viona worker LWPs should not be CPU-pinned#1146
Open
iximeow wants to merge 4 commits into
Open
Conversation
VNA_IOC_RING_INIT* includes, as part of init'ing a ring, creating an LWP in the calling process for that ring's worker thread. This is all fine and good, but for that LWP inheriting the binding of the original ioctl-caller. The ioctl-caller, then, is functionally always a vCPU LWP, in service of an MMIO exit by a guest who is trying to start their virtio NIC. Since one vCPU is probably handling a routine that loops over all desired virtio rings and enables them, the effective outcome is that all viona rings are handled on some sole arbitrary host CPU that is also responsible for a vCPU. Avoid all of this by temporarily unbinding whatever LWP is getting the viona ring going, then rebinding before we've continued on.
iximeow
added
bug
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
VNA_IOC_RING_INIT* includes, as part of init'ing a ring, creating an LWP in the calling process for that ring's worker thread. This is all fine and good, but for that LWP inheriting the binding of the original ioctl-caller. The ioctl-caller, then, is functionally always a vCPU LWP, in service of an MMIO exit by a guest who is trying to start their virtio NIC.
Since one vCPU is probably handling a routine that loops over all desired virtio rings and enables them, the effective outcome is that all viona rings are handled on some sole arbitrary host CPU that is also responsible for a vCPU.
Avoid all of this by temporarily unbinding whatever LWP is getting the viona ring going, then rebinding before we've continued on.