diff options
| author | Mark Brown <[email protected]> | 2025-04-16 23:32:49 +0000 |
|---|---|---|
| committer | Marc Zyngier <[email protected]> | 2025-05-06 08:50:56 +0000 |
| commit | e0ccc45b056d626d4b271820faeedf3837337ceb (patch) | |
| tree | b61d89089fe57033cd1e64d51211dcfd6ac7e012 /rust/helpers/workqueue.c | |
| parent | KVM: arm64: Force HCR_EL2.xMO to 1 at all times in VHE mode (diff) | |
| download | kernel-e0ccc45b056d626d4b271820faeedf3837337ceb.tar.gz kernel-e0ccc45b056d626d4b271820faeedf3837337ceb.zip | |
KVM: arm64: selftests: Add test for SVE host corruption
Until recently, the kernel could unexpectedly discard SVE state for a
period after a KVM_RUN ioctl, when the guest did not execute any
FPSIMD/SVE/SME instructions. We fixed that issue in commit:
fbc7e61195e2 ("KVM: arm64: Unconditionally save+flush host FPSIMD/SVE/SME state")
Add a test which tries to provoke that issue by manipulating SVE state
before/after running a guest which does not execute any FPSIMD/SVE/SME
instructions. The test executes a handful of iterations to miminize
the risk that the issue is masked by preemption.
Signed-off--by: Mark Rutland <[email protected]>
Signed-off-by: Mark Brown <[email protected]>
Acked-by: Mark Rutland <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
[maz: Restored MR's SoB, fixed commit message according to MR's write-up]
Signed-off-by: Marc Zyngier <[email protected]>
Diffstat (limited to 'rust/helpers/workqueue.c')
0 files changed, 0 insertions, 0 deletions