KVM: PPC: Support irq routing and irqfd for in-kernel MPIC

Now that all the irq routing and irqfd pieces are generic, we can expose
real irqchip support to all of KVM's internal helpers.

This allows us to use irqfd with the in-kernel MPIC.

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

7 files changed, 158 insertions, 1 deletions

diff --git a/Documentation/virtual/kvm/devices/mpic.txt b/Documentation/virtual/kvm/devices/mpic.txt
index ce98e3264fa8..ad0ac778f20a 100644
--- a/Documentation/virtual/kvm/devices/mpic.txt
+++ b/Documentation/virtual/kvm/devices/mpic.txt
@@ -35,3 +35,22 @@ Groups:
 
     "attr" is the IRQ number.  IRQ numbers for standard sources are the
     byte offset of the relevant IVPR from EIVPR0, divided by 32.
+
+IRQ Routing:
+
+  The MPIC emulation supports IRQ routing. Only a single MPIC device can
+  be instantiated. Once that device has been created, it's available as
+  irqchip id 0.
+
+  This irqchip 0 has 256 interrupt pins, which expose the interrupts in
+  the main array of interrupt sources (a.k.a. "SRC" interrupts).
+
+  The numbering is the same as the MPIC device tree binding -- based on
+  the register offset from the beginning of the sources array, without
+  regard to any subdivisions in chip documentation such as "internal"
+  or "external" interrupts.
+
+  Default routes are established for these pins, with the GSI being equal
+  to the pin number.
+
+  Access to non-SRC interrupts is not implemented through IRQ routing mechanisms.
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index c3f8ceffa412..13740a645a6d 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -44,6 +44,10 @@
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1
 #endif
 
+/* These values are internal and can be increased later */
+#define KVM_NR_IRQCHIPS          1
+#define KVM_IRQCHIP_NUM_PINS     256
+
 #if !defined(CONFIG_KVM_440)
 #include <linux/mmu_notifier.h>
 
@@ -256,6 +260,9 @@ struct kvm_arch {
 #ifdef CONFIG_PPC_BOOK3S_64
 	struct list_head spapr_tce_tables;
 #endif
+#ifdef CONFIG_KVM_MPIC
+	struct openpic *mpic;
+#endif
 };
 
 /*
diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h
index 02ad96606860..ca871067a69b 100644
--- a/arch/powerpc/include/uapi/asm/kvm.h
+++ b/arch/powerpc/include/uapi/asm/kvm.h
@@ -25,6 +25,7 @@
 /* Select powerpc specific features in <linux/kvm.h> */
 #define __KVM_HAVE_SPAPR_TCE
 #define __KVM_HAVE_PPC_SMT
+#define __KVM_HAVE_IRQCHIP
 
 struct kvm_regs {
 	__u64 pc;
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index f47e95e0b6de..4bf10b520765 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -154,6 +154,9 @@ config KVM_E500MC
 config KVM_MPIC
 	bool "KVM in-kernel MPIC emulation"
 	depends on KVM
+	select HAVE_KVM_IRQCHIP
+	select HAVE_KVM_IRQ_ROUTING
+	select HAVE_KVM_MSI
 	help
 	  Enable support for emulating MPIC devices inside the
           host kernel, rather than relying on userspace to emulate.
diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile
index 4a2277a221bb..4eada0c01082 100644
--- a/arch/powerpc/kvm/Makefile
+++ b/arch/powerpc/kvm/Makefile
@@ -104,6 +104,7 @@ kvm-book3s_32-objs := \
 kvm-objs-$(CONFIG_KVM_BOOK3S_32) := $(kvm-book3s_32-objs)
 
 kvm-objs-$(CONFIG_KVM_MPIC) += mpic.o
+kvm-objs-$(CONFIG_HAVE_KVM_IRQ_ROUTING) += $(addprefix ../../../virt/kvm/, irqchip.o)
 
 kvm-objs := $(kvm-objs-m) $(kvm-objs-y)
 
diff --git a/arch/powerpc/kvm/irq.h b/arch/powerpc/kvm/irq.h
new file mode 100644
index 000000000000..f1e27fdc8c2e
--- /dev/null
+++ b/arch/powerpc/kvm/irq.h
@@ -0,0 +1,17 @@
+#ifndef __IRQ_H
+#define __IRQ_H
+
+#include <linux/kvm_host.h>
+
+static inline int irqchip_in_kernel(struct kvm *kvm)
+{
+	int ret = 0;
+
+#ifdef CONFIG_KVM_MPIC
+	ret = ret || (kvm->arch.mpic != NULL);
+#endif
+	smp_rmb();
+	return ret;
+}
+
+#endif
diff --git a/arch/powerpc/kvm/mpic.c b/arch/powerpc/kvm/mpic.c
index 10bc08a246fd..89fe1d66a7fb 100644
--- a/arch/powerpc/kvm/mpic.c
+++ b/arch/powerpc/kvm/mpic.c
@@ -1076,7 +1076,9 @@ static int openpic_cpu_write_internal(void *opaque, gpa_t addr,
 	case 0xA0:		/* IACK */
 		/* Read-only register */
 		break;
-	case 0xB0:		/* EOI */
+	case 0xB0: {		/* EOI */
+		int notify_eoi;
+
 		pr_debug("EOI\n");
 		s_IRQ = IRQ_get_next(opp, &dst->servicing);
 
