[PATCH v6 07/21] RISC-V: KVM: Implement VCPU interrupts and requests handling

From: Anup Patel
Date: Thu Aug 29 2019 - 09:56:08 EST


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@xxxxxxx>
Acked-by: Paolo Bonzini <pbonzini@xxxxxxxxxx>
Reviewed-by: Paolo Bonzini <pbonzini@xxxxxxxxxx>
Reviewed-by: Alexander Graf <graf@xxxxxxxxxx>
---
arch/riscv/include/asm/kvm_host.h | 26 ++++
arch/riscv/include/uapi/asm/kvm.h | 3 +
arch/riscv/kvm/main.c | 8 ++
arch/riscv/kvm/vcpu.c | 193 ++++++++++++++++++++++++++++--
4 files changed, 217 insertions(+), 13 deletions(-)

diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h
index dab32c9c3470..d801216da6d0 100644
--- a/arch/riscv/include/asm/kvm_host.h
+++ b/arch/riscv/include/asm/kvm_host.h
@@ -122,6 +122,21 @@ 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;

@@ -135,6 +150,9 @@ static inline void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) {}
static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {}

+int kvm_riscv_setup_vsip(void);
+void kvm_riscv_cleanup_vsip(void);
+
void kvm_riscv_stage2_flush_cache(struct kvm_vcpu *vcpu);
int kvm_riscv_stage2_alloc_pgd(struct kvm *kvm);
void kvm_riscv_stage2_free_pgd(struct kvm *kvm);
@@ -146,4 +164,12 @@ 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_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);
+
#endif /* __RISCV_KVM_HOST_H__ */
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/main.c b/arch/riscv/kvm/main.c
index e1ffe6d42f39..d088247843c5 100644
--- a/arch/riscv/kvm/main.c
+++ b/arch/riscv/kvm/main.c
@@ -48,6 +48,8 @@ int kvm_arch_hardware_enable(void)
hideleg |= SIE_SEIE;
csr_write(CSR_HIDELEG, hideleg);

+ csr_write(CSR_VSIP, 0);
+
return 0;
}

@@ -59,11 +61,17 @@ void kvm_arch_hardware_disable(void)

int kvm_arch_init(void *opaque)
{
+ int ret;
+
if (!riscv_isa_extension_available(NULL, h)) {
kvm_info("hypervisor extension not available\n");
return -ENODEV;
}

+ ret = kvm_riscv_setup_vsip();
+ if (ret)
+ return ret;
+
kvm_info("hypervisor extension available\n");

return 0;
diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c
index 8272b05d6ce4..3223f723f79e 100644
--- a/arch/riscv/kvm/vcpu.c
+++ b/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>
@@ -40,6 +41,8 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
riscv_isa_extension_mask(s) | \
riscv_isa_extension_mask(u))

+static unsigned long __percpu *vsip_shadow;
+
static void kvm_riscv_reset_vcpu(struct kvm_vcpu *vcpu)
{
struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr;
@@ -50,6 +53,9 @@ 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);
}

struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id)
@@ -116,8 +122,8 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)

int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
{
- /* TODO: */
- return 0;
+ return READ_ONCE(vcpu->arch.irqs_pending) &
+ vcpu->arch.guest_csr.vsie & (1UL << IRQ_S_TIMER);
}

void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu)
@@ -130,20 +136,18 @@ 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)
@@ -164,7 +168,21 @@ 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;
}

@@ -213,18 +231,111 @@ 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->vsip &= ~mask;
+ csr->vsip |= val;
+ }
+}
+
+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);
+
+ /* Guest can directly update VSIP software interrupt bits */
+ if (vcpu->arch.guest_csr.vsip ^ READ_ONCE(vcpu->arch.irqs_pending)) {
+ if (vcpu->arch.guest_csr.vsip & (1UL << IRQ_S_SOFT))
+ kvm_riscv_vcpu_set_interrupt(vcpu, IRQ_S_SOFT);
+ else
+ kvm_riscv_vcpu_unset_interrupt(vcpu, IRQ_S_SOFT);
+ }
+}
+
+int kvm_riscv_vcpu_set_interrupt(struct kvm_vcpu *vcpu, unsigned int irq)
+{
+ if (irq != IRQ_S_SOFT &&
+ irq != IRQ_S_TIMER &&
+ irq != IRQ_S_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_S_SOFT &&
+ irq != IRQ_S_TIMER &&
+ irq != IRQ_S_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_interrupt(struct kvm_vcpu *vcpu)
+{
+ return (READ_ONCE(vcpu->arch.irqs_pending) &
+ vcpu->arch.guest_csr.vsie) ? 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,
@@ -248,7 +359,51 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)

static void kvm_riscv_check_vcpu_requests(struct kvm_vcpu *vcpu)
{
- /* TODO: */
+ struct swait_queue_head *wq = kvm_arch_vcpu_wq(vcpu);
+
+ if (kvm_request_pending(vcpu)) {
+ 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);
+ }
+}
+
+static void kvm_riscv_update_vsip(struct kvm_vcpu *vcpu)
+{
+ struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr;
+ unsigned long *vsip = raw_cpu_ptr(vsip_shadow);
+
+ if (*vsip != csr->vsip) {
+ csr_write(CSR_VSIP, csr->vsip);
+ *vsip = csr->vsip;
+ }
+}
+
+int kvm_riscv_setup_vsip(void)
+{
+ vsip_shadow = alloc_percpu(unsigned long);
+ if (!vsip_shadow)
+ return -ENOMEM;
+
+ return 0;
+}
+
+void kvm_riscv_cleanup_vsip(void)
+{
+ free_percpu(vsip_shadow);
}

int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
@@ -311,6 +466,15 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
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 VSIP CSR for current CPU */
+ kvm_riscv_update_vsip(vcpu);
+
if (ret <= 0 ||
kvm_request_pending(vcpu)) {
vcpu->mode = OUTSIDE_GUEST_MODE;
@@ -334,6 +498,9 @@ 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