Feature #5342

hugetlb mem wipe

Added by Tails 9 months ago. Updated 9 months ago.

Status:ConfirmedStart date:
Priority:NormalDue date:
Assignee:-% Done:

0%

Category:-
Target version:-
QA Check: Blueprint:
Feature Branch: Easy:
Type of work:Code

Description

Using a custom memory wiping program from initramfs is implemented in the feature/hugetlb_mem_wipe branch.

It makes the wipe much faster and better looking, but it's not as efficient as Tails' current parallel sdmem approach when using a PAE kernel (which usually results in 0 occurrences in my tests, if not it's just a few hundred occurences), which arguably is what most users will use. For the non-PAE kernel I believe this branch is better, though.

Next thing to do: fine tune the algorithm parameters and/or memory settings to be as efficient on PAE than current implementation.

Test results

Both tests performed in the same 8 GiB-RAM VM:

  • With PAE-kernel: 137K occurences =~ 2.1 MiB of unwiped memory.
  • With non-PAE-kernel: 155K occurences =~ 2.4 MiB of unwiped memory.

Related issues

Related to Tails - Feature #5762: faster memory wipe Confirmed
Related to Tails - Feature #5456: amd64 kernel Resolved
Blocks Tails - Feature #6006: more efficient memory wipe Confirmed
Blocks Tails - Feature #5658: move from sdmem to memtest Confirmed

Also available in: Atom PDF