@@ -607,6 +607,8 @@ struct kvm_ppc_rmmu_info {
#define KVM_REG_PPC_TIDR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbc)
#define KVM_REG_PPC_PSSCR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbd)
+#define KVM_REG_PPC_DEC_EXPIRY (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbe)
+
/* Transactional Memory checkpointed state:
* This is all GPRs, all VSX regs and a subset of SPRs
*/
@@ -1497,6 +1497,10 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
case KVM_REG_PPC_ARCH_COMPAT:
*val = get_reg_val(id, vcpu->arch.vcore->arch_compat);
break;
+ case KVM_REG_PPC_DEC_EXPIRY:
+ *val = get_reg_val(id, vcpu->arch.dec_expires +
+ vcpu->arch.vcore->tb_offset);
+ break;
default:
r = -EINVAL;
break;
@@ -1724,6 +1728,10 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
case KVM_REG_PPC_ARCH_COMPAT:
r = kvmppc_set_arch_compat(vcpu, set_reg_val(id, *val));
break;
+ case KVM_REG_PPC_DEC_EXPIRY:
+ vcpu->arch.dec_expires = set_reg_val(id, *val) -
+ vcpu->arch.vcore->tb_offset;
+ break;
default:
r = -EINVAL;
break;
@@ -758,7 +758,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
hrtimer_init(&vcpu->arch.dec_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS);
vcpu->arch.dec_timer.function = kvmppc_decrementer_wakeup;
- vcpu->arch.dec_expires = ~(u64)0;
+ vcpu->arch.dec_expires = get_tb();
#ifdef CONFIG_KVM_EXIT_TIMING
mutex_init(&vcpu->arch.exit_timing_lock);
This adds a register identifier for use with the one_reg interface to allow the decrementer expiry time to be read and written by userspace. The decrementer expiry time is in guest timebase units and is equal to the sum of the decrementer and the guest timebase. (The expiry time is used rather than the decrementer value itself because the expiry time is not constantly changing, though the decrementer value is, while the guest vcpu is not running.) Without this, a guest vcpu migrated to a new host will see its decrementer set to some random value. On POWER8 and earlier (and on POWER9 in POWER7 or POWER8 compatibility mode), the decrementer is 32 bits wide and counts down at 512MHz, so the guest vcpu will potentially see no decrementer interrupts for up to about 4 seconds, which will lead to a stall. With POWER9, the decrementer is now 56 bits side, so the stall can be much longer (up to 2.23 years) and more noticeable. To help work around the problem in cases where userspace has not been updated to migrate the decrementer expiry time, we now set the default decrementer expiry at vcpu creation time to the current time rather than the maximum possible value. This should mean an immediate decrementer interrupt when a migrated vcpu starts running. In cases where the decrementer is 32 bits wide and more than 4 seconds elapse between the creation of the vcpu and when it first runs, the decrementer would have wrapped around to positive values and there may still be a stall - but this is no worse than the current situation. In the large-decrementer case, we are sure to get an immediate decrementer interrupt (assuming the time from vcpu creation to first run is less than 2.23 years) and we thus avoid a very long stall. Signed-off-by: Paul Mackerras <paulus@ozlabs.org> --- arch/powerpc/include/uapi/asm/kvm.h | 2 ++ arch/powerpc/kvm/book3s_hv.c | 8 ++++++++ arch/powerpc/kvm/powerpc.c | 2 +- 3 files changed, 11 insertions(+), 1 deletion(-)