[RFC,v3] ARM: KVM: add irqfd and irq routing support

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index b4f5365..326e382 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -1339,7 +1339,7 @@  KVM_ASSIGN_DEV_IRQ. Partial deassignment of host or guest IRQ is allowed.
 4.52 KVM_SET_GSI_ROUTING
 
 Capability: KVM_CAP_IRQ_ROUTING
-Architectures: x86 ia64 s390
+Architectures: x86 ia64 s390 arm
 Type: vm ioctl
 Parameters: struct kvm_irq_routing (in)
 Returns: 0 on success, -1 on error
@@ -2126,7 +2126,7 @@  into the hash PTE second double word).
 4.75 KVM_IRQFD
 
 Capability: KVM_CAP_IRQFD
-Architectures: x86 s390
+Architectures: x86 s390 arm
 Type: vm ioctl
 Parameters: struct kvm_irqfd (in)
 Returns: 0 on success, -1 on error
@@ -2152,6 +2152,14 @@  Note that closing the resamplefd is not sufficient to disable the
 irqfd.  The KVM_IRQFD_FLAG_RESAMPLE is only necessary on assignment
 and need not be specified with KVM_IRQFD_FLAG_DEASSIGN.
 
+On ARM/arm64 the virtual IRQ injection mandates the existence of a
+routing table, set through KVM_SET_GSI_ROUTING. this latter contains
+entries which associate a gsi with an irqchip pin. The injected virtual
+IRQ actually corresponds to the irqchip.pin. It is up to the user to
+define gsi = irqchip.pin or not. On ARM the single irqchip is the GIC.
+Then irqchip.pin is interpreted as the system shared peripheral
+interrupt number (SPI). Associated GIC interrupt ID is irqchip.pin + 32.
+
 4.76 KVM_PPC_ALLOCATE_HTAB
 
 Capability: KVM_CAP_PPC_ALLOC_HTAB
diff --git a/arch/arm/include/uapi/asm/kvm.h b/arch/arm/include/uapi/asm/kvm.h
index ef0c878..9b642a3 100644
--- a/arch/arm/include/uapi/asm/kvm.h
+++ b/arch/arm/include/uapi/asm/kvm.h
@@ -192,6 +192,15 @@  struct kvm_arch_memory_slot {
 /* Highest supported SPI, from VGIC_NR_IRQS */
 #define KVM_ARM_IRQ_GIC_MAX		127
 
