[RFC PATCH 05/16] RISC-V: KVM: Implement VCPU interrupts and requests handling

[Anup Patel <Anup.Patel@wdc.com>]

This patch implements VCPU interrupts and requests which are both
asynchronous events.

The VCPU interrupts can be set/unset using KVM_INTERRUPT ioctl from
user-space. In future, the in-kernel IRQCHIP emulation will use
kvm_riscv_vcpu_set_interrupt() and kvm_riscv_vcpu_unset_interrupt()
functions to set/unset VCPU interrupts.

Important VCPU requests implemented by this patch are:
KVM_REQ_IRQ_PENDING - set whenever some VCPU interrupt pending
KVM_REQ_SLEEP       - set whenever VCPU itself goes to sleep state
KVM_REQ_VCPU_RESET  - set whenever VCPU reset is requested

The WFI trap-n-emulate (added later) will use KVM_REQ_SLEEP request
and kvm_riscv_vcpu_has_interrupt() function.

The KVM_REQ_VCPU_RESET request will be used by SBI emulation (added
later) to power-up a VCPU in power-off state. The user-space can use
the GET_MPSTATE/SET_MPSTATE ioctls to get/set power state of a VCPU.

Signed-off-by: Anup Patel <anup.patel@wdc.com>
---
 arch/riscv/include/asm/kvm_host.h |  13 +++
 arch/riscv/include/uapi/asm/kvm.h |   3 +
 arch/riscv/kvm/vcpu.c             | 174 +++++++++++++++++++++++++++---
 3 files changed, 177 insertions(+), 13 deletions(-)

diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h
index 244eabe62710..aa89f1922da1 100644
--- a/arch/riscv/include/asm/kvm_host.h
+++ b/arch/riscv/include/asm/kvm_host.h
@@ -125,6 +125,13 @@ struct kvm_vcpu_arch {
 	/* CPU CSR context upon Guest VCPU reset */
 	struct kvm_vcpu_csr guest_reset_csr;
 
+	/* VCPU interrupts */
+	raw_spinlock_t irqs_lock;
+	unsigned long irqs_pending;
+
+	/* VCPU power-off state */
+	bool power_off;
+
 	/* Don't run the VCPU (blocked) */
 	bool pause;
 };
@@ -146,6 +153,12 @@ int kvm_riscv_vcpu_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
 
 static inline void __kvm_riscv_switch_to(struct kvm_vcpu_arch *vcpu_arch) {}
 
+int kvm_riscv_vcpu_set_interrupt(struct kvm_vcpu *vcpu, unsigned int irq);
+int kvm_riscv_vcpu_unset_interrupt(struct kvm_vcpu *vcpu, unsigned int irq);
+bool kvm_riscv_vcpu_has_interrupt(struct kvm_vcpu *vcpu);
+void kvm_riscv_vcpu_power_off(struct kvm_vcpu *vcpu);
+void kvm_riscv_vcpu_power_on(struct kvm_vcpu *vcpu);
+
 void kvm_riscv_halt_guest(struct kvm *kvm);
 void kvm_riscv_resume_guest(struct kvm *kvm);
 
diff --git a/arch/riscv/include/uapi/asm/kvm.h b/arch/riscv/include/uapi/asm/kvm.h
index d15875818b6e..6dbc056d58ba 100644
--- a/arch/riscv/include/uapi/asm/kvm.h
+++ b/arch/riscv/include/uapi/asm/kvm.h
@@ -18,6 +18,9 @@
 
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1
 
+#define KVM_INTERRUPT_SET	-1U
+#define KVM_INTERRUPT_UNSET	-2U
+
 /* for KVM_GET_REGS and KVM_SET_REGS */
 struct kvm_regs {
 };
diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c
index 1ae806f28c0e..c6f57caa95f0 100644
--- a/arch/riscv/kvm/vcpu.c
+++ b/arch/riscv/kvm/vcpu.c
@@ -42,6 +42,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 
 static void kvm_riscv_reset_vcpu(struct kvm_vcpu *vcpu)
 {
+	unsigned long f;
 	struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr;
 	struct kvm_vcpu_csr *reset_csr = &vcpu->arch.guest_reset_csr;
 	struct kvm_cpu_context *cntx = &vcpu->arch.guest_context;
@@ -50,6 +51,10 @@ static void kvm_riscv_reset_vcpu(struct kvm_vcpu *vcpu)
 	memcpy(csr, reset_csr, sizeof(*csr));
 
 	memcpy(cntx, reset_cntx, sizeof(*cntx));
+
+	raw_spin_lock_irqsave(&vcpu->arch.irqs_lock, f);
+	vcpu->arch.irqs_pending = 0;
+	raw_spin_unlock_irqrestore(&vcpu->arch.irqs_lock, f);
 }
 
 struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id)
@@ -103,6 +108,9 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 	cntx->hstatus |= HSTATUS_SP2P;
 	cntx->hstatus |= HSTATUS_SPV;
 
