KVM: PPC: Book3S: Add kernel emulation for the XICS interrupt controller

This adds in-kernel emulation of the XICS (eXternal Interrupt
Controller Specification) interrupt controller specified by PAPR, for
both HV and PR KVM guests.

The XICS emulation supports up to 1048560 interrupt sources.
Interrupt source numbers below 16 are reserved; 0 is used to mean no
interrupt and 2 is used for IPIs.  Internally these are represented in
blocks of 1024, called ICS (interrupt controller source) entities, but
that is not visible to userspace.

Each vcpu gets one ICP (interrupt controller presentation) entity,
used to store the per-vcpu state such as vcpu priority, pending
interrupt state, IPI request, etc.

This does not include any API or any way to connect vcpus to their
ICP state; that will be added in later patches.

This is based on an initial implementation by Michael Ellerman
<michael@ellerman.id.au> reworked by Benjamin Herrenschmidt and
Paul Mackerras.
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: NPaul Mackerras <paulus@samba.org>
[agraf: fix typo, add dependency on !KVM_MPIC]
Signed-off-by: NAlexander Graf <agraf@suse.de>

arch/powerpc/include/asm/kvm_book3s.h

@@ -142,6 +142,8 @@ extern int kvmppc_mmu_hv_init(void);
 extern int kvmppc_ld(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr, bool data);
 extern int kvmppc_st(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr, bool data);
 extern void kvmppc_book3s_queue_irqprio(struct kvm_vcpu *vcpu, unsigned int vec);
+extern void kvmppc_book3s_dequeue_irqprio(struct kvm_vcpu *vcpu,
+					  unsigned int vec);
 extern void kvmppc_inject_interrupt(struct kvm_vcpu *vcpu, int vec, u64 flags);
 extern void kvmppc_set_bat(struct kvm_vcpu *vcpu, struct kvmppc_bat *bat,
 			   bool upper, u32 val);

arch/powerpc/include/asm/kvm_host.h

@@ -192,6 +192,10 @@ struct kvmppc_linear_info {
 	int		 type;
 };
 
+/* XICS components, defined in book3s_xics.c */
+struct kvmppc_xics;
+struct kvmppc_icp;
+
 /*
  * The reverse mapping array has one entry for each HPTE,
  * which stores the guest's view of the second word of the HPTE
@@ -264,6 +268,9 @@ struct kvm_arch {
 #ifdef CONFIG_KVM_MPIC
 	struct openpic *mpic;
 #endif
+#ifdef CONFIG_KVM_XICS
+	struct kvmppc_xics *xics;
+#endif
 };
 
 /*
@@ -387,6 +394,7 @@ struct kvmppc_booke_debug_reg {
 
 #define KVMPPC_IRQ_DEFAULT	0
 #define KVMPPC_IRQ_MPIC		1
+#define KVMPPC_IRQ_XICS		2
 
 struct openpic;
 
@@ -574,6 +582,9 @@ struct kvm_vcpu_arch {
 	int irq_type;		/* one of KVM_IRQ_* */
 	int irq_cpu_id;
 	struct openpic *mpic;	/* KVM_IRQ_MPIC */
+#ifdef CONFIG_KVM_XICS
+	struct kvmppc_icp *icp; /* XICS presentation controller */
+#endif
 
 #ifdef CONFIG_KVM_BOOK3S_64_HV
 	struct kvm_vcpu_arch_shared shregs;

arch/powerpc/include/asm/kvm_ppc.h

@@ -130,6 +130,7 @@ extern long kvmppc_prepare_vrma(struct kvm *kvm,
 extern void kvmppc_map_vrma(struct kvm_vcpu *vcpu,
 			struct kvm_memory_slot *memslot, unsigned long porder);
 extern int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu);
+
 extern long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 				struct kvm_create_spapr_tce *args);
 extern long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
@@ -169,6 +170,10 @@ int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, struct kvm_interrupt *irq);
 extern int kvm_vm_ioctl_rtas_define_token(struct kvm *kvm, void __user *argp);
 extern int kvmppc_rtas_hcall(struct kvm_vcpu *vcpu);
 extern void kvmppc_rtas_tokens_free(struct kvm *kvm);
+extern int kvmppc_xics_set_xive(struct kvm *kvm, u32 irq, u32 server,
+				u32 priority);
+extern int kvmppc_xics_get_xive(struct kvm *kvm, u32 irq, u32 *server,
+				u32 *priority);
 
