Skip to contentSkip to conversation

State of NMI support

DISCUSSION Jan Kiszka 2 participants 2 messages Apr 25, 2008 KVM

lore
Share & tools
lore

Jan Kiszka

author
#0 lore raw

Hi,

I saw kvm-userspace recently merged qemu's new CPU_INTERRUPT_NMI support. But the required infrastructure to use this in kvm mode is not yet visible. Is anyone working on this? Sheng? IIRC, you once said to work on it.

Currently I just need the basic mechanism for injecting NMIs into the guest (from special hardware emulation), no full support for in-kernel [A]PICs. But before starting some quick&dirty hack, I would like to know if someone already has a patch pending and is able to share even just preliminary results.

Thanks,
Jan

-------------------------------------------------------------------------
This SF.net email is sponsored by the 2008 JavaOne(SM) Conference Don't miss this year's exciting event. There's still time to save $100. Use priority code J8TL2D2.
http://ad.doubleclick.net/clk;198757673;13503038;p?http://java.sun.com/javaone

_______________________________________________
kvm-devel mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/kvm-devel

#1 lore raw
Quoted 7 lines · On Friday 25 April 2008 08:33:04 Jan Kiszka wrote:

Hi,

I saw kvm-userspace recently merged qemu's new CPU_INTERRUPT_NMI support. But the required infrastructure to use this in kvm mode is not yet visible. Is anyone working on this? Sheng? IIRC, you once said to work on it.

Quoted 8 lines

Currently I just need the basic mechanism for injecting NMIs into the guest (from special hardware emulation), no full support for in-kernel [A]PICs. But before starting some quick&dirty hack, I would like to know if someone already has a patch pending and is able to share even just preliminary results.

Thanks,
Jan

Yeah, the patchset is mostly completed. But I have to switch to do EPT enabling these days so don't have time to do more test and push them out...

I tested patchset by NMI watchdog(also introduce the logic of the NMI watchlog), about one thousand NMI per second at most. The patchset also did some clean up on VMX interrupt handling. I would like to push the patch next week (if the EPT things can be done this week or early next week). Sorry for keep you waiting so long...

--
Thanks
Yang, Sheng

-------------------------------------------------------------------------
This SF.net email is sponsored by the 2008 JavaOne(SM) Conference Don't miss this year's exciting event. There's still time to save $100. Use priority code J8TL2D2.
http://ad.doubleclick.net/clk;198757673;13503038;p?http://java.sun.com/javaone