target-ppc/spapr: Add FWNMI support in QEMU for PowerKM guests
v17 cover target-ppc/spapr: Add FWNMI support in QEMU for PowerKM guests
This patch set adds support for FWNMI in PowerKVM guests.
System errors such as SLB multihit and memory errors that cannot be corrected by hardware is passed on to the kernel for handling by raising machine check exception (an NMI). Upon such machine check exceptions, if the address in error belongs to guest then KVM invokes guests' 0x200 interrupt vector if the guest is not FWNMI capable. For FWNMI capable guest KVM passes the control to QEMU by exiting the guest.
This patch series adds functionality to QEMU to pass on such machine check exceptions to the FWNMI capable guest kernel by building an error log and invoking the guest registered machine check handling routine.
The KVM changes are now part of the upstream kernel (commit e20bbd3d). This series contain QEMU changes.
Change Log v17:
- Add fwnmi cap to migration state
- Reprhase the commit message in patch 2/7
Change Log v16:
- Fixed coding style problems
Change Log v15:
- Removed cap_ppc_fwnmi
- Moved fwnmi registeration to .apply hook
- Assume SLOF has allocated enough room for rtas error log
- Using ARRAY_SIZE to end the loop
- Do not set FWNMI cap in post_load, now its done in .apply hook
Change Log v14:
- Feature activation moved to a separate patch
- Fixed issues with migration blocker
Change Log v13:
- Minor fixes (mostly nits)
- Moved FWNMI guest registration check from patch 4 to 3.
Change Log v12:
- Rebased to latest ppc-for-4.2 (SHA b1e8156743)
Change Log v11:
- Moved FWNMI SPAPR cap defaults to 4.2 class option
- Fixed issues with handling fwnmi KVM capability
Change Log v10:
- Reshuffled the patch sequence + minor fixes
Change Log v9:
- Fixed kvm cap and spapr cap issues
Change Log v8:
- Added functionality to check FWNMI capability during VM migration
---
Aravinda Prasad (7):
Wrapper function to wait on condition for the main loop mutex
ppc: spapr: Introduce FWNMI capability
target/ppc: Handle NMI guest exit
target/ppc: Build rtas error log upon an MCE
ppc: spapr: Handle "ibm,nmi-register" and "ibm,nmi-interlock" RTAS
calls
migration: Include migration support for machine check handling
ppc: spapr: Activate the FWNMI functionality
cpus.c | 5 + hw/ppc/spapr.c | 52 ++++++++ hw/ppc/spapr_caps.c | 34 +++++ hw/ppc/spapr_events.c | 269 +++++++++++++++++++++++++++++++++++++++ hw/ppc/spapr_rtas.c | 85 +++++++++++++ include/hw/ppc/spapr.h | 26 +++- include/qemu/main-loop.h | 8 ++ target/ppc/kvm.c | 24 ++++ target/ppc/kvm_ppc.h | 8 ++ target/ppc/trace-events | 1 + 10 files changed, 510 insertions(+), 2 deletions(-)
Signature · 1 line
2.17.2
PATCH v17 4/7 target/ppc: Build rtas error log upon an MCE
From: Aravinda Prasad <[email protected]>
Upon a machine check exception (MCE) in a guest address space, KVM causes a guest exit to enable QEMU to build and pass the error to the guest in the PAPR defined rtas error log format.
This patch builds the rtas error log, copies it to the rtas_addr and then invokes the guest registered machine check handler. The handler in the guest takes suitable action(s) depending on the type and criticality of the error. For example, if an error is unrecoverable memory corruption in an application inside the guest, then the guest kernel sends a SIGBUS to the application. For recoverable errors, the guest performs recovery actions and logs the error.
--- hw/ppc/spapr_events.c | 220 ++++++++++++++++++++++++++++++++++++++++- hw/ppc/spapr_rtas.c | 26 +++++ include/hw/ppc/spapr.h | 6 +- target/ppc/kvm.c | 4 +- 4 files changed, 253 insertions(+), 3 deletions(-)
hw/ppc/spapr_events.c +219 -1
@@ -214,6 +214,104 @@ 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,
@@ -622,7 +720,125 @@ void spapr_hotplug_req_remove_by_count_indexed(SpaprDrcType drc_type, RTAS_LOG_V6_HP_ACTION_REMOVE, drc_type, &drc_id); } -void spapr_mce_req_event (PowerPCCPU *cpu) +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);
@@ -656,6 +872,8 @@ void spapr_mce_req_event(PowerPCCPU *cpu) } } spapr->mc_status = cpu->vcpu_id; + +spapr_mce_dispatch_elog (cpu, recovered); } static void check_exception(PowerPCCPU *cpu, SpaprMachineState *spapr,
hw/ppc/spapr_rtas.c +26 -0
@@ -477,6 +477,32 @@ void spapr_dt_rtas_tokens(void *fdt, int rtas) } } +hwaddr spapr_get_rtas_addr (void ) +{ +SpaprMachineState *spapr =SPAPR_MACHINE (qdev_get_machine ()); +int rtas_node; +const fdt32_t *rtas_data; +void *fdt = spapr->fdt_blob; + +/* fetch rtas addr from fdt */ + rtas_node =fdt_path_offset (fdt,"/rtas" ); +if (rtas_node <0 ) { +return 0 ; + } + + rtas_data =fdt_getprop (fdt, rtas_node,"linux,rtas-base" ,NULL ); +if (!rtas_data) { +return 0 ; + } + +/* +* We assume that the OS called RTAS instantiate-rtas, but some other +* OS might call RTAS instantiate-rtas-64 instead. This fine as of now +* as SLOF only supports 32-bit variant. +*/ +return (hwaddr )fdt32_to_cpu (*rtas_data); +} +static void core_rtas_register_types (void ) { spapr_rtas_register(RTAS_DISPLAY_CHARACTER, "display-character",
include/hw/ppc/spapr.h +5 -1
@@ -724,6 +724,9 @@ void spapr_load_rtas(SpaprMachineState *spapr, void *fdt, hwaddr addr);#define RTAS_ERROR_LOG_MAX 2048 +/* Offset from rtas-base where error log is placed */ +#define RTAS_ERROR_LOG_OFFSET 0x30 +#define RTAS_EVENT_SCAN_RATE 1/* This helper should be used to encode interrupt specifiers when the related
@@ -812,7 +815,7 @@ void spapr_clear_pending_events(SpaprMachineState *spapr);int spapr_max_server_number (SpaprMachineState *spapr);void spapr_store_hpte (PowerPCCPU *cpu,hwaddr ptex,uint64_t pte0,uint64_t pte1); -void spapr_mce_req_event (PowerPCCPU *cpu); +void spapr_mce_req_event (PowerPCCPU *cpu,bool recovered);/* DRC callbacks. */ void spapr_core_release (DeviceState *dev);
@@ -903,4 +906,5 @@ void spapr_check_pagesize(SpaprMachineState *spapr, hwaddr pagesize,#define SPAPR_OV5_XIVE_BOTH 0x80/* Only to advertise on the platform */ void spapr_set_all_lpcrs (target_ulong value,target_ulong mask); +hwaddr spapr_get_rtas_addr (void );#endif /* HW_SPAPR_H */
target/ppc/kvm.c +3 -1
@@ -2805,9 +2805,11 @@ int kvm_arch_msi_data_to_gsi(uint32_t data)int kvm_handle_nmi (PowerPCCPU *cpu,struct kvm_run *run) { +bool recovered = run->flags &KVM_RUN_PPC_NMI_DISP_FULLY_RECOV ; +cpu_synchronize_state (CPU (cpu)); -spapr_mce_req_event (cpu); +spapr_mce_req_event (cpu, recovered);return 0 ; }
Signature · 1 line
2.17.2
PATCH v17 3/7 target/ppc: Handle NMI guest exit
In reply to Ganesh GoudarFrom: Aravinda Prasad <[email protected]>
Memory error such as bit flips that cannot be corrected by hardware are passed on to the kernel for handling. If the memory address in error belongs to guest then the guest kernel is responsible for taking suitable action. Patch [1] enhances KVM to exit guest with exit reason set to KVM_EXIT_NMI in such cases. This patch handles KVM_EXIT_NMI exit.
[1] https://www.spinics.net/lists/kvm-ppc/msg12637.html
(e20bbd3d and related commits)
--- hw/ppc/spapr.c | 8 ++++++++ hw/ppc/spapr_events.c | 37 +++++++++++++++++++++++++++++++++++++ include/hw/ppc/spapr.h | 10 ++++++++++ target/ppc/kvm.c | 14 ++++++++++++++ target/ppc/kvm_ppc.h | 2 ++ target/ppc/trace-events | 1 + 6 files changed, 72 insertions(+)
hw/ppc/spapr.c +8 -0
@@ -1745,6 +1745,12 @@ static void spapr_machine_reset(MachineState *machine) first_ppc_cpu->env.gpr[5 ] =0 ; spapr->cas_reboot = false; + + spapr->mc_status =-1 ; + spapr->guest_machine_check_addr =-1 ; + +/* Signal all vCPUs waiting on this condition */ +qemu_cond_broadcast (&spapr->mc_delivery_cond); }static void spapr_create_nvram (SpaprMachineState *spapr)
@@ -3044,6 +3050,8 @@ static void spapr_machine_init(MachineState *machine)kvmppc_spapr_enable_inkernel_multitce (); } + +qemu_cond_init (&spapr->mc_delivery_cond); }static int spapr_kvm_type (MachineState *machine,const char *vm_type)
hw/ppc/spapr_events.c +37 -0
@@ -40,6 +40,7 @@#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>
@@ -621,6 +622,42 @@ void spapr_hotplug_req_remove_by_count_indexed(SpaprDrcType drc_type, RTAS_LOG_V6_HP_ACTION_REMOVE, drc_type, &drc_id); } +void spapr_mce_req_event (PowerPCCPU *cpu) +{ +SpaprMachineState *spapr =SPAPR_MACHINE (qdev_get_machine ()); +CPUState *cs =CPU (cpu); + +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 ; + } + } + spapr->mc_status = cpu->vcpu_id; +} + static void check_exception(PowerPCCPU *cpu, SpaprMachineState *spapr, uint32_t token, uint32_t nargs, target_ulong args,
include/hw/ppc/spapr.h +10 -0
@@ -190,6 +190,15 @@ 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; +QemuCond mc_delivery_cond; +/*< public >*/ char *kvm_type;char *host_model;
@@ -803,6 +812,7 @@ void spapr_clear_pending_events(SpaprMachineState *spapr);int spapr_max_server_number (SpaprMachineState *spapr);void spapr_store_hpte (PowerPCCPU *cpu,hwaddr ptex,uint64_t pte0,uint64_t pte1); +void spapr_mce_req_event (PowerPCCPU *cpu);/* DRC callbacks. */ void spapr_core_release (DeviceState *dev);
target/ppc/kvm.c +14 -0
@@ -1708,6 +1708,11 @@ int kvm_arch_handle_exit(CPUState *cs, struct kvm_run *run) ret =0 ;break ; +case KVM_EXIT_NMI : +trace_kvm_handle_nmi_exception (); + ret =kvm_handle_nmi (cpu, run); +break ; +default :fprintf (stderr,"KVM: unknown exit reason %d\n" , run->exit_reason); ret =-1 ;
@@ -2798,6 +2803,15 @@ int kvm_arch_msi_data_to_gsi(uint32_t data)return data &0xffff ; } +int kvm_handle_nmi (PowerPCCPU *cpu,struct kvm_run *run) +{ +cpu_synchronize_state (CPU (cpu)); + +spapr_mce_req_event (cpu); + +return 0 ; +} +int kvmppc_enable_hwrng (void ) {if (!kvm_enabled () || !kvm_check_extension (kvm_state,KVM_CAP_PPC_HWRNG )) {
target/ppc/kvm_ppc.h +2 -0
@@ -83,6 +83,8 @@ void kvm_check_mmu(PowerPCCPU *cpu, Error **errp);void kvmppc_set_reg_ppc_online (PowerPCCPU *cpu,unsigned int online);void kvmppc_set_reg_tb_offset (PowerPCCPU *cpu,int64_t tb_offset); +int kvm_handle_nmi (PowerPCCPU *cpu,struct kvm_run *run); +#else static inline uint32_t kvmppc_get_tbfreq (void )
target/ppc/trace-events +1 -0
@@ -28,3 +28,4 @@ kvm_handle_papr_hcall(void) "handle PAPR hypercall" kvm_handle_epr(void) "handle epr" kvm_handle_watchdog_expiry(void) "handle watchdog expiry" kvm_handle_debug_exception(void) "handle debug exception" +kvm_handle_nmi_exception(void) "handle NMI exception"
Signature · 1 line
2.17.2
PATCH v17 6/7 migration: Include migration support for machine check handling
In reply to Ganesh GoudarFrom: Aravinda Prasad <[email protected]>
This patch includes migration support for machine check handling. Especially this patch blocks VM migration requests until the machine check error handling is complete as these errors are specific to the source hardware and is irrelevant on the target hardware.
