Memory scrub system
A memory scrubbing system includes a persistent memory device coupled to an operating system (OS) and a Basic Input/Output System (BIOS). During a boot process and prior to loading the OS, the BIOS retrieves a known memory location list that identifies known memory locations of uncorrectable errors in the persistent memory device and performs a partial memory scrubbing operation on the known memory locations. The BIOS adds any known memory locations that maintain an uncorrectable error to a memory scrub error list. The BIOS then initiates a full memory scrubbing operation on the persistent memory device, cause the OS to load and enter a runtime environment while the full memory scrubbing operation is being performed, and provides the memory scrub error list to the OS.
1. A memory error management system, comprising:
a memory subsystem; and
a memory error management engine that is coupled to the memory subsystem, wherein the memory error management subsystem is configured to:
identify, during a boot process, memory locations that were previously identified with uncorrectable errors in the memory subsystem;
determine, during the boot process and while performing a partial memory scrubbing operation on the memory locations that were previously identified with uncorrectable errors, whether any of the memory locations that were previously identified with uncorrectable errors maintain an uncorrectable error;
perform, subsequent to performing the partial memory scrubbing operation, a full memory scrubbing operation on the memory subsystem;
report a completion of memory scrubbing operations to at least one runtime subsystem in order to allow the at least one runtime subsystem to enter a runtime environment; and
provide the memory locations that were previously identified with uncorrectable errors and that maintain an uncorrectable error to the at least one runtime subsystem.
2. The system of claim 1 , wherein the memory error management subsystem is configured to:
receive a memory scrubbing operation completion query from the at least one runtime subsystem and, in response, report the completion of memory scrubbing operations to the at least one runtime subsystem, wherein the full memory scrubbing operation is performed on the memory subsystem subsequent to reporting the completion of memory scrubbing operations to the at least one runtime subsystem.
3. The system of claim 2 , wherein the memory error management subsystem is configured to:
provide the memory locations that were previously identified with uncorrectable errors and that maintain an uncorrectable error to the at least one runtime subsystem in response to the memory scrubbing operation completion query.
4. The system of claim 1 , wherein the memory error management subsystem is configured to:
identify, based on the full memory scrubbing operation performed on the memory subsystem, a memory location with a currently detected uncorrectable error; and
report the memory location with the currently detected uncorrectable error to the at least one runtime subsystem.
5. The system of claim 4 , wherein the memory error management subsystem is configured to report the memory location with the currently detected uncorrectable error to the at least one runtime subsystem by:
generating an interrupt that causes the at least one runtime subsystem to retrieve an identity of the memory location with the currently detected uncorrectable error.
6. The system of claim 1 , wherein the memory error management subsystem is configured to:
initiate the performance of the full memory scrubbing operation on the memory subsystem prior to the at least one runtime subsystem entering the runtime environment.
7. The system of claim 1 , wherein the memory error management subsystem is configured to:
receive, from the at least one runtime subsystem subsequent to reporting the completion of memory scrubbing operations to the at least one runtime subsystem and while performing the full memory scrubbing operation, a new memory scrubbing operation instruction; and
notify, in response to receiving the new memory scrubbing operation instruction, the at least one runtime subsystem that the full memory scrubbing operation is in progress.
8. An Information Handling System (IHS), comprising:
a processing subsystem; and
a memory subsystem that is coupled to the processing subsystem and that includes instructions that, when executed by the processing subsystem, causes the processing subsystem to provide a memory error management engine that is configured to:
identify, during a boot process, memory locations that were previously identified with uncorrectable errors in a memory subsystem;
determine, during the boot process and while performing a partial memory scrubbing operation on the memory locations that were previously identified with uncorrectable errors, whether any of the memory locations that were previously identified with uncorrectable errors maintain an uncorrectable error;
perform, subsequent to performing the partial memory scrubbing operation, a full memory scrubbing operation on the memory subsystem;
report a completion of memory scrubbing operations to at least one runtime subsystem in order to allow the at least one runtime subsystem to enter a runtime environment; and
provide the memory locations that were previously identified with uncorrectable errors and that maintain an uncorrectable error to the at least one runtime subsystem.
