@@ -176,6 +176,8 @@ extern int kvmppc_xics_set_xive(struct kvm *kvm, u32 irq, u32 server, u32 priori
extern int kvmppc_xics_get_xive(struct kvm *kvm, u32 irq, u32 *server, u32 *priority);
extern int kvmppc_xics_int_on(struct kvm *kvm, u32 irq);
extern int kvmppc_xics_int_off(struct kvm *kvm, u32 irq);
+extern u64 kvmppc_xics_get_icp(struct kvm_vcpu *vcpu);
+extern int kvmppc_xics_set_icp(struct kvm_vcpu *vcpu, u64 icpval);
/*
* Cuts out inst bits with ordering according to spec.
@@ -425,4 +425,15 @@ struct kvm_book3e_206_tlb_params {
#define KVM_REG_PPC_VPA_SLB (KVM_REG_PPC | KVM_REG_SIZE_U128 | 0x83)
#define KVM_REG_PPC_VPA_DTL (KVM_REG_PPC | KVM_REG_SIZE_U128 | 0x84)
+/* Per-vcpu interrupt controller state */
+#define KVM_REG_PPC_ICP_STATE (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x85)
+#define KVM_REG_PPC_ICP_CPPR_SHIFT 56 /* current proc priority */
+#define KVM_REG_PPC_ICP_CPPR_MASK 0xff
+#define KVM_REG_PPC_ICP_XISR_SHIFT 32 /* interrupt status field */
+#define KVM_REG_PPC_ICP_XISR_MASK 0xffffff
+#define KVM_REG_PPC_ICP_MFRR_SHIFT 24 /* pending IPI priority */
+#define KVM_REG_PPC_ICP_MFRR_MASK 0xff
+#define KVM_REG_PPC_ICP_PPRI_SHIFT 16 /* pending irq priority */
+#define KVM_REG_PPC_ICP_PPRI_MASK 0xff
+
#endif /* __LINUX_KVM_POWERPC_H */
@@ -529,6 +529,15 @@ int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
val = get_reg_val(reg->id, vcpu->arch.vscr.u[3]);
break;
#endif /* CONFIG_ALTIVEC */
+#ifdef CONFIG_PPC_BOOK3S_64
+ case KVM_REG_PPC_ICP_STATE:
+ if (!vcpu->arch.icp) {
+ r = -ENXIO;
+ break;
+ }
+ val = get_reg_val(reg->id, kvmppc_xics_get_icp(vcpu));
+ break;
+#endif
default:
r = -EINVAL;
break;
@@ -591,6 +600,15 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
vcpu->arch.vscr.u[3] = set_reg_val(reg->id, val);
break;
#endif /* CONFIG_ALTIVEC */
+#ifdef CONFIG_PPC_BOOK3S_64
+ case KVM_REG_PPC_ICP_STATE:
+ if (!vcpu->arch.icp) {
+ r = -ENXIO;
+ break;
+ }
+ r = kvmppc_xics_set_icp(vcpu, set_reg_val(reg->id, val));
+ break;
+#endif
default:
r = -EINVAL;
break;
@@ -976,6 +976,96 @@ void kvmppc_xics_free(struct kvm *kvm)
kfree(xics);
}
+u64 kvmppc_xics_get_icp(struct kvm_vcpu *vcpu)
+{
+ struct kvmppc_icp *icp = vcpu->arch.icp;
+ union kvmppc_icp_state state;
+
+ if (!icp)
+ return 0;
+ state = icp->state;
+ return ((u64)state.cppr << KVM_REG_PPC_ICP_CPPR_SHIFT) |
+ ((u64)state.xisr << KVM_REG_PPC_ICP_XISR_SHIFT) |
+ ((u64)state.mfrr << KVM_REG_PPC_ICP_MFRR_SHIFT) |
+ ((u64)state.pending_pri << KVM_REG_PPC_ICP_PPRI_SHIFT);
+}
+
+int kvmppc_xics_set_icp(struct kvm_vcpu *vcpu, u64 icpval)
+{
+ struct kvmppc_icp *icp = vcpu->arch.icp;
+ struct kvmppc_xics *xics = vcpu->kvm->arch.xics;
+ union kvmppc_icp_state old_state, new_state;
