[PATCH v3 1/4] KVM: PPC: Allow nested guest creation when L0 hv_guest_state > L1

[Ravi Bangoria]

On powerpc, L1 hypervisor takes help of L0 using H_ENTER_NESTED
hcall to load L2 guest state in cpu. L1 hypervisor prepares the
L2 state in struct hv_guest_state and passes a pointer to it via
hcall. Using that pointer, L0 reads/writes that state directly
from/to L1 memory. Thus L0 must be aware of hv_guest_state layout
of L1. Currently it uses version field to achieve this. i.e. If
L0 hv_guest_state.version != L1 hv_guest_state.version, L0 won't
allow nested kvm guest.

This restriction can be loosen up a bit. L0 can be taught to
understand older layout of hv_guest_state, if we restrict the
new member to be added only at the end. i.e. we can allow
nested guest even when L0 hv_guest_state.version > L1
hv_guest_state.version. Though, the other way around is not
possible.

Signed-off-by: Ravi Bangoria <ravi.bangoria@xxxxxxxxxxxxx>
Reviewed-by: Fabiano Rosas <farosas@xxxxxxxxxxxxx>
---
 arch/powerpc/include/asm/hvcall.h   | 17 +++++++--
 arch/powerpc/kvm/book3s_hv_nested.c | 55 +++++++++++++++++++++++------
 2 files changed, 60 insertions(+), 12 deletions(-)

diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h
index c1fbccb04390..ca6840239f90 100644
--- a/arch/powerpc/include/asm/hvcall.h
+++ b/arch/powerpc/include/asm/hvcall.h
@@ -526,9 +526,12 @@ struct h_cpu_char_result {
 	u64 behaviour;
 };
 
-/* Register state for entering a nested guest with H_ENTER_NESTED */
+/*
+ * Register state for entering a nested guest with H_ENTER_NESTED.
+ * New member must be added at the end.
+ */
 struct hv_guest_state {
-	u64 version;		/* version of this structure layout */
+	u64 version;		/* version of this structure layout, must be first */
 	u32 lpid;
 	u32 vcpu_token;
 	/* These registers are hypervisor privileged (at least for writing) */
@@ -562,6 +565,16 @@ struct hv_guest_state {
 /* Latest version of hv_guest_state structure */
 #define HV_GUEST_STATE_VERSION	1
 
+static inline int hv_guest_state_size(unsigned int version)
+{
+	switch (version) {
+	case 1:
+		return offsetofend(struct hv_guest_state, ppr);
+	default:
+		return -1;
+	}
+}
+
 /*
  * From the document "H_GetPerformanceCounterInfo Interface" v1.07
  *
diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c
index 33b58549a9aa..937dd5114300 100644
--- a/arch/powerpc/kvm/book3s_hv_nested.c
+++ b/arch/powerpc/kvm/book3s_hv_nested.c
@@ -215,12 +215,51 @@ static void kvmhv_nested_mmio_needed(struct kvm_vcpu *vcpu, u64 regs_ptr)
 	}
 }
 
+static int kvmhv_read_guest_state_and_regs(struct kvm_vcpu *vcpu,
+					   struct hv_guest_state *l2_hv,
+					   struct pt_regs *l2_regs,
+					   u64 hv_ptr, u64 regs_ptr)
+{
+	int size;
+
+	if (kvm_vcpu_read_guest(vcpu, hv_ptr, &l2_hv->version,
+				sizeof(l2_hv->version)))
+		return -1;
+
+	if (kvmppc_need_byteswap(vcpu))
+		l2_hv->version = swab64(l2_hv->version);
+
+	size = hv_guest_state_size(l2_hv->version);
+	if (size < 0)
+		return -1;
+
+	return kvm_vcpu_read_guest(vcpu, hv_ptr, l2_hv, size) ||
+		kvm_vcpu_read_guest(vcpu, regs_ptr, l2_regs,
+				    sizeof(struct pt_regs));
+}
+
+static int kvmhv_write_guest_state_and_regs(struct kvm_vcpu *vcpu,
+					    struct hv_guest_state *l2_hv,
+					    struct pt_regs *l2_regs,
+					    u64 hv_ptr, u64 regs_ptr)
+{
+	int size;
+
+	size = hv_guest_state_size(l2_hv->version);
+	if (size < 0)
+		return -1;
+
+	return kvm_vcpu_write_guest(vcpu, hv_ptr, l2_hv, size) ||
+		kvm_vcpu_write_guest(vcpu, regs_ptr, l2_regs,
+				     sizeof(struct pt_regs));
+}
+
 long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu)
 {
 	long int err, r;
 	struct kvm_nested_guest *l2;
 	struct pt_regs l2_regs, saved_l1_regs;
-	struct hv_guest_state l2_hv, saved_l1_hv;
+	struct hv_guest_state l2_hv = {0}, saved_l1_hv;
 	struct kvmppc_vcore *vc = vcpu->arch.vcore;
 	u64 hv_ptr, regs_ptr;
 	u64 hdec_exp;
@@ -235,17 +274,15 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu)
 	hv_ptr = kvmppc_get_gpr(vcpu, 4);
 	regs_ptr = kvmppc_get_gpr(vcpu, 5);
 	vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
-	err = kvm_vcpu_read_guest(vcpu, hv_ptr, &l2_hv,
-				  sizeof(struct hv_guest_state)) ||
-		kvm_vcpu_read_guest(vcpu, regs_ptr, &l2_regs,
-				    sizeof(struct pt_regs));
+	err = kvmhv_read_guest_state_and_regs(vcpu, &l2_hv, &l2_regs,
+					      hv_ptr, regs_ptr);
 	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
 	if (err)
 		return H_PARAMETER;
 
 	if (kvmppc_need_byteswap(vcpu))
 		byteswap_hv_regs(&l2_hv);
-	if (l2_hv.version != HV_GUEST_STATE_VERSION)
+	if (l2_hv.version > HV_GUEST_STATE_VERSION)
 		return H_P2;
 
 	if (kvmppc_need_byteswap(vcpu))
@@ -325,10 +362,8 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu)
 		byteswap_pt_regs(&l2_regs);
 	}
 	vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
-	err = kvm_vcpu_write_guest(vcpu, hv_ptr, &l2_hv,
-				   sizeof(struct hv_guest_state)) ||
-		kvm_vcpu_write_guest(vcpu, regs_ptr, &l2_regs,
-				   sizeof(struct pt_regs));
+	err = kvmhv_write_guest_state_and_regs(vcpu, &l2_hv, &l2_regs,
+					       hv_ptr, regs_ptr);
 	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
 	if (err)
 		return H_AUTHORITY;
-- 
2.26.2