This repository has been archived by the owner on Jun 18, 2024. It is now read-only.
scx: Dispatch locally until ops.cpu_online() invoked #197
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Outdated suggestions cannot be applied.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.
In sched_ext, there's currently a corner case on the hotplug path wherein a CPU may be onlined and begin scheduling before we've invoked ops.cpu_online() to the scheduler. This can cause confusion by e.g. causing a scheduler to error out if it receives an ops.dispatch() call and accidentally dispatches to an invalid DSQ.
To avoid this scenario, this patch adds a per-CPU boolean variable that tracks when a CPU has been onlined from the perspective of sched_ext.
Note that this patch does not prevent any callback from being invoked on that CPU. It simply prevents us from invoking ops.dispatch(), and forces us to dispatch directly to the local DSQ. We can still, however, receive e.g. ops.runnable() if a per-CPU task is dispatched to the local DSQ of the onlined CPU before the hotplug event is received.