Re: [Qemu-ppc] [PATCH v7 1/6] ppc: spapr: Handle "ibm, nmi-register" and "ibm, nmi-interlock" RTAS calls

[Aravinda Prasad]

On Monday 25 March 2019 11:46 AM, David Gibson wrote:
> On Fri, Mar 22, 2019 at 12:03:39PM +0530, Aravinda Prasad wrote:
>> This patch adds support in QEMU to handle "ibm,nmi-register"
>> and "ibm,nmi-interlock" RTAS calls.
>>
>> The machine check notification address is saved when the
>> OS issues "ibm,nmi-register" RTAS call.
>>
>> This patch also handles the case when multiple processors
>> experience machine check at or about the same time by
>> handling "ibm,nmi-interlock" call. In such cases, as per
>> PAPR, subsequent processors serialize waiting for the first
>> processor to issue the "ibm,nmi-interlock" call. The second
>> processor that also received a machine check error waits
>> till the first processor is done reading the error log.
>> The first processor issues "ibm,nmi-interlock" call
>> when the error log is consumed. This patch implements the
>> releasing part of the error-log while subsequent patch
>> (which builds error log) handles the locking part.
>>
>> Signed-off-by: Aravinda Prasad <address@hidden>
>> ---
>>  hw/ppc/spapr.c         |   25 +++++++++++++++++++++++++
>>  hw/ppc/spapr_rtas.c    |   36 ++++++++++++++++++++++++++++++++++++
>>  include/hw/ppc/spapr.h |   15 ++++++++++++++-
>>  3 files changed, 75 insertions(+), 1 deletion(-)
>>
>> diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c
>> index adde36a..744dcad 100644
>> --- a/hw/ppc/spapr.c
>> +++ b/hw/ppc/spapr.c
>> @@ -1788,6 +1788,16 @@ static void spapr_machine_reset(void)
>>      first_ppc_cpu->env.gpr[5] = 0;
>>  
>>      spapr->cas_reboot = false;
>> +
>> +    spapr->mc_reset = 1;
>> +    spapr->mc_status = -1;
> 
> I don't love adding these fields so early, when they're never actually
> tested until later in the series.

Sure..

> 
>> +    spapr->guest_machine_check_addr = -1;
>> +
>> +    /* Before destroying, signal vCPUs waiting on this condition */
>> +    qemu_cond_broadcast(&spapr->mc_delivery_cond);
>> +    /* It is safe to call destroy as broadcast unblocks all vCPUs */
>> +    qemu_cond_destroy(&spapr->mc_delivery_cond);
>> +    qemu_cond_init(&spapr->mc_delivery_cond);
> 
> Why do you need to destroy and re-create the condition variable?

Hmm.. looks like I don't have to. qemu_cond_broadcast() should take care
of the vCPUs waiting on the condition. Let me check.

> 
>>  }
>>  
>>  static void spapr_create_nvram(SpaprMachineState *spapr)
>> @@ -2078,6 +2088,16 @@ static const VMStateDescription vmstate_spapr_dtb = {
>>      },
>>  };
>>  
>> +static const VMStateDescription vmstate_spapr_guest_mc_addr = {
>> +    .name = "spapr_guest_mc_addr",
>> +    .version_id = 1,
>> +    .minimum_version_id = 1,
>> +    .fields = (VMStateField[]) {
>> +        VMSTATE_UINT64(guest_machine_check_addr, SpaprMachineState),
> 
> It looks like mc_reset and mc_status would also need migration, at
> least once they actually do something.

Yes, they need to be migrated as well.

> 
>> +        VMSTATE_END_OF_LIST()
>> +    },
>> +};
>> +
>>  static const VMStateDescription vmstate_spapr = {
>>      .name = "spapr",
>>      .version_id = 3,
>> @@ -2110,6 +2130,7 @@ static const VMStateDescription vmstate_spapr = {
>>          &vmstate_spapr_dtb,
>>          &vmstate_spapr_cap_large_decr,
>>          &vmstate_spapr_cap_ccf_assist,
>> +        &vmstate_spapr_guest_mc_addr,
>>          NULL
>>      }
>>  };
>> @@ -3057,6 +3078,10 @@ static void spapr_machine_init(MachineState *machine)
>>  
>>          kvmppc_spapr_enable_inkernel_multitce();
>>      }
>> +
>> +    spapr->mc_status = -1;
>> +    spapr->mc_reset = 0;
> 
> Since this is a bool, you should use true/false rather than 0/1.

