KVM: PPC: Book3S HV: Fixes for late-joining threads

If a thread in a virtual core becomes runnable while other threads
in the same virtual core are already running in the guest, it is
possible for the latecomer to join the others on the core without
first pulling them all out of the guest.  Currently this only happens
rarely, when a vcpu is first started.  This fixes some bugs and
omissions in the code in this case.

First, we need to check for VPA updates for the latecomer and make
a DTL entry for it.  Secondly, if it comes along while the master
vcpu is doing a VPA update, we don't need to do anything since the
master will pick it up in kvmppc_run_core.  To handle this correctly
we introduce a new vcore state, VCORE_STARTING.  Thirdly, there is
a race because we currently clear the hardware thread's hwthread_req
before waiting to see it get to nap.  A latecomer thread could have
its hwthread_req cleared before it gets to test it, and therefore
never increment the nap_count, leading to messages about wait_for_nap
timeouts.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>

1 files changed, 11 insertions, 3 deletions

diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 3a737a4bb8b..89995fa6e94 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -336,6 +336,11 @@ static void kvmppc_update_vpa(struct kvm_vcpu *vcpu, struct kvmppc_vpa *vpap)
 
 static void kvmppc_update_vpas(struct kvm_vcpu *vcpu)
 {
+	if (!(vcpu->arch.vpa.update_pending ||
+	      vcpu->arch.slb_shadow.update_pending ||
+	      vcpu->arch.dtl.update_pending))
+		return;
+
 	spin_lock(&vcpu->arch.vpa_update_lock);
 	if (vcpu->arch.vpa.update_pending) {
 		kvmppc_update_vpa(vcpu, &vcpu->arch.vpa);
@@ -1009,7 +1014,7 @@ static void kvmppc_run_core(struct kvmppc_vcore *vc)
 	vc->n_woken = 0;
 	vc->nap_count = 0;
 	vc->entry_exit_count = 0;
-	vc->vcore_state = VCORE_RUNNING;
+	vc->vcore_state = VCORE_STARTING;
 	vc->in_guest = 0;
 	vc->napping_threads = 0;
 
@@ -1062,6 +1067,7 @@ static void kvmppc_run_core(struct kvmppc_vcore *vc)
 		kvmppc_create_dtl_entry(vcpu, vc);
 	}
 
+	vc->vcore_state = VCORE_RUNNING;
 	preempt_disable();
 	spin_unlock(&vc->lock);
 
@@ -1070,8 +1076,6 @@ static void kvmppc_run_core(struct kvmppc_vcore *vc)
 	srcu_idx = srcu_read_lock(&vcpu0->kvm->srcu);
 
 	__kvmppc_vcore_entry(NULL, vcpu0);
-	for (i = 0; i < threads_per_core; ++i)
-		kvmppc_release_hwthread(vc->pcpu + i);
 
 	spin_lock(&vc->lock);
 	/* disable sending of IPIs on virtual external irqs */
@@ -1080,6 +1084,8 @@ static void kvmppc_run_core(struct kvmppc_vcore *vc)
 	/* wait for secondary threads to finish writing their state to memory */
 	if (vc->nap_count < vc->n_woken)
 		kvmppc_wait_for_nap(vc);
+	for (i = 0; i < threads_per_core; ++i)
+		kvmppc_release_hwthread(vc->pcpu + i);
 	/* prevent other vcpu threads from doing kvmppc_start_thread() now */
 	vc->vcore_state = VCORE_EXITING;
 	spin_unlock(&vc->lock);
@@ -1170,6 +1176,7 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	kvm_run->exit_reason = 0;
 	vcpu->arch.ret = RESUME_GUEST;
 	vcpu->arch.trap = 0;
+	kvmppc_update_vpas(vcpu);
 
 	/*
 	 * Synchronize with other threads in this virtual core
@@ -1193,6 +1200,7 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 		if (vc->vcore_state == VCORE_RUNNING &&
 		    VCORE_EXIT_COUNT(vc) == 0) {
 			vcpu->arch.ptid = vc->n_runnable - 1;
+			kvmppc_create_dtl_entry(vcpu, vc);
 			kvmppc_start_thread(vcpu);
 		}