Isolation of PCI and EISA masters by masking control and interrupt lines

• US 5,933,614 A
• Filed: 12/31/1996
• Issued: 08/03/1999
• Est. Priority Date: 12/31/1996
• Status: Expired due to Term

• Current Assignee: Hewlett Packard Enterprise Development LP (Hewlett-Packard Enterprise Company)
• Original Assignee: Compaq Computer Corporation (HP Inc.)
• Inventors: Tavallaei, Siamak, Hull, Daniel Stuart
• Primary Examiner(s): Sheikh, Ayaz R.
• Assistant Examiner(s): WILEY, DAVID ARMAND
• Application Number:
  US08/775,392
• Time in Patent Office: 945 Days
• Field of Search: 395/200.55, 395/293, 395/280, 395/309
• US Class Current: 710/306
• 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
• CPC Class Codes: G06F 11/20 using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements
• CPC Class Codes: G06F 11/2025 using centralised failover control functionality
• CPC Class Codes: G06F 11/2294 by remote test
• CPC Class Codes: G06F 11/349 for interfaces, buses
• CPC Class Codes: G06F 11/3495 for systems

Abstract

A system management module (SMM) for a host server system includes a system management processor (SMP) connected to a system management local bus. The system management local bus connects to the system PCI bus through a system management central (SMC). The SMC includes the main arbitration unit for the PCI bus and also includes the arbiter for the system management local bus. The SMM includes a video controller and/or keyboard and mouse controller connected to the system management local bus to support remote consoling of the SMM. The SMC includes logic to monitor PCI cycles and to issue error signals in the event of a system error. The SMC also isolates failed components by masking request, grant and interrupt lines for the failed device. Further, if a spare component is provided, the SMC permits dynamic switching to the spare. In addition to detecting errors and performing survival and maintenance operations, the SMC enhances system performance during normal operations by supporting master-target priority determinations to more efficiently arbitrate mastership of system busses such as the PCI bus.

Claims

1. A computer system, comprising:

a host processor connected to a host bus;

a bus bridge connecting said host bus to a system expansion bus;

a system management module connected to said system expansion bus, said system management module including;

a system management processor connected to a system management local bus;

a system management central control unit connected to said system management local bus and to the expansion system bus;

wherein said system management central control unit includes an arbiter and monitor logic which operates as a bus arbiter for the expansion bus, and interrupt routing logic for selectively routing interrupt requests to the host processor originating from components on the expansion bus.

2. A system as in claim 1, wherein the system expansion bus comprises a PCI bus, and the system management central control unit operates as the bus arbiter for the PCI bus.

3. A system as in claim 2, further comprising a second system expansion bus coupled to said PCI bus by a second bus bridge.

4. A system as in claim 3, wherein the second expansion bus comprises an EISA bus.

5. A system as in claim 3, wherein the second bus bridge couples to said system management central control unit and to said host processor through an interrupt bus.

6. A system as in claim 5, wherein the interrupt bus comprises an APIC bus.

7. A system as in claim 5, wherein the second bus bridge functions to relay interrupt requests from devices connected to the second system expansion bus.

8. A system as in claim 7, further comprising a system management remote unit connected to said second system expansion bus, said system management remote unit connecting to said system management central control unit by a serial bus.

9. A system as in claim 8, wherein the system management remote unit provides a signal to said system management central control unit in the event that a device connected to the second system expansion bus fails.

10. A system as in claim 9, wherein the interrupt routing logic is capable of masking interrupt requests relayed by the second bus bridge in the event that the device requesting an interrupt has failed.

11. A system as in claim 2, wherein the system management central control unit receives requests for mastership of the PCI bus from PCI master devices connected to the PCI bus.

12. A system as in claim 11, wherein the arbiter and monitor logic receives the requests for mastership and grants mastership of the PCI bus to requesting masters.

13. A system as in claim 12, wherein the interrupt routing logic receives interrupt requests from devices connected to the PCI bus.

14. A system as in claim 13, wherein the arbiter and monitor logic monitors the PCI bus to determine if any components connected to the PCI bus have failed.

15. A system as in claim 14, wherein the system management central control unit masks the interrupts from failed devices on the PCI bus.

16. A system as in claim 14, wherein the arbiter and monitor logic ignores requests for mastership from failed devices on the PCI bus.

17. A system as in claim 4, further comprising a plurality of system management remote units coupled to said system management central control unit.

18. A system as in claim 17, wherein said system management remote units couple to said system management central control unit by a standard test bus.

19. A system as in claim 18, wherein at said system management remote units also couple to said system management central control unit by a bi-directional bus.