--- hw/ppc/spapr.c | 41 +++++++++++++++++++++++++++++++++++++++++ hw/ppc/spapr_events.c | 16 +++++++++++++++- hw/ppc/spapr_rtas.c | 2 ++ include/hw/ppc/spapr.h | 2 ++ 4 files changed, 60 insertions(+), 1 deletion(-)
hw/ppc/spapr.c +41 -0
@@ -46,6 +46,7 @@#include "migration/qemu-file-types.h" #include "migration/global_state.h" #include "migration/register.h" +#include "migration/blocker.h" #include "mmu-hash64.h" #include "mmu-book3s-v3.h" #include "cpu-models.h"
@@ -1751,6 +1752,8 @@ static void spapr_machine_reset(MachineState *machine)/* Signal all vCPUs waiting on this condition */ qemu_cond_broadcast (&spapr->mc_delivery_cond); + +migrate_del_blocker (spapr->fwnmi_migration_blocker); }static void spapr_create_nvram (SpaprMachineState *spapr)
@@ -2041,6 +2044,43 @@ static const VMStateDescription vmstate_spapr_dtb = { }, }; +static bool spapr_fwnmi_needed (void *opaque) +{ +SpaprMachineState *spapr = (SpaprMachineState *)opaque; + +return spapr->guest_machine_check_addr !=-1 ; +} + +static int spapr_fwnmi_pre_save (void *opaque) +{ +SpaprMachineState *spapr = (SpaprMachineState *)opaque; + +/* +* With -only-migratable QEMU option, we cannot block migration. +* Hence check if machine check handling is in progress and print +* a warning message. +*/ +if (spapr->mc_status !=-1 ) { +warn_report ("A machine check is being handled during migration. The" +"handler may run and log hardware error on the destination" ); + } + +return 0 ; +} + +static const VMStateDescription vmstate_spapr_machine_check = { + .name ="spapr_machine_check" , + .version_id =1 , + .minimum_version_id =1 , + .needed = spapr_fwnmi_needed, + .pre_save = spapr_fwnmi_pre_save, + .fields = (VMStateField []) { +VMSTATE_UINT64 (guest_machine_check_addr, SpaprMachineState), +VMSTATE_INT32 (mc_status, SpaprMachineState), +VMSTATE_END_OF_LIST () + }, +}; +static const VMStateDescription vmstate_spapr = { .name ="spapr" , .version_id =3 ,
@@ -2075,6 +2115,7 @@ static const VMStateDescription vmstate_spapr = { &vmstate_spapr_cap_large_decr, &vmstate_spapr_cap_ccf_assist, &vmstate_spapr_cap_fwnmi, + &vmstate_spapr_machine_check, NULL } };
hw/ppc/spapr_events.c +15 -1
@@ -43,6 +43,7 @@#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
@@ -842,6 +843,8 @@ 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 ) {/*
@@ -871,8 +874,19 @@ void spapr_mce_req_event(PowerPCCPU *cpu, bool recovered)return ; } } - spapr->mc_status = cpu->vcpu_id; + 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_err (local_err); + } + + spapr->mc_status = cpu->vcpu_id;spapr_mce_dispatch_elog (cpu, recovered); }
hw/ppc/spapr_rtas.c +2 -0
@@ -50,6 +50,7 @@#include "hw/ppc/fdt.h" #include "target/ppc/mmu-hash64.h" #include "target/ppc/mmu-book3s-v3.h" +#include "migration/blocker.h" static void rtas_display_character(PowerPCCPU *cpu, SpaprMachineState *spapr, uint32_t token, uint32_t nargs,
@@ -446,6 +447,7 @@ static void rtas_ibm_nmi_interlock(PowerPCCPU *cpu,*/ spapr->mc_status =-1 ;qemu_cond_signal (&spapr->mc_delivery_cond); +migrate_del_blocker (spapr->fwnmi_migration_blocker);rtas_st (rets,0 ,RTAS_OUT_SUCCESS ); }
include/hw/ppc/spapr.h +2 -0
@@ -215,6 +215,8 @@ struct SpaprMachineState {unsigned gpu_numa_id;SpaprTpmProxy *tpm_proxy; + +Error *fwnmi_migration_blocker; };#define H_SUCCESS 0
Signature · 1 line
2.17.2
PATCH v17 7/7 ppc: spapr: Activate the FWNMI functionality
In reply to Ganesh GoudarFrom: Aravinda Prasad <[email protected]>
This patch sets the default value of SPAPR_CAP_FWNMI_MCE to SPAPR_CAP_ON for machine type 4.2.
--- hw/ppc/spapr.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
hw/ppc/spapr.c +2 -1
@@ -4484,7 +4484,7 @@ static void spapr_machine_class_init(ObjectClass *oc, void *data) smc->default_caps.caps[SPAPR_CAP_NESTED_KVM_HV ] =SPAPR_CAP_OFF ; smc->default_caps.caps[SPAPR_CAP_LARGE_DECREMENTER ] =SPAPR_CAP_ON ; smc->default_caps.caps[SPAPR_CAP_CCF_ASSIST ] =SPAPR_CAP_OFF ; - smc->default_caps.caps[SPAPR_CAP_FWNMI_MCE ] =SPAPR_CAP_OFF ; + smc->default_caps.caps[SPAPR_CAP_FWNMI_MCE ] =SPAPR_CAP_ON ;spapr_caps_add_properties (smc, &error_abort); smc->irq = &spapr_irq_dual; smc->dr_phb_enabled = true;
@@ -4558,6 +4558,7 @@ static void spapr_machine_4_1_class_options(MachineClass *mc) smc->linux_pci_probe = false;compat_props_add (mc->compat_props, hw_compat_4_1, hw_compat_4_1_len);compat_props_add (mc->compat_props, compat,G_N_ELEMENTS (compat)); + smc->default_caps.caps[SPAPR_CAP_FWNMI_MCE ] =SPAPR_CAP_OFF ; } DEFINE_SPAPR_MACHINE(4_1, "4.1", false);
Signature · 1 line
2.17.2
PATCH v17 1/7 Wrapper function to wait on condition for the main loop mutex
In reply to Ganesh GoudarFrom: Aravinda Prasad <[email protected]>
Introduce a wrapper function to wait on condition for the main loop mutex. This function atomically releases the main loop mutex and causes the calling thread to block on the condition. This wrapper is required because qemu_global_mutex is a static variable.
--- cpus.c | 5 +++++ include/qemu/main-loop.h | 8 ++++++++ 2 files changed, 13 insertions(+)
cpus.c +5 -0
@@ -1897,6 +1897,11 @@ void qemu_mutex_unlock_iothread(void)qemu_mutex_unlock (&qemu_global_mutex); } +void qemu_cond_wait_iothread (QemuCond *cond) +{ +qemu_cond_wait (cond, &qemu_global_mutex); +} +static bool all_vcpus_paused (void ) {CPUState *cpu;
include/qemu/main-loop.h +8 -0
@@ -295,6 +295,14 @@ void qemu_mutex_lock_iothread_impl(const char *file, int line);*/ void qemu_mutex_unlock_iothread (void ); +/* +* qemu_cond_wait_iothread: Wait on condition for the main loop mutex +* +* This function atomically releases the main loop mutex and causes +* the calling thread to block on the condition. +*/ +void qemu_cond_wait_iothread (QemuCond *cond); +/* internal interfaces */ void qemu_fd_register (int fd);
Signature · 1 line
2.17.2
PATCH v17 2/7 ppc: spapr: Introduce FWNMI capability
In reply to Ganesh GoudarFrom: Aravinda Prasad <[email protected]>
Introduce fwnmi an spapr capability and validate it against the kernels existing capability by trying to enable it.
