Techniques for indicating a preferred virtual processor thread to service an interrupt in a data processing system

• US 9,678,901 B2
• Filed: 10/26/2016
• Issued: 06/13/2017
• Est. Priority Date: 11/16/2015
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Arndt, Richard L., Auernhammer, Florian A., Ouren, Wade B., Jacobs, Stuart Z.
• Primary Examiner(s): Myers, Paul R
• Application Number:
  US15/334,924
• Publication Number:
  US 20170139854A1
• Time in Patent Office: 230 Days
• Field of Search: 710260-269
• CPC Class Codes: G06F 12/12 Replacement control
• CPC Class Codes: G06F 12/122 of the least frequently used [LFU] type, e.g. with individual count value
• CPC Class Codes: G06F 13/24 using interrupt G06F13/32 takes precedence
• CPC Class Codes: G06F 13/26 with priority control
• CPC Class Codes: G06F 13/28 using burst mode transfer, e.g. direct memory access DMA, cycle steal G06F13/32 takes precedence
• CPC Class Codes: G06F 13/4068 Electrical coupling
• CPC Class Codes: G06F 2212/70 Details relating to dynamic memory management
• CPC Class Codes: G06F 9/4812 by interrupt, e.g. masked
• CPC Class Codes: G06F 9/542 Event management; Broadcasting; Multicasting; Notifications

Abstract

A technique for handling interrupts includes receiving an event notification message (ENM) that specifies an event target number (ETN) and a number of bits to ignore (NBI). The ETN identifies a specific virtual processor thread (VPT) and the NBI identifies the number of lower-order bits of the specific VPT to ignore when determining a group of VPTs that may be potentially interrupted. In response to two or more VPTs within the group of VPTs being dispatched and operating on an associated physical processor, whether multiple of the two or more VPTs do not have a pending interrupt is determined. In response to determining that multiple of the two or more VPTs do not have a pending interrupt, one of the two or more VPTs is selected to service an interrupt associated with the ENM based, at least in part, on respective preferred bits for the two or more VPTs.

Claims

1. A method of handling interrupts in a data processing system, the method comprising:

receiving, at an interrupt presentation controller (IPC), an event notification message (ENM), wherein the ENM specifies an event target number and a number of bits to ignore;

determining, by the IPC, a group of virtual processor threads that may be potentially interrupted based on the event target number and the number of bits to ignore, wherein the event target number identifies a specific virtual processor thread and the number of bits to ignore identifies the number of lower-order bits to ignore with respect to the specific virtual processor thread when determining the group of virtual processor threads that may be potentially interrupted;

in response to two or more virtual processor threads within the group of virtual processor threads being dispatched and operating on an associated physical processor, determining, by the IPC, whether multiple of the two or more virtual processor threads do not have a pending interrupt; and

in response to determining that multiple of the two or more virtual processor threads do not have a pending interrupt, selecting, by the IPC, one of the two or more virtual processor threads to service an interrupt associated with the ENM based, at least in part, on respective preferred bits for the two or more virtual processor threads.

2. The method of claim 1, wherein the ENM further specifies an event priority and the method further comprises:

in response to determining that all of the two or more virtual processor threads have a pending interrupt, determining whether the event priority is greater than an operating priority of all of the two or more virtual processor threads; and

in response to the event priority being greater than the operating priority for multiple of the two or more virtual processor threads, selecting one of the two or more virtual processor threads to service an interrupt associated with the ENM based, at least in part, on the respective preferred bits for the two or more virtual processor threads.

3. The method of claim 1, wherein the preferred bits are specified by an operating system or a hypervisor.

4. The method of claim 1, wherein the number of bits to ignore is ‘

n’

bits and the specific virtual processor thread and (2ⁿ−

1) other virtual processor threads may be potentially interrupted.

5. The method of claim 1, wherein the number of bits to ignore is not equal to zero, the ENM further includes an event source number, and the method further comprises:

in response to no virtual processor thread within the group of virtual processor threads being dispatched and operating on an associated physical processor, issuing a reject message to a notification source specified by the event source number.

6. The method of claim 1, wherein the number of bits to ignore is not equal to zero, the ENM further includes an event source number, and the method further comprises:

in response to multiple virtual processor threads within the group of virtual processor threads being dispatched and operating on an associated physical processor, determining whether all of the multiple processor threads have pending interrupts;

in response to determining that all of the multiple processor threads have pending interrupts, determining whether the event priority of the ENM is greater than an operating priority of any of the multiple virtual processor threads; and

in response to determining that the event priority of the ENM is not greater than the operating priority of any of the multiple virtual processor threads, issuing a reject message to a notification source specified by the event source number in the ENM.

7. The method of claim 1, wherein the number of bits to ignore is not equal to zero, the ENM further includes an escalate event number, and the method further comprises:

in response to no virtual processor thread within the group of virtual processor threads being dispatched and operating on an associated physical processor, issuing an escalate message with the escalate event number.

8. The method of claim 1, wherein the number of bits to ignore is not equal to zero and the method further comprises:

in response to no virtual processor thread within the group of virtual processor threads being dispatched and operating on an associated physical processor, issuing an escalate message with an escalate event number sourced from a table in the IPC.

