On Monday 25 March 2019 12:00 PM, David Gibson wrote:
> On Fri, Mar 22, 2019 at 12:04:07PM +0530, Aravinda Prasad wrote:
>> This patch builds the rtas error log, copies it to the
>> rtas_addr and then invokes the guest registered machine
>> check handler.
>
> This commit message needs more context. When is this occurring, why
> do we need this?
>
> [I can answer those questions now, but whether I - or anyone else -
> will be able to looking back at this commit from years in the future
> is a different question]
will add more info.
>
>>
>> Signed-off-by: Aravinda Prasad <aravi...@linux.vnet.ibm.com>
>> ---
>> hw/ppc/spapr.c | 4 +
>> hw/ppc/spapr_events.c | 247
>> ++++++++++++++++++++++++++++++++++++++++++++++++
>> include/hw/ppc/spapr.h | 4 +
>> 3 files changed, 255 insertions(+)
>>
>> diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c
>> index 744dcad..562d405 100644
>> --- a/hw/ppc/spapr.c
>> +++ b/hw/ppc/spapr.c
>> @@ -2910,6 +2910,10 @@ static void spapr_machine_init(MachineState *machine)
>> error_report("Could not get size of LPAR rtas '%s'", filename);
>> exit(1);
>> }
>> +
>> + /* Resize blob to accommodate error log. */
>> + spapr->rtas_size = spapr_get_rtas_size(spapr->rtas_size);
>> +
>> spapr->rtas_blob = g_malloc(spapr->rtas_size);
>> if (load_image_size(filename, spapr->rtas_blob, spapr->rtas_size) < 0) {
>> error_report("Could not load LPAR rtas '%s'", filename);
>> diff --git a/hw/ppc/spapr_events.c b/hw/ppc/spapr_events.c
>> index e7a24ad..d7cc0a4 100644
>> --- a/hw/ppc/spapr_events.c
>> +++ b/hw/ppc/spapr_events.c
>> @@ -212,6 +212,106 @@ struct hp_extended_log {
>> struct rtas_event_log_v6_hp hp;
>> } QEMU_PACKED;
>>
>> +struct rtas_event_log_v6_mc {
>> +#define RTAS_LOG_V6_SECTION_ID_MC 0x4D43 /* MC */
>> + struct rtas_event_log_v6_section_header hdr;
>> + uint32_t fru_id;
>> + uint32_t proc_id;
>> + uint8_t error_type;
>> +#define RTAS_LOG_V6_MC_TYPE_UE 0
>> +#define RTAS_LOG_V6_MC_TYPE_SLB 1
>> +#define RTAS_LOG_V6_MC_TYPE_ERAT 2
>> +#define RTAS_LOG_V6_MC_TYPE_TLB 4
>> +#define RTAS_LOG_V6_MC_TYPE_D_CACHE 5
>> +#define RTAS_LOG_V6_MC_TYPE_I_CACHE 7
>> + uint8_t sub_err_type;
>> +#define RTAS_LOG_V6_MC_UE_INDETERMINATE 0
>> +#define RTAS_LOG_V6_MC_UE_IFETCH 1
>> +#define RTAS_LOG_V6_MC_UE_PAGE_TABLE_WALK_IFETCH 2
>> +#define RTAS_LOG_V6_MC_UE_LOAD_STORE 3
>> +#define RTAS_LOG_V6_MC_UE_PAGE_TABLE_WALK_LOAD_STORE 4
>> +#define RTAS_LOG_V6_MC_SLB_PARITY 0
>> +#define RTAS_LOG_V6_MC_SLB_MULTIHIT 1
>> +#define RTAS_LOG_V6_MC_SLB_INDETERMINATE 2
>> +#define RTAS_LOG_V6_MC_ERAT_PARITY 1
>> +#define RTAS_LOG_V6_MC_ERAT_MULTIHIT 2
>> +#define RTAS_LOG_V6_MC_ERAT_INDETERMINATE 3
>> +#define RTAS_LOG_V6_MC_TLB_PARITY 1
>> +#define RTAS_LOG_V6_MC_TLB_MULTIHIT 2
>> +#define RTAS_LOG_V6_MC_TLB_INDETERMINATE 3
>> + uint8_t reserved_1[6];
>> + uint64_t effective_address;
>> + uint64_t logical_address;
>> +} QEMU_PACKED;
>> +
>> +struct mc_extended_log {
>> + struct rtas_event_log_v6 v6hdr;
>> + struct rtas_event_log_v6_mc mc;
>> +} QEMU_PACKED;
>> +
>> +struct MC_ierror_table {
