linux/Documentation/nommu-mmap.txt
<<
>>
Prefs
   1                         =============================
   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 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.
 115
 116 (*) 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 (*) The memory allocated by a request for an anonymous mapping will normally
 123     be cleared by the kernel before being returned in accordance with the
 124     Linux man pages (ver 2.22 or later).
 125
 126     In the MMU case this can be achieved with reasonable performance as
 127     regions are backed by virtual pages, with the contents only being mapped
 128     to cleared physical pages when a write happens on that specific page
 129     (prior to which, the pages are effectively mapped to the global zero page
 130     from which reads can take place).  This spreads out the time it takes to
 131     initialize the contents of a page - depending on the write-usage of the
 132     mapping.
 133
 134     In the no-MMU case, however, anonymous mappings are backed by physical
 135     pages, and the entire map is cleared at allocation time.  This can cause
 136     significant delays during a userspace malloc() as the C library does an
 137     anonymous mapping and the kernel then does a memset for the entire map.
 138
 139     However, for memory that isn't required to be precleared - such as that
 140     returned by malloc() - mmap() can take a MAP_UNINITIALIZED flag to
 141     indicate to the kernel that it shouldn't bother clearing the memory before
 142     returning it.  Note that CONFIG_MMAP_ALLOW_UNINITIALIZED must be enabled
 143     to permit this, otherwise the flag will be ignored.
 144
 145     uClibc uses this to speed up malloc(), and the ELF-FDPIC binfmt uses this
 146     to allocate the brk and stack region.
 147
 148 (*) A list of all the private copy and anonymous mappings on the system is
 149     visible through /proc/maps in no-MMU mode.
 150
 151 (*) A list of all the mappings in use by a process is visible through
 152     /proc/<pid>/maps in no-MMU mode.
 153
 154 (*) Supplying MAP_FIXED or a requesting a particular mapping address will
 155     result in an error.
 156
 157 (*) Files mapped privately usually have to have a read method provided by the
 158     driver or filesystem so that the contents can be read into the memory
 159     allocated if mmap() chooses not to map the backing device directly. An
 160     error will result if they don't. This is most likely to be encountered
 161     with character device files, pipes, fifos and sockets.
 162
 163
 164==========================
 165INTERPROCESS SHARED MEMORY
 166==========================
 167
 168Both SYSV IPC SHM shared memory and POSIX shared memory is supported in NOMMU
 169mode.  The former through the usual mechanism, the latter through files created
 170on ramfs or tmpfs mounts.
 171
 172
 173=======
 174FUTEXES
 175=======
 176
 177Futexes are supported in NOMMU mode if the arch supports them.  An error will
 178be given if an address passed to the futex system call lies outside the
 179mappings made by a process or if the mapping in which the address lies does not
 180support futexes (such as an I/O chardev mapping).
 181
 182
 183=============
 184NO-MMU MREMAP
 185=============
 186
 187The mremap() function is partially supported.  It may change the size of a
 188mapping, and may move it[*] if MREMAP_MAYMOVE is specified and if the new size
 189of the mapping exceeds the size of the slab object currently occupied by the
 190memory to which the mapping refers, or if a smaller slab object could be used.
 191
 192MREMAP_FIXED is not supported, though it is ignored if there's no change of
 193address and the object does not need to be moved.
 194
 195Shared mappings may not be moved.  Shareable mappings may not be moved either,
 196even if they are not currently shared.
 197
 198The mremap() function must be given an exact match for base address and size of
 199a previously mapped object.  It may not be used to create holes in existing
 200mappings, move parts of existing mappings or resize parts of mappings.  It must
 201act on a complete mapping.
 202
 203[*] Not currently supported.
 204
 205
 206============================================
 207PROVIDING SHAREABLE CHARACTER DEVICE SUPPORT
 208============================================
 209
 210To provide shareable character device support, a driver must provide a
 211file->f_op->get_unmapped_area() operation. The mmap() routines will call this
 212to get a proposed address for the mapping. This may return an error if it
 213doesn't wish to honour the mapping because it's too long, at a weird offset,
 214under some unsupported combination of flags or whatever.
 215
 216The driver should also provide backing device information with capabilities set
 217to indicate the permitted types of mapping on such devices. The default is
 218assumed to be readable and writable, not executable, and only shareable
 219directly (can't be copied).
 220
 221The file->f_op->mmap() operation will be called to actually inaugurate the
 222mapping. It can be rejected at that point. Returning the ENOSYS error will
 223cause the mapping to be copied instead if BDI_CAP_MAP_COPY is specified.
 224
 225The vm_ops->close() routine will be invoked when the last mapping on a chardev
 226is removed. An existing mapping will be shared, partially or not, if possible
 227without notifying the driver.
 228
 229It is permitted also for the file->f_op->get_unmapped_area() operation to
 230return -ENOSYS. This will be taken to mean that this operation just doesn't
 231want to handle it, despite the fact it's got an operation. For instance, it
 232might try directing the call to a secondary driver which turns out not to
 233implement it. Such is the case for the framebuffer driver which attempts to
 234direct the call to the device-specific driver. Under such circumstances, the
 235mapping request will be rejected if BDI_CAP_MAP_COPY is not specified, and a
 236copy mapped otherwise.
 237
 238IMPORTANT NOTE:
 239
 240        Some types of device may present a different appearance to anyone
 241        looking at them in certain modes. Flash chips can be like this; for
 242        instance if they're in programming or erase mode, you might see the
 243        status reflected in the mapping, instead of the data.
 244
 245        In such a case, care must be taken lest userspace see a shared or a
 246        private mapping showing such information when the driver is busy
 247        controlling the device. Remember especially: private executable
 248        mappings may still be mapped directly off the device under some
 249        circumstances!
 250
 251
 252==============================================
 253PROVIDING SHAREABLE MEMORY-BACKED FILE SUPPORT
 254==============================================
 255
 256Provision of shared mappings on memory backed files is similar to the provision
 257of support for shared mapped character devices. The main difference is that the
 258filesystem providing the service will probably allocate a contiguous collection
 259of pages and permit mappings to be made on that.
 260
 261It is recommended that a truncate operation applied to such a file that
 262increases the file size, if that file is empty, be taken as a request to gather
 263enough pages to honour a mapping. This is required to support POSIX shared
 264memory.
 265
 266Memory backed devices are indicated by the mapping's backing device info having
 267the memory_backed flag set.
 268
 269
 270========================================
 271PROVIDING SHAREABLE BLOCK DEVICE SUPPORT
 272========================================
 273
 274Provision of shared mappings on block device files is exactly the same as for
 275character devices. If there isn't a real device underneath, then the driver
 276should allocate sufficient contiguous memory to honour any supported mapping.
 277
 278
 279=================================
 280ADJUSTING PAGE TRIMMING BEHAVIOUR
 281=================================
 282
 283NOMMU mmap automatically rounds up to the nearest power-of-2 number of pages
 284when performing an allocation.  This can have adverse effects on memory
 285fragmentation, and as such, is left configurable.  The default behaviour is to
 286aggressively trim allocations and discard any excess pages back in to the page
 287allocator.  In order to retain finer-grained control over fragmentation, this
 288behaviour can either be disabled completely, or bumped up to a higher page
 289watermark where trimming begins.
 290
 291Page trimming behaviour is configurable via the sysctl `vm.nr_trim_pages'.
 292
lxr.linux.no kindly hosted by Redpill Linpro AS, provider of Linux consulting and operations services since 1995.