMORY HANDLING
4                 ====================
5
6By: Peter Zijlstra <a.p.zijlstra@chello.nl>
7
8Contents:
9
10 (*) What is high memory?
11
12 (*) Temporary virtual mappings.
13
14 (*) Using kmap_atomic.
15
16 (*) Cost of temporary mappings.
17
18 (*) i386 PAE.
19
20
21====================
22WHAT IS HIGH MEMORY?
23====================
24
25High memory (highmem) is used when the size of physical memory approaches or
26exceeds the maximum size of virtual memory. At that point it becomes
27impossible for the kernel to keep all of the available physical memory mapped
28at all times. This means the kernel needs to start using temporary mappings of
29the pieces of physical memory that it wants to access.
30
31The part of (physical) memory not covered by a permanent mapping is what we
32refer to as 'highmem'. There are various architecture dependent constraints on
33where exactly that border lies.
34
35In the i386 arch, for example, we choose to map the kernel into every process's
36VM space so that we don't have to pay the full TLB invalidation costs for
37kernel entry/exit. This means the available virtual memory space (4GiB on
38i386) has to be divided between user and kernel space.
39
40The traditional split for architectures using this approach is 3:1, 3GiB for
41userspace and the top 1GiB for kernel space:
42
43        +--------+ 0xffffffff
44        | Kernel |
45        +--------+ 0xc0000000
46        | |
47        | User |
48        | |
49        +--------+ 0x00000000
50
51This means that the kernel can at most map 1GiB of physical memory at any one
52time, but because we need virtual address space for other things - including
53temporary maps to access the rest of the physical memory - the actual direct
54map will typically be less (usually around ~896MiB).
55
56Other architectures that have mm context tagged TLBs can have separate kernel
57and user maps. Some hardware (like some ARMs), however, have limited virtual
58space when they use mm context tags.
59
60
61==========================
62TEMPORARY VIRTUAL MAPPINGS
63==========================
64
65The kernel contains several ways of creating temporary mappings:
66
67 (*) vmap(). This can be used to make a long duration mapping of multiple
68     physical pages into a contiguous virtual space. It needs global
69     synchronization to unmap.
70
71 (*) kmap(). This permits a short duration mapping of a single page. It needs
72     global synchronization, but is amortized somewhat. It is also prone to
73     deadlocks when using in a nested fashion, and so it is not recommended for
74     new code.
75
76 (*) kmap_atomic(). This permits a very short duration mapping of a single
77     page. Since the mapping is restricted to the CPU that issued it, it
78     performs well, but the issuing task is therefore required to stay on that
79     CPU until it has finished, lest some other task displace its mappings.
80
81     kmap_atomic() may also be used by interrupt contexts, since it is does not
82     sleep and the caller may not sleep until after kunmap_atomic() is called.
83
84     It may be assumed that k[un]map_atomic() won't fail.
85
86
87=================
88USING KMAP_ATOMIC
89=================
90
91When and where to use kmap_atomic() is straightforward. It is used when code
92wants to access the contents of a page that might be allocated from high memory
93(see __GFP_HIGHMEM), for example a page in the pagecache. The API has two
94functions, and they can be used in a manner similar to the following:
95
96    /* Find the page of interest. */
97    struct page *page = find_get_page(mapping, offset);
98
99    /* Gain access to the contents of that page. */
100    void *vaddr = kmap_atomic(page);
101
102    /* Do something to the contents of that page. */
103    memset(vaddr, 0, PAGE_SIZE);
104
105    /* Unmap that page. */
106    kunmap_atomic(vaddr);
107
108Note that the kunmap_atomic() call takes the result of the kmap_atomic() call
109not the argument.
110
111If you need to map two pages because you want to copy from one page to
112another you need to keep the kmap_atomic calls strictly nested, like:
113
114    vaddr1 = kmap_atomic(page1);
115    vaddr2 = kmap_atomic(page2);
116
117    memcpy(vaddr1, vaddr2, PAGE_SIZE);
118
119    kunmap_atomic(vaddr2);
120    kunmap_atomic(vaddr1);
121
122
123==========================
124COST OF TEMPORARY MAPPINGS
125==========================
126
127The cost of creating temporary mappings can be quite high. The arch has to
128manipulate the kernel's page tables, the data TLB and/or the MMU's registers.
129
130If CONFIG_HIGHMEM is not set, then the kernel will try and create a mapping
131simply with a bit of arithmetic that will convert the page struct address into
132a pointer to the page contents rather than juggling mappings about. In such a
133case, the unmap operation may be a null operation.
134
135If CONFIG_MMU is not set, then there can be no temporary mappings and no
136highmem. In such a case, the arithmetic approach will also be used.
137
138
139========
140i386 PAE
141========
142
143The i386 arch, under some circumstances, will permit you to stick up to 64GiB
144of RAM into your 32-bit machine. This has a number of consequences:
145
146 (*) Linux needs a page-frame structure for each page in the system and the
147     pageframes need to live in the permanent mapping, which means:
148
149 (*) you can have 896M/sizeof(struct page) page-frames at most; with struct
150     page being 32-bytes that would end up being something in the order of 112G
151     worth of pages; the kernel, however, needs to store more than just
152     page-frames in that memory...
153
154 (*) PAE makes your page tables larger - which slows the system down as more
155     data has to be accessed to traverse in TLB fills and the like. One
156     advantage is that PAE has more PTE bits and can provide advanced features
157     like NX and PAT.
158
159The general recommendation is that you don't use more than 8GiB on a 32-bit
160machine - although more might work for you and your workload, you're pretty
161much on your own - don't expect kernel developers to really care much if things
162come apart.
163

Archive Download this file



interactive