 /*
  * Cuts out inst bits with ordering according to spec.
@@ -267,6 +272,30 @@ static inline void kvmppc_set_xics_phys(int cpu, unsigned long addr)
 
 static inline void kvm_linear_init(void)
 {}
+
+#endif
+
+#ifdef CONFIG_KVM_XICS
+static inline int kvmppc_xics_enabled(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.irq_type == KVMPPC_IRQ_XICS;
+}
+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);
+#else
+static inline int kvmppc_xics_enabled(struct kvm_vcpu *vcpu)
+	{ return 0; }
+static inline void kvmppc_xics_free_icp(struct kvm_vcpu *vcpu) { }
+static inline int kvmppc_xics_create_icp(struct kvm_vcpu *vcpu,
+					 unsigned long server)
+	{ return -EINVAL; }
+static inline int kvm_vm_ioctl_xics_irq(struct kvm *kvm,
+					struct kvm_irq_level *args)
+	{ return -ENOTTY; }
+static inline int kvmppc_xics_hcall(struct kvm_vcpu *vcpu, u32 cmd)
+	{ return 0; }
 #endif
 
 static inline void kvmppc_set_epr(struct kvm_vcpu *vcpu, u32 epr)

arch/powerpc/kvm/Kconfig

@@ -163,6 +163,14 @@ config KVM_MPIC
           Currently, support is limited to certain versions of
           Freescale's MPIC implementation.
 
+config KVM_XICS
+	bool "KVM in-kernel XICS emulation"
+	depends on KVM_BOOK3S_64 && !KVM_MPIC
+	---help---
+	  Include support for the XICS (eXternal Interrupt Controller
+	  Specification) interrupt controller architecture used on
+	  IBM POWER (pSeries) servers.
+
 source drivers/vhost/Kconfig
 
 endif # VIRTUALIZATION

arch/powerpc/kvm/Makefile

@@ -79,6 +79,9 @@ kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HV) := \
 	book3s_hv_ras.o \
 	book3s_hv_builtin.o
 
+kvm-book3s_64-objs-$(CONFIG_KVM_XICS) += \
+	book3s_xics.o
+
 kvm-book3s_64-module-objs := \
 	../../../virt/kvm/kvm_main.o \
 	../../../virt/kvm/eventfd.o \

arch/powerpc/kvm/book3s.c

@@ -104,7 +104,7 @@ static int kvmppc_book3s_vec2irqprio(unsigned int vec)
 	return prio;
 }
 
-static void kvmppc_book3s_dequeue_irqprio(struct kvm_vcpu *vcpu,
+void kvmppc_book3s_dequeue_irqprio(struct kvm_vcpu *vcpu,
 					  unsigned int vec)
 {
 	unsigned long old_pending = vcpu->arch.pending_exceptions;

arch/powerpc/kvm/book3s_hv.c

@@ -532,6 +532,15 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
 
 		/* Send the error out to userspace via KVM_RUN */
 		return rc;
+
+	case H_XIRR:
+	case H_CPPR:
+	case H_EOI:
+	case H_IPI:
+		if (kvmppc_xics_enabled(vcpu)) {
+			ret = kvmppc_xics_hcall(vcpu, req);
+			break;
+		} /* fallthrough */
 	default:
 		return RESUME_HOST;
 	}

arch/powerpc/kvm/book3s_pr_papr.c

@@ -227,6 +227,13 @@ static int kvmppc_h_pr_put_tce(struct kvm_vcpu *vcpu)
 	return EMULATE_DONE;
 }
 
