Advertisement
www.ti.com
Figure 15-5
shows two benefits of using an MMU. Memory region 1 and memory region 2 are fragmented
in physical memory. Using the MMU, they appear as one contiguous memory region in the virtual memory
space.
On the other hand, task 1 and task 2 are located adjacent to each other in physical memory. In systems
without an MMU, there is a danger that task 1 can accidentally write into the memory area allocated to
task 2 and vice versa. Allocating task 1 and task 2 into two separate virtual memory regions prevents this
problem, because a region of unmapped memory separates the two tasks. Any erroneous access to this
region results in an error that can be detected easily.
15.3.2 MMU Architecture
The MMU translation process is based on translation entries stored in translation tables. One first-level
translation table can exist with several optional second-level translation tables.
Each table entry describes the translation of one contiguous memory region. For a description of the
structure of these tables, see
Two major functional units exist in the MMU to provide address translation automatically based on the
table entries:
SWPU177N – December 2009 – Revised November 2010
Public Version
Figure 15-5. MMU Usage Examples
Section
15.3.3, Tranlation Tables.
Copyright © 2009–2010, Texas Instruments Incorporated
MMU Functional Description
MMU-005
2669
Memory Management Units
Advertisement
Chapters
