Skip to content

Conversation

@GJL
Copy link
Collaborator

@GJL GJL commented Nov 27, 2025

No description provided.

Copy link
Collaborator

@koczkatamas koczkatamas left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Looks good! I had one question / change suggesion.

const uint64_t KASLR_SLOT_SIZE = 0x200000;

// The number of prefetch measurements per candidate address.
const int KASLR_NUM_MEASUREMENTS = 100;
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

How fast is the current leak algorithm (in seconds or milliseconds)?

If it is considerable amount (>500ms), then we should consider making this configurable (e.g. as an optional parameter for leak_kaslr_base) because in case of kernelCTF sometimes there is a race, and the seconds (milliseconds) matter who wins, so maybe researchers want to lower this value in some cases.

It is also possible that we want to increase this value in case of more noisy systems, I don't know how much noise affects prefetch leaks.

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Around 500k µs for 100 leaks on my laptop so around 5 ms per leak. I will make it configurable nonetheless.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants