INTEL MCE INJECTOR DRIVER

Background scrubbing gives a machine check. See Chapter 15 in this reference where it says: Thus, processes can decide how they want to handle the data poisoning. This is an early paper about the first version of mcelog. While single bit data errors can be corrected via ECC, multi-bit data errors cannot.

Uploader:	Dusida
Date Added:	21 July 2018
File Size:	5.80 Mb
Operating Systems:	Windows NT/2000/XP/2003/2003/7/8/10 MacOS 10/X
Downloads:	31650
Price:	Free* [*Free Regsitration Required]

But that's not the case the article describes.

The machine check is action optional and it can do just as you suggest. If I'm not mistaken, that's the processor family this article was referring to.

This document is dated Juneso it's not like it's anceint. Do you have different documentation that suggests otherwise? Posted Aug 31, 6: That's not how I mc this.

However, memory poisoning requires both hardware and kernel support. I guess what you're missing is who marks the memory as poisoned.

Usenix Annual Tech Conference The famous google memory error study. Action Optional means that the CPU detected some form of corruption in the background and tells the OS about using a machine check exception.

Perhaps this is handled properly, but by just unmapping, arn't you running the risk that some later memory allocation by that process might get the same virtual address and thus instead of a SIGBUS the process keeps running with corrupted memory? Note that this property would be system dependent—not all systems would necessarily be this imprecise.

For users:

Includes an overview of MCA recovery and a description of the Linux 2. ECC is able to injecor from multib i y te errors Posted Dec 4, 9: See this LWN article for further details about this issue.

The hardware now supports a concept of recoverable machine check, and the software uses it. Dirty pages are unmapped injwctor all associated processes, which are subsequently killed.

Posted Aug 28, 7: In case you think this feature is old and was supplanted by something more recent, I urge you to flip back to and read along here at the intro to Section It's still a machine check, and it can be triggered by mcce.

See Injectr 15 in this reference where it says: Once the hardware delivers the message to the OS via a machine checkthe OS is then free to deal with the machine check however it pleases. Its exact behavior depends upon the type of corrupted page and various kernel configuration parameters. ISTM you want to map a known bad page there instead.

So there we have it. There is a notion of an "action optional" machine check. The dirty flag is cleared for the page and the page swap cache entry is maintained.

HWPOISON []

ECC is able to recover from multib i y te errors Posted Dec 4, The poisoned bit in the flags field serves as a lock allowing rapid-fire poisoning machine checks on the same page to be handled only once by ignoring subsequent calls to the handler. Try to keep everything running as smoothly as possible and only bringing imtel the affected tasks if any. Without subscribers, LWN would simply not exist.

This allow system soft- ware to perform recovery action on certain class of uncorrected errors and continue If I'm not mistaken, that's the processor family this article was referring to.

Posted Dec 4, 9: Posted Sep 8,