Documentation\arm64\memory

Chinese translated version of  Documentation\arm64\memory

If you have any comment or update to the content, please contact the
original document maintainer directly.  However, if you have a problem
communicating in English you can also ask the Chinese maintainer for
help.  Contact the Chinese maintainer if this translation is outdated
or if there is a problem with the translation.

Chinese maintainer: 金丽丽 [e-mail]
---------------------------------------------------------------------
Documentation\arm64\memory的中文翻译

如果想评论或更新本文的内容，请直接联系原文档的维护者。如果你使用英文
交流有困难的话，也可以向中文版维护者求助。如果本翻译更新不及时或者翻
译存在问题，请联系中文版维护者。

中文版维护者： 金丽丽 [e-mail]
中文版翻译者： 金丽丽 [e-mail]
中文版校译者： 潘丽卡  [e-mail]

以下为正文
---------------------------------------------------------------------

 

Kernel Memory Layout on ARM Linux
Linux在ARM平台上的内存布局

Russell King <[e-mail] November 17, 2005 (2.6.15)

This document describes the virtual memory layout which the Linux
kernel uses for ARM processors.It indicates which regions are
free for platforms to use, and which are used by generic code.

本文档描述了Linux内核在ARM处理器上的虚拟内存布局,说明了哪些区域是给ARM平台使用的，哪些区域是通用代码使用的。

 

The ARM CPU is capable of addressing a maximum of 4GB virtual memory
space, and this must be shared between user space processes, the
kernel, and hardware devices.

ARM系列的CPU最大有4GB的虚拟内存空间寻址能力，但它必须用户空间，内存以及硬件设备共享地址空间。

 As the ARM architecture matures, it becomes necessary to reserve
certain regions of VM space for use for new facilities; therefore
this document may reserve more VM space over time.
 
在ARM架构成熟的同时，它也开始需要在VM空间保留明确的区域，让用户使用更简单，因此，随着时间的流逝，本文档可能保留了更多的VM空间。

Start  End  
Use
--------------------------------------------------------------------------

ffff8000 ffffffff copy_user_page / clear_user_page use. For SA11xx and Xscale, this is used to setup a minicache mapping.
ffff8000 ffffffff        clear_user_page的使用/对于SA11xx and Xscale，它用于设置机器映射。

ffff4000 ffffffff cache aliasing on ARMv6 and later CPUs。

 ffff4000 ffffffff        缓存在ARMv6中即CPU后。

ffff1000 ffff7fff Reserved.
Platforms must not use this address range.
ffff1000 ffff7fff        保留.ARM平台一定不使用这个区间

ffff0000 ffff0fff CPU vector page.The CPU vectors are mapped here if the CPU supports vector relocation (control
register V bit.)
 ffff0000 ffff0fff        CPU向量表。如果CPU支持向量重定向（控制寄存器的V位），则CPU向量被映射到这里。

fffe0000 fffeffff XScale cache flush area.  This is used
 in proc-xscale.S to flush the whole data
 cache. (XScale does not have TCM.)
 fffe0000 fffeffff XScale缓存刷新区域。这是用于proc-xscale去刷新数据缓存。(XScale没有TCM。)

 fffe8000 fffeffff DTCM mapping area for platforms with
DTCM mounted inside the CPU.
 fffe8000 fffeffff DTCM映射区域平台包括安装在CPU里的DTCM

fffe0000 fffe7fff ITCM mapping area for platforms with
 ITCM mounted inside the CPU.
  fffe7fff        ITCM映射区域平台包括安装在CPU里的ITCM

 fff00000 fffdffff Fixmap mapping region.  Addresses provided
 by fix_to_virt() will be located here.
 fff00000 fffdffff        内存映射区间。fix_to_virt()提供的地址位于这里。

 ffc00000 ffefffff DMA memory mapping region.  Memory returned by the dma_alloc_xxx functions will be dynamically mapped here.
  ffc00000 ffefffff DMA内存映射区。.由dma_ammoc_xxx系列函数返回的内存会动态的映射到这里。

 ff000000 ffbfffff Reserved for future expansion of DMA mapping region.
ff000000 ffbfffff 保留用于以后的DMA扩展映射区间。

 fee00000 feffffff Mapping of PCI I/O space. This is a static mapping within the vmalloc space.
 fee00000 feffffff 空间映射区. 这是一个在vmalloc空间的静态映射。

 

VMALLOC_START VMALLOC_END-1 vmalloc() / ioremap() space.
Memory returned by vmalloc/ioremap will
 be dynamically placed in this region.
 Machine specific static mappings are also
 located here through iotable_init().
VMALLOC_START is based upon the value
 of the high_memory variable, and VMALLOC_END
 is equal to 0xff000000.
  ioremap()空间
内存返回vmalloc / ioremap将动态地放置在这个地区。具体的静态映射通过iotable_init()也位于此。VMALLOC_START是基于价值的高端内存变量。xff000000 VMALLOC_END相当于0。

 PAGE_OFFSET high_memory-1 Kernel direct-mapped RAM region.
This maps the platforms RAM, and typically
 maps all platform RAM in a 1:1 relationship.
 内核直接映射内存区间。它映射平台的RAM，通常所有的平台都使用1：1的映射关系。

 PKMAP_BASE PAGE_OFFSET-1 Permanent kernel mappings
 One way of mapping HIGHMEM pages into kernel
 space.
  PKMAP_BASE PAGE_OFFSET-1 永久内核映射。一种highmem页映射到内核的方式。

 MODULES_VADDR MODULES_END-1 Kernel module space
 Kernel modules inserted via insmod are
 placed here using dynamic mappings.
  MODULES_VADDR MODULES_END-1 内核模块空间。内核模块使用动态映射通过放置insmod在这里。

 00001000 TASK_SIZE-1 User space mappings
 Per-thread mappings are placed here via
 the mmap() system call.
  00001000 TASK_SIZE-1 用户空间。每个进程通过mmap系统调用的映射放到这里。

 00000000 00000fff CPU vector page / null pointer trap
 CPUs which do not support vector remapping
 place their vector page here.  NULL pointer
 dereferences by both the kernel and user
 space are also caught via this mapping.
  00000000 00000fff CPU向量表，NULL指针陷井。不支持向量重映射的CPU的向量表被映射到这里。用户空间和内核态的NULL指针引通过这个映射可以被捕获。.

 Please note that mappings which collide with the above areas may result
in a non-bootable kernel, or may cause the kernel to
(eventually) panic
at run time.

请注意：一些与上面冲突的映射会导致内核无法启动，或者可能在运行时会产生（最终）内核panic !

 Since future CPUs may impact the kernel mapping layout, user programs
must not access any memory which is not mapped inside their 0x0001000
to TASK_SIZE address range.  If they wish to access these areas, they
must set up their own mappings using open() and mmap().
不管CPU特性会是否与内核的映射布局冲突，用户程序在内部没有映射0x0001000到TASK_SIZE之间的地址空间时，必须不能访问这里面的内存。如果他们想这样做，那么他们必须通过open和mmap来创建自己的映射。