+static int kvmppc_h_pr_xics_hcall(struct kvm_vcpu *vcpu, u32 cmd)
+{
+	long rc = kvmppc_xics_hcall(vcpu, cmd);
+	kvmppc_set_gpr(vcpu, 3, rc);
+	return EMULATE_DONE;
+}
+
 int kvmppc_h_pr(struct kvm_vcpu *vcpu, unsigned long cmd)
 {
 	switch (cmd) {
@@ -246,6 +253,13 @@ int kvmppc_h_pr(struct kvm_vcpu *vcpu, unsigned long cmd)
 		clear_bit(KVM_REQ_UNHALT, &vcpu->requests);
 		vcpu->stat.halt_wakeup++;
 		return EMULATE_DONE;
+	case H_XIRR:
+	case H_CPPR:
+	case H_EOI:
+	case H_IPI:
+		if (kvmppc_xics_enabled(vcpu))
+			return kvmppc_h_pr_xics_hcall(vcpu, cmd);
+		break;
 	case H_RTAS:
 		if (list_empty(&vcpu->kvm->arch.rtas_tokens))
 			return RESUME_HOST;

arch/powerpc/kvm/book3s_rtas.c

@@ -17,13 +17,65 @@
 #include <asm/hvcall.h>
 #include <asm/rtas.h>
 
+#ifdef CONFIG_KVM_XICS
+static void kvm_rtas_set_xive(struct kvm_vcpu *vcpu, struct rtas_args *args)
+{
+	u32 irq, server, priority;
+	int rc;
+
+	if (args->nargs != 3 || args->nret != 1) {
+		rc = -3;
+		goto out;
+	}
+
+	irq = args->args[0];
+	server = args->args[1];
+	priority = args->args[2];
+
+	rc = kvmppc_xics_set_xive(vcpu->kvm, irq, server, priority);
+	if (rc)
+		rc = -3;
+out:
+	args->rets[0] = rc;
+}
+
+static void kvm_rtas_get_xive(struct kvm_vcpu *vcpu, struct rtas_args *args)
+{
+	u32 irq, server, priority;
+	int rc;
+
+	if (args->nargs != 1 || args->nret != 3) {
+		rc = -3;
+		goto out;
+	}
+
+	irq = args->args[0];
+
+	server = priority = 0;
+	rc = kvmppc_xics_get_xive(vcpu->kvm, irq, &server, &priority);
+	if (rc) {
+		rc = -3;
+		goto out;
+	}
+
+	args->rets[1] = server;
+	args->rets[2] = priority;
+out:
+	args->rets[0] = rc;
+}
+#endif /* CONFIG_KVM_XICS */
 
 struct rtas_handler {
 	void (*handler)(struct kvm_vcpu *vcpu, struct rtas_args *args);
 	char *name;
 };
 
-static struct rtas_handler rtas_handlers[] = { };
+static struct rtas_handler rtas_handlers[] = {
+#ifdef CONFIG_KVM_XICS
+	{ .name = "ibm,set-xive", .handler = kvm_rtas_set_xive },
+	{ .name = "ibm,get-xive", .handler = kvm_rtas_get_xive },
+#endif
+};
 
 struct rtas_token_definition {
 	struct list_head list;

