Skip to content

Commit b5be991

Browse files
committed
chore: update prod-host-setup.md with arm physical counter info
Update a note about physical counter on ARM being reset instead of directly passed through. Signed-off-by: Egor Lazarchuk <yegorlz@amazon.co.uk>
1 parent 57b458b commit b5be991

File tree

1 file changed

+6
-6
lines changed

1 file changed

+6
-6
lines changed

docs/prod-host-setup.md

Lines changed: 6 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -328,13 +328,13 @@ For vendor-specific recommendations, please consult the resources below:
328328
- ARM:
329329
[Speculative Processor Vulnerability](https://developer.arm.com/support/arm-security-updates/speculative-processor-vulnerability)
330330

331-
##### [ARM only] Physical counter directly passed through to the guest
331+
##### [ARM only] VM Physical counter reset on VM boot
332332

333-
On ARM, the physical counter (i.e `CNTPCT`) it is returning the
334-
[actual EL1 physical counter value of the host][1]. From the discussions before
335-
merging this change [upstream][2], this seems like a conscious design decision
336-
of the ARM code contributors, giving precedence to performance over the ability
337-
to trap and control this in the hypervisor.
333+
On ARM, Firecracker tries to reset the `CNTPCT` physical counter on VM boot.
334+
This is done in order to prevent VM from reading host physical counter value.
335+
Because this is only possible in kernels containing [this](https://lore.kernel.org/all/20230330174800.2677007-1-maz@kernel.org/)
336+
patch series (6.4 and newer) Firecracker does not fail if it cannot reset the counter
337+
and instead prints a warning message.
338338

339339
##### Verification
340340

0 commit comments

Comments
 (0)