Tighten up vector entry to memcpy, etc. codes
Nobody has claimed this yet.
- Dominant language
- No language data
- Stars
- 14
- Forks
- 0
- PR merge metrics
- No merged PRs in 30d
Description
Currently, vmx operations have to set up a stack frame and save lr to call enter_vmx_copy. This could possibly be streamlined by just testing a couple of things inline (e.g., in_interrupt / msr & VEC) to avoid the stack and call overhead in the common case.
The cutoff for vector operations should probably also be lowered dynamically if userspace is not presently using the registers.
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by locating enter_vmx_copy and the VMX operations that call it. Review how in_interrupt, MSR & VEC, and current userspace register use determine the path; done means reducing common-case stack and call overhead while dynamically lowering the vector-operation cutoff when appropriate.
Written by the indexing model from the issue text.
Assessment
- Domain
- operating-systems, performance
- Issue type
- Refactor
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100