Commit 99cdc6c1 authored by Anup Patel's avatar Anup Patel Committed by Anup Patel

RISC-V: Add initial skeletal KVM support

This patch adds initial skeletal KVM RISC-V support which has:
1. A simple implementation of arch specific VM functions
   except kvm_vm_ioctl_get_dirty_log() which will implemeted
   in-future as part of stage2 page loging.
2. Stubs of required arch specific VCPU functions except
   kvm_arch_vcpu_ioctl_run() which is semi-complete and
   extended by subsequent patches.
3. Stubs for required arch specific stage2 MMU functions.
Signed-off-by: default avatarAnup Patel <anup.patel@wdc.com>
Acked-by: default avatarPaolo Bonzini <pbonzini@redhat.com>
Reviewed-by: default avatarPaolo Bonzini <pbonzini@redhat.com>
Reviewed-by: default avatarAlexander Graf <graf@amazon.com>
Acked-by: default avatarPalmer Dabbelt <palmerdabbelt@google.com>
parent 3f2401f4
......@@ -562,4 +562,5 @@ source "kernel/power/Kconfig"
endmenu
source "arch/riscv/kvm/Kconfig"
source "drivers/firmware/Kconfig"
......@@ -100,6 +100,7 @@ endif
head-y := arch/riscv/kernel/head.o
core-$(CONFIG_RISCV_ERRATA_ALTERNATIVE) += arch/riscv/errata/
core-$(CONFIG_KVM) += arch/riscv/kvm/
libs-y += arch/riscv/lib/
libs-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a
......
/* SPDX-License-Identifier: GPL-2.0-only */
/*
* Copyright (C) 2019 Western Digital Corporation or its affiliates.
*
* Authors:
* Anup Patel <anup.patel@wdc.com>
*/
#ifndef __RISCV_KVM_HOST_H__
#define __RISCV_KVM_HOST_H__
#include <linux/types.h>
#include <linux/kvm.h>
#include <linux/kvm_types.h>
#ifdef CONFIG_64BIT
#define KVM_MAX_VCPUS (1U << 16)
#else
#define KVM_MAX_VCPUS (1U << 9)
#endif
#define KVM_HALT_POLL_NS_DEFAULT 500000
#define KVM_VCPU_MAX_FEATURES 0
#define KVM_REQ_SLEEP \
KVM_ARCH_REQ_FLAGS(0, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
#define KVM_REQ_VCPU_RESET KVM_ARCH_REQ(1)
struct kvm_vm_stat {
struct kvm_vm_stat_generic generic;
};
struct kvm_vcpu_stat {
struct kvm_vcpu_stat_generic generic;
u64 ecall_exit_stat;
u64 wfi_exit_stat;
u64 mmio_exit_user;
u64 mmio_exit_kernel;
u64 exits;
};
struct kvm_arch_memory_slot {
};
struct kvm_arch {
/* stage2 page table */
pgd_t *pgd;
phys_addr_t pgd_phys;
};
struct kvm_cpu_trap {
unsigned long sepc;
unsigned long scause;
unsigned long stval;
unsigned long htval;
unsigned long htinst;
};
struct kvm_vcpu_arch {
/* Don't run the VCPU (blocked) */
bool pause;
/* SRCU lock index for in-kernel run loop */
int srcu_idx;
};
static inline void kvm_arch_hardware_unsetup(void) {}
static inline void kvm_arch_sync_events(struct kvm *kvm) {}
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) {}
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);
void kvm_riscv_stage2_update_hgatp(struct kvm_vcpu *vcpu);
int kvm_riscv_vcpu_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run);
int kvm_riscv_vcpu_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
struct kvm_cpu_trap *trap);
static inline void __kvm_riscv_switch_to(struct kvm_vcpu_arch *vcpu_arch) {}
#endif /* __RISCV_KVM_HOST_H__ */
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _ASM_RISCV_KVM_TYPES_H
#define _ASM_RISCV_KVM_TYPES_H
#define KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE 40
#endif /* _ASM_RISCV_KVM_TYPES_H */
/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
/*
* Copyright (C) 2019 Western Digital Corporation or its affiliates.
*
* Authors:
* Anup Patel <anup.patel@wdc.com>
*/
#ifndef __LINUX_KVM_RISCV_H
#define __LINUX_KVM_RISCV_H
#ifndef __ASSEMBLY__
#include <linux/types.h>
#include <asm/ptrace.h>
#define __KVM_HAVE_READONLY_MEM
#define KVM_COALESCED_MMIO_PAGE_OFFSET 1
/* for KVM_GET_REGS and KVM_SET_REGS */
struct kvm_regs {
};
/* for KVM_GET_FPU and KVM_SET_FPU */
struct kvm_fpu {
};
/* KVM Debug exit structure */
struct kvm_debug_exit_arch {
};
/* for KVM_SET_GUEST_DEBUG */
struct kvm_guest_debug_arch {
};
/* definition of registers in kvm_run */
struct kvm_sync_regs {
};
/* dummy definition */
struct kvm_sregs {
};
#endif
#endif /* __LINUX_KVM_RISCV_H */
# SPDX-License-Identifier: GPL-2.0
#
# KVM configuration
#
source "virt/kvm/Kconfig"
menuconfig VIRTUALIZATION
bool "Virtualization"
help
Say Y here to get to see options for using your Linux host to run
other operating systems inside virtual machines (guests).
This option alone does not add any kernel code.
If you say N, all options in this submenu will be skipped and
disabled.
if VIRTUALIZATION
config KVM
tristate "Kernel-based Virtual Machine (KVM) support (EXPERIMENTAL)"
depends on RISCV_SBI && MMU
select PREEMPT_NOTIFIERS
select ANON_INODES
select KVM_MMIO
select HAVE_KVM_VCPU_ASYNC_IOCTL
select SRCU
help
Support hosting virtualized guest machines.
If unsure, say N.
endif # VIRTUALIZATION
# SPDX-License-Identifier: GPL-2.0
#
# Makefile for RISC-V KVM support
#
ccflags-y += -I $(srctree)/$(src)
KVM := ../../../virt/kvm
obj-$(CONFIG_KVM) += kvm.o
kvm-y += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/binary_stats.o \
main.o vm.o mmu.o vcpu.o vcpu_exit.o
// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (C) 2019 Western Digital Corporation or its affiliates.
*
* Authors:
* Anup Patel <anup.patel@wdc.com>
*/
#include <linux/errno.h>
#include <linux/err.h>
#include <linux/module.h>
#include <linux/kvm_host.h>
#include <asm/csr.h>
#include <asm/hwcap.h>
#include <asm/sbi.h>
long kvm_arch_dev_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg)
{
return -EINVAL;
}
int kvm_arch_check_processor_compat(void *opaque)
{
return 0;
}
int kvm_arch_hardware_setup(void *opaque)
{
return 0;
}
int kvm_arch_hardware_enable(void)
{
unsigned long hideleg, hedeleg;
hedeleg = 0;
hedeleg |= (1UL << EXC_INST_MISALIGNED);
hedeleg |= (1UL << EXC_BREAKPOINT);
hedeleg |= (1UL << EXC_SYSCALL);
hedeleg |= (1UL << EXC_INST_PAGE_FAULT);
hedeleg |= (1UL << EXC_LOAD_PAGE_FAULT);
hedeleg |= (1UL << EXC_STORE_PAGE_FAULT);
csr_write(CSR_HEDELEG, hedeleg);
hideleg = 0;
hideleg |= (1UL << IRQ_VS_SOFT);
hideleg |= (1UL << IRQ_VS_TIMER);
hideleg |= (1UL << IRQ_VS_EXT);
csr_write(CSR_HIDELEG, hideleg);
csr_write(CSR_HCOUNTEREN, -1UL);
csr_write(CSR_HVIP, 0);
return 0;
}
void kvm_arch_hardware_disable(void)
{
csr_write(CSR_HEDELEG, 0);
csr_write(CSR_HIDELEG, 0);
}
int kvm_arch_init(void *opaque)
{
if (!riscv_isa_extension_available(NULL, h)) {
kvm_info("hypervisor extension not available\n");
return -ENODEV;
}
if (sbi_spec_is_0_1()) {
kvm_info("require SBI v0.2 or higher\n");
return -ENODEV;
}
if (sbi_probe_extension(SBI_EXT_RFENCE) <= 0) {
kvm_info("require SBI RFENCE extension\n");
return -ENODEV;
}
kvm_info("hypervisor extension available\n");
return 0;
}
void kvm_arch_exit(void)
{
}
static int riscv_kvm_init(void)
{
return kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE);
}
module_init(riscv_kvm_init);
// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (C) 2019 Western Digital Corporation or its affiliates.