+	/* Setup VCPU irqs lock */
+	raw_spin_lock_init(&vcpu->arch.irqs_lock);
+
 	/* Setup reset state of HEDELEG and HIDELEG CSRs */
 	csr = &vcpu->arch.guest_reset_csr;
 	csr->hedeleg = 0;
@@ -131,8 +139,15 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 
 int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
 {
-	/* TODO: */
-	return 0;
+	int ret;
+	unsigned long f, irqs;
+
+	raw_spin_lock_irqsave(&vcpu->arch.irqs_lock, f);
+	irqs = vcpu->arch.irqs_pending & vcpu->arch.guest_csr.vsie;
+	ret = (irqs & (1UL << IRQ_S_TIMER)) ? 1 : 0;
+	raw_spin_unlock_irqrestore(&vcpu->arch.irqs_lock, f);
+
+	return ret;
 }
 
 void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu)
@@ -145,20 +160,18 @@ void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu)
 
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
 {
-	/* TODO: */
-	return 0;
+	return (kvm_riscv_vcpu_has_interrupt(vcpu) &&
+		!vcpu->arch.power_off && !vcpu->arch.pause);
 }
 
 int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
 {
-	/* TODO: */
-	return 0;
+	return kvm_vcpu_exiting_guest_mode(vcpu) == IN_GUEST_MODE;
 }
 
 bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu)
 {
-	/* TODO: */
-	return false;
+	return (vcpu->arch.guest_context.sstatus & SR_SPP) ? true : false;
 }
 
 bool kvm_arch_has_vcpu_debugfs(void)
@@ -179,7 +192,21 @@ vm_fault_t kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
 long kvm_arch_vcpu_async_ioctl(struct file *filp,
 			       unsigned int ioctl, unsigned long arg)
 {
-	/* TODO; */
+	struct kvm_vcpu *vcpu = filp->private_data;
+	void __user *argp = (void __user *)arg;
+
+	if (ioctl == KVM_INTERRUPT) {
+		struct kvm_interrupt irq;
+
+		if (copy_from_user(&irq, argp, sizeof(irq)))
+			return -EFAULT;
+
+		if (irq.irq == KVM_INTERRUPT_SET)
+			return kvm_riscv_vcpu_set_interrupt(vcpu, IRQ_S_EXT);
+		else
+			return kvm_riscv_vcpu_unset_interrupt(vcpu, IRQ_S_EXT);
+	}
+
 	return -ENOIOCTLCMD;
 }
 
@@ -228,18 +255,113 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 	return -EINVAL;
 }
 