>> + unsigned long srr1_mask;
>> + unsigned long srr1_value;
>> + bool nip_valid; /* nip is a valid indicator of faulting address */
>> + uint8_t error_type;
>> + uint8_t error_subtype;
>> + unsigned int initiator;
>> + unsigned int severity;
>> +};
>> +
>> +static const struct MC_ierror_table mc_ierror_table[] = {
>> +{ 0x00000000081c0000, 0x0000000000040000, true,
>> + RTAS_LOG_V6_MC_TYPE_UE, RTAS_LOG_V6_MC_UE_IFETCH,
>> + RTAS_LOG_INITIATOR_CPU, RTAS_LOG_SEVERITY_ERROR_SYNC, },
>> +{ 0x00000000081c0000, 0x0000000000080000, true,
>> + RTAS_LOG_V6_MC_TYPE_SLB, RTAS_LOG_V6_MC_SLB_PARITY,
>> + RTAS_LOG_INITIATOR_CPU, RTAS_LOG_SEVERITY_ERROR_SYNC, },
>> +{ 0x00000000081c0000, 0x00000000000c0000, true,
>> + RTAS_LOG_V6_MC_TYPE_SLB, RTAS_LOG_V6_MC_SLB_MULTIHIT,
>> + RTAS_LOG_INITIATOR_CPU, RTAS_LOG_SEVERITY_ERROR_SYNC, },
>> +{ 0x00000000081c0000, 0x0000000000100000, true,
>> + RTAS_LOG_V6_MC_TYPE_ERAT, RTAS_LOG_V6_MC_ERAT_MULTIHIT,
>> + RTAS_LOG_INITIATOR_CPU, RTAS_LOG_SEVERITY_ERROR_SYNC, },
>> +{ 0x00000000081c0000, 0x0000000000140000, true,
>> + RTAS_LOG_V6_MC_TYPE_TLB, RTAS_LOG_V6_MC_TLB_MULTIHIT,
>> + RTAS_LOG_INITIATOR_CPU, RTAS_LOG_SEVERITY_ERROR_SYNC, },
>> +{ 0x00000000081c0000, 0x0000000000180000, true,
>> + RTAS_LOG_V6_MC_TYPE_UE, RTAS_LOG_V6_MC_UE_PAGE_TABLE_WALK_IFETCH,
>> + RTAS_LOG_INITIATOR_CPU, RTAS_LOG_SEVERITY_ERROR_SYNC, },
>> +{ 0, 0, 0, 0, 0, 0 } };
>> +
>> +struct MC_derror_table {
>> + unsigned long dsisr_value;
>> + bool dar_valid; /* dar is a valid indicator of faulting address */
>> + uint8_t error_type;
>> + uint8_t error_subtype;
>> + unsigned int initiator;
>> + unsigned int severity;
>> +};
>> +
>> +static const struct MC_derror_table mc_derror_table[] = {
>> +{ 0x00008000, false,
>> + RTAS_LOG_V6_MC_TYPE_UE, RTAS_LOG_V6_MC_UE_LOAD_STORE,
>> + RTAS_LOG_INITIATOR_CPU, RTAS_LOG_SEVERITY_ERROR_SYNC, },
>> +{ 0x00004000, true,
>> + RTAS_LOG_V6_MC_TYPE_UE, RTAS_LOG_V6_MC_UE_PAGE_TABLE_WALK_LOAD_STORE,
>> + RTAS_LOG_INITIATOR_CPU, RTAS_LOG_SEVERITY_ERROR_SYNC, },
>> +{ 0x00000800, true,
>> + RTAS_LOG_V6_MC_TYPE_ERAT, RTAS_LOG_V6_MC_ERAT_MULTIHIT,
>> + RTAS_LOG_INITIATOR_CPU, RTAS_LOG_SEVERITY_ERROR_SYNC, },
>> +{ 0x00000400, true,
>> + RTAS_LOG_V6_MC_TYPE_TLB, RTAS_LOG_V6_MC_TLB_MULTIHIT,
>> + RTAS_LOG_INITIATOR_CPU, RTAS_LOG_SEVERITY_ERROR_SYNC, },
>> +{ 0x00000080, true,
>> + RTAS_LOG_V6_MC_TYPE_SLB, RTAS_LOG_V6_MC_SLB_MULTIHIT, /* Before PARITY */
>> + RTAS_LOG_INITIATOR_CPU, RTAS_LOG_SEVERITY_ERROR_SYNC, },
>> +{ 0x00000100, true,
>> + RTAS_LOG_V6_MC_TYPE_SLB, RTAS_LOG_V6_MC_SLB_PARITY,
>> + RTAS_LOG_INITIATOR_CPU, RTAS_LOG_SEVERITY_ERROR_SYNC, },
>> +{ 0, false, 0, 0, 0, 0 } };
>> +
>> +#define SRR1_MC_LOADSTORE(srr1) ((srr1) & PPC_BIT(42))
>> +
>> typedef enum EventClass {
>> EVENT_CLASS_INTERNAL_ERRORS = 0,
>> EVENT_CLASS_EPOW = 1,
>> @@ -620,6 +720,149 @@ void
>> spapr_hotplug_req_remove_by_count_indexed(SpaprDrcType drc_type,
>> RTAS_LOG_V6_HP_ACTION_REMOVE, drc_type,
>> &drc_id);
>> }
>>
>> +ssize_t spapr_get_rtas_size(ssize_t old_rtas_size)
>> +{