*
* Authors:
* Anup Patel <anup.patel@wdc.com>
*/
#include <linux/bitops.h>
#include <linux/errno.h>
#include <linux/err.h>
#include <linux/hugetlb.h>
#include <linux/module.h>
#include <linux/uaccess.h>
#include <linux/vmalloc.h>
#include <linux/kvm_host.h>
#include <linux/sched/signal.h>
#include <asm/page.h>
#include <asm/pgtable.h>
void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot)
{
}
void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free)
{
}
void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen)
{
}
void kvm_arch_flush_shadow_all(struct kvm *kvm)
{
/* TODO: */
}
void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
struct kvm_memory_slot *slot)
{
}
void kvm_arch_commit_memory_region(struct kvm *kvm,
const struct kvm_userspace_memory_region *mem,
struct kvm_memory_slot *old,
const struct kvm_memory_slot *new,
enum kvm_mr_change change)
{
/* TODO: */
}
int kvm_arch_prepare_memory_region(struct kvm *kvm,
struct kvm_memory_slot *memslot,
const struct kvm_userspace_memory_region *mem,
enum kvm_mr_change change)
{
/* TODO: */
return 0;
}
void kvm_riscv_stage2_flush_cache(struct kvm_vcpu *vcpu)
{
/* TODO: */
}
int kvm_riscv_stage2_alloc_pgd(struct kvm *kvm)
{
/* TODO: */
return 0;
}
void kvm_riscv_stage2_free_pgd(struct kvm *kvm)
{
/* TODO: */
}
void kvm_riscv_stage2_update_hgatp(struct kvm_vcpu *vcpu)
{
/* TODO: */
}
// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (C) 2019 Western Digital Corporation or its affiliates.
*
* Authors:
* Anup Patel <anup.patel@wdc.com>
*/
#include <linux/bitops.h>
#include <linux/errno.h>
#include <linux/err.h>
#include <linux/kdebug.h>
#include <linux/module.h>
#include <linux/uaccess.h>
#include <linux/vmalloc.h>
#include <linux/sched/signal.h>
#include <linux/fs.h>
#include <linux/kvm_host.h>
#include <asm/csr.h>
#include <asm/delay.h>
#include <asm/hwcap.h>
const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = {
KVM_GENERIC_VCPU_STATS(),
STATS_DESC_COUNTER(VCPU, ecall_exit_stat),
STATS_DESC_COUNTER(VCPU, wfi_exit_stat),
STATS_DESC_COUNTER(VCPU, mmio_exit_user),
STATS_DESC_COUNTER(VCPU, mmio_exit_kernel),
STATS_DESC_COUNTER(VCPU, exits)
};
const struct kvm_stats_header kvm_vcpu_stats_header = {
.name_size = KVM_STATS_NAME_SIZE,
.num_desc = ARRAY_SIZE(kvm_vcpu_stats_desc),
.id_offset = sizeof(struct kvm_stats_header),
.desc_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE,
.data_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE +
sizeof(kvm_vcpu_stats_desc),
};
int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id)
{
return 0;
}
int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
{
/* TODO: */
return 0;
}
void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
{
}
int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
{
/* TODO: */
return 0;
}
void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
{
/* TODO: */
}
int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
{
/* TODO: */
return 0;
}
void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu)
{
}
void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu)
{
}
int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
{
/* TODO: */
return 0;
}
int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
{
/* TODO: */
return 0;
}
bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu)
{
/* TODO: */
return false;
}
vm_fault_t kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
{
return VM_FAULT_SIGBUS;
}
long kvm_arch_vcpu_async_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg)
