[PATCH 0/3] Add support for handling IRQs in userspace

[PATCH 0/3] Add support for handling IRQs in userspace

[Pavel Fedin]

This patch series introduces ability to handle IRQs in userspace. This is
currently necessary for ARM KVM in order to be able to use virtual CP15
timer without in-kernel irqchip. This allows to use KVM on machines with
either broken vGIC or custom interrupt controller, like Raspberry Pi 2.

The API is designed to be as much architecture-agnostic is possible.
Currently it actually supports only a single IRQ, but it can be easily
extended to accomodate more.

Pavel Fedin (3):
  KVM: Introduce KVM_EXIT_IRQ
  KVM: Documentation: Document KVM_EXIT_IRQ
  KVM: arm/arm64: Decouple virtual timer from vGIC

 Documentation/virtual/kvm/api.txt | 14 ++++++++++++++
 arch/arm/kvm/arm.c                | 14 +++++++-------
 include/linux/kvm_host.h          |  7 +++++++
 include/uapi/linux/kvm.h          |  3 +++
 virt/kvm/arm/arch_timer.c         | 23 +++++++++++++----------
 5 files changed, 44 insertions(+), 17 deletions(-)

-- 
2.4.4

[PATCH 1/3] KVM: Introduce KVM_EXIT_IRQ

[Pavel Fedin]

This exit code means that this vCPU wants to inject an interrupt using
userspace-emulated controller.

IRQs are signalled by adding pending interrupt descriptors to vcpu
structure. For simplicity, we currently reserve only one pointer for a
single interrupt, which will be used by ARM virtual timer code. This can
be extended in the future if necessary.

The interface is designed to be as much arch-agnostic as possible.
Therefore, it has IRQ number and level as parameters (encoded in
struct kvm_irq_level).

Signed-off-by: Pavel Fedin <p.fedin@samsung.com>
---
 arch/arm/kvm/arm.c       | 6 ++++++
 include/linux/kvm_host.h | 7 +++++++
 include/uapi/linux/kvm.h | 3 +++
 3 files changed, 16 insertions(+)

diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index 66f90c1..6392a5b 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -585,6 +585,12 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		if (signal_pending(current)) {
 			ret = -EINTR;
 			run->exit_reason = KVM_EXIT_INTR;
+		} else if (vcpu->irq) {
+			ret = 0;
+			run->exit_reason = KVM_EXIT_IRQ;
+			run->irq.irq = vcpu->irq->irq;
+			run->irq.level = vcpu->irq->level;
+			vcpu->irq = NULL;
 		}
 
 		if (ret <= 0 || need_new_vmid_gen(vcpu->kvm) ||
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index c923350..93f59c5 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -281,6 +281,13 @@ struct kvm_vcpu {
 	} spin_loop;
 #endif
 	bool preempted;
+
+	/*
+	 * IRQ pending to the userspace on this CPU.
+	 * Currently we support only one slot, used only by ARM architecture.
+	 */
+	const struct kvm_irq_level *irq;
+
 	struct kvm_vcpu_arch arch;
 };
 
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 03f3618..a717a9b 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -184,6 +184,7 @@ struct kvm_s390_skeys {
 #define KVM_EXIT_SYSTEM_EVENT     24
 #define KVM_EXIT_S390_STSI        25
 #define KVM_EXIT_IOAPIC_EOI       26
+#define KVM_EXIT_IRQ              27
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 /* Emulate instruction failed. */
@@ -338,6 +339,8 @@ struct kvm_run {
 		struct {
 			__u8 vector;
 		} eoi;
+		/* KVM_EXIT_IRQ */
+		struct kvm_irq_level irq;
 		/* Fix the size of the union. */
 		char padding[256];
 	};
-- 
2.4.4

[PATCH 2/3] KVM: Documentation: Document KVM_EXIT_IRQ

[Pavel Fedin]

Add documentation for the new exit code.

Signed-off-by: Pavel Fedin <p.fedin@samsung.com>
---
 Documentation/virtual/kvm/api.txt | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 092ee9f..d8aae4c 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -3331,6 +3331,20 @@ the userspace IOAPIC should process the EOI and retrigger the interrupt if
 it is still asserted.  Vector is the LAPIC interrupt vector for which the
 EOI was received.
 
