RISC-V: KVM: Implement VCPU interrupts and requests handling

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_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>
Acked-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Alexander Graf <graf@amazon.com>
Acked-by: Palmer Dabbelt <palmerdabbelt@google.com>

arch/riscv/include/asm/kvm_host.h

@@ -127,6 +127,21 @@ struct kvm_vcpu_arch {
 	/* CPU CSR context upon Guest VCPU reset */
 	struct kvm_vcpu_csr guest_reset_csr;
 
+	/*
+	 * VCPU interrupts
+	 *
+	 * We have a lockless approach for tracking pending VCPU interrupts
+	 * implemented using atomic bitops. The irqs_pending bitmap represent
+	 * pending interrupts whereas irqs_pending_mask represent bits changed
+	 * in irqs_pending. Our approach is modeled around multiple producer
+	 * and single consumer problem where the consumer is the VCPU itself.
+	 */
+	unsigned long irqs_pending;
+	unsigned long irqs_pending_mask;
+
+	/* VCPU power-off state */
+	bool power_off;
+
 	/* Don't run the VCPU (blocked) */
 	bool pause;
 
@@ -150,4 +165,12 @@ 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);
+void kvm_riscv_vcpu_flush_interrupts(struct kvm_vcpu *vcpu);
+void kvm_riscv_vcpu_sync_interrupts(struct kvm_vcpu *vcpu);
+bool kvm_riscv_vcpu_has_interrupts(struct kvm_vcpu *vcpu, unsigned long mask);
+void kvm_riscv_vcpu_power_off(struct kvm_vcpu *vcpu);
+void kvm_riscv_vcpu_power_on(struct kvm_vcpu *vcpu);
+
 #endif /* __RISCV_KVM_HOST_H__ */

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 {
 };

arch/riscv/kvm/vcpu.c

@@ -11,6 +11,7 @@
 #include <linux/err.h>
 #include <linux/kdebug.h>
 #include <linux/module.h>
+#include <linux/percpu.h>
 #include <linux/uaccess.h>
 #include <linux/vmalloc.h>
 #include <linux/sched/signal.h>
@@ -57,6 +58,9 @@ static void kvm_riscv_reset_vcpu(struct kvm_vcpu *vcpu)
 	memcpy(csr, reset_csr, sizeof(*csr));
 
 	memcpy(cntx, reset_cntx, sizeof(*cntx));
+
+	WRITE_ONCE(vcpu->arch.irqs_pending, 0);
+	WRITE_ONCE(vcpu->arch.irqs_pending_mask, 0);
 }
 
 int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id)
@@ -100,8 +104,7 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 
 int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
 {
-	/* TODO: */
-	return 0;
+	return kvm_riscv_vcpu_has_interrupts(vcpu, 1UL << IRQ_VS_TIMER);
 }
 
 void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu)
@@ -114,20 +117,18 @@ 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_interrupts(vcpu, -1UL) &&
+		!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;
 }
 
 vm_fault_t kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
@@ -138,7 +139,21 @@ 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_VS_EXT);
+		else
+			return kvm_riscv_vcpu_unset_interrupt(vcpu, IRQ_VS_EXT);
+	}
+
 	return -ENOIOCTLCMD;
 }
 
@@ -187,18 +202,123 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 	return -EINVAL;
 }
 