20. A system as in claim 18, wherein at least one of the system management remote units also couple to the system management central control unit by an ICIB bus.

21. A system as in claim 20, wherein at least one of the system management remote units also couple to the system management central control unit by a GI bus.

22. A system as in claim 21, wherein said system management central control unit includes common terminals for connecting to both the ICIB bus and the GI bus.

23. A system as in claim 17, wherein at least one of the system management remote units couple to an IIC bus.

24. A system as in claim 17,wherein one of said plurality of system management remote units also couples to the EISA bus.

25. A system as in claim 17, wherein one of said plurality of system management remote units also couples to the first bus bridge.

26. A system as in claim 17, wherein one of said plurality of system management remote units also couples to the second bus bridge.

27. A system as in claim 17, wherein one of said plurality of system management remote units also couples to the host bus.

28. A computer system, comprising:

a host processor connected to a host bus;

a bus bridge connecting said host bus to a PCI bus;

a system management module connected to said PCI bus, said system management module including a system management central control unit connected to said PCI bus;

wherein said system management central control unit includes an arbiter and monitor logic which operates as a PCI bus arbitration unit, and said arbiter and monitor logic receives requests for mastership of the PCI bus from PCI master devices connected to the PCI bus, and said arbiter and monitor logic monitors the PCI bus to determine if any components connected to the PCI bus have failed.

29. A system as in claim 28, wherein the arbiter and monitor logic ignores requests for mastership from failed devices on the PCI bus.

30. A system as in claim 29, wherein the system management central control unit also includes interrupt routing logic for receiving interrupt requests from devices connected to the PCI bus.

31. A system as in claim 30, wherein the system management central control unit masks the interrupts from failed devices on the PCI bus.

32. A system as in claim 31, wherein one of the devices requesting mastership of the PCI bus is a PCI to EISA bus bridge, and the PCI-to-EISA bus bridge interfaces the PCI bus to an EISA bus.

33. A system as in claim 32, wherein the PCI-to-EISA bus bridge connects to said interrupt routing logic through an interrupt bus to route all interrupts from the EISA bus to the system management central control unit.

34. A system as in claim 33, further comprising a system management remote unit connected to said EISA bus, said system management remote unit connecting to said system management central control unit by a serial bus.

35. A system as in claim 34, wherein the serial bus comprises a high speed bi-directional inter-chip interrupt bus.

36. A system as in claim 35, wherein the system management remote unit provides a signal to said system management central control unit in the event that a device connected to the EISA bus fails.

37. A system as in claim 36, wherein the interrupt routing logic is capable of masking interrupt requests relayed by the bus bridge in the event that the device requesting an interrupt has failed.

38. A system as in claim 28, further comprising a system management processor coupled to said system management central control unit through a system management local bus.

39. A computer system, comprising:

a host processor connected to a host bus;

a bus bridge connecting said host bus to a PCI bus;

a system management module connected to said PCI bus, said system management module including a system management central control unit connected to said PCI bus;

wherein said system management central control unit includes monitor logic to monitor the PCI bus to determine if any components connected to the PCI bus have failed, and interrupt routing logic for selectively routing interrupt request to the host processor originating from components on the PCI bus, said interrupt routing logic capable of isolating failed devices on the PCI bus.

40. A system as in claim 39, wherein the system management central control unit masks the interrupts from a failed device on the PCI bus to prevent interrupt requests from the failed device from being routed to the host processor.

41. A system as in claim 40, further comprising a system management processor coupled to said system management central control unit through a system management local bus.

42. A computer system, comprising:

a host processor connected to a host bus;

a bus bridge connecting said host bus to a PCI bus;

a second bus bridge connected to said PCI bus and to a system expansion bus;

a system management module connected to said PCI bus, said system management module including a system management central control unit connected to said PCI bus;

said system management central control unit including interrupt routing logic for selectively routing interrupt requests to the host processor;

a system management remote unit connected to said system expansion bus, said system management remote unit connecting to said interrupt routing logic by a serial bus; and

said second bus bridge connects to said interrupt logic by an interrupt bus, and said second bus bridge relays interrupt requests from devices connected to the system expansion bus.

43. A system as in claim 42, wherein the system expansion bus comprises an EISA bus, and the second bus bridge comprises a PCI-to-EISA bridge.

44. A system as in claim 42, wherein the system management remote unit provides a signal to said system management central control unit in the event that a device connected to the system expansion bus fails.

45. A system as in claim 44, wherein the interrupt routing logic is capable of masking interrupt requests relayed by the second bus bridge in the event that the device requesting an interrupt has failed.