+		/* KVM_EXIT_IRQ */
+		struct kvm_irq_level irq;
+
+Indicates that an interrupt happens, to be processed by irqchip implemented in
+userspace. irq.irq specifies the raw IRQ number, and irq.status is to be
+interpreted according to interrupt type:
+ For level-triggered interrupts irq.status is set to new level of the line, and
+  the exit happens upon level change.
+ For edge-triggered interrupts irq.status is set to active level of the line
+  (low or high), and the exit happens when the line is pulsed.
+
+CPU-private interrupts (like per-CPU timers) belong to the vCPU where the exit
+happened.
+
 		/* Fix the size of the union. */
 		char padding[256];
 	};
-- 
2.4.4

[PATCH 3/3] KVM: arm/arm64: Decouple virtual timer from vGIC

[Pavel Fedin]

Remove dependency on vgic_initialized() and use the newly introduced
infrastructure to send interrupts via the userspace if vGIC is not being
used.

Signed-off-by: Pavel Fedin <p.fedin@samsung.com>
---
 arch/arm/kvm/arm.c        |  8 +-------
 virt/kvm/arm/arch_timer.c | 23 +++++++++++++----------
 2 files changed, 14 insertions(+), 17 deletions(-)

diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index 6392a5b..e729068 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -468,13 +468,7 @@ static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu)
 			return ret;
 	}
 
-	/*
-	 * Enable the arch timers only if we have an in-kernel VGIC
-	 * and it has been properly initialized, since we cannot handle
-	 * interrupts from the virtual timer with a userspace gic.
-	 */
-	if (irqchip_in_kernel(kvm) && vgic_initialized(kvm))
-		kvm_timer_enable(kvm);
+	kvm_timer_enable(kvm);
 
 	return 0;
 }
diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c
index 69bca18..90c91b0 100644
--- a/virt/kvm/arm/arch_timer.c
+++ b/virt/kvm/arm/arch_timer.c
@@ -128,15 +128,17 @@ static void kvm_timer_update_irq(struct kvm_vcpu *vcpu, bool new_level)
 	int ret;
 	struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
 
-	BUG_ON(!vgic_initialized(vcpu->kvm));
-
 	timer->irq.level = new_level;
 	trace_kvm_timer_update_irq(vcpu->vcpu_id, timer->map->virt_irq,
 				   timer->irq.level);
-	ret = kvm_vgic_inject_mapped_irq(vcpu->kvm, vcpu->vcpu_id,
-					 timer->map,
-					 timer->irq.level);
-	WARN_ON(ret);
+	if (irqchip_in_kernel(vcpu->kvm)) {
+		ret = kvm_vgic_inject_mapped_irq(vcpu->kvm, vcpu->vcpu_id,
+						 timer->map,
+						 timer->irq.level);
+		WARN_ON(ret);
+	} else {
+		vcpu->irq = &timer->irq;
+	}
 }
 
 /*
@@ -149,12 +151,12 @@ static void kvm_timer_update_state(struct kvm_vcpu *vcpu)
 
 	/*
 	 * If userspace modified the timer registers via SET_ONE_REG before
-	 * the vgic was initialized, we mustn't set the timer->irq.level value
+	 * the timer was initialized, we mustn't set the timer->irq.level value
 	 * because the guest would never see the interrupt.  Instead wait
 	 * until we call this function from kvm_timer_flush_hwstate.
 	 */
-	if (!vgic_initialized(vcpu->kvm))
-	    return;
+	if (!vcpu->kvm->arch.timer.enabled)
+		return;
 
 	if (kvm_timer_should_fire(vcpu) != timer->irq.level)
 		kvm_timer_update_irq(vcpu, !timer->irq.level);
@@ -237,7 +239,8 @@ void kvm_timer_flush_hwstate(struct kvm_vcpu *vcpu)
 	* to ensure that hardware interrupts from the timer triggers a guest
 	* exit.
 	*/
-	if (timer->irq.level || kvm_vgic_map_is_active(vcpu, timer->map))
+	if (timer->irq.level || (irqchip_in_kernel(vcpu->kvm) &&
+				 kvm_vgic_map_is_active(vcpu, timer->map)))
 		phys_active = true;
 	else
 		phys_active = false;
-- 
2.4.4