[PATCH 5/9] KVM: PPC: Book3S: Facilities to save/restore XICS presentation ctrler state

[Paul Mackerras <paulus@samba.org>]

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>
---
 Documentation/virtual/kvm/api.txt   |    1 +
 arch/powerpc/include/asm/kvm_host.h |    2 +
 arch/powerpc/include/uapi/asm/kvm.h |   13 +++++
 arch/powerpc/kvm/book3s.c           |   19 ++++++++
 arch/powerpc/kvm/book3s_xics.c      |   92 +++++++++++++++++++++++++++++++++++
 5 files changed, 127 insertions(+)

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 0ff9dcf..466636b 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -1762,6 +1762,7 @@ registers, find a list below:
   PPC   | KVM_REG_PPC_VPA_DTL   | 128
   PPC   | KVM_REG_PPC_EPCR	| 32
   PPC   | KVM_REG_PPC_EPR	| 32
+  PPC   | KVM_REG_PPC_ICP_STATE | 64
 
 4.69 KVM_GET_ONE_REG
 
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 8af4c0b..2eb4c27 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -236,6 +236,8 @@ struct kvm_irq_ctrler {
 	void (*free_ctrler)(struct kvm *kvm);
 	int (*hcall)(struct kvm_vcpu *vcpu, unsigned long req);
 	int (*ioctl)(struct kvm *kvm, unsigned int ioctl, unsigned long arg);
+	u64 (*get_one_reg)(struct kvm_vcpu *vcpu, u64 reg);
+	int (*set_one_reg)(struct kvm_vcpu *vcpu, u64 reg, u64 val);
 };
 
 struct kvm_arch {
diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h
index d90743c..8e34553 100644
--- a/arch/powerpc/include/uapi/asm/kvm.h
+++ b/arch/powerpc/include/uapi/asm/kvm.h
@@ -423,4 +423,17 @@ struct kvm_get_htab_header {
 #define KVM_REG_PPC_EPCR	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x85)
 #define KVM_REG_PPC_EPR		(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x86)
 
+/* Per-vcpu interrupt controller state */
+#define KVM_REG_PPC_ICP_STATE	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x87)
+
+/* Layout of above for XICS */
+#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 */
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index c5a4478..8d5ee31 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -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 */
+		case KVM_REG_PPC_ICP_STATE: {
+			struct kvm_irq_ctrler *ic = vcpu->kvm->arch.irq_ctrler;
+			if (!ic) {
+				r = -ENXIO;
+				break;
+			}
+			val = get_reg_val(reg->id, ic->get_one_reg(vcpu, reg->id));
+			break;
+		}
 		default:
 			r = -EINVAL;
 			break;
@@ -591,6 +600,16 @@ 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 */
+		case KVM_REG_PPC_ICP_STATE: {
+			struct kvm_irq_ctrler *ic = vcpu->kvm->arch.irq_ctrler;
+
+			if (!ic) {
+				r = -ENXIO;
+				break;
+			}
+			r = ic->set_one_reg(vcpu, reg->id, set_reg_val(reg->id, val));
+			break;
+		}
 		default:
 			r = -EINVAL;
 			break;
diff --git a/arch/powerpc/kvm/book3s_xics.c b/arch/powerpc/kvm/book3s_xics.c
index 2312b56..f54b934 100644
--- a/arch/powerpc/kvm/book3s_xics.c
+++ b/arch/powerpc/kvm/book3s_xics.c
@@ -888,6 +888,96 @@ static void kvmppc_xics_free(struct kvm *kvm)
 	kfree(xics);
 }
 
+static u64 kvmppc_xics_get_icp(struct kvm_vcpu *vcpu, u64 reg_id)
+{
+	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);
+}
+
+static int kvmppc_xics_set_icp(struct kvm_vcpu *vcpu, u64 reg_id, u64 icpval)
+{
+	struct kvmppc_icp *icp = vcpu->arch.icp;
+	struct kvmppc_xics *xics = vcpu->kvm->arch.irq_ctrler_private;
+	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;
+}
+
 static int kvm_xics_get_sources(struct kvm *kvm, struct kvm_irq_sources *srcs)
 {
 	int ret = 0;
@@ -1080,6 +1170,8 @@ static struct kvm_irq_ctrler xics_ctrler = {
 	.free_ctrler = kvmppc_xics_free,
 	.hcall = kvmppc_xics_hcall,
 	.ioctl = kvmppc_xics_ioctl,
+	.get_one_reg = kvmppc_xics_get_icp,
+	.set_one_reg = kvmppc_xics_set_icp,
 };
 
 int kvmppc_xics_create(struct kvm *kvm, struct kvm_irqchip_args *args)
-- 
1.7.10.rc3.219.g53414