blob: b565e8279d133f969fbd6cc2642592c3d44058ed [file] [log] [blame]
Linus Torvalds1da177e2005-04-16 15:20:36 -07001 =============================
2 NO-MMU MEMORY MAPPING SUPPORT
3 =============================
4
5The kernel has limited support for memory mapping under no-MMU conditions, such
6as are used in uClinux environments. From the userspace point of view, memory
7mapping is made use of in conjunction with the mmap() system call, the shmat()
8call and the execve() system call. From the kernel's point of view, execve()
9mapping is actually performed by the binfmt drivers, which call back into the
10mmap() routines to do the actual work.
11
12Memory mapping behaviour also involves the way fork(), vfork(), clone() and
13ptrace() work. Under uClinux there is no fork(), and clone() must be supplied
14the CLONE_VM flag.
15
16The behaviour is similar between the MMU and no-MMU cases, but not identical;
17and it's also much more restricted in the latter case:
18
19 (*) Anonymous mapping, MAP_PRIVATE
20
21 In the MMU case: VM regions backed by arbitrary pages; copy-on-write
22 across fork.
23
24 In the no-MMU case: VM regions backed by arbitrary contiguous runs of
25 pages.
26
27 (*) Anonymous mapping, MAP_SHARED
28
29 These behave very much like private mappings, except that they're
30 shared across fork() or clone() without CLONE_VM in the MMU case. Since
31 the no-MMU case doesn't support these, behaviour is identical to
32 MAP_PRIVATE there.
33
34 (*) File, MAP_PRIVATE, PROT_READ / PROT_EXEC, !PROT_WRITE
35
36 In the MMU case: VM regions backed by pages read from file; changes to
37 the underlying file are reflected in the mapping; copied across fork.
38
39 In the no-MMU case:
40
41 - If one exists, the kernel will re-use an existing mapping to the
42 same segment of the same file if that has compatible permissions,
43 even if this was created by another process.
44
45 - If possible, the file mapping will be directly on the backing device
46 if the backing device has the BDI_CAP_MAP_DIRECT capability and
47 appropriate mapping protection capabilities. Ramfs, romfs, cramfs
48 and mtd might all permit this.
49
50 - If the backing device device can't or won't permit direct sharing,
51 but does have the BDI_CAP_MAP_COPY capability, then a copy of the
52 appropriate bit of the file will be read into a contiguous bit of
53 memory and any extraneous space beyond the EOF will be cleared
54
55 - Writes to the file do not affect the mapping; writes to the mapping
56 are visible in other processes (no MMU protection), but should not
57 happen.
58
59 (*) File, MAP_PRIVATE, PROT_READ / PROT_EXEC, PROT_WRITE
60
61 In the MMU case: like the non-PROT_WRITE case, except that the pages in
62 question get copied before the write actually happens. From that point
63 on writes to the file underneath that page no longer get reflected into
64 the mapping's backing pages. The page is then backed by swap instead.
65
66 In the no-MMU case: works much like the non-PROT_WRITE case, except
67 that a copy is always taken and never shared.
68
69 (*) Regular file / blockdev, MAP_SHARED, PROT_READ / PROT_EXEC / PROT_WRITE
70
71 In the MMU case: VM regions backed by pages read from file; changes to
72 pages written back to file; writes to file reflected into pages backing
73 mapping; shared across fork.
74
75 In the no-MMU case: not supported.
76
77 (*) Memory backed regular file, MAP_SHARED, PROT_READ / PROT_EXEC / PROT_WRITE
78
79 In the MMU case: As for ordinary regular files.
80
81 In the no-MMU case: The filesystem providing the memory-backed file
82 (such as ramfs or tmpfs) may choose to honour an open, truncate, mmap
83 sequence by providing a contiguous sequence of pages to map. In that
84 case, a shared-writable memory mapping will be possible. It will work
85 as for the MMU case. If the filesystem does not provide any such
86 support, then the mapping request will be denied.