+/* One single KVM irqchip, ie. the VGIC */
+#define KVM_NR_IRQCHIPS          1
+
+/*
+ * temporary solution until static allocation of chip[][] in irqchip.c
+ * is changed
+ */
+#define KVM_IRQCHIP_NUM_PINS    VGIC_NR_IRQS
+
 /* PSCI interface */
 #define KVM_PSCI_FN_BASE		0x95c1ba5e
 #define KVM_PSCI_FN(n)			(KVM_PSCI_FN_BASE + (n))
diff --git a/arch/arm/kvm/Kconfig b/arch/arm/kvm/Kconfig
index 4be5bb1..096692c 100644
--- a/arch/arm/kvm/Kconfig
+++ b/arch/arm/kvm/Kconfig
@@ -24,6 +24,7 @@  config KVM
 	select KVM_MMIO
 	select KVM_ARM_HOST
 	depends on ARM_VIRT_EXT && ARM_LPAE && !CPU_BIG_ENDIAN
+	select HAVE_KVM_EVENTFD
 	---help---
 	  Support hosting virtualized guest machines. You will also
 	  need to select one or more of the processor modules below.
@@ -56,6 +57,7 @@  config KVM_ARM_VGIC
 	bool "KVM support for Virtual GIC"
 	depends on KVM_ARM_HOST && OF
 	select HAVE_KVM_IRQCHIP
+	select HAVE_KVM_IRQ_ROUTING
 	default y
 	---help---
 	  Adds support for a hardware assisted, in-kernel GIC emulation.
diff --git a/arch/arm/kvm/Makefile b/arch/arm/kvm/Makefile
index 789bca9..29de111 100644
--- a/arch/arm/kvm/Makefile
+++ b/arch/arm/kvm/Makefile
@@ -21,4 +21,5 @@  obj-y += kvm-arm.o init.o interrupts.o
 obj-y += arm.o handle_exit.o guest.o mmu.o emulate.o reset.o
 obj-y += coproc.o coproc_a15.o coproc_a7.o mmio.o psci.o perf.o
 obj-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic.o
+obj-$(CONFIG_HAVE_KVM_EVENTFD) += $(KVM)/eventfd.o $(KVM)/irqchip.o
 obj-$(CONFIG_KVM_ARM_TIMER) += $(KVM)/arm/arch_timer.o
diff --git a/arch/arm/kvm/irq.h b/arch/arm/kvm/irq.h
new file mode 100644
index 0000000..1275d91
--- /dev/null
+++ b/arch/arm/kvm/irq.h
@@ -0,0 +1,25 @@ 
+/*
+ * Copyright (C) 2014 Linaro Ltd.
+ * Authors: Eric Auger <eric.auger@linaro.org>
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef __IRQ_H
+#define __IRQ_H
+
+#include <linux/kvm_host.h>
+/*
+ * Placeholder for irqchip and irq/msi routing declarations
+ * included in irqchip.c
+ */
+
+#endif
diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c
index 66fc48b..c06bed0 100644
--- a/virt/kvm/arm/vgic.c
+++ b/virt/kvm/arm/vgic.c
@@ -99,6 +99,7 @@  static struct device_node *vgic_node;
 #define ACCESS_WRITE_VALUE	(3 << 1)
 #define ACCESS_WRITE_MASK(x)	((x) & (3 << 1))
 
+static int vgic_set_default_irq_routing(struct kvm *kvm);
 static void vgic_retire_disabled_irqs(struct kvm_vcpu *vcpu);
 static void vgic_update_state(struct kvm *kvm);
 static void vgic_kick_vcpus(struct kvm *kvm);
@@ -1259,7 +1260,10 @@  epilog:
 static bool vgic_process_maintenance(struct kvm_vcpu *vcpu)
 {
 	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
 	bool level_pending = false;
+	struct kvm *kvm = vcpu->kvm;
+	int is_assigned_irq;
 
 	kvm_debug("MISR = %08x\n", vgic_cpu->vgic_misr);
 
@@ -1273,6 +1277,7 @@  static bool vgic_process_maintenance(struct kvm_vcpu *vcpu)
 		for_each_set_bit(lr, (unsigned long *)vgic_cpu->vgic_eisr,
 				 vgic_cpu->nr_lr) {
 			irq = vgic_cpu->vgic_lr[lr] & GICH_LR_VIRTUALID;
+			spin_lock(&dist->lock);
 			BUG_ON(vgic_irq_is_edge(vcpu, irq));
 
 			vgic_irq_clear_queued(vcpu, irq);
@@ -1285,6 +1290,17 @@  static bool vgic_process_maintenance(struct kvm_vcpu *vcpu)
 			 * interrupt.
 			 */
 			vgic_dist_irq_clear_soft_pend(vcpu, irq);
+			spin_unlock(&dist->lock);
+
+			is_assigned_irq = kvm_irq_has_notifier(kvm, 0,
+						irq - VGIC_NR_PRIVATE_IRQS);
+
+			if (is_assigned_irq) {
+				kvm_debug("EOI irqchip routed vIRQ %d\n", irq);
+				kvm_notify_acked_irq(kvm, 0,
+					irq - VGIC_NR_PRIVATE_IRQS);
+			}
+			spin_lock(&dist->lock);
 
