[PATCH] KVM: PPC: Book3s PR: Disable AIL mode with OPAL

[PATCH] KVM: PPC: Book3s PR: Disable AIL mode with OPAL

[Alexander Graf]

When we're using PR KVM we must not allow the CPU to take interrupts
in virtual mode, as the SLB does not contain host kernel mappings
when running inside the guest context.

To make sure we get good performance for non-KVM tasks but still
properly functioning PR KVM, let's just disable AIL whenever a vcpu
is scheduled in.

This patch fixes running PR KVM on POWER8 bare metal for me.

Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/book3s_pr.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index 03fc884..cdc0eef 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -71,6 +71,12 @@ static void kvmppc_core_vcpu_load_pr(struct kvm_vcpu *vcpu, int cpu)
 	svcpu->in_use = 0;
 	svcpu_put(svcpu);
 #endif
+
+	/* Disable AIL if supported */
+	if (cpu_has_feature(CPU_FTR_HVMODE) &&
+	    cpu_has_feature(CPU_FTR_ARCH_207S))
+		mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) & ~LPCR_AIL);
+
 	vcpu->cpu = smp_processor_id();
 #ifdef CONFIG_PPC_BOOK3S_32
 	current->thread.kvm_shadow_vcpu = vcpu->arch.shadow_vcpu;
@@ -91,6 +97,12 @@ static void kvmppc_core_vcpu_put_pr(struct kvm_vcpu *vcpu)
 
 	kvmppc_giveup_ext(vcpu, MSR_FP | MSR_VEC | MSR_VSX);
 	kvmppc_giveup_fac(vcpu, FSCR_TAR_LG);
+
+	/* Enable AIL if supported */
+	if (cpu_has_feature(CPU_FTR_HVMODE) &&
+	    cpu_has_feature(CPU_FTR_ARCH_207S))
+		mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) | LPCR_AIL_3);
+
 	vcpu->cpu = -1;
 }
 
-- 
1.8.1.4

Re: [PATCH] KVM: PPC: Book3s PR: Disable AIL mode with OPAL

[Paul Mackerras]

On Tue, Jun 10, 2014 at 07:23:00PM +0200, Alexander Graf wrote:
> When we're using PR KVM we must not allow the CPU to take interrupts
> in virtual mode, as the SLB does not contain host kernel mappings
> when running inside the guest context.
> 
> To make sure we get good performance for non-KVM tasks but still
> properly functioning PR KVM, let's just disable AIL whenever a vcpu
> is scheduled in.
> 
> This patch fixes running PR KVM on POWER8 bare metal for me.

We already handle this for the situation where we're running under a
hypervisor with the calls to pSeries_disable_reloc_on_exc() and
pSeries_enable_reloc_on_exc() in kvmppc_core_init_vm_pr() and
kvmppc_core_destroy_vm_pr() respectively.

The obvious approach to fixing this problem would be to generalize
those calls, perhaps via a ppc_md callback, to work on the powernv
platform too.  If you don't want to do that, for instance because
those calls are defined to operate across the whole machine rather
than a single CPU thread, and you prefer to affect just the one thread
we're running on, then I think you need to explain that in the commit
message.

Regards,
Paul.

Re: [PATCH] KVM: PPC: Book3s PR: Disable AIL mode with OPAL

[Alexander Graf]

On 12.06.14 05:56, Paul Mackerras wrote:
> On Tue, Jun 10, 2014 at 07:23:00PM +0200, Alexander Graf wrote:
>> When we're using PR KVM we must not allow the CPU to take interrupts
>> in virtual mode, as the SLB does not contain host kernel mappings
>> when running inside the guest context.
>>
>> To make sure we get good performance for non-KVM tasks but still
>> properly functioning PR KVM, let's just disable AIL whenever a vcpu
>> is scheduled in.
>>
>> This patch fixes running PR KVM on POWER8 bare metal for me.
> We already handle this for the situation where we're running under a
> hypervisor with the calls to pSeries_disable_reloc_on_exc() and
> pSeries_enable_reloc_on_exc() in kvmppc_core_init_vm_pr() and
> kvmppc_core_destroy_vm_pr() respectively.
>
> The obvious approach to fixing this problem would be to generalize
> those calls, perhaps via a ppc_md callback, to work on the powernv
> platform too.  If you don't want to do that, for instance because
> those calls are defined to operate across the whole machine rather
> than a single CPU thread, and you prefer to affect just the one thread
> we're running on, then I think you need to explain that in the commit
> message.

It's what I've done at first, yes. Unfortunately the pSeries call is 
system global, while we need to do the AIL switching per cpu on bare metal.

Once you start considering CPU hotplug and how that affects the 
secondary bringup paths you start wondering whether it's worth the 
hassle :). This way you can have a single guest running which only slows 
down (disables AIL) on its own vcpu, while all the others still enjoy 
the benefits of AIL.


Alex