diff options
| author | Paul Mackerras <paulus@ozlabs.org> | 2018-09-14 10:11:50 +1000 |
|---|---|---|
| committer | Paul Mackerras <paulus@ozlabs.org> | 2018-10-09 11:44:54 +1100 |
| commit | 04ea6930cefb497d32cfea62c61a6adcb6c428cd (patch) | |
| tree | dd2723ad72a1e34e898b1cf019598a60b4c6dfda | |
| parent | a27fb6d983c7b5bb0129ae4d7a7c81758173bfab (diff) | |
| download | powerpc-04ea6930cefb497d32cfea62c61a6adcb6c428cd.tar.gz | |
powerpc: Turn off CPU_FTR_P9_TM_HV_ASSIST in non-hypervisor mode
When doing nested virtualization, it is only necessary to do the
transactional memory hypervisor assist at level 0, that is, when
we are in hypervisor mode. Nested hypervisors can just use the TM
facilities as architected. Therefore we should clear the
CPU_FTR_P9_TM_HV_ASSIST bit when we are not in hypervisor mode,
along with the CPU_FTR_HVMODE bit.
Doing this will not change anything at this stage because the only
code that tests CPU_FTR_P9_TM_HV_ASSIST is in HV KVM, which currently
can only be used when when CPU_FTR_HVMODE is set.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
| -rw-r--r-- | arch/powerpc/kernel/cpu_setup_power.S | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/arch/powerpc/kernel/cpu_setup_power.S b/arch/powerpc/kernel/cpu_setup_power.S index 458b928dbd8447..c317080db771e2 100644 --- a/arch/powerpc/kernel/cpu_setup_power.S +++ b/arch/powerpc/kernel/cpu_setup_power.S @@ -147,8 +147,8 @@ __init_hvmode_206: rldicl. r0,r3,4,63 bnelr ld r5,CPU_SPEC_FEATURES(r4) - LOAD_REG_IMMEDIATE(r6,CPU_FTR_HVMODE) - xor r5,r5,r6 + LOAD_REG_IMMEDIATE(r6,CPU_FTR_HVMODE | CPU_FTR_P9_TM_HV_ASSIST) + andc r5,r5,r6 std r5,CPU_SPEC_FEATURES(r4) blr |