@@ -1087,6 +1089,8 @@ static int openpic_cpu_write_internal(void *opaque, gpa_t addr,
 		}
 
 		IRQ_resetbit(&dst->servicing, s_IRQ);
+		/* Notify listeners that the IRQ is over */
+		notify_eoi = s_IRQ;
 		/* Set up next servicing IRQ */
 		s_IRQ = IRQ_get_next(opp, &dst->servicing);
 		/* Check queued interrupts. */
@@ -1099,7 +1103,13 @@ static int openpic_cpu_write_internal(void *opaque, gpa_t addr,
 				idx, n_IRQ);
 			mpic_irq_raise(opp, dst, ILR_INTTGT_INT);
 		}
+
+		spin_unlock(&opp->lock);
+		kvm_notify_acked_irq(opp->kvm, 0, notify_eoi);
+		spin_lock(&opp->lock);
+
 		break;
+	}
 	default:
 		break;
 	}
@@ -1639,14 +1649,34 @@ static void mpic_destroy(struct kvm_device *dev)
 		unmap_mmio(opp);
 	}
 
+	dev->kvm->arch.mpic = NULL;
 	kfree(opp);
 }
 
+static int mpic_set_default_irq_routing(struct openpic *opp)
+{
+	struct kvm_irq_routing_entry *routing;
+
+	/* Create a nop default map, so that dereferencing it still works */
+	routing = kzalloc((sizeof(*routing)), GFP_KERNEL);
+	if (!routing)
+		return -ENOMEM;
+
+	kvm_set_irq_routing(opp->kvm, routing, 0, 0);
+
+	kfree(routing);
+	return 0;
+}
+
 static int mpic_create(struct kvm_device *dev, u32 type)
 {
 	struct openpic *opp;
 	int ret;
 
+	/* We only support one MPIC at a time for now */
+	if (dev->kvm->arch.mpic)
+		return -EINVAL;
+
 	opp = kzalloc(sizeof(struct openpic), GFP_KERNEL);
 	if (!opp)
 		return -ENOMEM;
@@ -1691,7 +1721,15 @@ static int mpic_create(struct kvm_device *dev, u32 type)
 		goto err;
 	}
 
+	ret = mpic_set_default_irq_routing(opp);
+	if (ret)
+		goto err;
+
 	openpic_reset(opp);
+
+	smp_wmb();
+	dev->kvm->arch.mpic = opp;
+
 	return 0;
 
 err:
@@ -1761,3 +1799,74 @@ void kvmppc_mpic_disconnect_vcpu(struct openpic *opp, struct kvm_vcpu *vcpu)
 	opp->dst[vcpu->arch.irq_cpu_id].vcpu = NULL;
 	kvm_device_put(opp->dev);
 }
+
+/*
+ * Return value:
+ *  < 0   Interrupt was ignored (masked or not delivered for other reasons)
+ *  = 0   Interrupt was coalesced (previous irq is still pending)
+ *  > 0   Number of CPUs interrupt was delivered to
+ */
+static int mpic_set_irq(struct kvm_kernel_irq_routing_entry *e,
+			struct kvm *kvm, int irq_source_id, int level,
+			bool line_status)
+{
+	u32 irq = e->irqchip.pin;
+	struct openpic *opp = kvm->arch.mpic;
+	unsigned long flags;
+
+	spin_lock_irqsave(&opp->lock, flags);
+	openpic_set_irq(opp, irq, level);
+	spin_unlock_irqrestore(&opp->lock, flags);
+
+	/* All code paths we care about don't check for the return value */
+	return 0;
+}
+
+int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
+		struct kvm *kvm, int irq_source_id, int level, bool line_status)
+{
+	struct openpic *opp = kvm->arch.mpic;
+	unsigned long flags;
+
+	spin_lock_irqsave(&opp->lock, flags);
+
+	/*
+	 * XXX We ignore the target address for now, as we only support
+	 *     a single MSI bank.
+	 */
+	openpic_msi_write(kvm->arch.mpic, MSIIR_OFFSET, e->msi.data);
+	spin_unlock_irqrestore(&opp->lock, flags);
+
+	/* All code paths we care about don't check for the return value */
+	return 0;
+}
+
+int kvm_set_routing_entry(struct kvm_irq_routing_table *rt,
+			  struct kvm_kernel_irq_routing_entry *e,
+			  const struct kvm_irq_routing_entry *ue)
+{
+	int r = -EINVAL;
+
+	switch (ue->type) {
+	case KVM_IRQ_ROUTING_IRQCHIP:
+		e->set = mpic_set_irq;
+		e->irqchip.irqchip = ue->u.irqchip.irqchip;
+		e->irqchip.pin = ue->u.irqchip.pin;
+		if (e->irqchip.pin >= KVM_IRQCHIP_NUM_PINS)
+			goto out;
+		rt->chip[ue->u.irqchip.irqchip][e->irqchip.pin] = ue->gsi;
+		break;
+	case KVM_IRQ_ROUTING_MSI:
+		e->set = kvm_set_msi;
+		e->msi.address_lo = ue->u.msi.address_lo;
+		e->msi.address_hi = ue->u.msi.address_hi;
+		e->msi.data = ue->u.msi.data;
+		break;
+	default:
+		goto out;
+	}
+
+	r = 0;
+out:
+	return r;
+}