 			/* Any additional pending interrupt? */
 			if (vgic_dist_irq_get_level(vcpu, irq)) {
@@ -1305,6 +1321,7 @@  static bool vgic_process_maintenance(struct kvm_vcpu *vcpu)
 			 */
 			set_bit(lr, (unsigned long *)vgic_cpu->vgic_elrsr);
 			vgic_cpu->vgic_lr[lr] &= ~GICH_LR_ACTIVE_BIT;
+			spin_unlock(&dist->lock);
 		}
 	}
 
@@ -1344,8 +1361,10 @@  static void __kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu)
 	/* Check if we still have something up our sleeve... */
 	pending = find_first_zero_bit((unsigned long *)vgic_cpu->vgic_elrsr,
 				      vgic_cpu->nr_lr);
+	spin_lock(&dist->lock);
 	if (level_pending || pending < vgic_cpu->nr_lr)
 		set_bit(vcpu->vcpu_id, &dist->irq_pending_on_cpu);
+	spin_unlock(&dist->lock);
 }
 
 void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu)
@@ -1362,14 +1381,10 @@  void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu)
 
 void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu)
 {
-	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
-
 	if (!irqchip_in_kernel(vcpu->kvm))
 		return;
 
-	spin_lock(&dist->lock);
 	__kvm_vgic_sync_hwstate(vcpu);
-	spin_unlock(&dist->lock);
 }
 
 int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu)
@@ -1740,6 +1755,8 @@  int kvm_vgic_create(struct kvm *kvm)
 	kvm->arch.vgic.vgic_dist_base = VGIC_ADDR_UNDEF;
 	kvm->arch.vgic.vgic_cpu_base = VGIC_ADDR_UNDEF;
 
+	vgic_set_default_irq_routing(kvm);
+
 out_unlock:
 	for (; vcpu_lock_idx >= 0; vcpu_lock_idx--) {
 		vcpu = kvm_get_vcpu(kvm, vcpu_lock_idx);
@@ -2130,3 +2147,86 @@  struct kvm_device_ops kvm_arm_vgic_v2_ops = {
 	.get_attr = vgic_get_attr,
 	.has_attr = vgic_has_attr,
 };
+
+static int vgic_set_default_irq_routing(struct kvm *kvm)
+{
+	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(kvm, routing, 0, 0);
+
+	kfree(routing);
+	return 0;
+}
+
+
+/**
+ * vgic_set_assigned_irq - Inject a routed IRQ to the vgic
+ * @e: the routing entry describing how to route the IRQ
+ * @kvm: the kvm struct
+ * @irq_source_id: the irq source id (userspace or resample)
+ * @level: wire level
+ * @line_status: currently unused
+ * return 0
+ *
+ * This is the function that is eventually called by kvm_set_irq
+ * implemented in irqchip.c.
+ */
+static int vgic_set_assigned_irq(struct kvm_kernel_irq_routing_entry *e,
+			   struct kvm *kvm, int irq_source_id, int level,
+			   bool line_status)
+{
+	int r = -EINVAL;
+	unsigned int spi = e->irqchip.pin + VGIC_NR_PRIVATE_IRQS;
+
+	if (spi > KVM_ARM_IRQ_GIC_MAX)
+		return r;
+
+	kvm_debug("Inject irqchip routed vIRQ %d\n", e->irqchip.pin);
+	r = kvm_vgic_inject_irq(kvm, 0, spi, level);
+	return r;
+}
+
+/* MSI not implemented yet */
+int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
+		struct kvm *kvm, int irq_source_id, int level, bool line_status)
+{
+	return 0;
+}
+
+/**
+ * Populates a kvm routing entry from a user routing entry
+ * and update the routing table chip array
+ * @rt: routing table
+ * @e: kvm internal formatted entry
+ * @ue: user api formatted entry
+ * return 0 on success, -EINVAL on errors.
+ */
+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 = vgic_set_assigned_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;
+		if (e->irqchip.irqchip >= KVM_NR_IRQCHIPS)
+			goto out;
+		rt->chip[e->irqchip.irqchip][e->irqchip.pin] = ue->gsi;
+		break;
+	default:
+		goto out;
+	}
+	r = 0;
+out:
+	return r;
+}