87
88 (*) Memory backed blockdev, MAP_SHARED, PROT_READ / PROT_EXEC / PROT_WRITE
89
90 In the MMU case: As for ordinary regular files.
91
92 In the no-MMU case: As for memory backed regular files, but the
93 blockdev must be able to provide a contiguous run of pages without
94 truncate being called. The ramdisk driver could do this if it allocated
95 all its memory as a contiguous array upfront.
96
97 (*) Memory backed chardev, MAP_SHARED, PROT_READ / PROT_EXEC / PROT_WRITE
98
99 In the MMU case: As for ordinary regular files.
100
101 In the no-MMU case: The character device driver may choose to honour
102 the mmap() by providing direct access to the underlying device if it
103 provides memory or quasi-memory that can be accessed directly. Examples
104 of such are frame buffers and flash devices. If the driver does not
105 provide any such support, then the mapping request will be denied.
106
107
108============================
109FURTHER NOTES ON NO-MMU MMAP
110============================
111
David Howells8feae132009-01-08 12:04:47 +0000112 (*) A request for a private mapping of a file may return a buffer that is not
113 page-aligned. This is because XIP may take place, and the data may not be
114 paged aligned in the backing store.
Linus Torvalds1da177e2005-04-16 15:20:36 -0700115
David Howells8feae132009-01-08 12:04:47 +0000116 (*) A request for an anonymous mapping will always be page aligned. If
117 possible the size of the request should be a power of two otherwise some
118 of the space may be wasted as the kernel must allocate a power-of-2
119 granule but will only discard the excess if appropriately configured as
120 this has an effect on fragmentation.
121
122 (*) A list of all the private copy and anonymous mappings on the system is
123 visible through /proc/maps in no-MMU mode.
Linus Torvalds1da177e2005-04-16 15:20:36 -0700124
David Howellsdbf86852006-09-27 01:50:19 -0700125 (*) A list of all the mappings in use by a process is visible through
126 /proc/<pid>/maps in no-MMU mode.
127
Linus Torvalds1da177e2005-04-16 15:20:36 -0700128 (*) Supplying MAP_FIXED or a requesting a particular mapping address will
129 result in an error.
130
131 (*) Files mapped privately usually have to have a read method provided by the
132 driver or filesystem so that the contents can be read into the memory
133 allocated if mmap() chooses not to map the backing device directly. An
134 error will result if they don't. This is most likely to be encountered
135 with character device files, pipes, fifos and sockets.
136
David Howells6fa5f802006-09-27 01:50:21 -0700137
David Howells0112c4c2006-09-27 01:50:21 -0700138==========================
139INTERPROCESS SHARED MEMORY
140==========================
141
142Both SYSV IPC SHM shared memory and POSIX shared memory is supported in NOMMU
143mode. The former through the usual mechanism, the latter through files created
144on ramfs or tmpfs mounts.
145
146
David Howells930e6522006-09-27 01:50:22 -0700147=======
148FUTEXES
149=======
150
151Futexes are supported in NOMMU mode if the arch supports them. An error will
152be given if an address passed to the futex system call lies outside the
153mappings made by a process or if the mapping in which the address lies does not
154support futexes (such as an I/O chardev mapping).
155
156
David Howells6fa5f802006-09-27 01:50:21 -0700157=============
158NO-MMU MREMAP
159=============
160
161The mremap() function is partially supported. It may change the size of a
162mapping, and may move it[*] if MREMAP_MAYMOVE is specified and if the new size
163of the mapping exceeds the size of the slab object currently occupied by the
164memory to which the mapping refers, or if a smaller slab object could be used.
165
166MREMAP_FIXED is not supported, though it is ignored if there's no change of
167address and the object does not need to be moved.
168
169Shared mappings may not be moved. Shareable mappings may not be moved either,
170even if they are not currently shared.
