Managing processing associated with hardware events

• US 8,510,599 B2
• Filed: 06/23/2010
• Issued: 08/13/2013
• Est. Priority Date: 06/23/2010
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Coneski, Anthony F., Craddock, David, Gainey, Charles W. Jr., Glendening, Beth A., Gregg, Thomas A., Njoku, Ugochukwu C., Szwed, Peter K.
• Primary Examiner(s): PATEL, KAMINI B
• Application Number:
  US12/821,191
• Publication Number:
  US 20110320860A1
• Time in Patent Office: 1,147 Days
• Field of Search: 714/25
• US Class Current: 714/25
• CPC Class Codes: G06F 11/0748 in a remote unit communicating with a single-box computer node experiencing an error/fault remote testing G06F11/2294
• CPC Class Codes: G06F 11/0793 Remedial or corrective actions recovery from an exception in an instruction pipeline G06F9/3861; by retry G06F11/1402; for recovering from a failure of a protocol instance or entity H04L69/40

Abstract

Detection, notification and/or processing of events, such as errors associated with adapters, are facilitated. Hardware detects an event, places one or more adapters in an error state to prevent access to/from the adapters, and notifies the operating system of the event.

Claims

1. A computer program product for managing events of a computing environment, said computer program product comprising:

a non-transitory computer readable storage medium readable by a processing circuit and storing instructions for execution by the processing circuit for performing a method comprising;

performing processing, based on detecting an event associated with an adapter, the performing processing comprising;

blocking instructions from accessing the adapter, the blocking comprising setting one or more indicators in a function table entry located in a system memory and associated with the adapter, the function table entry located using a function handle associated with the adapter, the function handle comprising at least one of a function number identifying the adapter, an enable indicator indicating whether the function handle is enabled, and an instance number specifying a particular instance of the function handle;

determining from a plurality of possible error types a type of error of the event being detected;

creating a PCI event based on the determined type of error of the event, the PCI event comprising one or more error details depending on the determined type of error;

initiating notification of an operating system of the created PCI event; and

executing a Store Event Information command issued by the operating system to obtain information from the created PCI event, the information comprising the function handle identifying the adapter, error details depending on the determined type of error, and a PCI event code describing a reason for notification of the event.

2. The computer program product of claim 1, wherein the event is associated with a plurality of adapters, each adapter having a separate error log.

3. The computer program product of claim 1, wherein the initiating notification comprises employing a channel report word (CRW).

4. The computer program product of claim 1, wherein the method further comprises blocking accesses from the adapter, the blocking comprises setting one or more indicators in a device table entry associated with the adapter.

5. The computer program product of claim 1, wherein the method further comprises:

setting an error vector indicator in an error vector to indicate an error; and

providing an attention interrupt to a processing unit executing the operating system.

6. The computer program product of claim 5, wherein the method further comprises:

determining whether data regarding the error is to be logged; and

logging the data, based on the determining indicating data is to be logged.

7. The computer program product of claim 5, wherein the method further comprises based on the attention interrupt, setting, by the processing unit, the one or more indicators in the function table entry associated with the adapter to block access to the adapter.

8. The computer program product of claim 7, wherein the method further comprises:

determining whether recovery is to be performed by a component of the computing environment other than the operating system; and

performing recovery, based on the determining indicating recovery is to be performed.

9. The computer program product of claim 8, wherein the method further comprises:

generating an error event, based on at least attempting to perform recovery;

presenting the error event to a hypervisor managing the operating system;

determining based on the error event whether recovery was successful; and

re-enabling one or more operations of the adapter, based on determining recovery was successful.

10. The computer program product of claim 1, wherein the method further comprises:

determining, based on detecting the event, that the event is not of the adapter;

determining, based on the event not being of the adapter, a hardware component providing the event; and

identifying, based on the hardware component, the adapter to be placed in an error state.

11. The computer program product of claim 10, wherein the method further comprises:

identifying, based on the hardware component, a plurality of adapters to be placed in the error state; and

placing the plurality of adapters in the error state.

12. The computer program product of claim 1, wherein the plurality of possible error types includes a direct memory access error, an interrupt error, and a bus error.

13. The computer program product of claim 1, wherein the determining the type of error comprises decoding an error type included in an error log entry located using a value associated with a device table entry located in an I/O hub coupled to the adapter, the device table entry corresponding to the adapter and including an error indicator indicating whether memory accesses are to be blocked.

14. A computer system for managing events of a computing environment, said computer system comprising:

a memory; and

a processor in communications with the memory, wherein the computer system is configured to perform a method, said method comprising;

performing processing, based on detecting an event associated with an adapter, the performing processing comprising;

blocking instructions from accessing the adapter, the blocking comprising setting one or more indicators in a function table entry located in a system memory and associated with the adapter, the function table entry located using a function handle associated with the adapter, the function handle comprising at least one of a function number identifying the adapter, an enable indicator indicating whether the function handle is enabled, and an instance number specifying a particular instance of the function handle;

determining from a plurality of possible error types a type of error of the event being detected;

creating a PCI event based on the determined type of error of the event, the PCI event comprising one or more error details depending on the determined type of error;

initiating notification of an operating system of the created PCI event; and

executing a Store Event Information command issued by the operating system to obtain information from the created PCI event, the information comprising the function handle identifying the adapter, error details depending on the determined type of error, and a PCI event code describing a reason for notification of the event.

15. The computer system of claim 14, wherein the event is associated with a plurality of adapters, each adapter having a separate error log.

16. The computer system of claim 14, wherein the initiating notification comprises employing a channel report word (CRW).

17. The computer system of claim 14, wherein the method further comprises:

setting an error vector indicator in an error vector to indicate an error;

providing an attention interrupt to a processing unit executing the operating system; and

based on the attention interrupt, setting, by the processing unit, the one or more indicators in the function table entry associated with the adapter to block access to the adapter.

18. The computer system of claim 14, wherein the method further comprises:

determining whether recovery is to be performed by a component of the computing environment other than the operating system; and

performing recovery, based on to the determining indicating recovery is to be performed.

19. The computer system of claim 18, wherein the method further comprises:

generating an error event, based on at least attempting to perform recovery;

presenting the error event to a hypervisor managing the operating system;

determining based on the error event whether recovery was successful; and

re-enabling one or more operations of the adapter, based on determining recovery was successful.

20. The computer system of claim 14, wherein the method further comprises:

determining, based on detecting the event, that the event is not of the adapter;

determining, based on the event not being of the adapter, a hardware component providing the event; and

identifying, based on the hardware component, the adapter to be placed in an error state.

21. A method for managing events of a computing environment, said method comprising:

performing processing by a processing unit, based on detecting an event associated with an adapter, the performing processing comprises;

blocking instructions from accessing the adapter, the blocking comprising setting one or more indicators in a function table entry located in a system memory and associated with the adapter, the function table entry located using a function handle associated with the adapter, the function handle comprising at least one of a function number identifying the adapter, an enable indicator indicating whether the function handle is enabled, and an instance number specifying a particular instance of the function handle;

determining from a plurality of possible error types a type of error of the event being detected;

creating a PCI event based on the determined type of error of the event, the PCI event comprising one or more error details depending on the determined type of error;

initiating notification of an operating system of the created PCI event; and

executing a Store Event Information command issued by the operating system to obtain information from the created PCI event, the information comprising the function handle identifying the adapter, error details depending on the determined type of error, and a PCI event code describing a reason for notification of the event.

22. The method of claim 21, wherein the event is associated with a plurality of adapters, each adapter having a separate error log.