+static void kvm_riscv_vcpu_flush_interrupts(struct kvm_vcpu *vcpu)
+{
+	unsigned long f;
+
+	raw_spin_lock_irqsave(&vcpu->arch.irqs_lock, f);
+	if (vcpu->arch.irqs_pending ^ vcpu->arch.guest_csr.vsip) {
+		csr_write(CSR_VSIP, vcpu->arch.irqs_pending);
+		vcpu->arch.guest_csr.vsip = vcpu->arch.irqs_pending;
+	}
+	raw_spin_unlock_irqrestore(&vcpu->arch.irqs_lock, f);
+}
+
+static void kvm_riscv_vcpu_sync_interrupts(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.guest_csr.vsip = csr_read(CSR_VSIP);
+	vcpu->arch.guest_csr.vsie = csr_read(CSR_VSIE);
+}
+
+int kvm_riscv_vcpu_set_interrupt(struct kvm_vcpu *vcpu, unsigned int irq)
+{
+	unsigned long f;
+
+	if (irq != IRQ_S_SOFT &&
+	    irq != IRQ_S_TIMER &&
+	    irq != IRQ_S_EXT)
+		return -EINVAL;
+
+	raw_spin_lock_irqsave(&vcpu->arch.irqs_lock, f);
+	vcpu->arch.irqs_pending |= (1UL << irq);
+	raw_spin_unlock_irqrestore(&vcpu->arch.irqs_lock, f);
+
+	kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu);
+	kvm_vcpu_kick(vcpu);
+
+	return 0;
+}
+
+int kvm_riscv_vcpu_unset_interrupt(struct kvm_vcpu *vcpu, unsigned int irq)
+{
+	unsigned long f;
+
+	if (irq != IRQ_S_SOFT &&
+	    irq != IRQ_S_TIMER &&
+	    irq != IRQ_S_EXT)
+		return -EINVAL;
+
+	raw_spin_lock_irqsave(&vcpu->arch.irqs_lock, f);
+	vcpu->arch.irqs_pending &= ~(1UL << irq);
+	raw_spin_unlock_irqrestore(&vcpu->arch.irqs_lock, f);
+
+	return 0;
+}
+
+bool kvm_riscv_vcpu_has_interrupt(struct kvm_vcpu *vcpu)
+{
+	bool ret = false;
+	unsigned long f;
+
+	raw_spin_lock_irqsave(&vcpu->arch.irqs_lock, f);
+	if (vcpu->arch.irqs_pending & vcpu->arch.guest_csr.vsie)
+		ret = true;
+	raw_spin_unlock_irqrestore(&vcpu->arch.irqs_lock, f);
+
+	return ret;
+}
+
+void kvm_riscv_vcpu_power_off(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.power_off = true;
+	kvm_make_request(KVM_REQ_SLEEP, vcpu);
+	kvm_vcpu_kick(vcpu);
+}
+
+void kvm_riscv_vcpu_power_on(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.power_off = false;
+	kvm_vcpu_wake_up(vcpu);
+}
+
 int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
 				    struct kvm_mp_state *mp_state)
 {
-	/* TODO: */
+	if (vcpu->arch.power_off)
+		mp_state->mp_state = KVM_MP_STATE_STOPPED;
+	else
+		mp_state->mp_state = KVM_MP_STATE_RUNNABLE;
+
 	return 0;
 }
 
 int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
 				    struct kvm_mp_state *mp_state)
 {
-	/* TODO: */
-	return 0;
+	int ret = 0;
+
+	switch (mp_state->mp_state) {
+	case KVM_MP_STATE_RUNNABLE:
+		vcpu->arch.power_off = false;
+		break;
+	case KVM_MP_STATE_STOPPED:
+		kvm_riscv_vcpu_power_off(vcpu);
+		break;
+	default:
+		ret = -EINVAL;
+	}
+
+	return ret;
 }
 
 int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
@@ -263,8 +385,25 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 
 static void kvm_riscv_check_vcpu_requests(struct kvm_vcpu *vcpu)
 {
+	struct swait_queue_head *wq = kvm_arch_vcpu_wq(vcpu);
+
 	if (kvm_request_pending(vcpu)) {
-		/* TODO: */
+		if (kvm_check_request(KVM_REQ_SLEEP, vcpu)) {
+			swait_event_interruptible_exclusive(*wq,
+						((!vcpu->arch.power_off) &&
+						(!vcpu->arch.pause)));
+
+			if (vcpu->arch.power_off || vcpu->arch.pause) {
+				/*
+				 * Awaken to handle a signal, request to
+				 * sleep again later.
+				 */
+				kvm_make_request(KVM_REQ_SLEEP, vcpu);
+			}
+		}
+
+		if (kvm_check_request(KVM_REQ_VCPU_RESET, vcpu))
+			kvm_riscv_reset_vcpu(vcpu);
 
 		/*
 		 * Clear IRQ_PENDING requests that were made to guarantee
@@ -317,6 +456,12 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 			run->exit_reason = KVM_EXIT_INTR;
 		}
 
+		/*
+		 * We might have got VCPU interrupts updated asynchronously
+		 * so update it in HW.
+		 */
+		kvm_riscv_vcpu_flush_interrupts(vcpu);
+
 		/*
 		 * Ensure we set mode to IN_GUEST_MODE after we disable
 		 * interrupts and before the final VCPU requests check.
@@ -347,6 +492,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		scause = csr_read(CSR_SCAUSE);
 		stval = csr_read(CSR_STVAL);
 
+		/* Syncup interrupts state with HW */
+		kvm_riscv_vcpu_sync_interrupts(vcpu);
+
 		/*
 		 * We may have taken a host interrupt in VS/VU-mode (i.e.
 		 * while executing the guest). This interrupt is still
-- 
2.17.1