[eliminate cap_ppc_fwnmi, add fwnmi cap to migration state
and reprhase the commit message]
--- hw/ppc/spapr.c | 2 ++ hw/ppc/spapr_caps.c | 29 +++++++++++++++++++++++++++++ include/hw/ppc/spapr.h | 5 ++++- target/ppc/kvm.c | 8 ++++++++ target/ppc/kvm_ppc.h | 6 ++++++ 5 files changed, 49 insertions(+), 1 deletion(-)
hw/ppc/spapr.c +2 -0
@@ -2068,6 +2068,7 @@ static const VMStateDescription vmstate_spapr = { &vmstate_spapr_dtb, &vmstate_spapr_cap_large_decr, &vmstate_spapr_cap_ccf_assist, + &vmstate_spapr_cap_fwnmi, NULL } };
@@ -4434,6 +4435,7 @@ static void spapr_machine_class_init(ObjectClass *oc, void *data) smc->default_caps.caps[SPAPR_CAP_NESTED_KVM_HV ] =SPAPR_CAP_OFF ; smc->default_caps.caps[SPAPR_CAP_LARGE_DECREMENTER ] =SPAPR_CAP_ON ; smc->default_caps.caps[SPAPR_CAP_CCF_ASSIST ] =SPAPR_CAP_OFF ; + smc->default_caps.caps[SPAPR_CAP_FWNMI_MCE ] =SPAPR_CAP_OFF ;spapr_caps_add_properties (smc, &error_abort); smc->irq = &spapr_irq_dual; smc->dr_phb_enabled = true;
hw/ppc/spapr_caps.c +29 -0
@@ -496,6 +496,25 @@ static void cap_ccf_assist_apply(SpaprMachineState *spapr, uint8_t val, } } +static void cap_fwnmi_mce_apply (SpaprMachineState *spapr,uint8_t val, +Error **errp) +{ +if (!val) { +return ;/* Disabled by default */ + } + +if (tcg_enabled ()) { +/* +* TCG support may not be correct in some conditions (e.g., in case +* of software injected faults like duplicate SLBs). +*/ +warn_report ("Firmware Assisted Non-Maskable Interrupts not supported in TCG" ); + }else if (kvm_enabled () && (kvmppc_set_fwnmi () !=0 )) { +error_setg (errp, +"Firmware Assisted Non-Maskable Interrupts not supported by KVM, try cap-fwnmi-mce=off" ); + } +} +SpaprCapabilityInfo capability_table[SPAPR_CAP_NUM ] = { [SPAPR_CAP_HTM ] = { .name ="htm" ,
@@ -595,6 +614,15 @@ SpaprCapabilityInfo capability_table[SPAPR_CAP_NUM] = { .type = "bool", .apply = cap_ccf_assist_apply, }, + [SPAPR_CAP_FWNMI_MCE] = { + .name = "fwnmi-mce", + .description = "Handle fwnmi machine check exceptions", + .index = SPAPR_CAP_FWNMI_MCE, + .get = spapr_cap_get_bool, + .set = spapr_cap_set_bool, + .type = "bool", + .apply = cap_fwnmi_mce_apply, + }, }; static SpaprCapabilities default_caps_with_cpu(SpaprMachineState *spapr,
@@ -734,6 +762,7 @@ SPAPR_CAP_MIG_STATE(hpt_maxpagesize, SPAPR_CAP_HPT_MAXPAGESIZE);SPAPR_CAP_MIG_STATE (nested_kvm_hv,SPAPR_CAP_NESTED_KVM_HV );SPAPR_CAP_MIG_STATE (large_decr,SPAPR_CAP_LARGE_DECREMENTER );SPAPR_CAP_MIG_STATE (ccf_assist,SPAPR_CAP_CCF_ASSIST ); +SPAPR_CAP_MIG_STATE (fwnmi,SPAPR_CAP_FWNMI_MCE );void spapr_caps_init (SpaprMachineState *spapr) {
include/hw/ppc/spapr.h +4 -1
@@ -79,8 +79,10 @@ typedef enum {#define SPAPR_CAP_LARGE_DECREMENTER 0x08/* Count Cache Flush Assist HW Instruction */ #define SPAPR_CAP_CCF_ASSIST 0x09 +/* FWNMI machine check handling */ +#define SPAPR_CAP_FWNMI_MCE 0x0A/* Num Caps */ -#define SPAPR_CAP_NUM (SPAPR_CAP_CCF_ASSIST + 1) +#define SPAPR_CAP_NUM (SPAPR_CAP_FWNMI_MCE + 1)/* * Capability Values
@@ -868,6 +870,7 @@ extern const VMStateDescription vmstate_spapr_cap_hpt_maxpagesize;extern const VMStateDescription vmstate_spapr_cap_nested_kvm_hv;extern const VMStateDescription vmstate_spapr_cap_large_decr;extern const VMStateDescription vmstate_spapr_cap_ccf_assist; +extern const VMStateDescription vmstate_spapr_cap_fwnmi;static inline uint8_t spapr_get_cap (SpaprMachineState *spapr,int cap) {
target/ppc/kvm.c +8 -0
@@ -2060,6 +2060,14 @@ void kvmppc_set_mpic_proxy(PowerPCCPU *cpu, int mpic_proxy) } } +int kvmppc_set_fwnmi (void ) +{ +PowerPCCPU *cpu =POWERPC_CPU (first_cpu); +CPUState *cs =CPU (cpu); + +return kvm_vcpu_enable_cap (cs,KVM_CAP_PPC_FWNMI ,0 ); +} +int kvmppc_smt_threads (void ) {return cap_ppc_smt ? cap_ppc_smt :1 ;
target/ppc/kvm_ppc.h +6 -0
@@ -27,6 +27,7 @@ void kvmppc_enable_h_page_init(void);void kvmppc_set_papr (PowerPCCPU *cpu);int kvmppc_set_compat (PowerPCCPU *cpu,uint32_t compat_pvr);void kvmppc_set_mpic_proxy (PowerPCCPU *cpu,int mpic_proxy); +int kvmppc_set_fwnmi (void );int kvmppc_smt_threads (void );void kvmppc_hint_smt_possible (Error **errp);int kvmppc_set_smt_threads (int smt);
@@ -159,6 +160,11 @@ static inline void kvmppc_set_mpic_proxy(PowerPCCPU *cpu, int mpic_proxy) { } +static inline int kvmppc_set_fwnmi (void ) +{ +return -1 ; +} +static inline int kvmppc_smt_threads (void ) {return 1 ;
Signature · 1 line
2.17.2
PATCH v17 5/7 ppc: spapr: Handle "ibm, nmi-register" and "ibm, nmi-interlock" RTAS calls
In reply to Ganesh GoudarFrom: Aravinda Prasad <[email protected]>
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.
--- hw/ppc/spapr_caps.c | 9 +++++-- hw/ppc/spapr_rtas.c | 57 ++++++++++++++++++++++++++++++++++++++++++ include/hw/ppc/spapr.h | 5 +++- 3 files changed, 68 insertions(+), 3 deletions(-)
hw/ppc/spapr_caps.c +7 -2
@@ -509,9 +509,14 @@ static void cap_fwnmi_mce_apply(SpaprMachineState *spapr, uint8_t val,* of software injected faults like duplicate SLBs). */ warn_report ("Firmware Assisted Non-Maskable Interrupts not supported in TCG" ); - }else if (kvm_enabled () && (kvmppc_set_fwnmi () !=0 )) { -error_setg (errp, + }else if (kvm_enabled ()) { +if (!kvmppc_set_fwnmi ()) { +/* Register ibm,nmi-register and ibm,nmi-interlock RTAS calls */ +spapr_fwnmi_register (); + }else { +error_setg (errp,"Firmware Assisted Non-Maskable Interrupts not supported by KVM, try cap-fwnmi-mce=off" ); + } } }
hw/ppc/spapr_rtas.c +57 -0
69 lines not on this page · raw message
include/hw/ppc/spapr.h +4 -1
@@ -653,8 +653,10 @@ target_ulong spapr_hypercall(PowerPCCPU *cpu, target_ulong opcode,#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_SUSPEND_ME (RTAS_TOKEN_BASE + 0x2A) +#define RTAS_IBM_NMI_REGISTER (RTAS_TOKEN_BASE + 0x2B) +#define RTAS_IBM_NMI_INTERLOCK (RTAS_TOKEN_BASE + 0x2C) -#define RTAS_TOKEN_MAX (RTAS_TOKEN_BASE + 0x2B) +#define RTAS_TOKEN_MAX (RTAS_TOKEN_BASE + 0x2D)/* RTAS ibm,get-system-parameter token values */ #define RTAS_SYSPARM_SPLPAR_CHARACTERISTICS 20
@@ -907,4 +909,5 @@ void spapr_check_pagesize(SpaprMachineState *spapr, hwaddr pagesize,void spapr_set_all_lpcrs (target_ulong value,target_ulong mask);hwaddr spapr_get_rtas_addr (void ); +void spapr_fwnmi_register (void );#endif /* HW_SPAPR_H */
Signature · 1 line
2.17.2
Re: [PATCH v17 4/7] target/ppc: Build rtas error log upon an MCE
In reply to Ganesh GoudarQuoted 15 lines · Ganesh Goudar
From: Aravinda Prasad <[email protected]>
Upon a machine check exception (MCE) in a guest address space, KVM causes a guest exit to enable QEMU to build and pass the error to the guest in the PAPR defined rtas error log format.
This patch builds the rtas error log, copies it to the
rtas_addrand then invokes the guest registered machine check handler. The handler in the guest takes suitable action(s) depending on the type and criticality of the error. For example, if an error is unrecoverable memory corruption in an application inside the guest, then the guest kernel sends a SIGBUS to the application. For recoverable errors, the guest performs recovery actions and logs the error.
Quoted 1 line
[Assume SLOF has allocated enough room for rtas error log]
Is that correct with the SLOF image currently included in qemu?
Apart from that detail,
Quoted 340 lines
Signed-off-by Ganesh Goudar <[email protected]>Signed-off-by Aravinda Prasad <[email protected]>--- hw/ppc/spapr_events.c | 220 ++++++++++++++++++++++++++++++++++++++++- hw/ppc/spapr_rtas.c | 26 +++++ include/hw/ppc/spapr.h | 6 +- target/ppc/kvm.c | 4 +- 4 files changed, 253 insertions(+), 3 deletions(-)hw/ppc/spapr_events.c +219
-1@@ -214,6 +214,104 @@ 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,@@ -622,7 +720,125 @@ void spapr_hotplug_req_remove_by_count_indexed(SpaprDrcType drc_type, RTAS_LOG_V6_HP_ACTION_REMOVE, drc_type, &drc_id); } -void spapr_mce_req_event (PowerPCCPU *cpu) +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);@@ -656,6 +872,8 @@ void spapr_mce_req_event(PowerPCCPU *cpu) } } spapr->mc_status = cpu->vcpu_id; + +spapr_mce_dispatch_elog (cpu, recovered); } static void check_exception(PowerPCCPU *cpu, SpaprMachineState *spapr,hw/ppc/spapr_rtas.c +26
-0@@ -477,6 +477,32 @@ void spapr_dt_rtas_tokens(void *fdt, int rtas) } } +hwaddr spapr_get_rtas_addr (void ) +{ +SpaprMachineState *spapr =SPAPR_MACHINE (qdev_get_machine ()); +int rtas_node; +const fdt32_t *rtas_data; +void *fdt = spapr->fdt_blob; + +/* fetch rtas addr from fdt */ + rtas_node =fdt_path_offset (fdt,"/rtas" ); +if (rtas_node <0 ) { +return 0 ; + } + + rtas_data =fdt_getprop (fdt, rtas_node,"linux,rtas-base" ,NULL ); +if (!rtas_data) { +return 0 ; + } + +/* +* We assume that the OS called RTAS instantiate-rtas, but some other +* OS might call RTAS instantiate-rtas-64 instead. This fine as of now +* as SLOF only supports 32-bit variant. +*/ +return (hwaddr )fdt32_to_cpu (*rtas_data); +} +static void core_rtas_register_types (void ) { spapr_rtas_register(RTAS_DISPLAY_CHARACTER, "display-character",include/hw/ppc/spapr.h +5
-1@@ -724,6 +724,9 @@ void spapr_load_rtas(SpaprMachineState *spapr, void *fdt, hwaddr addr);#define RTAS_ERROR_LOG_MAX 2048 +/* Offset from rtas-base where error log is placed */ +#define RTAS_ERROR_LOG_OFFSET 0x30 +#define RTAS_EVENT_SCAN_RATE 1/* This helper should be used to encode interrupt specifiers when the related @@ -812,7 +815,7 @@ void spapr_clear_pending_events(SpaprMachineState *spapr);int spapr_max_server_number (SpaprMachineState *spapr);void spapr_store_hpte (PowerPCCPU *cpu,hwaddr ptex,uint64_t pte0,uint64_t pte1); -void spapr_mce_req_event (PowerPCCPU *cpu); +void spapr_mce_req_event (PowerPCCPU *cpu,bool recovered);/* DRC callbacks. */ void spapr_core_release (DeviceState *dev);@@ -903,4 +906,5 @@ void spapr_check_pagesize(SpaprMachineState *spapr, hwaddr pagesize,#define SPAPR_OV5_XIVE_BOTH 0x80/* Only to advertise on the platform */ void spapr_set_all_lpcrs (target_ulong value,target_ulong mask); +hwaddr spapr_get_rtas_addr (void );#endif /* HW_SPAPR_H */ target/ppc/kvm.c +3
-1@@ -2805,9 +2805,11 @@ int kvm_arch_msi_data_to_gsi(uint32_t data)int kvm_handle_nmi (PowerPCCPU *cpu,struct kvm_run *run) { +bool recovered = run->flags &KVM_RUN_PPC_NMI_DISP_FULLY_RECOV ; +cpu_synchronize_state (CPU (cpu)); -spapr_mce_req_event (cpu); +spapr_mce_req_event (cpu, recovered);return 0 ; }
Signature · 4 lines
David Gibson | I'll have my music baroque, and my code david AT gibson.dropbear.id.au | minimalist, thank you. NOT _the_ _other_ | _way_ _around_! http://www.ozlabs.org/~dgibson
Re: [PATCH v17 4/7] target/ppc: Build rtas error log upon an MCE
Quoted 16 lines · David Gibson
Quoted 15 lines · Ganesh Goudar
From: Aravinda Prasad <[email protected]>
Upon a machine check exception (MCE) in a guest address space, KVM causes a guest exit to enable QEMU to build and pass the error to the guest in the PAPR defined rtas error log format.
This patch builds the rtas error log, copies it to the
rtas_addrand then invokes the guest registered machine check handler. The handler in the guest takes suitable action(s) depending on the type and criticality of the error. For example, if an error is unrecoverable memory corruption in an application inside the guest, then the guest kernel sends a SIGBUS to the application. For recoverable errors, the guest performs recovery actions and logs the error.
Quoted 2 lines
Quoted 1 line
[Assume SLOF has allocated enough room for rtas error log]
Is that correct with the SLOF image currently included in qemu?
Yes
Quoted 344 lines
Apart from that detail,
Reviewed-by David Gibson <[email protected]>Quoted 339 lines
Signed-off-by Ganesh Goudar <[email protected]>Signed-off-by Aravinda Prasad <[email protected]>--- hw/ppc/spapr_events.c | 220 ++++++++++++++++++++++++++++++++++++++++- hw/ppc/spapr_rtas.c | 26 +++++ include/hw/ppc/spapr.h | 6 +- target/ppc/kvm.c | 4 +- 4 files changed, 253 insertions(+), 3 deletions(-)hw/ppc/spapr_events.c +219
-1@@ -214,6 +214,104 @@ 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,@@ -622,7 +720,125 @@ void spapr_hotplug_req_remove_by_count_indexed(SpaprDrcType drc_type, RTAS_LOG_V6_HP_ACTION_REMOVE, drc_type, &drc_id); } -void spapr_mce_req_event (PowerPCCPU *cpu) +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);@@ -656,6 +872,8 @@ void spapr_mce_req_event(PowerPCCPU *cpu) } } spapr->mc_status = cpu->vcpu_id; + +spapr_mce_dispatch_elog (cpu, recovered); } static void check_exception(PowerPCCPU *cpu, SpaprMachineState *spapr,hw/ppc/spapr_rtas.c +26
-0@@ -477,6 +477,32 @@ void spapr_dt_rtas_tokens(void *fdt, int rtas) } } +hwaddr spapr_get_rtas_addr (void ) +{ +SpaprMachineState *spapr =SPAPR_MACHINE (qdev_get_machine ()); +int rtas_node; +const fdt32_t *rtas_data; +void *fdt = spapr->fdt_blob; + +/* fetch rtas addr from fdt */ + rtas_node =fdt_path_offset (fdt,"/rtas" ); +if (rtas_node <0 ) { +return 0 ; + } + + rtas_data =fdt_getprop (fdt, rtas_node,"linux,rtas-base" ,NULL ); +if (!rtas_data) { +return 0 ; + } + +/* +* We assume that the OS called RTAS instantiate-rtas, but some other +* OS might call RTAS instantiate-rtas-64 instead. This fine as of now +* as SLOF only supports 32-bit variant. +*/ +return (hwaddr )fdt32_to_cpu (*rtas_data); +} +static void core_rtas_register_types (void ) { spapr_rtas_register(RTAS_DISPLAY_CHARACTER, "display-character",include/hw/ppc/spapr.h +5
-1@@ -724,6 +724,9 @@ void spapr_load_rtas(SpaprMachineState *spapr, void *fdt, hwaddr addr);#define RTAS_ERROR_LOG_MAX 2048 +/* Offset from rtas-base where error log is placed */ +#define RTAS_ERROR_LOG_OFFSET 0x30 +#define RTAS_EVENT_SCAN_RATE 1/* This helper should be used to encode interrupt specifiers when the related @@ -812,7 +815,7 @@ void spapr_clear_pending_events(SpaprMachineState *spapr);int spapr_max_server_number (SpaprMachineState *spapr);void spapr_store_hpte (PowerPCCPU *cpu,hwaddr ptex,uint64_t pte0,uint64_t pte1); -void spapr_mce_req_event (PowerPCCPU *cpu); +void spapr_mce_req_event (PowerPCCPU *cpu,bool recovered);/* DRC callbacks. */ void spapr_core_release (DeviceState *dev);@@ -903,4 +906,5 @@ void spapr_check_pagesize(SpaprMachineState *spapr, hwaddr pagesize,#define SPAPR_OV5_XIVE_BOTH 0x80/* Only to advertise on the platform */ void spapr_set_all_lpcrs (target_ulong value,target_ulong mask); +hwaddr spapr_get_rtas_addr (void );#endif /* HW_SPAPR_H */ target/ppc/kvm.c +3
-1@@ -2805,9 +2805,11 @@ int kvm_arch_msi_data_to_gsi(uint32_t data)int kvm_handle_nmi (PowerPCCPU *cpu,struct kvm_run *run) { +bool recovered = run->flags &KVM_RUN_PPC_NMI_DISP_FULLY_RECOV ; +cpu_synchronize_state (CPU (cpu)); -spapr_mce_req_event (cpu); +spapr_mce_req_event (cpu, recovered);return 0 ; }
Re: [PATCH v17 4/7] target/ppc: Build rtas error log upon an MCE
Quoted 18 lines · Ganesh
Quoted 16 lines · David Gibson
Quoted 15 lines · Ganesh Goudar
From: Aravinda Prasad <[email protected]>
Upon a machine check exception (MCE) in a guest address space, KVM causes a guest exit to enable QEMU to build and pass the error to the guest in the PAPR defined rtas error log format.
This patch builds the rtas error log, copies it to the
rtas_addrand then invokes the guest registered machine check handler. The handler in the guest takes suitable action(s) depending on the type and criticality of the error. For example, if an error is unrecoverable memory corruption in an application inside the guest, then the guest kernel sends a SIGBUS to the application. For recoverable errors, the guest performs recovery actions and logs the error.
Quoted 7 lines
Quoted 2 lines
Quoted 1 line
[Assume SLOF has allocated enough room for rtas error log]
Is that correct with the SLOF image currently included in qemu?
Yes
Quoted 4 lines
Apart from that detail,
Reviewed-by David Gibson <[email protected]>
Hi David, Please see if this patch series can be merged to 4.2.
Quoted 346 lines
Quoted 346 lines
Quoted 346 lines
Signed-off-by Ganesh Goudar <[email protected]>Signed-off-by Aravinda Prasad <[email protected]>---
hw/ppc/spapr_events.c | 220
++++++++++++++++++++++++++++++++++++++++-
hw/ppc/spapr_rtas.c | 26 +++++
include/hw/ppc/spapr.h| 6 +-
target/ppc/kvm.c | 4 +-4 files changed, 253 insertions(+), 3 deletions(-)hw/ppc/spapr_events.c +90
-0@@ -214,6 +214,104 @@ 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, /* BeforePARITY */
+RTAS_LOG_INITIATOR_CPU,RTAS_LOG_SEVERITY_ERROR_SYNC, },hw/ppc/spapr_events.c +6
-0+{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,hw/ppc/spapr_events.c +25
-0@@ -622,7 +720,125 @@ void spapr_hotplug_req_remove_by_count_indexed(SpaprDrcType drc_type, RTAS_LOG_V6_HP_ACTION_REMOVE, drc_type, &drc_id); } -void spapr_mce_req_event(PowerPCCPU *cpu) +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]);
+ }hw/ppc/spapr_events.c +15
-0+ + 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);
+ }hw/ppc/spapr_events.c +46
-0+ + 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;hw/ppc/spapr_events.c +11
-0+ + /* 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));hw/ppc/spapr_events.c +9
-0+ + 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);hw/ppc/spapr_events.c +2
-0@@ -656,6 +872,8 @@ void spapr_mce_req_event(PowerPCCPU *cpu) } } spapr->mc_status = cpu->vcpu_id; + + spapr_mce_dispatch_elog(cpu, recovered); } static void check_exception(PowerPCCPU *cpu, SpaprMachineState *spapr,hw/ppc/spapr_rtas.c +19
-0@@ -477,6 +477,32 @@ void spapr_dt_rtas_tokens(void *fdt, int rtas) } } +hwaddr spapr_get_rtas_addr(void) +{ + SpaprMachineState *spapr = SPAPR_MACHINE(qdev_get_machine()); + int rtas_node; + const fdt32_t *rtas_data; + void *fdt = spapr->fdt_blob; + + /* fetch rtas addr from fdt */ + rtas_node = fdt_path_offset(fdt, "/rtas"); + if (rtas_node < 0) { + return 0; + } + + rtas_data = fdt_getprop(fdt, rtas_node, "linux,rtas-base", NULL); + if (!rtas_data) { + return 0; + } + + /* +* We assume that the OS called RTAS instantiate-rtas, but some other
+ * OS might call RTAS instantiate-rtas-64 instead. This fine as of now
+ * as SLOF only supports 32-bit variant.
