[RFC v6 16/16] KVM: arm/arm64: vgic: forwarding control

[Eric Auger]

This patch sets __KVM_HAVE_ARCH_KVM_VFIO_FORWARD and implements
kvm_arch_set_forward for ARM/ARM64.

As a result the KVM-VFIO device now allows to forward/unforward a
VFIO device IRQ on ARM.

kvm_arch_set_forward and kvm_arch_unset_forward mostly take care of
VGIC programming: physical IRQ/guest IRQ mapping, list register cleanup,
VGIC state machine.

Signed-off-by: Eric Auger <eric.auger@xxxxxxxxxx>

---

v4 -> v5:
- fix arm64 compilation issues, ie. also defines
  __KVM_HAVE_ARCH_HALT_GUEST for arm64

v3 -> v4:
- code originally located in kvm_vfio_arm.c
- kvm_arch_vfio_{set|unset}_forward renamed into
  kvm_arch_{set|unset}_forward
- split into 2 functions (set/unset) since unset does not fail anymore
- unset can be invoked at whatever time. Extra care is taken to handle
  transition in VGIC state machine, LR cleanup, ...

v2 -> v3:
- renaming of kvm_arch_set_fwd_state into kvm_arch_vfio_set_forward
- takes a bool arg instead of kvm_fwd_irq_action enum
- removal of KVM_VFIO_IRQ_CLEANUP
- platform device check now happens here
- more precise errors returned
- irq_eoi handled externally to this patch (VGIC)
- correct enable_irq bug done twice
- reword the commit message
- correct check of platform_bus_type
- use raw_spin_lock_irqsave and check the validity of the handler
---
 arch/arm/include/asm/kvm_host.h   |   1 +
 arch/arm64/include/asm/kvm_host.h |   1 +
 virt/kvm/arm/vgic.c               | 190 ++++++++++++++++++++++++++++++++++++++
 3 files changed, 192 insertions(+)

diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
index b829f93..8e3fd7f 100644
--- a/arch/arm/include/asm/kvm_host.h
+++ b/arch/arm/include/asm/kvm_host.h
@@ -29,6 +29,7 @@
 
 #define __KVM_HAVE_ARCH_INTC_INITIALIZED
 #define __KVM_HAVE_ARCH_HALT_GUEST
+#define __KVM_HAVE_ARCH_KVM_VFIO_FORWARD
 
 #if defined(CONFIG_KVM_ARM_MAX_VCPUS)
 #define KVM_MAX_VCPUS CONFIG_KVM_ARM_MAX_VCPUS
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index ffcc698..9be392a 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -30,6 +30,7 @@
 
 #define __KVM_HAVE_ARCH_INTC_INITIALIZED
 #define __KVM_HAVE_ARCH_HALT_GUEST
+#define __KVM_HAVE_ARCH_KVM_VFIO_FORWARD
 
