RISC-V: KVM: Add timer functionality

The RISC-V hypervisor specification doesn't have any virtual timer
feature.

Due to this, the guest VCPU timer will be programmed via SBI calls.
The host will use a separate hrtimer event for each guest VCPU to
provide timer functionality. We inject a virtual timer interrupt to
the guest VCPU whenever the guest VCPU hrtimer event expires.

This patch adds guest VCPU timer implementation along with ONE_REG
interface to access VCPU timer state from user space.

Signed-off-by: Atish Patra <atish.patra@wdc.com>
Signed-off-by: Anup Patel <anup.patel@wdc.com>
Acked-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Acked-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Acked-by: Palmer Dabbelt <palmerdabbelt@google.com>

arch/riscv/include/asm/kvm_host.h

@@ -12,6 +12,7 @@
 #include <linux/types.h>
 #include <linux/kvm.h>
 #include <linux/kvm_types.h>
+#include <asm/kvm_vcpu_timer.h>
 
 #ifdef CONFIG_64BIT
 #define KVM_MAX_VCPUS			(1U << 16)
@@ -60,6 +61,9 @@ struct kvm_arch {
 	/* stage2 page table */
 	pgd_t *pgd;
 	phys_addr_t pgd_phys;
+
+	/* Guest Timer */
+	struct kvm_guest_timer timer;
 };
 
 struct kvm_mmio_decode {
@@ -175,6 +179,9 @@ struct kvm_vcpu_arch {
 	unsigned long irqs_pending;
 	unsigned long irqs_pending_mask;
 
+	/* VCPU Timer */
+	struct kvm_vcpu_timer timer;
+
 	/* MMIO instruction details */
 	struct kvm_mmio_decode mmio_decode;
 

arch/riscv/include/asm/kvm_vcpu_timer.h

@@ -0,0 +1,44 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2019 Western Digital Corporation or its affiliates.
+ *
+ * Authors:
+ *	Atish Patra <atish.patra@wdc.com>
+ */
+
+#ifndef __KVM_VCPU_RISCV_TIMER_H
+#define __KVM_VCPU_RISCV_TIMER_H
+
+#include <linux/hrtimer.h>
+
+struct kvm_guest_timer {
+	/* Mult & Shift values to get nanoseconds from cycles */
+	u32 nsec_mult;
+	u32 nsec_shift;
+	/* Time delta value */
+	u64 time_delta;
+};
+
+struct kvm_vcpu_timer {
+	/* Flag for whether init is done */
+	bool init_done;
+	/* Flag for whether timer event is configured */
+	bool next_set;
+	/* Next timer event cycles */
+	u64 next_cycles;
+	/* Underlying hrtimer instance */
+	struct hrtimer hrt;
+};
+
+int kvm_riscv_vcpu_timer_next_event(struct kvm_vcpu *vcpu, u64 ncycles);
+int kvm_riscv_vcpu_get_reg_timer(struct kvm_vcpu *vcpu,
+				 const struct kvm_one_reg *reg);
+int kvm_riscv_vcpu_set_reg_timer(struct kvm_vcpu *vcpu,
+				 const struct kvm_one_reg *reg);
+int kvm_riscv_vcpu_timer_init(struct kvm_vcpu *vcpu);
+int kvm_riscv_vcpu_timer_deinit(struct kvm_vcpu *vcpu);
+int kvm_riscv_vcpu_timer_reset(struct kvm_vcpu *vcpu);
+void kvm_riscv_vcpu_timer_restore(struct kvm_vcpu *vcpu);
+int kvm_riscv_guest_timer_init(struct kvm *kvm);
+
+#endif

arch/riscv/include/uapi/asm/kvm.h

@@ -74,6 +74,18 @@ struct kvm_riscv_csr {
 	unsigned long scounteren;
 };
 
+/* TIMER registers for KVM_GET_ONE_REG and KVM_SET_ONE_REG */
+struct kvm_riscv_timer {
+	__u64 frequency;
+	__u64 time;
+	__u64 compare;
+	__u64 state;
+};
+
+/* Possible states for kvm_riscv_timer */
+#define KVM_RISCV_TIMER_STATE_OFF	0
+#define KVM_RISCV_TIMER_STATE_ON	1
+
 #define KVM_REG_SIZE(id)		\
 	(1U << (((id) & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT))
 
@@ -96,6 +108,11 @@ struct kvm_riscv_csr {
 #define KVM_REG_RISCV_CSR_REG(name)	\
 		(offsetof(struct kvm_riscv_csr, name) / sizeof(unsigned long))
 
+/* Timer registers are mapped as type 4 */
+#define KVM_REG_RISCV_TIMER		(0x04 << KVM_REG_RISCV_TYPE_SHIFT)
+#define KVM_REG_RISCV_TIMER_REG(name)	\
+		(offsetof(struct kvm_riscv_timer, name) / sizeof(__u64))
+
 #endif
 
 #endif /* __LINUX_KVM_RISCV_H */

arch/riscv/kvm/Makefile

@@ -21,3 +21,4 @@ kvm-y += mmu.o
 kvm-y += vcpu.o
 kvm-y += vcpu_exit.o
 kvm-y += vcpu_switch.o
+kvm-y += vcpu_timer.o

arch/riscv/kvm/vcpu.c

@@ -58,6 +58,8 @@ static void kvm_riscv_reset_vcpu(struct kvm_vcpu *vcpu)
 
 	memcpy(cntx, reset_cntx, sizeof(*cntx));
 
+	kvm_riscv_vcpu_timer_reset(vcpu);
+
 	WRITE_ONCE(vcpu->arch.irqs_pending, 0);
 	WRITE_ONCE(vcpu->arch.irqs_pending_mask, 0);
 }
@@ -85,6 +87,9 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 	cntx->hstatus |= HSTATUS_SPVP;
 	cntx->hstatus |= HSTATUS_SPV;
 
+	/* Setup VCPU timer */
+	kvm_riscv_vcpu_timer_init(vcpu);
+
 	/* Reset VCPU */
 	kvm_riscv_reset_vcpu(vcpu);
 
@@ -97,6 +102,9 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
 
 void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 {
+	/* Cleanup VCPU timer */
+	kvm_riscv_vcpu_timer_deinit(vcpu);
+
 	/* Flush the pages pre-allocated for Stage2 page table mappings */
 	kvm_riscv_stage2_flush_cache(vcpu);
 }
@@ -332,6 +340,8 @@ static int kvm_riscv_vcpu_set_reg(struct kvm_vcpu *vcpu,
 		return kvm_riscv_vcpu_set_reg_core(vcpu, reg);
 	else if ((reg->id & KVM_REG_RISCV_TYPE_MASK) == KVM_REG_RISCV_CSR)
 		return kvm_riscv_vcpu_set_reg_csr(vcpu, reg);
+	else if ((reg->id & KVM_REG_RISCV_TYPE_MASK) == KVM_REG_RISCV_TIMER)
+		return kvm_riscv_vcpu_set_reg_timer(vcpu, reg);
 
 	return -EINVAL;
 }
@@ -345,6 +355,8 @@ static int kvm_riscv_vcpu_get_reg(struct kvm_vcpu *vcpu,
 		return kvm_riscv_vcpu_get_reg_core(vcpu, reg);
 	else if ((reg->id & KVM_REG_RISCV_TYPE_MASK) == KVM_REG_RISCV_CSR)
 		return kvm_riscv_vcpu_get_reg_csr(vcpu, reg);
+	else if ((reg->id & KVM_REG_RISCV_TYPE_MASK) == KVM_REG_RISCV_TIMER)
+		return kvm_riscv_vcpu_get_reg_timer(vcpu, reg);
 
 	return -EINVAL;
 }
@@ -579,6 +591,8 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 	kvm_riscv_stage2_update_hgatp(vcpu);
 
+	kvm_riscv_vcpu_timer_restore(vcpu);
+
 	vcpu->cpu = cpu;
 }
 

arch/riscv/kvm/vcpu_timer.c

@@ -0,0 +1,225 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2019 Western Digital Corporation or its affiliates.
+ *
+ * Authors:
+ *     Atish Patra <atish.patra@wdc.com>
+ */
+
+#include <linux/errno.h>
+#include <linux/err.h>
+#include <linux/kvm_host.h>
+#include <linux/uaccess.h>
+#include <clocksource/timer-riscv.h>
+#include <asm/csr.h>
+#include <asm/delay.h>
+#include <asm/kvm_vcpu_timer.h>
+
+static u64 kvm_riscv_current_cycles(struct kvm_guest_timer *gt)
+{
+	return get_cycles64() + gt->time_delta;
+}
+
+static u64 kvm_riscv_delta_cycles2ns(u64 cycles,
+				     struct kvm_guest_timer *gt,
+				     struct kvm_vcpu_timer *t)
+{
+	unsigned long flags;
+	u64 cycles_now, cycles_delta, delta_ns;
+
+	local_irq_save(flags);
+	cycles_now = kvm_riscv_current_cycles(gt);
+	if (cycles_now < cycles)
+		cycles_delta = cycles - cycles_now;
+	else
+		cycles_delta = 0;
+	delta_ns = (cycles_delta * gt->nsec_mult) >> gt->nsec_shift;
+	local_irq_restore(flags);
+
+	return delta_ns;
+}
+
+static enum hrtimer_restart kvm_riscv_vcpu_hrtimer_expired(struct hrtimer *h)
+{
+	u64 delta_ns;
+	struct kvm_vcpu_timer *t = container_of(h, struct kvm_vcpu_timer, hrt);
+	struct kvm_vcpu *vcpu = container_of(t, struct kvm_vcpu, arch.timer);
+	struct kvm_guest_timer *gt = &vcpu->kvm->arch.timer;
+
+	if (kvm_riscv_current_cycles(gt) < t->next_cycles) {
+		delta_ns = kvm_riscv_delta_cycles2ns(t->next_cycles, gt, t);
+		hrtimer_forward_now(&t->hrt, ktime_set(0, delta_ns));
+		return HRTIMER_RESTART;
+	}
+
+	t->next_set = false;
+	kvm_riscv_vcpu_set_interrupt(vcpu, IRQ_VS_TIMER);
+
+	return HRTIMER_NORESTART;
+}
+
+static int kvm_riscv_vcpu_timer_cancel(struct kvm_vcpu_timer *t)
+{
+	if (!t->init_done || !t->next_set)
+		return -EINVAL;
+
+	hrtimer_cancel(&t->hrt);
+	t->next_set = false;
+
+	return 0;
+}
+
+int kvm_riscv_vcpu_timer_next_event(struct kvm_vcpu *vcpu, u64 ncycles)
+{
+	struct kvm_vcpu_timer *t = &vcpu->arch.timer;
+	struct kvm_guest_timer *gt = &vcpu->kvm->arch.timer;
+	u64 delta_ns;
+
+	if (!t->init_done)
+		return -EINVAL;
+
+	kvm_riscv_vcpu_unset_interrupt(vcpu, IRQ_VS_TIMER);
+
+	delta_ns = kvm_riscv_delta_cycles2ns(ncycles, gt, t);
+	t->next_cycles = ncycles;
+	hrtimer_start(&t->hrt, ktime_set(0, delta_ns), HRTIMER_MODE_REL);
+	t->next_set = true;
+
+	return 0;
+}
+
+int kvm_riscv_vcpu_get_reg_timer(struct kvm_vcpu *vcpu,
+				 const struct kvm_one_reg *reg)
+{
+	struct kvm_vcpu_timer *t = &vcpu->arch.timer;
+	struct kvm_guest_timer *gt = &vcpu->kvm->arch.timer;
+	u64 __user *uaddr = (u64 __user *)(unsigned long)reg->addr;
+	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
+					    KVM_REG_SIZE_MASK |
+					    KVM_REG_RISCV_TIMER);
+	u64 reg_val;
+
+	if (KVM_REG_SIZE(reg->id) != sizeof(u64))
+		return -EINVAL;
+	if (reg_num >= sizeof(struct kvm_riscv_timer) / sizeof(u64))
+		return -EINVAL;
+
+	switch (reg_num) {
+	case KVM_REG_RISCV_TIMER_REG(frequency):
+		reg_val = riscv_timebase;
+		break;
+	case KVM_REG_RISCV_TIMER_REG(time):
+		reg_val = kvm_riscv_current_cycles(gt);
+		break;
+	case KVM_REG_RISCV_TIMER_REG(compare):
+		reg_val = t->next_cycles;
+		break;
+	case KVM_REG_RISCV_TIMER_REG(state):
+		reg_val = (t->next_set) ? KVM_RISCV_TIMER_STATE_ON :
+					  KVM_RISCV_TIMER_STATE_OFF;
+		break;
+	default:
+		return -EINVAL;
+	};
+
+	if (copy_to_user(uaddr, &reg_val, KVM_REG_SIZE(reg->id)))
+		return -EFAULT;
+
+	return 0;
+}
+
+int kvm_riscv_vcpu_set_reg_timer(struct kvm_vcpu *vcpu,
+				 const struct kvm_one_reg *reg)
+{
+	struct kvm_vcpu_timer *t = &vcpu->arch.timer;
+	struct kvm_guest_timer *gt = &vcpu->kvm->arch.timer;
+	u64 __user *uaddr = (u64 __user *)(unsigned long)reg->addr;
+	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
+					    KVM_REG_SIZE_MASK |
+					    KVM_REG_RISCV_TIMER);
+	u64 reg_val;
+	int ret = 0;
+
+	if (KVM_REG_SIZE(reg->id) != sizeof(u64))
+		return -EINVAL;
+	if (reg_num >= sizeof(struct kvm_riscv_timer) / sizeof(u64))
+		return -EINVAL;
+
+	if (copy_from_user(&reg_val, uaddr, KVM_REG_SIZE(reg->id)))
+		return -EFAULT;
+
+	switch (reg_num) {
+	case KVM_REG_RISCV_TIMER_REG(frequency):
+		ret = -EOPNOTSUPP;
+		break;
+	case KVM_REG_RISCV_TIMER_REG(time):
+		gt->time_delta = reg_val - get_cycles64();
+		break;
+	case KVM_REG_RISCV_TIMER_REG(compare):
+		t->next_cycles = reg_val;
+		break;
+	case KVM_REG_RISCV_TIMER_REG(state):
+		if (reg_val == KVM_RISCV_TIMER_STATE_ON)
+			ret = kvm_riscv_vcpu_timer_next_event(vcpu, reg_val);
+		else
+			ret = kvm_riscv_vcpu_timer_cancel(t);
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	};
+
+	return ret;
+}
+
+int kvm_riscv_vcpu_timer_init(struct kvm_vcpu *vcpu)
+{
+	struct kvm_vcpu_timer *t = &vcpu->arch.timer;
+
+	if (t->init_done)
+		return -EINVAL;
+
+	hrtimer_init(&t->hrt, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	t->hrt.function = kvm_riscv_vcpu_hrtimer_expired;
+	t->init_done = true;
+	t->next_set = false;
+
+	return 0;
+}
+
+int kvm_riscv_vcpu_timer_deinit(struct kvm_vcpu *vcpu)
+{
+	int ret;
+
+	ret = kvm_riscv_vcpu_timer_cancel(&vcpu->arch.timer);
+	vcpu->arch.timer.init_done = false;
+
+	return ret;
+}
+
+int kvm_riscv_vcpu_timer_reset(struct kvm_vcpu *vcpu)
+{
+	return kvm_riscv_vcpu_timer_cancel(&vcpu->arch.timer);
+}
+
+void kvm_riscv_vcpu_timer_restore(struct kvm_vcpu *vcpu)
+{
+	struct kvm_guest_timer *gt = &vcpu->kvm->arch.timer;
+
+#ifdef CONFIG_64BIT
+	csr_write(CSR_HTIMEDELTA, gt->time_delta);
+#else
+	csr_write(CSR_HTIMEDELTA, (u32)(gt->time_delta));
+	csr_write(CSR_HTIMEDELTAH, (u32)(gt->time_delta >> 32));
+#endif
+}
+
+int kvm_riscv_guest_timer_init(struct kvm *kvm)
+{
+	struct kvm_guest_timer *gt = &kvm->arch.timer;
+
+	riscv_cs_get_mult_shift(&gt->nsec_mult, &gt->nsec_shift);
+	gt->time_delta = -get_cycles64();
+
+	return 0;
+}

arch/riscv/kvm/vm.c

@@ -41,7 +41,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 		return r;
 	}
 
-	return 0;
+	return kvm_riscv_guest_timer_init(kvm);
 }
 
 void kvm_arch_destroy_vm(struct kvm *kvm)

drivers/clocksource/timer-riscv.c

@@ -13,10 +13,12 @@
 #include <linux/delay.h>
 #include <linux/irq.h>
 #include <linux/irqdomain.h>
+#include <linux/module.h>
 #include <linux/sched_clock.h>
 #include <linux/io-64-nonatomic-lo-hi.h>
 #include <linux/interrupt.h>
 #include <linux/of_irq.h>
+#include <clocksource/timer-riscv.h>
 #include <asm/smp.h>
 #include <asm/sbi.h>
 #include <asm/timex.h>
@@ -79,6 +81,13 @@ static int riscv_timer_dying_cpu(unsigned int cpu)
 	return 0;
 }
 
+void riscv_cs_get_mult_shift(u32 *mult, u32 *shift)
+{
+	*mult = riscv_clocksource.mult;
+	*shift = riscv_clocksource.shift;
+}
+EXPORT_SYMBOL_GPL(riscv_cs_get_mult_shift);
+
 /* called directly from the low-level interrupt handler */
 static irqreturn_t riscv_timer_interrupt(int irq, void *dev_id)
 {

include/clocksource/timer-riscv.h

@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2019 Western Digital Corporation or its affiliates.
+ *
+ * Authors:
+ *	Atish Patra <atish.patra@wdc.com>
+ */
+
+#ifndef __TIMER_RISCV_H
+#define __TIMER_RISCV_H
+
+#include <linux/types.h>
+
+extern void riscv_cs_get_mult_shift(u32 *mult, u32 *shift);
+
+#endif