Re: [PATCH] target/riscv: fix the issue of guest reboot then no response or crash in kvm-mode

[Alistair Francis]

On Mon, Jun 12, 2023 at 11:07 PM liguang.zhang <18622748025@163.com> wrote:
>
> From: "liguang.zhang" <liguang.zhang@hexintek.com>

Hello, thanks for the patch

>
> There have a issue of guest reboot bug in kvm-mode:
> 1. in guest shell just run the reboot, guest can't reboot success, and host 
> kvm stop the vcpu schedual.
> 2. for smp guest, ctrl+a+c switch to qemu command, use system_reset command 
> to reset the guest, then vcpu crash

There are two issues when rebooting a guest using KVM
 1. When the guest initiates a reboot the host is unable to stop the vcpu
 2. When running a SMP guest the qemu monitor system_reset causes a vcpu crash

This can be fixed by clearing the CSR values at reset and syncing the
MPSTATE with the host.

>
> kernel log
> ```shell
> $reboot
>
> The system is going down NOW!
> Sent SIGTERM to all processes
> logout
> Sent SIGKILL to all processes
> Requesting system reboot
>
> ```
> then no response
>
> for qemu command:
> $system_reset:
>
> kernel log:
> ```shell
> [   53.739556] kvm [150]: VCPU exit error -95
> [   53.739563] kvm [148]: VCPU exit error -95
> [   53.739557] kvm [149]: VCPU exit error -95
> [   53.740957] kvm [149]: SEPC=0x0 SSTATUS=0x200004120 HSTATUS=0x2002001c0
> [   53.740957] kvm [148]: SEPC=0x0 SSTATUS=0x200004120 HSTATUS=0x2002001c0
> [   53.741054] kvm [148]: SCAUSE=0x14 STVAL=0x0 HTVAL=0x0 HTINST=0x0
> [   53.741058] kvm [149]: SCAUSE=0x14 STVAL=0x0 HTVAL=0x0 HTINST=0x0
> [   53.756187] kvm [150]: SEPC=0x0 SSTATUS=0x200004120 HSTATUS=0x2002001c0
> [   53.757797] kvm [150]: SCAUSE=0x14 STVAL=0x0 HTVAL=0x0 HTINST=0x0
> ```
>
> solution:
>
> add reset csr and context for riscv vcpu
> qemu ioctl reset vcpu->arch.power_off state of kvm
>
> tests:
>
> qemu-system-riscv64 -M virt -bios none -kernel Image \
>    -smp 4 -enable-kvm \
>    -append "rootwait root=/dev/vda ro" \
>    -drive file=rootfs.ext2,format=raw,id=hd0 \
>    -device virtio-blk-device,drive=hd0
>
> in guest shell:
> $reboot
>
> qemu command:
> $system_reset
>
> ---
> v2:
> - update submit description
>
> Signed-off-by: liguang.zhang <liguang.zhang@hexintek.com>
> ---
>  target/riscv/kvm.c       | 43 ++++++++++++++++++++++++++++++++++++++++
>  target/riscv/kvm_riscv.h |  1 +
>  2 files changed, 44 insertions(+)
>
> diff --git a/target/riscv/kvm.c b/target/riscv/kvm.c
> index 0f932a5b96..c6a7824c9e 100644
> --- a/target/riscv/kvm.c
> +++ b/target/riscv/kvm.c
> @@ -42,6 +42,8 @@
>  #include "migration/migration.h"
>  #include "sysemu/runstate.h"
>
> +static bool cap_has_mp_state;
> +
>  static uint64_t kvm_riscv_reg_id(CPURISCVState *env, uint64_t type,
>                                   uint64_t idx)
>  {
> @@ -335,6 +337,25 @@ int kvm_arch_get_registers(CPUState *cs)
>      return ret;
>  }
>
> +int kvm_riscv_set_mpstate_to_kvm(RISCVCPU *cpu, int state)

This should probably be called:

kvm_riscv_sync_mpstate_to_kvm()

instead

> +{
> +    if (cap_has_mp_state) {
> +

No newline required

Otherwise the patch looks good

Alistair

> +        struct kvm_mp_state mp_state = {
> +            .mp_state = state
> +        };
> +
> +        int ret = kvm_vcpu_ioctl(CPU(cpu), KVM_SET_MP_STATE, &mp_state);
> +        if (ret) {
> +            fprintf(stderr, "%s: failed to set MP_STATE %d/%s\n",
> +                    __func__, ret, strerror(-ret));
> +            return -1;
> +        }
> +    }
> +
> +    return 0;
> +}
> +
>  int kvm_arch_put_registers(CPUState *cs, int level)
>  {
>      int ret = 0;
> @@ -354,6 +375,18 @@ int kvm_arch_put_registers(CPUState *cs, int level)
>          return ret;
>      }
>
> +    if (KVM_PUT_RESET_STATE == level) {
> +        RISCVCPU *cpu = RISCV_CPU(cs);
> +        if (cs->cpu_index == 0) {
> +            ret = kvm_riscv_set_mpstate_to_kvm(cpu, KVM_MP_STATE_RUNNABLE);
> +        } else {
> +            ret = kvm_riscv_set_mpstate_to_kvm(cpu, KVM_MP_STATE_STOPPED);
> +        }
> +        if (ret) {
> +            return ret;
> +        }
> +    }
> +
>      return ret;
>  }
>
> @@ -428,6 +461,7 @@ int kvm_arch_add_msi_route_post(struct 
> kvm_irq_routing_entry *route,
>
>  int kvm_arch_init(MachineState *ms, KVMState *s)
>  {
> +    cap_has_mp_state = kvm_check_extension(s, KVM_CAP_MP_STATE);
>      return 0;
>  }
>
> @@ -506,10 +540,19 @@ void kvm_riscv_reset_vcpu(RISCVCPU *cpu)
>      if (!kvm_enabled()) {
>          return;
>      }
> +    for (int i=0; i<32; i++)
> +        env->gpr[i] = 0;
>      env->pc = cpu->env.kernel_addr;
>      env->gpr[10] = kvm_arch_vcpu_id(CPU(cpu)); /* a0 */
>      env->gpr[11] = cpu->env.fdt_addr;          /* a1 */
>      env->satp = 0;
> +    env->mie = 0;
> +    env->stvec = 0;
> +    env->sscratch = 0;
> +    env->sepc = 0;
> +    env->scause = 0;
> +    env->stval = 0;
> +    env->mip = 0;
>  }
>
>  void kvm_riscv_set_irq(RISCVCPU *cpu, int irq, int level)
> diff --git a/target/riscv/kvm_riscv.h b/target/riscv/kvm_riscv.h
> index ed281bdce0..4a4c262820 100644
> --- a/target/riscv/kvm_riscv.h
> +++ b/target/riscv/kvm_riscv.h
> @@ -21,5 +21,6 @@
>
>  void kvm_riscv_reset_vcpu(RISCVCPU *cpu);
>  void kvm_riscv_set_irq(RISCVCPU *cpu, int irq, int level);
> +int kvm_riscv_set_mpstate_to_kvm(RISCVCPU *cpu, int state);
>
>  #endif
> --
> 2.17.1
>
>