171
172The mremap() function must be given an exact match for base address and size of
173a previously mapped object. It may not be used to create holes in existing
174mappings, move parts of existing mappings or resize parts of mappings. It must
175act on a complete mapping.
176
177[*] Not currently supported.
178
179
Linus Torvalds1da177e2005-04-16 15:20:36 -0700180============================================
181PROVIDING SHAREABLE CHARACTER DEVICE SUPPORT
182============================================
183
184To provide shareable character device support, a driver must provide a
185file->f_op->get_unmapped_area() operation. The mmap() routines will call this
186to get a proposed address for the mapping. This may return an error if it
187doesn't wish to honour the mapping because it's too long, at a weird offset,
188under some unsupported combination of flags or whatever.
189
190The driver should also provide backing device information with capabilities set
191to indicate the permitted types of mapping on such devices. The default is
192assumed to be readable and writable, not executable, and only shareable
193directly (can't be copied).
194
195The file->f_op->mmap() operation will be called to actually inaugurate the
196mapping. It can be rejected at that point. Returning the ENOSYS error will
197cause the mapping to be copied instead if BDI_CAP_MAP_COPY is specified.
198
199The vm_ops->close() routine will be invoked when the last mapping on a chardev
200is removed. An existing mapping will be shared, partially or not, if possible
201without notifying the driver.
202
203It is permitted also for the file->f_op->get_unmapped_area() operation to
204return -ENOSYS. This will be taken to mean that this operation just doesn't
205want to handle it, despite the fact it's got an operation. For instance, it
206might try directing the call to a secondary driver which turns out not to
207implement it. Such is the case for the framebuffer driver which attempts to
208direct the call to the device-specific driver. Under such circumstances, the
209mapping request will be rejected if BDI_CAP_MAP_COPY is not specified, and a
210copy mapped otherwise.
211
212IMPORTANT NOTE:
213
214 Some types of device may present a different appearance to anyone
215 looking at them in certain modes. Flash chips can be like this; for
216 instance if they're in programming or erase mode, you might see the
217 status reflected in the mapping, instead of the data.
218
219 In such a case, care must be taken lest userspace see a shared or a
220 private mapping showing such information when the driver is busy
221 controlling the device. Remember especially: private executable
222 mappings may still be mapped directly off the device under some
223 circumstances!
224
225
226==============================================
227PROVIDING SHAREABLE MEMORY-BACKED FILE SUPPORT
228==============================================
229
230Provision of shared mappings on memory backed files is similar to the provision
231of support for shared mapped character devices. The main difference is that the
232filesystem providing the service will probably allocate a contiguous collection
233of pages and permit mappings to be made on that.
234
235It is recommended that a truncate operation applied to such a file that
236increases the file size, if that file is empty, be taken as a request to gather
237enough pages to honour a mapping. This is required to support POSIX shared
238memory.
239
240Memory backed devices are indicated by the mapping's backing device info having
241the memory_backed flag set.
242
243
244========================================
245PROVIDING SHAREABLE BLOCK DEVICE SUPPORT
246========================================
247
248Provision of shared mappings on block device files is exactly the same as for
249character devices. If there isn't a real device underneath, then the driver
250should allocate sufficient contiguous memory to honour any supported mapping.
Paul Mundtdd8632a2009-01-08 12:04:47 +0000251
252
253=================================
254ADJUSTING PAGE TRIMMING BEHAVIOUR
255=================================
256
257NOMMU mmap automatically rounds up to the nearest power-of-2 number of pages
258when performing an allocation. This can have adverse effects on memory
259fragmentation, and as such, is left configurable. The default behaviour is to
260aggressively trim allocations and discard any excess pages back in to the page
261allocator. In order to retain finer-grained control over fragmentation, this
262behaviour can either be disabled completely, or bumped up to a higher page
263watermark where trimming begins.
264
265Page trimming behaviour is configurable via the sysctl `vm.nr_trim_pages'.