+ */
+ return (hwaddr)fdt32_to_cpu(*rtas_data);hw/ppc/spapr_rtas.c +2
-0+} +static void
core_rtas_register_types(void)
{
spapr_rtas_register(RTAS_DISPLAY_CHARACTER, "display-character",include/hw/ppc/spapr.h +0
-0@@ -724,6 +724,9 @@ void spapr_load_rtas(SpaprMachineState *spapr, void *fdt, hwaddr addr); #define RTAS_ERROR_LOG_MAX 2048+/* Offset from rtas-base where error log is placed */
include/hw/ppc/spapr.h +2
-0+#define RTAS_ERROR_LOG_OFFSET 0x30 +#define RTAS_EVENT_SCAN_RATE 1
/* This helper should be used to encode interrupt specifiers when the relatedinclude/hw/ppc/spapr.h +2
-1@@ -812,7 +815,7 @@ voidspapr_clear_pending_events (SpaprMachineState *spapr); int spapr_max_server_number(SpaprMachineState *spapr); void spapr_store_hpte(PowerPCCPU *cpu, hwaddr ptex, uint64_t pte0, uint64_t pte1); -void spapr_mce_req_event (PowerPCCPU *cpu); +void spapr_mce_req_event (PowerPCCPU *cpu,bool recovered); /* DRC callbacks. */ void spapr_core_release(DeviceState *dev);@@ -903,4 +906,5 @@ void spapr_check_pagesize(SpaprMachineState *spapr, hwaddr pagesize, #define SPAPR_OV5_XIVE_BOTH 0x80 /* Only to advertise on the platform */ void spapr_set_all_lpcrs(target_ulong value, target_ulong mask); +hwaddr spapr_get_rtas_addr (void ); #endif /* HW_SPAPR_H */target/ppc/kvm.c +3
-0@@ -2805,9 +2805,11 @@ int kvm_arch_msi_data_to_gsi(uint32_t data) int kvm_handle_nmi(PowerPCCPU *cpu, struct kvm_run *run) { + bool recovered = run->flags & KVM_RUN_PPC_NMI_DISP_FULLY_RECOV; + cpu_synchronize_state(CPU(cpu)); - spapr_mce_req_event(cpu); + spapr_mce_req_event(cpu, recovered); return 0; }
Re: [PATCH v17 4/7] target/ppc: Build rtas error log upon an MCE
Quoted 20 lines · Ganesh
Quoted 18 lines · Ganesh
Quoted 16 lines · David Gibson
Quoted 15 lines · Ganesh Goudar
From: Aravinda Prasad <[email protected]>
Upon a machine check exception (MCE) in a guest address space, KVM causes a guest exit to enable QEMU to build and pass the error to the guest in the PAPR defined rtas error log format.
This patch builds the rtas error log, copies it to the
rtas_addrand then invokes the guest registered machine check handler. The handler in the guest takes suitable action(s) depending on the type and criticality of the error. For example, if an error is unrecoverable memory corruption in an application inside the guest, then the guest kernel sends a SIGBUS to the application. For recoverable errors, the guest performs recovery actions and logs the error.
Quoted 8 lines
Quoted 7 lines
Quoted 2 lines
Quoted 1 line
[Assume SLOF has allocated enough room for rtas error log]
Is that correct with the SLOF image currently included in qemu?
Yes
Quoted 4 lines
Apart from that detail,
Reviewed-by David Gibson <[email protected]>Hi David, Please see if this patch series can be merged to 4.2.
Sorry, we're much too late for 4.2 now. I am hoping to merge it for 5.0, the next release.
Quoted 351 lines
Quoted 350 lines
Quoted 350 lines
Quoted 350 lines
Signed-off-by Ganesh Goudar <[email protected]>Signed-off-by Aravinda Prasad <[email protected]>---
hw/ppc/spapr_events.c | 220
++++++++++++++++++++++++++++++++++++++++-
hw/ppc/spapr_rtas.c | 26 +++++
include/hw/ppc/spapr.h| 6 +-
target/ppc/kvm.c | 4 +-4 files changed, 253 insertions(+), 3 deletions(-)hw/ppc/spapr_events.c +90
-0@@ -214,6 +214,104 @@ 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, },hw/ppc/spapr_events.c +6
-0+{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,hw/ppc/spapr_events.c +23
-0@@ -622,7 +720,125 @@ void spapr_hotplug_req_remove_by_count_indexed(SpaprDrcType drc_type, RTAS_LOG_V6_HP_ACTION_REMOVE, drc_type, &drc_id); } -void spapr_mce_req_event(PowerPCCPU *cpu) +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]);
+ }hw/ppc/spapr_events.c +15
-0+ + 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);
+ }hw/ppc/spapr_events.c +46
-0+ + 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;hw/ppc/spapr_events.c +11
-0+ + /* 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));hw/ppc/spapr_events.c +9
-0+ + 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);hw/ppc/spapr_events.c +2
-0@@ -656,6 +872,8 @@ void spapr_mce_req_event(PowerPCCPU *cpu) } } spapr->mc_status = cpu->vcpu_id; + + spapr_mce_dispatch_elog(cpu, recovered); } static void check_exception(PowerPCCPU *cpu, SpaprMachineState *spapr,hw/ppc/spapr_rtas.c +19
-0@@ -477,6 +477,32 @@ void spapr_dt_rtas_tokens(void *fdt, int rtas) } } +hwaddr spapr_get_rtas_addr(void) +{ + SpaprMachineState *spapr = SPAPR_MACHINE(qdev_get_machine()); + int rtas_node; + const fdt32_t *rtas_data; + void *fdt = spapr->fdt_blob; + + /* fetch rtas addr from fdt */ + rtas_node = fdt_path_offset(fdt, "/rtas"); + if (rtas_node < 0) { + return 0; + } + + rtas_data = fdt_getprop(fdt, rtas_node, "linux,rtas-base", NULL); + if (!rtas_data) { + return 0; + } + + /* +* We assume that the OS called RTAS instantiate-rtas, but some other
+ * OS might call RTAS instantiate-rtas-64 instead. This fine as of now
+ * as SLOF only supports 32-bit variant.
+ */
+ return (hwaddr)fdt32_to_cpu(*rtas_data);hw/ppc/spapr_rtas.c +2
-0+} +static void
core_rtas_register_types(void)
{
spapr_rtas_register(RTAS_DISPLAY_CHARACTER, "display-character",include/hw/ppc/spapr.h +0
-0@@ -724,6 +724,9 @@ void spapr_load_rtas(SpaprMachineState *spapr, void *fdt, hwaddr addr); #define RTAS_ERROR_LOG_MAX 2048+/* Offset from rtas-base where error log is placed */
include/hw/ppc/spapr.h +2
-0+#define RTAS_ERROR_LOG_OFFSET 0x30 +#define RTAS_EVENT_SCAN_RATE 1
/* This helper should be used to encode interrupt specifiers when the relatedinclude/hw/ppc/spapr.h +1
-1@@ -812,7 +815,7 @@ voidspapr_clear_pending_events (SpaprMachineState *spapr); int spapr_max_server_number(SpaprMachineState *spapr); void spapr_store_hpte(PowerPCCPU *cpu, hwaddr ptex, uint64_t pte0, uint64_t pte1); -void spapr_mce_req_event (PowerPCCPU *cpu); +void spapr_mce_req_event (PowerPCCPU *cpu,bool recovered); /* DRC callbacks. */ void spapr_core_release(DeviceState *dev);@@ -903,4 +906,5 @@ void spapr_check_pagesize(SpaprMachineState *spapr, hwaddr pagesize, #define SPAPR_OV5_XIVE_BOTH 0x80 /* Only to advertise onthe platform */
voidspapr_set_all_lpcrs(target_ulong value, target_ulong mask); +hwaddrspapr_get_rtas_addr(void);
#endif /*HW_SPAPR_H*/target/ppc/kvm.c +3
-0@@ -2805,9 +2805,11 @@ int kvm_arch_msi_data_to_gsi(uint32_t data) int kvm_handle_nmi(PowerPCCPU *cpu, struct kvm_run *run) { + bool recovered = run->flags & KVM_RUN_PPC_NMI_DISP_FULLY_RECOV; + cpu_synchronize_state(CPU(cpu)); - spapr_mce_req_event(cpu); + spapr_mce_req_event(cpu, recovered); return 0; }
Signature · 4 lines
David Gibson | I'll have my music baroque, and my code david AT gibson.dropbear.id.au | minimalist, thank you. NOT _the_ _other_ | _way_ _around_! http://www.ozlabs.org/~dgibson
Re: [PATCH v17 6/7] migration: Include migration support for machine check handling
In reply to Ganesh GoudarQuoted 49 lines · Ganesh Goudar
From: Aravinda Prasad <[email protected]>
This patch includes migration support for machine check handling. Especially this patch blocks VM migration requests until the machine check error handling is complete as these errors are specific to the source hardware and is irrelevant on the target hardware.
[Do not set FWNMI cap in post_load, now its done in .apply hook]Signed-off-by Ganesh Goudar <[email protected]>Signed-off-by Aravinda Prasad <[email protected]>--- hw/ppc/spapr.c | 41 +++++++++++++++++++++++++++++++++++++++++ hw/ppc/spapr_events.c | 16 +++++++++++++++- hw/ppc/spapr_rtas.c | 2 ++ include/hw/ppc/spapr.h | 2 ++ 4 files changed, 60 insertions(+), 1 deletion(-)hw/ppc/spapr.c +9
-0@@ -46,6 +46,7 @@#include "migration/qemu-file-types.h" #include "migration/global_state.h" #include "migration/register.h" +#include "migration/blocker.h" #include "mmu-hash64.h" #include "mmu-book3s-v3.h" #include "cpu-models.h" @@ -1751,6 +1752,8 @@ static void spapr_machine_reset(MachineState *machine)/* Signal all vCPUs waiting on this condition */ qemu_cond_broadcast (&spapr->mc_delivery_cond); + +migrate_del_blocker (spapr->fwnmi_migration_blocker); }static void spapr_create_nvram (SpaprMachineState *spapr)@@ -2041,6 +2044,43 @@ static const VMStateDescription vmstate_spapr_dtb = { }, }; +static bool spapr_fwnmi_needed (void *opaque) +{ +SpaprMachineState *spapr = (SpaprMachineState *)opaque; + +return spapr->guest_machine_check_addr !=-1 ; +}
hw/ppc/spapr.c static const VMStateDescription vmstate_spapr_dtb = { · line 2062
Quoted 10 lines
hw/ppc/spapr.c +10
-0+ +static int spapr_fwnmi_pre_save (void *opaque) +{ +SpaprMachineState *spapr = (SpaprMachineState *)opaque; + +/* +* With -only-migratable QEMU option, we cannot block migration. +* Hence check if machine check handling is in progress and print +* a warning message. +*/
IIUC the logic below this could also occur in the case where the fwnmi event occurs after a migration has started, but before it completes, not just with -only-migratable. Is that correct?