9. A processing unit for a multithreaded data processing system, the processing unit comprising:

an interrupt source controller (ISC); and

an interrupt presentation controller (IPC) coupled to the ISC, wherein the IPC is configured to;

receive an event notification message (ENM), wherein the ENM specifies an event target number and a number of bits to ignore;

determine a group of virtual processor threads that may be potentially interrupted based on the event target number and the number of bits to ignore, wherein the event target number identifies a specific virtual processor thread and the number of bits to ignore identifies the number of lower-order bits to ignore with respect to the specific virtual processor thread when determining the group of virtual processor threads that may be potentially interrupted;

in response to two or more virtual processor threads within the group of virtual processor threads being dispatched and operating on an associated physical processor, determine whether multiple of the two or more virtual processor threads do not have a pending interrupt; and

in response to determining that multiple of the two or more virtual processor threads do not have a pending interrupt, select one of the two or more virtual processor threads to service an interrupt associated with the ENM based, at least in part, on respective preferred bits for the two or more virtual processor threads.

10. The processing unit of claim 9, wherein the ENM further specifies an event priority and the IPC is further configured to:

in response to determining that all of the two or more virtual processor threads have a pending interrupt, determine whether the event priority is greater than an operating priority of all of the two or more virtual processor threads; and

in response to the event priority being greater than the operating priority for multiple of the two or more virtual processor threads, select one of the two or more virtual processor threads to service an interrupt associated with the ENM based, at least in part, on the respective preferred bits for the two or more virtual processor threads.

11. The processing unit of claim 9, wherein the preferred bits are specified by an operating system or a hypervisor.

12. The processing unit of claim 9, wherein the number of bits to ignore is ‘

n’

bits and the specific virtual processor thread and (2ⁿ−

1) other virtual processor threads may be potentially interrupted.

13. The processing unit of claim 9, wherein the number of bits to ignore is not equal to zero, the ENM further includes an event source number, and the IPC is further configured to:

in response to no virtual processor thread within the group of virtual processor threads being dispatched and operating on an associated physical processor, issue a reject message to a notification source specified by the event source number.

14. The processing unit of claim 9, wherein the number of bits to ignore is not equal to zero, the ENM further includes an event source number, and the IPC is further configured to:

in response to multiple virtual processor threads within the group of virtual processor threads being dispatched and operating on an associated physical processor, determine whether all of the multiple processor threads have pending interrupts;

in response to determining that all of the multiple processor threads have pending interrupts, determine whether the event priority of the ENM is greater than an operating priority of any of the multiple virtual processor threads; and

in response to determining that the event priority of the ENM is not greater than the operating priority of any of the multiple virtual processor threads, issue a reject message to a notification source specified by the event source number in the ENM.

15. The processing unit of claim 9, wherein the number of bits to ignore is not equal to zero, the ENM further includes an escalate event number, and the IPC is further configured to:

in response to no virtual processor thread within the group of virtual processor threads being dispatched and operating on an associated physical processor, issue an escalate message with the escalate event number.

16. The processing unit of claim 9, wherein the number of bits to ignore is not equal to zero and the IPC is further configured to:

in response to no virtual processor thread within the group of virtual processor threads being dispatched and operating on an associated physical processor, issue an escalate message with an escalate event number sourced from a table in the IPC.

17. A design structure tangibly embodied in a computer-readable storage device for designing, manufacturing, or testing an integrated circuit, the design structure comprising:

an interrupt source controller (ISC); and

an interrupt presentation controller (IPC) coupled to the ISC, wherein the IPC is configured to;

receive an event notification message (ENM), wherein the ENM specifies an event target number and a number of bits to ignore;

determine a group of virtual processor threads that may be potentially interrupted based on the event target number and the number of bits to ignore, wherein the event target number identifies a specific virtual processor thread and the number of bits to ignore identifies the number of lower-order bits to ignore with respect to the specific virtual processor thread when determining the group of virtual processor threads that may be potentially interrupted;

in response to two or more virtual processor threads within the group of virtual processor threads being dispatched and operating on an associated physical processor, determine whether multiple of the two or more virtual processor threads do not have a pending interrupt; and

in response to determining that multiple of the two or more virtual processor threads do not have a pending interrupt, select one of the two or more virtual processor threads to service an interrupt associated with the ENM based, at least in part, on respective preferred bits for the two or more virtual processor threads.

18. The design structure of claim 17, wherein the ENM further specifies an event priority and the IPC is further configured to:

in response to determining that all of the two or more virtual processor threads have a pending interrupt, determine whether the event priority is greater than an operating priority of all of the two or more virtual processor threads; and

in response to the event priority being greater than the operating priority for multiple of the two or more virtual processor threads, select one of the two or more virtual processor threads to service an interrupt associated with the ENM based, at least in part, on the respective preferred bits for the two or more virtual processor threads.

19. The design structure of claim 17, wherein the preferred bits are specified by an operating system or a hypervisor.

20. The design structure of claim 17, wherein the number of bits to ignore is ‘

n’

bits and the specific virtual processor thread and (2ⁿ−

1) other virtual processor threads may be potentially interrupted.