9. The IHS of claim 8 , wherein the memory error management engine is configured to:
receive a memory scrubbing operation completion query from the at least one runtime subsystem and, in response, report the completion of memory scrubbing operations to the at least one runtime subsystem, wherein the full memory scrubbing operation is performed on the memory subsystem subsequent to reporting the completion of memory scrubbing operations to the at least one runtime subsystem.
10. The IHS of claim 9 , wherein the memory error management engine is configured to:
provide the memory locations that were previously identified with uncorrectable errors and that maintain an uncorrectable error to the at least one runtime subsystem in response to the memory scrubbing operation completion query.
11. The IHS of claim 8 , wherein the memory error management engine is configured to:
identify, based on the full memory scrubbing operation performed on the memory subsystem, a memory location with a currently detected uncorrectable error; and
report the memory location with the currently detected uncorrectable error to the at least one runtime subsystem.
12. The IHS of claim 11 , wherein the memory error management engine is configured to report the memory location with the currently detected uncorrectable error to the at least one runtime subsystem by:
generating an interrupt that causes the at least one runtime subsystem to retrieve an identity of the memory location with the currently detected uncorrectable error.
13. The IHS of claim 8 , wherein the memory error management engine is configured to:
initiate the performance of the full memory scrubbing operation on the memory subsystem prior to the at least one runtime subsystem entering the runtime environment.
14. A method for memory error management, comprising:
identifying, by a memory error management subsystem during a boot process, memory locations that were previously identified with uncorrectable errors in a memory subsystem;
determining, by the memory error management subsystem during the boot process and while performing a partial memory scrubbing operation on the memory locations that were previously identified with uncorrectable errors, whether any of the memory locations that were previously identified with uncorrectable errors maintain an uncorrectable error;
performing, by the memory error management subsystem subsequent to performing the partial memory scrubbing operation, a full memory scrubbing operation on the memory subsystem;
reporting, by the memory error management subsystem, a completion of memory scrubbing operations to at least one runtime subsystem in order to allow the at least one runtime subsystem to enter a runtime environment; and
providing, by the memory error management subsystem, the memory locations that were previously identified with uncorrectable errors and that maintain an uncorrectable error to the at least one runtime subsystem.
15. The method of claim 14 , further comprising:
receiving, by the memory error management subsystem, a memory scrubbing operation completion query from the at least one runtime subsystem and, in response, reporting the completion of memory scrubbing operations to the at least one runtime subsystem, wherein the full memory scrubbing operation is performed on the memory subsystem subsequent to reporting the completion of memory scrubbing operations to the at least one runtime subsystem.
16. The method of claim 15 , further comprising:
providing, by the memory error management subsystem, the memory locations that were previously identified with uncorrectable errors and that maintain an uncorrectable error to the at least one runtime subsystem in response to the memory scrubbing operation completion query.
17. The method of claim 14 , further comprising:
identifying, by the memory error management subsystem based on the full memory scrubbing operation performed on the memory subsystem, a memory location with a currently detected uncorrectable error; and
reporting, by the memory error management subsystem, the memory location with the currently detected uncorrectable error to the at least one runtime subsystem.
18. The method of claim 16 , wherein the reporting the memory location with the currently detected uncorrectable error to the at least one runtime subsystem includes:
generating, by the memory error management subsystem, an interrupt that causes the at least one runtime subsystem to retrieve an identity of the memory location with the currently detected uncorrectable error.
19. The method of claim 14 , further comprising:
initiating, by the memory error management subsystem, the performance of the full memory scrubbing operation on the memory subsystem prior to the at least one runtime subsystem entering the runtime environment.
20. The method of claim 14 , further comprising:
receiving, by the memory error management subsystem from the at least one runtime subsystem subsequent to reporting the completion of memory scrubbing operations to the at least one runtime subsystem and while performing the full memory scrubbing operation, a new memory scrubbing operation instruction; and
notifying, by the memory error management subsystem in response to receiving the new memory scrubbing operation instruction, the at least one runtime subsystem that the full memory scrubbing operation is in progress.