Level One Memory System
ARM DDI 0363G Copyright © 2006-2011 ARM Limited. All rights reserved. 8-7
ID073015 Non-Confidential
8.3 Fault handling
Faults can occur on instruction fetches for the following reasons:
• MPU background fault
• MPU permission fault
• External AXI slave error (SLVERR)
• External AXI decode error (DECERR)
• Cache parity or ECC error
• TCM parity or ECC error
• TCM external error
• TCM external retry request
• Breakpoints, and vector capture events.
Faults can occur on data accesses for the following reasons:
• MPU background fault
• MPU permission fault
• MPU alignment fault
• External AXI slave error (SLVERR)
• External AXI decode error (DECERR)
• Cache parity or ECC error
• TCM parity or ECC error
• TCM external error
• TCM external retry request
• Watchpoints.
Fault handling is described in:
• Faults
• Fault status information on page 8-9
• Correctable Fault Location Register on page 8-10
• Usage models on page 8-10.
8.3.1 Faults
The classes of fault that can occur are:
• MPU faults
• External faults on page 8-8
• Cache and TCM parity and ECC errors on page 8-8
• TCM external faults on page 8-8
• Debug events on page 8-9
• Synchronous and asynchronous aborts on page 8-9.
MPU faults
The MPU can generate an abort for various reasons. See MPU faults on page 7-10 for more
information. MPU faults are always synchronous, and take priority over other types of abort. If
an MPU fault occurs on an access that is not in the TCM, and is Non-cacheable, or has generated
a cache-miss, the AXI transactions for that access are not performed.