ok

Regards,
Aravinda

> 
>> +    qemu_cond_init(&spapr->mc_delivery_cond);
>>  }
>>  
>>  static int spapr_kvm_type(MachineState *machine, const char *vm_type)
>> diff --git a/hw/ppc/spapr_rtas.c b/hw/ppc/spapr_rtas.c
>> index 24c45b1..fb594a4 100644
>> --- a/hw/ppc/spapr_rtas.c
>> +++ b/hw/ppc/spapr_rtas.c
>> @@ -348,6 +348,38 @@ static void rtas_get_power_level(PowerPCCPU *cpu, 
>> SpaprMachineState *spapr,
>>      rtas_st(rets, 1, 100);
>>  }
>>  
>> +static void rtas_ibm_nmi_register(PowerPCCPU *cpu,
>> +                                  SpaprMachineState *spapr,
>> +                                  uint32_t token, uint32_t nargs,
>> +                                  target_ulong args,
>> +                                  uint32_t nret, target_ulong rets)
>> +{
>> +    spapr->mc_reset = 0;
>> +    spapr->guest_machine_check_addr = rtas_ld(args, 1);
>> +    rtas_st(rets, 0, RTAS_OUT_SUCCESS);
>> +}
>> +
>> +static void rtas_ibm_nmi_interlock(PowerPCCPU *cpu,
>> +                                   SpaprMachineState *spapr,
>> +                                   uint32_t token, uint32_t nargs,
>> +                                   target_ulong args,
>> +                                   uint32_t nret, target_ulong rets)
>> +{
>> +    if (!spapr->guest_machine_check_addr) {
>> +        /* NMI register not called */
>> +        rtas_st(rets, 0, RTAS_OUT_PARAM_ERROR);
>> +    } else {
>> +        /*
>> +         * VCPU issuing "ibm,nmi-interlock" is done with NMI handling,
>> +         * hence unset mc_status.
>> +         */
>> +        spapr->mc_status = -1;
>> +        qemu_cond_signal(&spapr->mc_delivery_cond);
>> +        rtas_st(rets, 0, RTAS_OUT_SUCCESS);
>> +    }
>> +}
>> +
>> +
>>  static struct rtas_call {
>>      const char *name;
>>      spapr_rtas_fn fn;
>> @@ -489,6 +521,10 @@ static void core_rtas_register_types(void)
>>                          rtas_set_power_level);
>>      spapr_rtas_register(RTAS_GET_POWER_LEVEL, "get-power-level",
>>                          rtas_get_power_level);
>> +    spapr_rtas_register(RTAS_IBM_NMI_REGISTER, "ibm,nmi-register",
>> +                        rtas_ibm_nmi_register);
>> +    spapr_rtas_register(RTAS_IBM_NMI_INTERLOCK, "ibm,nmi-interlock",
>> +                        rtas_ibm_nmi_interlock);
>>  }
>>  
>>  type_init(core_rtas_register_types)
>> diff --git a/include/hw/ppc/spapr.h b/include/hw/ppc/spapr.h
>> index 74ce638..ee5589d 100644
>> --- a/include/hw/ppc/spapr.h
>> +++ b/include/hw/ppc/spapr.h
>> @@ -186,6 +186,17 @@ struct SpaprMachineState {
>>       * occurs during the unplug process. */
>>      QTAILQ_HEAD(, SpaprDimmState) pending_dimm_unplugs;
>>  
>> +    /* State related to "ibm,nmi-register" and "ibm,nmi-interlock" calls */
>> +    target_ulong guest_machine_check_addr;
>> +    /*
>> +     * mc_status is set to -1 if mc is not in progress, else is set to the 
>> CPU
>> +     * handling the mc.
>> +     */
>> +    int mc_status;
>> +    /* mc_reset is set to 1 if machine reset is in progress */
>> +    bool mc_reset;
>> +    QemuCond mc_delivery_cond;
>> +
>>      /*< public >*/
>>      char *kvm_type;
>>      char *host_model;
>> @@ -622,8 +633,10 @@ target_ulong spapr_hypercall(PowerPCCPU *cpu, 
>> target_ulong opcode,
>>  #define RTAS_IBM_CREATE_PE_DMA_WINDOW           (RTAS_TOKEN_BASE + 0x27)
>>  #define RTAS_IBM_REMOVE_PE_DMA_WINDOW           (RTAS_TOKEN_BASE + 0x28)
>>  #define RTAS_IBM_RESET_PE_DMA_WINDOW            (RTAS_TOKEN_BASE + 0x29)
>> +#define RTAS_IBM_NMI_REGISTER                   (RTAS_TOKEN_BASE + 0x2A)
>> +#define RTAS_IBM_NMI_INTERLOCK                  (RTAS_TOKEN_BASE + 0x2B)
>>  
>> -#define RTAS_TOKEN_MAX                          (RTAS_TOKEN_BASE + 0x2A)
>> +#define RTAS_TOKEN_MAX                          (RTAS_TOKEN_BASE + 0x2C)
>>  
>>  /* RTAS ibm,get-system-parameter token values */
>>  #define RTAS_SYSPARM_SPLPAR_CHARACTERISTICS      20
>>
> 

-- 
Regards,
Aravinda