Browse Prior Art Database

Handling Disabled Page Faults

IP.com Disclosure Number: IPCOM000078249D
Original Publication Date: 1972-Dec-01
Included in the Prior Art Database: 2005-Feb-25
Document File: 3 page(s) / 63K

Publishing Venue

IBM

Related People

Johnson, JK: AUTHOR

Abstract

GTF (Generalized Trace Facility) is a known system trace facility, operable in a relocate system to collect and record data related to task switches and SVC (Supervisor Call), program, external, and I/O interrupts. The collection of data is done in a disabled state by serially reusable routines, that execute as an extension of a Program First Level Interrupt Handler. With the exception of SVC tracing, the data collected for a particular event normally exists in real storage so there is no page-fault exposure. In the case of SVC's, however, the parameters and parameter lists hat are accessed might not always be in real storage and hence produce a page fault. Because of the serially reusable nature of the synchronous data gathering routines, enabling to allow a page-in to be performed would result in a catastrophic failure.

This text was extracted from a PDF file.
At least one non-text object (such as an image or picture) has been suppressed.
This is the abbreviated version, containing approximately 53% of the total text.

Page 1 of 3

Handling Disabled Page Faults

GTF (Generalized Trace Facility) is a known system trace facility, operable in a relocate system to collect and record data related to task switches and SVC (Supervisor Call), program, external, and I/O interrupts. The collection of data is done in a disabled state by serially reusable routines, that execute as an extension of a Program First Level Interrupt Handler. With the exception of SVC tracing, the data collected for a particular event normally exists in real storage so there is no page-fault exposure. In the case of SVC's, however, the parameters and parameter lists hat are accessed might not always be in real storage and hence produce a page fault. Because of the serially reusable nature of the synchronous data gathering routines, enabling to allow a page-in to be performed would result in a catastrophic failure. To resolve this problem, the process illustrated in the flow chart was designed.

The process is used by disabled SVC processing routines to obtain SVC parameter data that presents a page-fault exposure. There are basically three routines involved in the process: (1) the synchronous SVC processing routine 10; (2) an error routine 11 associated with the SVC routine; and (3) a resident reentrant routine 12 that can be scheduled to asynchronously collect SVC parameter data in a temporary fixed storage area. Also key to the process, is the existence of a field in the TCB (Task Control Block) which can be used to point to a temporary work area.

As for system capability required by the process, the system control program must provide an error recovery interface which will allow the SVC error routine to obtain control, when a page fault occurs during synchronous SVC processing in disabled state. Also the system must provide the capability to schedule an asynchronous routine under a task on a high-priority bas...