>> + g_assert(old_rtas_size < RTAS_ERRLOG_OFFSET);
>> + return RTAS_ERROR_LOG_MAX;
>> +}
>> +
>> +static uint64_t spapr_get_rtas_addr(void)
>> +{
>> + SpaprMachineState *spapr = SPAPR_MACHINE(qdev_get_machine());
>> + int rtas_node;
>> + const struct fdt_property *rtas_addr_prop;
>> + void *fdt = spapr->fdt_blob;
>> + uint32_t rtas_addr;
>> +
>> + /* fetch rtas addr from fdt */
>> + rtas_node = fdt_path_offset(fdt, "/rtas");
>> + g_assert(rtas_node >= 0);
>> +
>> + rtas_addr_prop = fdt_get_property(fdt, rtas_node, "linux,rtas-base",
>> NULL);
>> + g_assert(rtas_addr_prop);
>> +
>> + rtas_addr = fdt32_to_cpu(*(uint32_t *)rtas_addr_prop->data);
>> + return (uint64_t)rtas_addr;
>
> It seems a bit roundabout to pull the rtas address out of the device
> tree, since it was us that put it in there in the first place.
Slof can change the rtas address. So we need to get the updated rtas
address.
>
>> +}
>> +
>> +static uint32_t spapr_mce_get_elog_type(PowerPCCPU *cpu, bool recovered,
>> + struct mc_extended_log *ext_elog)
>> +{
>> + int i;
>> + CPUPPCState *env = &cpu->env;
>> + uint32_t summary;
>> + uint64_t dsisr = env->spr[SPR_DSISR];
>> +
>> + summary = RTAS_LOG_VERSION_6 | RTAS_LOG_OPTIONAL_PART_PRESENT;
>> + if (recovered) {
>> + summary |= RTAS_LOG_DISPOSITION_FULLY_RECOVERED;
>> + } else {
>> + summary |= RTAS_LOG_DISPOSITION_NOT_RECOVERED;
>> + }
>> +
>> + if (SRR1_MC_LOADSTORE(env->spr[SPR_SRR1])) {
>> + for (i = 0; mc_derror_table[i].dsisr_value; i++) {
>> + if (!(dsisr & mc_derror_table[i].dsisr_value)) {
>> + continue;
>> + }
>> +
>> + ext_elog->mc.error_type = mc_derror_table[i].error_type;
>> + ext_elog->mc.sub_err_type = mc_derror_table[i].error_subtype;
>> + if (mc_derror_table[i].dar_valid) {
>> + ext_elog->mc.effective_address =
>> cpu_to_be64(env->spr[SPR_DAR]);
>> + }
>> +
>> + summary |= mc_derror_table[i].initiator
>> + | mc_derror_table[i].severity;
>> +
>> + return summary;
>> + }
>> + } else {
>> + for (i = 0; mc_ierror_table[i].srr1_mask; i++) {
>> + if ((env->spr[SPR_SRR1] & mc_ierror_table[i].srr1_mask) !=
>> + mc_ierror_table[i].srr1_value) {
>> + continue;
>> + }
>> +
>> + ext_elog->mc.error_type = mc_ierror_table[i].error_type;
>> + ext_elog->mc.sub_err_type = mc_ierror_table[i].error_subtype;
>> + if (mc_ierror_table[i].nip_valid) {
>> + ext_elog->mc.effective_address = cpu_to_be64(env->nip);
>> + }
>> +
>> + summary |= mc_ierror_table[i].initiator
>> + | mc_ierror_table[i].severity;
>> +
>> + return summary;
>> + }
>> + }
>> +
>> + summary |= RTAS_LOG_INITIATOR_CPU;
>> + return summary;
>> +}
>> +
>> +static void spapr_mce_build_elog(PowerPCCPU *cpu, bool recovered)
>> +{
>> + SpaprMachineState *spapr = SPAPR_MACHINE(qdev_get_machine());
>> + uint64_t rtas_addr;
>> + CPUPPCState *env = &cpu->env;
>> + PowerPCCPUClass *pcc = POWERPC_CPU_GET_CLASS(cpu);
>> + target_ulong r3, msr = 0;
>> + struct rtas_error_log log;
>> + struct mc_extended_log *ext_elog;
>> + uint32_t summary;
>> +
>> + ext_elog = g_malloc0(sizeof(*ext_elog));
>
> g_new0() is preferred to g_malloc0().
ok..
>
>> +
>> + /*
>> + * Properly set bits in MSR before we invoke the handler.
>> + * SRR0/1, DAR and DSISR are properly set by KVM
>> + */
>> + if (!(*pcc->interrupts_big_endian)(cpu)) {
>> + msr |= (1ULL << MSR_LE);
>> + }
>> +
>> + if (env->msr && (1ULL << MSR_SF)) {
>> + msr |= (1ULL << MSR_SF);
>> + }
>> +
>> + msr |= (1ULL << MSR_ME);
>> + env->msr = msr;
>
> The name seems a bit misleading, since this is clearly doing more than
> just building the error log, it's doing at least some of the work of
> dispatching it as well.
ok will rename.
>
>> +
>> + summary = spapr_mce_get_elog_type(cpu, recovered, ext_elog);
>> +
>> + log.summary = cpu_to_be32(summary);
>> + log.extended_length = cpu_to_be32(sizeof(struct mc_extended_log));
>> +
>> + /* r3 should be in BE always */
>> + r3 = cpu_to_be64(env->gpr[3]);
>> +
>> + spapr_init_v6hdr(&ext_elog->v6hdr);
>> + ext_elog->mc.hdr.section_id = cpu_to_be16(RTAS_LOG_V6_SECTION_ID_MC);
>> + ext_elog->mc.hdr.section_length =
>> + cpu_to_be16(sizeof(struct rtas_event_log_v6_mc));
>> + ext_elog->mc.hdr.section_version = 1;
>> +
>> + /* get rtas addr from fdt */
>> + rtas_addr = spapr_get_rtas_addr();
>> +
>> + cpu_physical_memory_write(rtas_addr + RTAS_ERRLOG_OFFSET, &r3,
>> sizeof(r3));
>> + cpu_physical_memory_write(rtas_addr + RTAS_ERRLOG_OFFSET + sizeof(r3),
>> + &log, sizeof(log));
>> + cpu_physical_memory_write(rtas_addr + RTAS_ERRLOG_OFFSET + sizeof(r3) +
>> + sizeof(log), ext_elog,
>> + sizeof(struct mc_extended_log));
>> +
>> + /* Save gpr[3] in the guest endian mode */
>> + if ((*pcc->interrupts_big_endian)(cpu)) {
>> + env->gpr[3] = cpu_to_be64(rtas_addr + RTAS_ERRLOG_OFFSET);
>> + } else {
>> + env->gpr[3] = cpu_to_le64(rtas_addr + RTAS_ERRLOG_OFFSET);
>> + }
>> +
>> + env->nip = spapr->guest_machine_check_addr;
>> +}
>> +
>> void spapr_mce_req_event(PowerPCCPU *cpu, bool recovered)
>> {
>> SpaprMachineState *spapr = SPAPR_MACHINE(qdev_get_machine());
>> @@ -640,6 +883,10 @@ void spapr_mce_req_event(PowerPCCPU *cpu, bool
>> recovered)
>> }
>> }
>> spapr->mc_status = cpu->vcpu_id;
>> +
>> + spapr_mce_build_elog(cpu, recovered);
>> +
>> + return;
>> }
>>
>> static void check_exception(PowerPCCPU *cpu, SpaprMachineState *spapr,
>> diff --git a/include/hw/ppc/spapr.h b/include/hw/ppc/spapr.h
>> index b0d8c18..0c9dec1 100644
>> --- a/include/hw/ppc/spapr.h
>> +++ b/include/hw/ppc/spapr.h
>> @@ -662,6 +662,9 @@ target_ulong spapr_hypercall(PowerPCCPU *cpu,
>> target_ulong opcode,
>> #define DIAGNOSTICS_RUN_MODE_IMMEDIATE 2
>> #define DIAGNOSTICS_RUN_MODE_PERIODIC 3
>>
>> +/* Offset from rtas-base where error log is placed */
>> +#define RTAS_ERRLOG_OFFSET 0x25
>> +
>> static inline uint64_t ppc64_phys_to_real(uint64_t addr)
>> {
>> return addr & ~0xF000000000000000ULL;
>> @@ -793,6 +796,7 @@ void spapr_reallocate_hpt(SpaprMachineState *spapr, int
>> shift,
>> void spapr_clear_pending_events(SpaprMachineState *spapr);
>> int spapr_max_server_number(SpaprMachineState *spapr);
>> void spapr_mce_req_event(PowerPCCPU *cpu, bool recovered);
>> +ssize_t spapr_get_rtas_size(ssize_t old_rtas_sizea);
>>
>> /* DRC callbacks. */
>> void spapr_core_release(DeviceState *dev);
>>
>
--
Regards,
Aravinda