Quoted 58 lines
hw/ppc/spapr.c +22
-0+if (spapr->mc_status !=-1 ) { +warn_report ("A machine check is being handled during migration. The" +"handler may run and log hardware error on the destination" ); + } + +return 0 ; +} + +static const VMStateDescription vmstate_spapr_machine_check = { + .name ="spapr_machine_check" , + .version_id =1 , + .minimum_version_id =1 , + .needed = spapr_fwnmi_needed, + .pre_save = spapr_fwnmi_pre_save, + .fields = (VMStateField []) { +VMSTATE_UINT64 (guest_machine_check_addr, SpaprMachineState), +VMSTATE_INT32 (mc_status, SpaprMachineState), +VMSTATE_END_OF_LIST () + }, +}; +static const VMStateDescription vmstate_spapr = { .name ="spapr" , .version_id =3 ,@@ -2075,6 +2115,7 @@ static const VMStateDescription vmstate_spapr = { &vmstate_spapr_cap_large_decr, &vmstate_spapr_cap_ccf_assist, &vmstate_spapr_cap_fwnmi, + &vmstate_spapr_machine_check, NULL } };hw/ppc/spapr_events.c +3
-1@@ -43,6 +43,7 @@#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@@ -842,6 +843,8 @@ 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 ) {/* @@ -871,8 +874,19 @@ void spapr_mce_req_event(PowerPCCPU *cpu, bool recovered)return ; } } - spapr->mc_status = cpu->vcpu_id;
hw/ppc/spapr_events.c void spapr_mce_req_event(PowerPCCPU *cpu, bool recovered) · line 886
Quoted 10 lines
hw/ppc/spapr_events.c +9
-0+ 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_err (local_err);
I suspect the error message in local_err won't be particularly meaningful on its own. Perhaps you need to add a prefix to clarify that the problem is you've received a fwnmi after migration has commenced?
Quoted 19 lines
hw/ppc/spapr_events.c +3
-0+ } + + spapr->mc_status = cpu->vcpu_id;spapr_mce_dispatch_elog (cpu, recovered); }hw/ppc/spapr_rtas.c +1
-0@@ -50,6 +50,7 @@#include "hw/ppc/fdt.h" #include "target/ppc/mmu-hash64.h" #include "target/ppc/mmu-book3s-v3.h" +#include "migration/blocker.h" static void rtas_display_character(PowerPCCPU *cpu, SpaprMachineState *spapr, uint32_t token, uint32_t nargs,
hw/ppc/spapr_rtas.c static void rtas_ibm_nmi_interlock(PowerPCCPU *cpu, · line 450
Quoted 4 lines
hw/ppc/spapr_rtas.c +1
-0@@ -446,6 +447,7 @@ static void rtas_ibm_nmi_interlock(PowerPCCPU *cpu,*/ spapr->mc_status =-1 ;qemu_cond_signal (&spapr->mc_delivery_cond); +migrate_del_blocker (spapr->fwnmi_migration_blocker);
Oh... damn. I suggested using a static fwnmi_migration_blocker instance, but I just realized there's a problem with it.
If we do receive multiple fwnmi events on different cpus at roughly the same time, this will break: I think we'll try to add the same migration blocker instance multiple times, which won't be good. Even if that doesn't do anything *too* bad, then we'll unblock the migration on the first interlock, rather than waiting for all pending fwnmi events to complete.
Quoted 16 lines
hw/ppc/spapr_rtas.c +0
-0rtas_st (rets,0 ,RTAS_OUT_SUCCESS ); }include/hw/ppc/spapr.h +2
-0@@ -215,6 +215,8 @@ struct SpaprMachineState {unsigned gpu_numa_id;SpaprTpmProxy *tpm_proxy; + +Error *fwnmi_migration_blocker; };#define H_SUCCESS 0
Signature · 4 lines
David Gibson | I'll have my music baroque, and my code david AT gibson.dropbear.id.au | minimalist, thank you. NOT _the_ _other_ | _way_ _around_! http://www.ozlabs.org/~dgibson
Re: [PATCH v17 5/7] ppc: spapr: Handle "ibm,nmi-register" and "ibm,nmi-interlock" RTAS calls
In reply to Ganesh GoudarQuoted 18 lines · Ganesh Goudar
From: Aravinda Prasad <[email protected]>
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.
Quoted 1 line
[Move fwnmi registeration to .apply hook]
s/registeration/registration/
Quoted 13 lines
Signed-off-by Ganesh Goudar <[email protected]>Signed-off-by Aravinda Prasad <[email protected]>--- hw/ppc/spapr_caps.c | 9 +++++-- hw/ppc/spapr_rtas.c | 57 ++++++++++++++++++++++++++++++++++++++++++ include/hw/ppc/spapr.h | 5 +++- 3 files changed, 68 insertions(+), 3 deletions(-)hw/ppc/spapr_caps.c +0
-0
hw/ppc/spapr_caps.c static void cap_fwnmi_mce_apply(SpaprMachineState *spapr, uint8_t val, · line 511
Quoted 3 lines
hw/ppc/spapr_caps.c +0
-0@@ -509,9 +509,14 @@ static void cap_fwnmi_mce_apply(SpaprMachineState *spapr, uint8_t val,* of software injected faults like duplicate SLBs). */ warn_report ("Firmware Assisted Non-Maskable Interrupts not supported in TCG" );
This logic still isn't quite right. To start with the warn_report() above possible wants to be more weakly worded. With TCG, FWNMI won't generally *do* anything, and there are some edge cases where the behaviour is arguably incorrect. However there's no reason we can't make the RTAS calls work basically as expected and in almost all cases things will behave correctly - at least according to the case where no fwnmi events are delivered...
hw/ppc/spapr_caps.c static void cap_fwnmi_mce_apply(SpaprMachineState *spapr, uint8_t val, · line 515
Quoted 6 lines
hw/ppc/spapr_caps.c +4
-2- }else if (kvm_enabled () && (kvmppc_set_fwnmi () !=0 )) { - error_setg(errp, + }else if (kvm_enabled ()) { +if (!kvmppc_set_fwnmi ()) { +/* Register ibm,nmi-register and ibm,nmi-interlock RTAS calls */ +spapr_fwnmi_register ();
..but here you only register the RTAS calls in the KVM case, which breaks that. If there really is a strong reason to do this, then the warn_report() above should be error_setg() and fail the apply.
Quoted 20 lines
hw/ppc/spapr_caps.c +3
-0+ }else { +error_setg (errp,"Firmware Assisted Non-Maskable Interrupts not supported by KVM, try cap-fwnmi-mce=off" ); + } } }hw/ppc/spapr_rtas.c +5
-0@@ -400,6 +400,55 @@ 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)
hw/ppc/spapr_rtas.c static void rtas_get_power_level(PowerPCCPU *cpu, SpaprMachineState *spapr, · line 417
Quoted 10 lines
hw/ppc/spapr_rtas.c +10
-0+{ +hwaddr rtas_addr =spapr_get_rtas_addr (); + +if (!rtas_addr) { +rtas_st (rets,0 ,RTAS_OUT_NOT_SUPPORTED ); +return ; + } + +if (spapr_get_cap (spapr,SPAPR_CAP_FWNMI_MCE ) ==SPAPR_CAP_OFF ) { +rtas_st (rets,0 ,RTAS_OUT_NOT_SUPPORTED );
Actually, since you explicitly test for the cap being enabled here, there's no reason not to *always* register this RTAS call. Also this test for the feature flag should go first, before delving into the device tree for the RTAS address.
Quoted 74 lines
hw/ppc/spapr_rtas.c +42
-0+return ; + } + + 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 ==-1 ) { +/* NMI register not called */ +rtas_st (rets,0 ,RTAS_OUT_PARAM_ERROR ); +return ; + } + +if (spapr->mc_status != cpu->vcpu_id) { +/* The vCPU that hit the NMI should invoke "ibm,nmi-interlock" */ +rtas_st (rets,0 ,RTAS_OUT_PARAM_ERROR ); +return ; + } + +/* +* 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;@@ -503,6 +552,14 @@ hwaddr spapr_get_rtas_addr(void)return (hwaddr )fdt32_to_cpu (*rtas_data); } +void spapr_fwnmi_register (void ) +{ +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); +} +static void core_rtas_register_types (void ) { spapr_rtas_register(RTAS_DISPLAY_CHARACTER, "display-character",include/hw/ppc/spapr.h +4
-1@@ -653,8 +653,10 @@ target_ulong spapr_hypercall(PowerPCCPU *cpu, target_ulong opcode,#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_SUSPEND_ME (RTAS_TOKEN_BASE + 0x2A) +#define RTAS_IBM_NMI_REGISTER (RTAS_TOKEN_BASE + 0x2B) +#define RTAS_IBM_NMI_INTERLOCK (RTAS_TOKEN_BASE + 0x2C) -#define RTAS_TOKEN_MAX (RTAS_TOKEN_BASE + 0x2B) +#define RTAS_TOKEN_MAX (RTAS_TOKEN_BASE + 0x2D)/* RTAS ibm,get-system-parameter token values */ #define RTAS_SYSPARM_SPLPAR_CHARACTERISTICS 20@@ -907,4 +909,5 @@ void spapr_check_pagesize(SpaprMachineState *spapr, hwaddr pagesize,void spapr_set_all_lpcrs (target_ulong value,target_ulong mask);hwaddr spapr_get_rtas_addr (void ); +void spapr_fwnmi_register (void );#endif /* HW_SPAPR_H */
Signature · 4 lines
David Gibson | I'll have my music baroque, and my code david AT gibson.dropbear.id.au | minimalist, thank you. NOT _the_ _other_ | _way_ _around_! http://www.ozlabs.org/~dgibson
Re: [PATCH v17 5/7] ppc: spapr: Handle "ibm,nmi-register" and "ibm,nmi-interlock" RTAS calls
Quoted 19 lines · David Gibson
Quoted 18 lines · Ganesh Goudar
From: Aravinda Prasad <[email protected]>
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.
