blob: 7714f57caad5b4312e7289761c0561c68b822049 [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
112 (*) A request for a private mapping of less than a page in size may not return
113 a page-aligned buffer. This is because the kernel calls kmalloc() to
114 allocate the buffer, not get_free_page().
115
116 (*) A list of all the mappings on the system is visible through /proc/maps in
117 no-MMU mode.
118
David Howellsdbf86852006-09-27 01:50:19 -0700119 (*) A list of all the mappings in use by a process is visible through
120 /proc/<pid>/maps in no-MMU mode.
121
Linus Torvalds1da177e2005-04-16 15:20:36 -0700122 (*) Supplying MAP_FIXED or a requesting a particular mapping address will
123 result in an error.
124
125 (*) Files mapped privately usually have to have a read method provided by the
126 driver or filesystem so that the contents can be read into the memory
127 allocated if mmap() chooses not to map the backing device directly. An
128 error will result if they don't. This is most likely to be encountered
129 with character device files, pipes, fifos and sockets.
130
David Howells6fa5f802006-09-27 01:50:21 -0700131
David Howells0112c4c2006-09-27 01:50:21 -0700132==========================
133INTERPROCESS SHARED MEMORY
134==========================
135
136Both SYSV IPC SHM shared memory and POSIX shared memory is supported in NOMMU
137mode. The former through the usual mechanism, the latter through files created
138on ramfs or tmpfs mounts.
139
140
David Howells930e6522006-09-27 01:50:22 -0700141=======
142FUTEXES
143=======
144
145Futexes are supported in NOMMU mode if the arch supports them. An error will
146be given if an address passed to the futex system call lies outside the
147mappings made by a process or if the mapping in which the address lies does not
148support futexes (such as an I/O chardev mapping).
149
150
David Howells6fa5f802006-09-27 01:50:21 -0700151=============
152NO-MMU MREMAP
153=============
154
155The mremap() function is partially supported. It may change the size of a
156mapping, and may move it[*] if MREMAP_MAYMOVE is specified and if the new size
157of the mapping exceeds the size of the slab object currently occupied by the
158memory to which the mapping refers, or if a smaller slab object could be used.
159
160MREMAP_FIXED is not supported, though it is ignored if there's no change of
161address and the object does not need to be moved.
162
163Shared mappings may not be moved. Shareable mappings may not be moved either,
164even if they are not currently shared.
165
166The mremap() function must be given an exact match for base address and size of
167a previously mapped object. It may not be used to create holes in existing
168mappings, move parts of existing mappings or resize parts of mappings. It must
169act on a complete mapping.
170
171[*] Not currently supported.
172
173
Linus Torvalds1da177e2005-04-16 15:20:36 -0700174============================================
175PROVIDING SHAREABLE CHARACTER DEVICE SUPPORT
176============================================
177
178To provide shareable character device support, a driver must provide a
179file->f_op->get_unmapped_area() operation. The mmap() routines will call this
180to get a proposed address for the mapping. This may return an error if it
181doesn't wish to honour the mapping because it's too long, at a weird offset,
182under some unsupported combination of flags or whatever.
183
184The driver should also provide backing device information with capabilities set
185to indicate the permitted types of mapping on such devices. The default is
186assumed to be readable and writable, not executable, and only shareable
187directly (can't be copied).
188
189The file->f_op->mmap() operation will be called to actually inaugurate the
190mapping. It can be rejected at that point. Returning the ENOSYS error will
191cause the mapping to be copied instead if BDI_CAP_MAP_COPY is specified.
192
193The vm_ops->close() routine will be invoked when the last mapping on a chardev
194is removed. An existing mapping will be shared, partially or not, if possible
195without notifying the driver.
196
197It is permitted also for the file->f_op->get_unmapped_area() operation to
198return -ENOSYS. This will be taken to mean that this operation just doesn't
199want to handle it, despite the fact it's got an operation. For instance, it
200might try directing the call to a secondary driver which turns out not to
201implement it. Such is the case for the framebuffer driver which attempts to
202direct the call to the device-specific driver. Under such circumstances, the
203mapping request will be rejected if BDI_CAP_MAP_COPY is not specified, and a
204copy mapped otherwise.
205
206IMPORTANT NOTE:
207
208 Some types of device may present a different appearance to anyone
209 looking at them in certain modes. Flash chips can be like this; for
210 instance if they're in programming or erase mode, you might see the
211 status reflected in the mapping, instead of the data.
212
213 In such a case, care must be taken lest userspace see a shared or a
214 private mapping showing such information when the driver is busy
215 controlling the device. Remember especially: private executable
216 mappings may still be mapped directly off the device under some
217 circumstances!
218
219
220==============================================
221PROVIDING SHAREABLE MEMORY-BACKED FILE SUPPORT
222==============================================
223
224Provision of shared mappings on memory backed files is similar to the provision
225of support for shared mapped character devices. The main difference is that the
226filesystem providing the service will probably allocate a contiguous collection
227of pages and permit mappings to be made on that.
228
229It is recommended that a truncate operation applied to such a file that
230increases the file size, if that file is empty, be taken as a request to gather
231enough pages to honour a mapping. This is required to support POSIX shared
232memory.
233
234Memory backed devices are indicated by the mapping's backing device info having
235the memory_backed flag set.
236
237
238========================================
239PROVIDING SHAREABLE BLOCK DEVICE SUPPORT
240========================================
241
242Provision of shared mappings on block device files is exactly the same as for
243character devices. If there isn't a real device underneath, then the driver
244should allocate sufficient contiguous memory to honour any supported mapping.