Table of Contents
Advertisement
8.7.1
Possible Fault Handling Procedure Actions
The processor allows easy recovery from many faults that occur. When fault recovery is possible,
the processor's fault handling mechanism allows the processor to automatically resume work on
the program or pending interrupt when the fault occurred. Resumption is initiated with a
instruction in the fault handling procedure.
If recovery from the fault is not possible or not desirable, the fault handling procedure can take one
of the following actions, depending on the nature and severity of the fault condition (or conditions,
in the case of multiple faults):
•
Return to a point in the program or interrupt code other than the point of the fault.
•
Call a debug monitor.
•
Perform processor or system shutdown with or without explicitly saving the processor state
and fault information.
When working with the processor at the development level, a common fault handling strategy is to
save the fault and processor state information and call a debugging tool such as a monitor.
8.7.2
Program Resumption Following a Fault
Because of the wide variety of faults, they can occur at different times with respect to the faulting
instruction:
•
Before execution of the faulting instruction (e.g., fetch from on-chip RAM)
•
During instruction execution (e.g., integer overflow)
•
Immediately following execution (e.g., trace)
8.7.2.1
Faults Happening Before Instruction Execution
The following fault types occur before instruction execution:
•
ARITHMETIC.ZERO_DIVIDE
•
TYPE.MISMATCH
•
PROTECTION.LENGTH
•
All OPERATION subtypes except UNALIGNED
For these faults, the contents of a destination register are lost, and memory is not updated. The RIP
is defined for the ARITHMETIC.ZERO_DIVIDE fault only. In some cases the fault occurs before
the faulting instruction is executed, the faulting instruction may be fixed and re-executed upon
return from the fault handling procedure.
FAULTS
ret
8
8-13
Advertisement
Table of Contents
