Hardware-assisted paravirtualized hardware watchdog

Patent metadata

Field	Value
Publication number	US-11726852-B2
Application number	US-202217577627-A
Country	US
Kind code	B2
Filing date	Jan 18, 2022
Priority date	Jan 18, 2022
Publication date	Aug 15, 2023
Grant date	Aug 15, 2023

Abstract

A hardware-assisted paravirtualized hardware watchdog is described that is used to detect and recover from computer malfunctions. A computing device determines that a hardware-implemented watchdog of the computing device does not comply with predetermined watchdog criteria, where the hardware-implemented watchdog is configured to send a reset signal when a first predetermined amount of time elapses without receipt of a first refresh signal. If the hardware-implemented watchdog does not comply with the predetermined watchdog criteria, a runtime watchdog service is initialized using a second predetermined amount of time. The runtime watchdog service is directed to periodically send the refresh signal to the hardware-implemented watchdog before an expiration of the first predetermined amount of time that causes the hardware-implemented watchdog to expire. The hardware-implemented watchdog is directed to send the reset signal when the second predetermined amount of time elapses without receipt of a second refresh signal.

First claim

Therefore, the following is claimed:

1. A system for implementing a hardware-assisted paravirtualized hardware watchdog, comprising:
at least one computing device comprising a hardware-implemented watchdog and at least one hardware processor; and
program instructions stored in memory and executable by the at least one computing device that, when executed by the at least one hardware processor, direct the at least one computing device to:
determine that the hardware-implemented watchdog of the at least one computing device does not comply with predetermined watchdog criteria, the hardware-implemented watchdog configured to send a reset signal when a first predetermined amount of time elapses without receipt of a first refresh signal, wherein the predetermined watchdog criteria specifies a requirement that the hardware-implemented watchdog is capable of handling a period of time above a threshold time, the hardware-implemented watchdog is capable of handling a bite operation that causes a system reset, and the hardware-assisted watchdog has a predefined watchdog offset register;
in response to the hardware-implemented watchdog not complying with the predetermined watchdog criteria, initialize a runtime watchdog service using a second predetermined amount of time, the second predetermined amount of time being greater than the first predetermined amount of time;
direct the runtime watchdog service to periodically send the first refresh signal to the hardware-implemented watchdog before an expiration of the first predetermined amount of time that causes the hardware-implemented watchdog to expire; and
direct the hardware-implemented watchdog to send the reset signal when the second predetermined amount of time elapses without receipt of a second refresh signal.

2. The system of claim 1 , wherein:
the program instructions are a portion of firmware of the at least one computing device stored in non-volatile memory; and
the reset signal directs the at least one computing device to enter into a safe mode or perform a device reset.

3. The system of claim 1 , wherein the runtime watchdog service is initialized by a Unified Extensible Firmware Interface (UEFI) service during an operating system loading stage of a boot process.

4. The system of claim 3 , wherein the runtime watchdog service is further initialized in response to a secure monitor call (SMC) invoked by an operating system loading service or a bare-metal hypervisor loading service.

5. The system of claim 1 , wherein the runtime watchdog service is accessible to an operating system or a bare-metal hypervisor by providing information related to the runtime watchdog service in an advanced configuration and power interface (ACPI) table.

6. The system of claim 1 , wherein the at least one computing device is at least one smart network interface card (smartNIC).

7. A computer-implemented method, comprising:
determining that a hardware-implemented watchdog of at least one computing device does not comply with predetermined watchdog criteria, the hardware-implemented watchdog configured to send a reset signal when a first predetermined amount of time elapses without receipt of a first refresh signal;
in response to the hardware-implemented watchdog not complying with the predetermined watchdog criteria, initializing a runtime watchdog service using a second predetermined amount of time, the second predetermined amount of time being greater than the first predetermined amount of time, wherein the predetermined watchdog criteria specifies a requirement that the hardware-implemented watchdog is capable of handling a period of time above a threshold time, the hardware-implemented watchdog is capable of handling a bite operation that causes a system reset, and the hardware-assisted watchdog has a predefined watchdog offset register;
directing the runtime watchdog service to periodically send the first refresh signal to the hardware-implemented watchdog before an expiration of the first predetermined amount of time that causes the hardware-implemented watchdog to expire; and
directing the hardware-implemented watchdog to send the reset signal when the second predetermined amount of time elapses without receipt of a second refresh signal.

8. The computer-implemented method of claim 7 , wherein:
the computer-implemented method is performed through execution of a portion of firmware of the at least one computing device stored in non-volatile memory; and
the reset signal directs the at least one computing device to enter into a safe mode or perform a device reset.

9. The computer-implemented method of claim 7 , wherein the runtime watchdog service is initialized by a Unified Extensible Firmware Interface (UEFI) service during an operating system loading stage of a boot process.

10. The computer-implemented method of claim 9 , wherein the runtime watchdog service is further initialized in response to a secure monitor call (SMC) invoked by an operating system loading service or a bare-metal hypervisor loading service.

11. The computer-implemented method of claim 7 , wherein the runtime watchdog service is accessible to an operating system or a bare-metal hypervisor by providing information related to the runtime watchdog service in an advanced configuration and power interface (ACPI) table.

12. The computer-implemented method of claim 7 , wherein the at least one computing device is at least one smart network interface card (smartNIC).

13. A non-transitory computer-readable medium having program instructions stored thereon executable by at least one hardware processor that, when executed by the at least one hardware processor, direct the at least one hardware processor to:
determine that a hardware-implemented watchdog of at least one computing device does not comply with predetermined watchdog criteria, the hardware-implemented watchdog configured to send a reset signal when a first predetermined amount of time elapses without receipt of a first refresh signal;
in response to the hardware-implemented watchdog not complying with the predetermined watchdog criteria, initialize a runtime watchdog service using a second predetermined amount of time, the second predetermined amount of time being greater than the first predetermined amount of time, wherein the predetermined watchdog criteria specifies a requirement that the hardware-implemented watchdog is capable of handling a period of time above a threshold time, the hardware-implemented watchdog is capable of handling a bite operation that causes a system reset, and the hardware-assisted watchdog has a predefined watchdog offset register;
direct the runtime watchdog service to periodically send the first refresh signal to the hardware-implemented watchdog before an expiration of the first predetermined amount of time that causes the hardware-implemented watchdog to expire; and
direct the hardware-implemented watchdog to send the reset signal when the second predetermined amount of time elapses without receipt of a second refresh signal.

14. The non-transitory computer-readable medium of claim 13 , wherein:
the program instructions are a portion of firmware of the at least one computing device stored in non-volatile memory;
the reset signal directs the at least one computing device to enter into a safe mode or perform a device reset; and
the at least one computing device is at least one smart network interface card (smartNIC).

15. The non-transitory computer-readable medium of claim 13 , wherein the runtime watchdog service is initialized by a Unified Extensible Firmware Interface (UEFI) service during an operating system

Assignees

• Vmware Inc

Inventors

• Warkentin Andrei
• Kotian Sunil
• Mcneill Jared
• Hiriyuru Shruthi
• Fainkichen Alexander

Classifications

• G06F11/0757 Primary

  by exceeding a time limit, i.e. time-out, e.g. watchdogs · CPC title

• G06F9/45541

  Bare-metal, i.e. hypervisor runs directly on hardware · CPC title

• G06F11/0772

  Means for error signaling, e.g. using interrupts, exception flags, dedicated error registers · CPC title

• G06F11/1417

  Boot up procedures · CPC title

• G06F11/1484

  involving virtual machines · CPC title