arch/powerpc/kvm/book3s_xics.h

+/*
+ * Copyright 2012 Michael Ellerman, IBM Corporation.
+ * Copyright 2012 Benjamin Herrenschmidt, IBM Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _KVM_PPC_BOOK3S_XICS_H
+#define _KVM_PPC_BOOK3S_XICS_H
+
+/*
+ * We use a two-level tree to store interrupt source information.
+ * There are up to 1024 ICS nodes, each of which can represent
+ * 1024 sources.
+ */
+#define KVMPPC_XICS_MAX_ICS_ID	1023
+#define KVMPPC_XICS_ICS_SHIFT	10
+#define KVMPPC_XICS_IRQ_PER_ICS	(1 << KVMPPC_XICS_ICS_SHIFT)
+#define KVMPPC_XICS_SRC_MASK	(KVMPPC_XICS_IRQ_PER_ICS - 1)
+
+/*
+ * Interrupt source numbers below this are reserved, for example
+ * 0 is "no interrupt", and 2 is used for IPIs.
+ */
+#define KVMPPC_XICS_FIRST_IRQ	16
+#define KVMPPC_XICS_NR_IRQS	((KVMPPC_XICS_MAX_ICS_ID + 1) * \
+				 KVMPPC_XICS_IRQ_PER_ICS)
+
+/* Priority value to use for disabling an interrupt */
+#define MASKED	0xff
+
+/* State for one irq source */
+struct ics_irq_state {
+	u32 number;
+	u32 server;
+	u8  priority;
+	u8  saved_priority; /* currently unused */
+	u8  resend;
+	u8  masked_pending;
+	u8  asserted; /* Only for LSI */
+	u8  exists;
+};
+
+/* Atomic ICP state, updated with a single compare & swap */
+union kvmppc_icp_state {
+	unsigned long raw;
+	struct {
+		u8 out_ee:1;
+		u8 need_resend:1;
+		u8 cppr;
+		u8 mfrr;
+		u8 pending_pri;
+		u32 xisr;
+	};
+};
+
+/* One bit per ICS */
+#define ICP_RESEND_MAP_SIZE	(KVMPPC_XICS_MAX_ICS_ID / BITS_PER_LONG + 1)
+
+struct kvmppc_icp {
+	struct kvm_vcpu *vcpu;
+	unsigned long server_num;
+	union kvmppc_icp_state state;
+	unsigned long resend_map[ICP_RESEND_MAP_SIZE];
+};
+
+struct kvmppc_ics {
+	struct mutex lock;
+	u16 icsid;
+	struct ics_irq_state irq_state[KVMPPC_XICS_IRQ_PER_ICS];
+};
+
+struct kvmppc_xics {
+	struct kvm *kvm;
+	struct dentry *dentry;
+	u32 max_icsid;
+	struct kvmppc_ics *ics[KVMPPC_XICS_MAX_ICS_ID + 1];
+};
+
+static inline struct kvmppc_icp *kvmppc_xics_find_server(struct kvm *kvm,
+							 u32 nr)
+{
+	struct kvm_vcpu *vcpu = NULL;
+	int i;
+
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		if (vcpu->arch.icp && nr == vcpu->arch.icp->server_num)
+			return vcpu->arch.icp;
+	}
+	return NULL;
+}
+
+static inline struct kvmppc_ics *kvmppc_xics_find_ics(struct kvmppc_xics *xics,
+						      u32 irq, u16 *source)
+{
+	u32 icsid = irq >> KVMPPC_XICS_ICS_SHIFT;
+	u16 src = irq & KVMPPC_XICS_SRC_MASK;
+	struct kvmppc_ics *ics;
+
+	if (source)
+		*source = src;
+	if (icsid > KVMPPC_XICS_MAX_ICS_ID)
+		return NULL;
+	ics = xics->ics[icsid];
+	if (!ics)
+		return NULL;
+	return ics;
+}
+
+
+#endif /* _KVM_PPC_BOOK3S_XICS_H */

arch/powerpc/kvm/powerpc.c

@@ -471,6 +471,9 @@ void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
 	case KVMPPC_IRQ_MPIC:
 		kvmppc_mpic_disconnect_vcpu(vcpu->arch.mpic, vcpu);
 		break;
+	case KVMPPC_IRQ_XICS:
+		kvmppc_xics_free_icp(vcpu);
+		break;
 	}
 
 	kvmppc_core_vcpu_free(vcpu);