KVM: PPC: Book3S: Facilities to save/restore XICS presentation ctrler state

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>
Signed-off-by: Alexander Graf <agraf@suse.de>

5 files changed, 124 insertions, 0 deletions

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index fb308be8521b..c09d1832e935 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -1808,6 +1808,7 @@ registers, find a list below:
   PPC   | KVM_REG_PPC_TLB2PS	| 32
   PPC   | KVM_REG_PPC_TLB3PS	| 32
   PPC   | KVM_REG_PPC_EPTCFG	| 32
+  PPC   | KVM_REG_PPC_ICP_STATE | 64
 
 ARM registers are mapped using the lower 32 bits.  The upper 16 of that
 is the register group type, or coprocessor number:
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index cfaa47995c0e..d7339df19259 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -313,6 +313,8 @@ extern void kvmppc_xics_free_icp(struct kvm_vcpu *vcpu);
 extern int kvmppc_xics_create_icp(struct kvm_vcpu *vcpu, unsigned long server);
 extern int kvm_vm_ioctl_xics_irq(struct kvm *kvm, struct kvm_irq_level *args);
 extern int kvmppc_xics_hcall(struct kvm_vcpu *vcpu, u32 cmd);
+extern u64 kvmppc_xics_get_icp(struct kvm_vcpu *vcpu);
+extern int kvmppc_xics_set_icp(struct kvm_vcpu *vcpu, u64 icpval);
 #else
 static inline int kvmppc_xics_enabled(struct kvm_vcpu *vcpu)
 	{ return 0; }
diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h
index eb9e25c194ad..427b9aca2a0f 100644
--- a/arch/powerpc/include/uapi/asm/kvm.h
+++ b/arch/powerpc/include/uapi/asm/kvm.h
@@ -390,6 +390,18 @@ struct kvm_get_htab_header {
 	__u16	n_invalid;
 };
 
+/* Per-vcpu XICS interrupt controller state */
+#define KVM_REG_PPC_ICP_STATE	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x8c)
+
+#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
+
 /* Device control API: PPC-specific devices */
 #define KVM_DEV_MPIC_GRP_MISC		1
 #define   KVM_DEV_MPIC_BASE_ADDR	0	/* 64-bit */
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 1a4d787df507..700df6f1d32c 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -535,6 +535,15 @@ int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 					 &opcode, sizeof(u32));
 			break;
 		}
+#ifdef CONFIG_KVM_XICS
+		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 /* CONFIG_KVM_XICS */
 		default:
 			r = -EINVAL;
 			break;
@@ -597,6 +606,16 @@ 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_KVM_XICS
+		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 /* CONFIG_KVM_XICS */
 		default:
 			r = -EINVAL;
 			break;
diff --git a/arch/powerpc/kvm/book3s_xics.c b/arch/powerpc/kvm/book3s_xics.c
index 9fb2d3909c46..ee841ed8a690 100644
--- a/arch/powerpc/kvm/book3s_xics.c
+++ b/arch/powerpc/kvm/book3s_xics.c
@@ -954,6 +954,96 @@ int kvmppc_xics_create_icp(struct kvm_vcpu *vcpu, unsigned long server_num)
 	return 0;
 }
 
+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 -- */
 
 int kvm_vm_ioctl_xics_irq(struct kvm *kvm, struct kvm_irq_level *args)