Quoted 2 lines
Quoted 1 line
[Move fwnmi registeration to .apply hook]
s/registeration/registration/
Thanks
Quoted 9 lines
Quoted 9 lines
Signed-off-by Ganesh Goudar <[email protected]>Signed-off-by Aravinda Prasad <[email protected]>--- hw/ppc/spapr_caps.c | 9 +++++-- hw/ppc/spapr_rtas.c | 57 ++++++++++++++++++++++++++++++++++++++++++ include/hw/ppc/spapr.h | 5 +++- 3 files changed, 68 insertions(+), 3 deletions(-)
Quoted 15 lines
hw/ppc/spapr_caps.c static void cap_fwnmi_mce_apply(SpaprMachineState *spapr, uint8_t val, · line 511
Quoted 8 lines
hw/ppc/spapr_caps.c +0
-0@@ -509,9 +509,14 @@ static void cap_fwnmi_mce_apply(SpaprMachineState *spapr, uint8_t val,* of software injected faults like duplicate SLBs). */ warn_report ("Firmware Assisted Non-Maskable Interrupts not supported in TCG" );This logic still isn't quite right. To start with the
warn_report()above possible wants to be more weakly worded. With TCG, FWNMI won't generally *do* anything, and there are some edge cases where the behaviour is arguably incorrect. However there's no reason we can't make the RTAS calls work basically as expected and in almost all cases things will behave correctly - at least according to the case where no fwnmi events are delivered...
ok
Quoted 37 lines
hw/ppc/spapr_caps.c static void cap_fwnmi_mce_apply(SpaprMachineState *spapr, uint8_t val, · line 515
Quoted 7 lines
hw/ppc/spapr_caps.c +4
-2- }else if (kvm_enabled () && (kvmppc_set_fwnmi () !=0 )) { - error_setg(errp, + }else if (kvm_enabled ()) { +if (!kvmppc_set_fwnmi ()) { +/* Register ibm,nmi-register and ibm,nmi-interlock RTAS calls */ +spapr_fwnmi_register ();..but here you only register the RTAS calls in the KVM case, which breaks that. If there really is a strong reason to do this, then the
warn_report()above should beerror_setg()and fail the apply.Quoted 26 lines
hw/ppc/spapr_caps.c +3
-0+ }else { +error_setg (errp,"Firmware Assisted Non-Maskable Interrupts not supported by KVM, try cap-fwnmi-mce=off" ); + } } }hw/ppc/spapr_rtas.c +11
-0@@ -400,6 +400,55 @@ 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) +{ +hwaddr rtas_addr =spapr_get_rtas_addr (); + +if (!rtas_addr) { +rtas_st (rets,0 ,RTAS_OUT_NOT_SUPPORTED ); +return ;
Quoted 8 lines
hw/ppc/spapr_rtas.c static void rtas_get_power_level(PowerPCCPU *cpu, SpaprMachineState *spapr, · line 417
Quoted 4 lines
hw/ppc/spapr_rtas.c +4
-0+ } + +if (spapr_get_cap (spapr,SPAPR_CAP_FWNMI_MCE ) ==SPAPR_CAP_OFF ) { +rtas_st (rets,0 ,RTAS_OUT_NOT_SUPPORTED );Actually, since you explicitly test for the cap being enabled here, there's no reason not to *always* register this RTAS call. Also this test for the feature flag should go first, before delving into the device tree for the RTAS address.
Sure, will do
Quoted 75 lines
Quoted 75 lines
hw/ppc/spapr_rtas.c +42
-0+return ; + } + + 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 ==-1 ) { +/* NMI register not called */ +rtas_st (rets,0 ,RTAS_OUT_PARAM_ERROR ); +return ; + } + +if (spapr->mc_status != cpu->vcpu_id) { +/* The vCPU that hit the NMI should invoke "ibm,nmi-interlock" */ +rtas_st (rets,0 ,RTAS_OUT_PARAM_ERROR ); +return ; + } + +/* +* 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;@@ -503,6 +552,14 @@ hwaddr spapr_get_rtas_addr(void)return (hwaddr )fdt32_to_cpu (*rtas_data); } +void spapr_fwnmi_register (void ) +{ +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); +} +static void core_rtas_register_types (void ) { spapr_rtas_register(RTAS_DISPLAY_CHARACTER, "display-character",include/hw/ppc/spapr.h +4
-1@@ -653,8 +653,10 @@ target_ulong spapr_hypercall(PowerPCCPU *cpu, target_ulong opcode,#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_SUSPEND_ME (RTAS_TOKEN_BASE + 0x2A) +#define RTAS_IBM_NMI_REGISTER (RTAS_TOKEN_BASE + 0x2B) +#define RTAS_IBM_NMI_INTERLOCK (RTAS_TOKEN_BASE + 0x2C) -#define RTAS_TOKEN_MAX (RTAS_TOKEN_BASE + 0x2B) +#define RTAS_TOKEN_MAX (RTAS_TOKEN_BASE + 0x2D)/* RTAS ibm,get-system-parameter token values */ #define RTAS_SYSPARM_SPLPAR_CHARACTERISTICS 20@@ -907,4 +909,5 @@ void spapr_check_pagesize(SpaprMachineState *spapr, hwaddr pagesize,void spapr_set_all_lpcrs (target_ulong value,target_ulong mask);hwaddr spapr_get_rtas_addr (void ); +void spapr_fwnmi_register (void );#endif /* HW_SPAPR_H */
Re: [PATCH v17 6/7] migration: Include migration support for machine check handling
In reply to David GibsonQuoted 55 lines · David Gibson
Quoted 54 lines · Ganesh Goudar
From: Aravinda Prasad <[email protected]>
This patch includes migration support for machine check handling. Especially this patch blocks VM migration requests until the machine check error handling is complete as these errors are specific to the source hardware and is irrelevant on the target hardware.
[Do not set FWNMI cap in post_load, now its done in .apply hook]Signed-off-by Ganesh Goudar <[email protected]>Signed-off-by Aravinda Prasad <[email protected]>--- hw/ppc/spapr.c | 41 +++++++++++++++++++++++++++++++++++++++++ hw/ppc/spapr_events.c | 16 +++++++++++++++- hw/ppc/spapr_rtas.c | 2 ++ include/hw/ppc/spapr.h | 2 ++ 4 files changed, 60 insertions(+), 1 deletion(-)hw/ppc/spapr.c +14
-0@@ -46,6 +46,7 @@#include "migration/qemu-file-types.h" #include "migration/global_state.h" #include "migration/register.h" +#include "migration/blocker.h" #include "mmu-hash64.h" #include "mmu-book3s-v3.h" #include "cpu-models.h" @@ -1751,6 +1752,8 @@ static void spapr_machine_reset(MachineState *machine)/* Signal all vCPUs waiting on this condition */ qemu_cond_broadcast (&spapr->mc_delivery_cond); + +migrate_del_blocker (spapr->fwnmi_migration_blocker); }static void spapr_create_nvram (SpaprMachineState *spapr)@@ -2041,6 +2044,43 @@ static const VMStateDescription vmstate_spapr_dtb = { }, }; +static bool spapr_fwnmi_needed (void *opaque) +{ +SpaprMachineState *spapr = (SpaprMachineState *)opaque; + +return spapr->guest_machine_check_addr !=-1 ; +} + +static int spapr_fwnmi_pre_save (void *opaque) +{ +SpaprMachineState *spapr = (SpaprMachineState *)opaque; +
Quoted 8 lines
hw/ppc/spapr.c static const VMStateDescription vmstate_spapr_dtb = { · line 2062
Quoted 5 lines
hw/ppc/spapr.c +5
-0+/* +* With -only-migratable QEMU option, we cannot block migration. +* Hence check if machine check handling is in progress and print +* a warning message. +*/ IIUC the logic below this could also occur in the case where the fwnmi event occurs after a migration has started, but before it completes, not just with -only-migratable. Is that correct?
Yes
Quoted 60 lines
Quoted 60 lines
hw/ppc/spapr.c +22
-0+if (spapr->mc_status !=-1 ) { +warn_report ("A machine check is being handled during migration. The" +"handler may run and log hardware error on the destination" ); + } + +return 0 ; +} + +static const VMStateDescription vmstate_spapr_machine_check = { + .name ="spapr_machine_check" , + .version_id =1 , + .minimum_version_id =1 , + .needed = spapr_fwnmi_needed, + .pre_save = spapr_fwnmi_pre_save, + .fields = (VMStateField []) { +VMSTATE_UINT64 (guest_machine_check_addr, SpaprMachineState), +VMSTATE_INT32 (mc_status, SpaprMachineState), +VMSTATE_END_OF_LIST () + }, +}; +static const VMStateDescription vmstate_spapr = { .name ="spapr" , .version_id =3 ,@@ -2075,6 +2115,7 @@ static const VMStateDescription vmstate_spapr = { &vmstate_spapr_cap_large_decr, &vmstate_spapr_cap_ccf_assist, &vmstate_spapr_cap_fwnmi, + &vmstate_spapr_machine_check, NULL } };hw/ppc/spapr_events.c +3
-1@@ -43,6 +43,7 @@#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@@ -842,6 +843,8 @@ 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 ) {/* @@ -871,8 +874,19 @@ void spapr_mce_req_event(PowerPCCPU *cpu, bool recovered)return ; } } - spapr->mc_status = cpu->vcpu_id;
Quoted 13 lines
hw/ppc/spapr_events.c void spapr_mce_req_event(PowerPCCPU *cpu, bool recovered) · line 886
Quoted 9 lines
hw/ppc/spapr_events.c +9
-0+ 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_err (local_err);I suspect the error message in
local_errwon't be particularly meaningful on its own. Perhaps you need to add a prefix to clarify that the problem is you've received a fwnmi after migration has commenced?
ok
Quoted 27 lines
Quoted 20 lines
hw/ppc/spapr_events.c +3
-0+ } + + spapr->mc_status = cpu->vcpu_id;spapr_mce_dispatch_elog (cpu, recovered); }hw/ppc/spapr_rtas.c +1
-0@@ -50,6 +50,7 @@#include "hw/ppc/fdt.h" #include "target/ppc/mmu-hash64.h" #include "target/ppc/mmu-book3s-v3.h" +#include "migration/blocker.h" static void rtas_display_character(PowerPCCPU *cpu, SpaprMachineState *spapr, uint32_t token, uint32_t nargs,hw/ppc/spapr_rtas.c static void rtas_ibm_nmi_interlock(PowerPCCPU *cpu, · line 450
Quoted 4 lines
hw/ppc/spapr_rtas.c +1
-0@@ -446,6 +447,7 @@ static void rtas_ibm_nmi_interlock(PowerPCCPU *cpu,*/ spapr->mc_status =-1 ;qemu_cond_signal (&spapr->mc_delivery_cond); +migrate_del_blocker (spapr->fwnmi_migration_blocker);Oh... damn. I suggested using a static
fwnmi_migration_blockerinstance, but I just realized there's a problem with it.