{
/* TODO; */
return -ENOIOCTLCMD;
}
long kvm_arch_vcpu_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg)
{
/* TODO: */
return -EINVAL;
}
int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
struct kvm_sregs *sregs)
{
return -EINVAL;
}
int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
struct kvm_sregs *sregs)
{
return -EINVAL;
}
int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
{
return -EINVAL;
}
int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
{
return -EINVAL;
}
int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
struct kvm_translation *tr)
{
return -EINVAL;
}
int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
{
return -EINVAL;
}
int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
{
return -EINVAL;
}
int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
struct kvm_mp_state *mp_state)
{
/* TODO: */
return 0;
}
int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
struct kvm_mp_state *mp_state)
{
/* TODO: */
return 0;
}
int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
struct kvm_guest_debug *dbg)
{
/* TODO; To be implemented later. */
return -EINVAL;
}
void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
/* TODO: */
kvm_riscv_stage2_update_hgatp(vcpu);
}
void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
{
/* TODO: */
}
static void kvm_riscv_check_vcpu_requests(struct kvm_vcpu *vcpu)
{
/* TODO: */
}
int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
{
int ret;
struct kvm_cpu_trap trap;
struct kvm_run *run = vcpu->run;
vcpu->arch.srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
/* Process MMIO value returned from user-space */
if (run->exit_reason == KVM_EXIT_MMIO) {
ret = kvm_riscv_vcpu_mmio_return(vcpu, vcpu->run);
if (ret) {
srcu_read_unlock(&vcpu->kvm->srcu, vcpu->arch.srcu_idx);
return ret;
}
}
if (run->immediate_exit) {
srcu_read_unlock(&vcpu->kvm->srcu, vcpu->arch.srcu_idx);
return -EINTR;
}
vcpu_load(vcpu);
kvm_sigset_activate(vcpu);
ret = 1;
run->exit_reason = KVM_EXIT_UNKNOWN;
while (ret > 0) {
/* Check conditions before entering the guest */
cond_resched();
kvm_riscv_check_vcpu_requests(vcpu);
preempt_disable();
local_irq_disable();
/*
* Exit if we have a signal pending so that we can deliver
* the signal to user space.
*/
if (signal_pending(current)) {
ret = -EINTR;
run->exit_reason = KVM_EXIT_INTR;
}
/*
* Ensure we set mode to IN_GUEST_MODE after we disable
* interrupts and before the final VCPU requests check.
* See the comment in kvm_vcpu_exiting_guest_mode() and
* Documentation/virtual/kvm/vcpu-requests.rst
*/
vcpu->mode = IN_GUEST_MODE;
srcu_read_unlock(&vcpu->kvm->srcu, vcpu->arch.srcu_idx);
smp_mb__after_srcu_read_unlock();
if (ret <= 0 ||
kvm_request_pending(vcpu)) {
vcpu->mode = OUTSIDE_GUEST_MODE;
local_irq_enable();
preempt_enable();
vcpu->arch.srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
continue;
}
guest_enter_irqoff();
__kvm_riscv_switch_to(&vcpu->arch);
vcpu->mode = OUTSIDE_GUEST_MODE;
vcpu->stat.exits++;
/*
* Save SCAUSE, STVAL, HTVAL, and HTINST because we might
* get an interrupt between __kvm_riscv_switch_to() and
* local_irq_enable() which can potentially change CSRs.
*/
trap.sepc = 0;
trap.scause = csr_read(CSR_SCAUSE);
trap.stval = csr_read(CSR_STVAL);
trap.htval = csr_read(CSR_HTVAL);
trap.htinst = csr_read(CSR_HTINST);
/*
* We may have taken a host interrupt in VS/VU-mode (i.e.
* while executing the guest). This interrupt is still
* pending, as we haven't serviced it yet!
