Before running a guest, the host process (e.g., QEMU) FP/VEC registers
are saved if they were being used, similarly to when the kernel uses FP
registers. The guest values are then be loaded into regs, and the host
process registers will be restored lazily when it uses FP/VEC.
KVM HV has a bug here: the host process registers do get saved, but the
user MSR bits remain enabled, which indicates the registers are valid
for the process. After they are clobbered by running the guest, this
valid indication causes the host process to take on the FP/VEC regiter
values of the guest.
Fixes: de2a20aa7237b ("powerpc: Prepare for splitting giveup_{fpu, altivec,
vsx} in two")
Signed-off-by: Nicholas Piggin <npig...@gmail.com>
---
arch/powerpc/kernel/process.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 392404688cec..9452a54d356c 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1198,11 +1198,11 @@ void kvmppc_save_user_regs(void)
usermsr = current->thread.regs->msr;
+ /* Caller has enabled FP/VEC/VSX/TM in MSR */
if (usermsr & MSR_FP)
- save_fpu(current);
-
+ __giveup_fpu(current);
if (usermsr & MSR_VEC)
- save_altivec(current);
+ __giveup_altivec(current);
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
if (usermsr & MSR_TM) {
--
2.42.0