 #if defined(CONFIG_KVM_ARM_MAX_VCPUS)
 #define KVM_MAX_VCPUS CONFIG_KVM_ARM_MAX_VCPUS
diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c
index f345c41..c0ac151 100644
--- a/virt/kvm/arm/vgic.c
+++ b/virt/kvm/arm/vgic.c
@@ -2133,3 +2133,193 @@ int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
 {
 	return 0;
 }
+
+/**
+ * kvm_arch_set_forward - Set forwarding for a given IRQ
+ *
+ * @kvm: handle to the VM
+ * @host_irq: physical IRQ number
+ * @guest_irq: virtual IRQ number
+ *
+ * This function is supposed to be called only if the IRQ
+ * is not in progress: ie. not active at VGIC level and not
+ * currently under injection in the KVM.
+ */
+int kvm_arch_set_forward(struct kvm *kvm, unsigned int host_irq,
+			 unsigned int guest_irq)
+{
+	irq_hw_number_t gic_irq;
+	struct irq_desc *desc = irq_to_desc(host_irq);
+	struct irq_data *d;
+	unsigned long flags;
+	struct kvm_vcpu *vcpu = kvm_get_vcpu(kvm, 0);
+	int ret = 0;
+	int spi_id = guest_irq + VGIC_NR_PRIVATE_IRQS;
+	struct vgic_dist *dist = &kvm->arch.vgic;
+
+	if (!vcpu)
+		return 0;
+
+	spin_lock(&dist->lock);
+
+	raw_spin_lock_irqsave(&desc->lock, flags);
+	d = &desc->irq_data;
+	gic_irq = irqd_to_hwirq(d);
+	irqd_set_irq_forwarded(d);
+	/*
+	 * next physical IRQ will be be handled as forwarded
+	 * by the host (priority drop only)
+	 */
+
+	raw_spin_unlock_irqrestore(&desc->lock, flags);
+
+	/*
+	 * need to release the dist spin_lock here since
+	 * vgic_map_phys_irq can sleep
+	 */
+	spin_unlock(&dist->lock);
+	ret = vgic_map_phys_irq(vcpu, spi_id, (int)gic_irq);
+	/*
+	 * next guest_irq injection will be considered as
+	 * forwarded and next flush will program LR
+	 * without maintenance IRQ but with HW bit set
+	 */
+	return ret;
+}
+
+/**
+ * kvm_arch_unset_forward - Unset forwarding for a given IRQ
+ *
+ * @kvm: handle to the VM
+ * @host_irq: physical IRQ number
+ * @guest_irq: virtual IRQ number
+ * @active: returns whether the physical IRQ is active
+ *
+ * This function must be called when the host_irq is disabled
+ * and guest has been exited and prevented from being re-entered.
+ *
+ */
+void kvm_arch_unset_forward(struct kvm *kvm,
+			    unsigned int host_irq,
+			    unsigned int guest_irq,
+			    bool *active)
+{
+	struct kvm_vcpu *vcpu = kvm_get_vcpu(kvm, 0);
+	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+	struct vgic_dist *dist = &kvm->arch.vgic;
+	int ret, lr;
+	struct vgic_lr vlr;
+	struct irq_desc *desc = irq_to_desc(host_irq);
+	struct irq_data *d;
+	unsigned long flags;
+	irq_hw_number_t gic_irq;
+	int spi_id = guest_irq + VGIC_NR_PRIVATE_IRQS;
+	struct irq_chip *chip;
+	bool queued, needs_deactivate = true;
+
+	spin_lock(&dist->lock);
+
+	irq_get_irqchip_state(host_irq, IRQCHIP_STATE_ACTIVE, active);
+
+	if (!vcpu)
+		goto out;
+
+	raw_spin_lock_irqsave(&desc->lock, flags);
+	d = irq_desc_get_irq_data(desc);
+	gic_irq = irqd_to_hwirq(d);
+	raw_spin_unlock_irqrestore(&desc->lock, flags);
+
+	ret = vgic_unmap_phys_irq(vcpu, spi_id, gic_irq);
+	/*
+	 * subsequent update_irq_pending or flush will handle this
+	 * irq as forwarded
+	 */
+
+	if (likely(!(*active))) {
+		/*
+		 * the IRQ was not active. It may happen the handle_fasteoi_irq
+		 * is entered afterwards due to lazy disable_irq. If this
+		 * happens the IRQ will be deactivated and never be injected.
+		 * let's simply prepare the states for subsequent non forwarded
+		 * injection
+		 */
+		vgic_dist_irq_clear_level(vcpu, spi_id);
+		vgic_dist_irq_clear_pending(vcpu, spi_id);
+		vgic_irq_clear_queued(vcpu, spi_id);
+		needs_deactivate = false;
+		goto out;
+	}
+
+	/* is there any list register with valid state? */
+	lr = vgic_cpu->vgic_irq_lr_map[spi_id];
+	queued = false;
+	if (lr != LR_EMPTY) {
+		vlr = vgic_get_lr(vcpu, lr);
+		if (vlr.state & LR_STATE_MASK)
+			queued = true;
+	}
+
+	if (!queued) {
+		vgic_irq_clear_queued(vcpu, spi_id);
+		if (vgic_dist_irq_is_pending(vcpu, spi_id)) {
+			/*
+			 * IRQ is injected but not yet queued. LR will be
+			 * written with EOI_INT and process_maintenance will
+			 * reset the states: queued, level(resampler). Pending
+			 * will be reset on flush.
+			 */
+			vgic_dist_irq_set_level(vcpu, spi_id);
+		} else {
+			/*
+			 * We are before the injection (update_irq_pending).
+			 * This is the most tricky window. Due to the usage of
+			 * disable_irq in generic unforward part (mandated by
+			 * resamplefd unmask VFIO integration), there is a risk
+			 * the fasteoi handler returns without calling the VFIO
+			 * handler and deactivates the physical IRQ (lazy
+			 * disable). Hence we cannot know whether the IRQ will
+			 * ever be injected. The only solution found is to do as
+			 * if the IRQ were not active. The active parameter
+			 * typically is used by the caller to know whether
+			 * it needs to mask * the IRQ. If not duly masked,
+			 * another physical IRQ may hit again while the previous
+			 * virtual IRQ is in progress. Update_irq_pending
+			 * validate_injection will prevent this injection.
+			 */
+			vgic_dist_irq_clear_level(vcpu, spi_id);
+			*active = false;
+		}
+		goto out;
+	}
+
+	/*
+	 * the virtual IRQ is queued and a valid LR exists, let's patch it for
+	 * EOI maintenance
+	 */
+	vlr.state |= LR_EOI_INT;
+	vgic_set_lr(vcpu, lr, vlr);
+	/*
+	 * we expect a maintenance IRQ which will reset the
+	 * queued, pending and level states
+	 */
+	vgic_dist_irq_set_level(vcpu, spi_id);
+	vgic_dist_irq_set_pending(vcpu, spi_id);
+	vgic_irq_set_queued(vcpu, spi_id);
+
+out:
+
+	raw_spin_lock_irqsave(&desc->lock, flags);
+	d = irq_desc_get_irq_data(desc);
+	if (needs_deactivate) {
+		chip = irq_data_get_irq_chip(d);
+		chip->irq_eoi(d);
+	}
+	irqd_clr_irq_forwarded(d);
+	/* next occurrence will be deactivated by the host */
+	raw_spin_unlock_irqrestore(&desc->lock, flags);
+
+	*active = *active && vcpu;
+
+	spin_unlock(&dist->lock);
+}
+
-- 
1.9.1

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/