*
* We're now back in HS-mode with interrupts disabled
* so enabling the interrupts now will have the effect
* of taking the interrupt again, in HS-mode this time.
*/
local_irq_enable();
/*
* We do local_irq_enable() before calling guest_exit() so
* that if a timer interrupt hits while running the guest
* we account that tick as being spent in the guest. We
* enable preemption after calling guest_exit() so that if
* we get preempted we make sure ticks after that is not
* counted as guest time.
*/
guest_exit();
preempt_enable();
vcpu->arch.srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
ret = kvm_riscv_vcpu_exit(vcpu, run, &trap);
}
kvm_sigset_deactivate(vcpu);
vcpu_put(vcpu);
srcu_read_unlock(&vcpu->kvm->srcu, vcpu->arch.srcu_idx);
return ret;
}
// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (C) 2019 Western Digital Corporation or its affiliates.
*
* Authors:
* Anup Patel <anup.patel@wdc.com>
*/
#include <linux/errno.h>
#include <linux/err.h>
#include <linux/kvm_host.h>
/**
* kvm_riscv_vcpu_mmio_return -- Handle MMIO loads after user space emulation
* or in-kernel IO emulation
*
* @vcpu: The VCPU pointer
* @run: The VCPU run struct containing the mmio data
*/
int kvm_riscv_vcpu_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run)
{
/* TODO: */
return 0;
}
/*
* Return > 0 to return to guest, < 0 on error, 0 (and set exit_reason) on
* proper exit to userspace.
*/
int kvm_riscv_vcpu_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
struct kvm_cpu_trap *trap)
{
/* TODO: */
return 0;
}
// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (C) 2019 Western Digital Corporation or its affiliates.
*
* Authors:
* Anup Patel <anup.patel@wdc.com>
*/
#include <linux/errno.h>
#include <linux/err.h>
#include <linux/module.h>
#include <linux/uaccess.h>
#include <linux/kvm_host.h>
const struct _kvm_stats_desc kvm_vm_stats_desc[] = {
KVM_GENERIC_VM_STATS()
};
static_assert(ARRAY_SIZE(kvm_vm_stats_desc) ==
sizeof(struct kvm_vm_stat) / sizeof(u64));
const struct kvm_stats_header kvm_vm_stats_header = {
.name_size = KVM_STATS_NAME_SIZE,
.num_desc = ARRAY_SIZE(kvm_vm_stats_desc),
.id_offset = sizeof(struct kvm_stats_header),
.desc_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE,
.data_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE +
sizeof(kvm_vm_stats_desc),
};
int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log)
{
/* TODO: To be added later. */
return -EOPNOTSUPP;
}
int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
{
int r;
r = kvm_riscv_stage2_alloc_pgd(kvm);
if (r)
return r;
return 0;
}
void kvm_arch_destroy_vm(struct kvm *kvm)
{
int i;
for (i = 0; i < KVM_MAX_VCPUS; ++i) {
if (kvm->vcpus[i]) {
kvm_vcpu_destroy(kvm->vcpus[i]);
kvm->vcpus[i] = NULL;
}
}
atomic_set(&kvm->online_vcpus, 0);
}
int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
{
int r;
switch (ext) {
case KVM_CAP_DEVICE_CTRL:
case KVM_CAP_USER_MEMORY:
case KVM_CAP_DESTROY_MEMORY_REGION_WORKS:
case KVM_CAP_ONE_REG:
case KVM_CAP_READONLY_MEM:
case KVM_CAP_MP_STATE:
case KVM_CAP_IMMEDIATE_EXIT:
r = 1;
break;
case KVM_CAP_NR_VCPUS:
r = num_online_cpus();
break;
case KVM_CAP_MAX_VCPUS:
r = KVM_MAX_VCPUS;
break;
case KVM_CAP_NR_MEMSLOTS:
r = KVM_USER_MEM_SLOTS;
break;
default:
r = 0;
break;
}
return r;
}
long kvm_arch_vm_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg)
{
return -EINVAL;
}
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment