diff options
Diffstat (limited to 'hw/ppc/spapr_events.c')
-rw-r--r-- | hw/ppc/spapr_events.c | 269 |
1 files changed, 269 insertions, 0 deletions
diff --git a/hw/ppc/spapr_events.c b/hw/ppc/spapr_events.c index e355e00..884e455 100644 --- a/hw/ppc/spapr_events.c +++ b/hw/ppc/spapr_events.c @@ -40,8 +40,10 @@ #include "hw/ppc/spapr_drc.h" #include "qemu/help_option.h" #include "qemu/bcd.h" +#include "qemu/main-loop.h" #include "hw/ppc/spapr_ovec.h" #include <libfdt.h> +#include "migration/blocker.h" #define RTAS_LOG_VERSION_MASK 0xff000000 #define RTAS_LOG_VERSION_6 0x06000000 @@ -213,6 +215,104 @@ 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, } }; + +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, } }; + +#define SRR1_MC_LOADSTORE(srr1) ((srr1) & PPC_BIT(42)) + typedef enum EventClass { EVENT_CLASS_INTERNAL_ERRORS = 0, EVENT_CLASS_EPOW = 1, @@ -622,6 +722,175 @@ void spapr_hotplug_req_remove_by_count_indexed(SpaprDrcType drc_type, RTAS_LOG_V6_HP_ACTION_REMOVE, drc_type, &drc_id); } +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; i < ARRAY_SIZE(mc_derror_table); 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; i < ARRAY_SIZE(mc_ierror_table); 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_dispatch_elog(PowerPCCPU *cpu, bool recovered) +{ + SpaprMachineState *spapr = SPAPR_MACHINE(qdev_get_machine()); + CPUState *cs = CPU(cpu); + uint64_t rtas_addr; + CPUPPCState *env = &cpu->env; + PowerPCCPUClass *pcc = POWERPC_CPU_GET_CLASS(cpu); + target_ulong msr = 0; + struct rtas_error_log log; + struct mc_extended_log *ext_elog; + uint32_t summary; + + /* + * 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); + + ext_elog = g_malloc0(sizeof(*ext_elog)); + summary = spapr_mce_get_elog_type(cpu, recovered, ext_elog); + + log.summary = cpu_to_be32(summary); + log.extended_length = cpu_to_be32(sizeof(*ext_elog)); + + 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(); + if (!rtas_addr) { + /* Unable to fetch rtas_addr. Hence reset the guest */ + ppc_cpu_do_system_reset(cs); + g_free(ext_elog); + return; + } + + stq_be_phys(&address_space_memory, rtas_addr + RTAS_ERROR_LOG_OFFSET, + env->gpr[3]); + cpu_physical_memory_write(rtas_addr + RTAS_ERROR_LOG_OFFSET + + sizeof(env->gpr[3]), &log, sizeof(log)); + cpu_physical_memory_write(rtas_addr + RTAS_ERROR_LOG_OFFSET + + sizeof(env->gpr[3]) + sizeof(log), ext_elog, + sizeof(*ext_elog)); + + env->gpr[3] = rtas_addr + RTAS_ERROR_LOG_OFFSET; + env->msr = msr; + env->nip = spapr->guest_machine_check_addr; + + g_free(ext_elog); +} + +void spapr_mce_req_event(PowerPCCPU *cpu, bool recovered) +{ + SpaprMachineState *spapr = SPAPR_MACHINE(qdev_get_machine()); + CPUState *cs = CPU(cpu); + int ret; + Error *local_err = NULL; + + if (spapr->guest_machine_check_addr == -1) { + /* + * This implies that we have hit a machine check either when the + * guest has not registered FWNMI (i.e., "ibm,nmi-register" not + * called) or between system reset and "ibm,nmi-register". + * Fall back to the old machine check behavior in such cases. + */ + cs->exception_index = POWERPC_EXCP_MCHECK; + ppc_cpu_do_interrupt(cs); + return; + } + + while (spapr->mc_status != -1) { + /* + * Check whether the same CPU got machine check error + * while still handling the mc error (i.e., before + * that CPU called "ibm,nmi-interlock") + */ + if (spapr->mc_status == cpu->vcpu_id) { + qemu_system_guest_panicked(NULL); + return; + } + qemu_cond_wait_iothread(&spapr->mc_delivery_cond); + /* Meanwhile if the system is reset, then just return */ + if (spapr->guest_machine_check_addr == -1) { + return; + } + } + + ret = migrate_add_blocker(spapr->fwnmi_migration_blocker, &local_err); + if (ret == -EBUSY) { + /* + * We don't want to abort so we let the migration to continue. + * In a rare case, the machine check handler will run on the target. + * Though this is not preferable, it is better than aborting + * the migration or killing the VM. + */ + warn_report("Received a fwnmi while migration was in progress"); + } + + spapr->mc_status = cpu->vcpu_id; + spapr_mce_dispatch_elog(cpu, recovered); +} + static void check_exception(PowerPCCPU *cpu, SpaprMachineState *spapr, uint32_t token, uint32_t nargs, target_ulong args, |