+ struct kvmppc_ics *ics;
+ u8 cppr, mfrr, pending_pri;
+ u32 xisr;
+ u16 src;
+ bool resend;
+
+ if (!icp || !xics)
+ return -ENOENT;
+
+ cppr = icpval >> KVM_REG_PPC_ICP_CPPR_SHIFT;
+ xisr = (icpval >> KVM_REG_PPC_ICP_XISR_SHIFT) &
+ KVM_REG_PPC_ICP_XISR_MASK;
+ mfrr = icpval >> KVM_REG_PPC_ICP_MFRR_SHIFT;
+ pending_pri = icpval >> KVM_REG_PPC_ICP_PPRI_SHIFT;
+
+ /* Require the new state to be internally consistent */
+ if (xisr == 0) {
+ if (pending_pri != 0xff)
+ return -EINVAL;
+ } else if (xisr == XICS_IPI) {
+ if (pending_pri != mfrr || pending_pri >= cppr)
+ return -EINVAL;
+ } else {
+ if (pending_pri >= mfrr || pending_pri >= cppr)
+ return -EINVAL;
+ ics = kvmppc_xics_find_ics(xics, xisr, &src);
+ if (!ics)
+ return -EINVAL;
+ }
+
+ new_state.raw = 0;
+ new_state.cppr = cppr;
+ new_state.xisr = xisr;
+ new_state.mfrr = mfrr;
+ new_state.pending_pri = pending_pri;
+
+ /*
+ * Deassert the CPU interrupt request.
+ * icp_try_update will reassert it if necessary.
+ */
+ kvmppc_book3s_dequeue_irqprio(icp->vcpu,
+ BOOK3S_INTERRUPT_EXTERNAL_LEVEL);
+
+ /*
+ * Note that if we displace an interrupt from old_state.xisr,
+ * we don't mark it as rejected. We expect userspace to set
+ * the state of the interrupt sources to be consistent with
+ * the ICP states (either before or afterwards, which doesn't
+ * matter). We do handle resends due to CPPR becoming less
+ * favoured because that is necessary to end up with a
+ * consistent state in the situation where userspace restores
+ * the ICS states before the ICP states.
+ */
+ do {
+ old_state = ACCESS_ONCE(icp->state);
+
+ if (new_state.mfrr <= old_state.mfrr) {
+ resend = false;
+ new_state.need_resend = old_state.need_resend;
+ } else {
+ resend = old_state.need_resend;
+ new_state.need_resend = 0;
+ }
+ } while (!icp_try_update(icp, old_state, new_state, false));
+
+ if (resend)
+ icp_check_resend(xics, icp);
+
+ return 0;
+}
+
/* -- ioctls -- */
static int kvm_vm_ioctl_create_icp(struct kvm *kvm,
This adds the ability for userspace to save and restore the state of the XICS interrupt presentation controllers (ICPs) via the KVM_GET/SET_ONE_REG interface. Since there is one ICP per vcpu, we simply define a new 64-bit register in the ONE_REG space for the ICP state. The state includes the CPU priority setting, the pending IPI priority, and the priority and source number of any pending external interrupt. Signed-off-by: Paul Mackerras <paulus@samba.org> --- arch/powerpc/include/asm/kvm_ppc.h | 2 + arch/powerpc/include/uapi/asm/kvm.h | 11 +++++ arch/powerpc/kvm/book3s.c | 18 +++++++ arch/powerpc/kvm/book3s_xics.c | 90 +++++++++++++++++++++++++++++++++++ 4 files changed, 121 insertions(+)