+void kvm_riscv_vcpu_flush_interrupts(struct kvm_vcpu *vcpu)
+{
+	struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr;
+	unsigned long mask, val;
+
+	if (READ_ONCE(vcpu->arch.irqs_pending_mask)) {
+		mask = xchg_acquire(&vcpu->arch.irqs_pending_mask, 0);
+		val = READ_ONCE(vcpu->arch.irqs_pending) & mask;
+
+		csr->hvip &= ~mask;
+		csr->hvip |= val;
+	}
+}
+
+void kvm_riscv_vcpu_sync_interrupts(struct kvm_vcpu *vcpu)
+{
+	unsigned long hvip;
+	struct kvm_vcpu_arch *v = &vcpu->arch;
+	struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr;
+
+	/* Read current HVIP and VSIE CSRs */
+	csr->vsie = csr_read(CSR_VSIE);
+
+	/* Sync-up HVIP.VSSIP bit changes does by Guest */
+	hvip = csr_read(CSR_HVIP);
+	if ((csr->hvip ^ hvip) & (1UL << IRQ_VS_SOFT)) {
+		if (hvip & (1UL << IRQ_VS_SOFT)) {
+			if (!test_and_set_bit(IRQ_VS_SOFT,
+					      &v->irqs_pending_mask))
+				set_bit(IRQ_VS_SOFT, &v->irqs_pending);
+		} else {
+			if (!test_and_set_bit(IRQ_VS_SOFT,
+					      &v->irqs_pending_mask))
+				clear_bit(IRQ_VS_SOFT, &v->irqs_pending);
+		}
+	}
+}
+
+int kvm_riscv_vcpu_set_interrupt(struct kvm_vcpu *vcpu, unsigned int irq)
+{
+	if (irq != IRQ_VS_SOFT &&
+	    irq != IRQ_VS_TIMER &&
+	    irq != IRQ_VS_EXT)
+		return -EINVAL;
+
+	set_bit(irq, &vcpu->arch.irqs_pending);
+	smp_mb__before_atomic();
+	set_bit(irq, &vcpu->arch.irqs_pending_mask);
+
+	kvm_vcpu_kick(vcpu);
+
+	return 0;
+}
+
+int kvm_riscv_vcpu_unset_interrupt(struct kvm_vcpu *vcpu, unsigned int irq)
+{
+	if (irq != IRQ_VS_SOFT &&
+	    irq != IRQ_VS_TIMER &&
+	    irq != IRQ_VS_EXT)
+		return -EINVAL;
+
+	clear_bit(irq, &vcpu->arch.irqs_pending);
+	smp_mb__before_atomic();
+	set_bit(irq, &vcpu->arch.irqs_pending_mask);
+
+	return 0;
+}
+
+bool kvm_riscv_vcpu_has_interrupts(struct kvm_vcpu *vcpu, unsigned long mask)
+{
+	unsigned long ie = ((vcpu->arch.guest_csr.vsie & VSIP_VALID_MASK)
+			    << VSIP_TO_HVIP_SHIFT) & mask;
+
+	return (READ_ONCE(vcpu->arch.irqs_pending) & ie) ? true : false;
+}
+
+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,
@@ -222,7 +342,33 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 
 static void kvm_riscv_check_vcpu_requests(struct kvm_vcpu *vcpu)
 {
-	/* TODO: */
+	struct rcuwait *wait = kvm_arch_vcpu_get_wait(vcpu);
+
+	if (kvm_request_pending(vcpu)) {
+		if (kvm_check_request(KVM_REQ_SLEEP, vcpu)) {
+			rcuwait_wait_event(wait,
+				(!vcpu->arch.power_off) && (!vcpu->arch.pause),
+				TASK_INTERRUPTIBLE);
+
+			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);
+	}
+}
+
+static void kvm_riscv_update_hvip(struct kvm_vcpu *vcpu)
+{
+	struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr;
+
+	csr_write(CSR_HVIP, csr->hvip);
 }
 
 int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
@@ -286,6 +432,15 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		srcu_read_unlock(&vcpu->kvm->srcu, vcpu->arch.srcu_idx);
 		smp_mb__after_srcu_read_unlock();
 
+		/*
+		 * We might have got VCPU interrupts updated asynchronously
+		 * so update it in HW.
+		 */
+		kvm_riscv_vcpu_flush_interrupts(vcpu);
+
+		/* Update HVIP CSR for current CPU */
+		kvm_riscv_update_hvip(vcpu);
+
 		if (ret <= 0 ||
 		    kvm_request_pending(vcpu)) {
 			vcpu->mode = OUTSIDE_GUEST_MODE;
@@ -313,6 +468,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		trap.htval = csr_read(CSR_HTVAL);
 		trap.htinst = csr_read(CSR_HTINST);
 
+		/* 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