Quoted 6 lines
If we do receive multiple fwnmi events on different cpus at roughly the same time, this will break: I think we'll try to add the same migration blocker instance multiple times, which won't be good. Even if that doesn't do anything *too* bad, then we'll unblock the migration on the first interlock, rather than waiting for all pending fwnmi events to complete.
Ok, not sure how to handle this, ill look into it.
Quoted 17 lines
Quoted 17 lines
hw/ppc/spapr_rtas.c +0
-0rtas_st (rets,0 ,RTAS_OUT_SUCCESS ); }include/hw/ppc/spapr.h +2
-0@@ -215,6 +215,8 @@ struct SpaprMachineState {unsigned gpu_numa_id;SpaprTpmProxy *tpm_proxy; + +Error *fwnmi_migration_blocker; };#define H_SUCCESS 0
Re: [PATCH v17 6/7] migration: Include migration support for machine check handling
Quoted 62 lines · Ganesh
Quoted 52 lines · David Gibson
Quoted 51 lines · Ganesh Goudar
From: Aravinda Prasad <[email protected]>
This patch includes migration support for machine check handling. Especially this patch blocks VM migration requests until the machine check error handling is complete as these errors are specific to the source hardware and is irrelevant on the target hardware.
[Do not set FWNMI cap in post_load, now its done in .apply hook]Signed-off-by Ganesh Goudar <[email protected]>Signed-off-by Aravinda Prasad <[email protected]>--- hw/ppc/spapr.c | 41 +++++++++++++++++++++++++++++++++++++++++ hw/ppc/spapr_events.c | 16 +++++++++++++++- hw/ppc/spapr_rtas.c | 2 ++ include/hw/ppc/spapr.h | 2 ++ 4 files changed, 60 insertions(+), 1 deletion(-)hw/ppc/spapr.c +14
-0@@ -46,6 +46,7 @@#include "migration/qemu-file-types.h" #include "migration/global_state.h" #include "migration/register.h" +#include "migration/blocker.h" #include "mmu-hash64.h" #include "mmu-book3s-v3.h" #include "cpu-models.h" @@ -1751,6 +1752,8 @@ static void spapr_machine_reset(MachineState *machine)/* Signal all vCPUs waiting on this condition */ qemu_cond_broadcast (&spapr->mc_delivery_cond); + +migrate_del_blocker (spapr->fwnmi_migration_blocker); }static void spapr_create_nvram (SpaprMachineState *spapr)@@ -2041,6 +2044,43 @@ static const VMStateDescription vmstate_spapr_dtb = { }, }; +static bool spapr_fwnmi_needed (void *opaque) +{ +SpaprMachineState *spapr = (SpaprMachineState *)opaque; + +return spapr->guest_machine_check_addr !=-1 ; +} + +static int spapr_fwnmi_pre_save (void *opaque) +{ +SpaprMachineState *spapr = (SpaprMachineState *)opaque; +Quoted 8 lines
hw/ppc/spapr.c static const VMStateDescription vmstate_spapr_dtb = { · line 2062
Quoted 5 lines
hw/ppc/spapr.c +5
-0+/* +* With -only-migratable QEMU option, we cannot block migration. +* Hence check if machine check handling is in progress and print +* a warning message. +*/ IIUC the logic below this could also occur in the case where the fwnmi event occurs after a migration has started, but before it completes, not just with -only-migratable. Is that correct?
Quoted 1 line
Yes
Ok, please update the comment accordingly.
Quoted 96 lines
Quoted 62 lines
Quoted 62 lines
hw/ppc/spapr.c +22
-0+if (spapr->mc_status !=-1 ) { +warn_report ("A machine check is being handled during migration. The" +"handler may run and log hardware error on the destination" ); + } + +return 0 ; +} + +static const VMStateDescription vmstate_spapr_machine_check = { + .name ="spapr_machine_check" , + .version_id =1 , + .minimum_version_id =1 , + .needed = spapr_fwnmi_needed, + .pre_save = spapr_fwnmi_pre_save, + .fields = (VMStateField []) { +VMSTATE_UINT64 (guest_machine_check_addr, SpaprMachineState), +VMSTATE_INT32 (mc_status, SpaprMachineState), +VMSTATE_END_OF_LIST () + }, +}; +static const VMStateDescription vmstate_spapr = { .name ="spapr" , .version_id =3 ,@@ -2075,6 +2115,7 @@ static const VMStateDescription vmstate_spapr = { &vmstate_spapr_cap_large_decr, &vmstate_spapr_cap_ccf_assist, &vmstate_spapr_cap_fwnmi, + &vmstate_spapr_machine_check, NULL } };hw/ppc/spapr_events.c +8
-1@@ -43,6 +43,7 @@#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@@ -842,6 +843,8 @@ 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 ) {/* @@ -871,8 +874,19 @@ void spapr_mce_req_event(PowerPCCPU *cpu, bool recovered)return ; } } - spapr->mc_status = cpu->vcpu_id; + 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. Quoted 8 lines
hw/ppc/spapr_events.c void spapr_mce_req_event(PowerPCCPU *cpu, bool recovered) · line 886
Quoted 4 lines
hw/ppc/spapr_events.c +4
-0+* Though this is not preferable, it is better than aborting +* the migration or killing the VM. +*/ +warn_report_err (local_err);I suspect the error message in
local_errwon't be particularly meaningful on its own. Perhaps you need to add a prefix to clarify that the problem is you've received a fwnmi after migration has commenced?ok
Quoted 25 lines
Quoted 18 lines
hw/ppc/spapr_events.c +3
-0+ } + + spapr->mc_status = cpu->vcpu_id;spapr_mce_dispatch_elog (cpu, recovered); }hw/ppc/spapr_rtas.c +1
-0@@ -50,6 +50,7 @@#include "hw/ppc/fdt.h" #include "target/ppc/mmu-hash64.h" #include "target/ppc/mmu-book3s-v3.h" +#include "migration/blocker.h" static void rtas_display_character(PowerPCCPU *cpu, SpaprMachineState *spapr, uint32_t token, uint32_t nargs,hw/ppc/spapr_rtas.c static void rtas_ibm_nmi_interlock(PowerPCCPU *cpu, · line 450
Quoted 4 lines
hw/ppc/spapr_rtas.c +1
-0@@ -446,6 +447,7 @@ static void rtas_ibm_nmi_interlock(PowerPCCPU *cpu,*/ spapr->mc_status =-1 ;qemu_cond_signal (&spapr->mc_delivery_cond); +migrate_del_blocker (spapr->fwnmi_migration_blocker);Oh... damn. I suggested using a static
fwnmi_migration_blockerinstance, but I just realized there's a problem with it.
Quoted 7 lines
Quoted 6 lines
If we do receive multiple fwnmi events on different cpus at roughly the same time, this will break: I think we'll try to add the same migration blocker instance multiple times, which won't be good. Even if that doesn't do anything *too* bad, then we'll unblock the migration on the first interlock, rather than waiting for all pending fwnmi events to complete.
Ok, not sure how to handle this, ill look into it.
Well, you can do it by reverting to the old approach of dynamically creating the Error object before adding it as blocker (and freeing it when the blocker is removed). It's a bit ugly, but it will suffice.
Quoted 15 lines
Quoted 14 lines
Quoted 14 lines
hw/ppc/spapr_rtas.c +0
-0rtas_st (rets,0 ,RTAS_OUT_SUCCESS ); }include/hw/ppc/spapr.h +2
-0@@ -215,6 +215,8 @@ struct SpaprMachineState {unsigned gpu_numa_id;SpaprTpmProxy *tpm_proxy; + +Error *fwnmi_migration_blocker; };#define H_SUCCESS 0
Signature · 4 lines
David Gibson | I'll have my music baroque, and my code david AT gibson.dropbear.id.au | minimalist, thank you. NOT _the_ _other_ | _way_ _around_! http://www.ozlabs.org/~dgibson
Re: [PATCH v17 6/7] migration: Include migration support for machine check handling
Quoted 62 lines · David Gibson
Quoted 61 lines · Ganesh
Quoted 60 lines · David Gibson
Quoted 46 lines · Ganesh Goudar
From: Aravinda Prasad <[email protected]>
This patch includes migration support for machine check handling. Especially this patch blocks VM migration requests until the machine check error handling is complete as these errors are specific to the source hardware and is irrelevant on the target hardware.
[Do not set FWNMI cap in post_load, now its done in .apply hook]Signed-off-by Ganesh Goudar <[email protected]>Signed-off-by Aravinda Prasad <[email protected]>--- hw/ppc/spapr.c | 41 +++++++++++++++++++++++++++++++++++++++++ hw/ppc/spapr_events.c | 16 +++++++++++++++- hw/ppc/spapr_rtas.c | 2 ++ include/hw/ppc/spapr.h | 2 ++ 4 files changed, 60 insertions(+), 1 deletion(-)hw/ppc/spapr.c +9
-0@@ -46,6 +46,7 @@#include "migration/qemu-file-types.h" #include "migration/global_state.h" #include "migration/register.h" +#include "migration/blocker.h" #include "mmu-hash64.h" #include "mmu-book3s-v3.h" #include "cpu-models.h" @@ -1751,6 +1752,8 @@ static void spapr_machine_reset(MachineState *machine)/* Signal all vCPUs waiting on this condition */ qemu_cond_broadcast (&spapr->mc_delivery_cond); + +migrate_del_blocker (spapr->fwnmi_migration_blocker); }static void spapr_create_nvram (SpaprMachineState *spapr)@@ -2041,6 +2044,43 @@ static const VMStateDescription vmstate_spapr_dtb = { }, }; +static bool spapr_fwnmi_needed (void *opaque) +{ +SpaprMachineState *spapr = (SpaprMachineState *)opaque; + +return spapr->guest_machine_check_addr !=-1 ; +}hw/ppc/spapr.c static const VMStateDescription vmstate_spapr_dtb = { · line 2061
Quoted 10 lines
hw/ppc/spapr.c +10
-0+ +static int spapr_fwnmi_pre_save (void *opaque) +{ +SpaprMachineState *spapr = (SpaprMachineState *)opaque; + +/* +* With -only-migratable QEMU option, we cannot block migration. +* Hence check if machine check handling is in progress and print +* a warning message. +*/ IIUC the logic below this could also occur in the case where the fwnmi event occurs after a migration has started, but before it completes, not just with -only-migratable. Is that correct?
Quoted 2 lines
Quoted 1 line
Yes
Ok, please update the comment accordingly.
sure
Quoted 101 lines
Quoted 101 lines
Quoted 62 lines
Quoted 62 lines
hw/ppc/spapr.c +22
-0+if (spapr->mc_status !=-1 ) { +warn_report ("A machine check is being handled during migration. The" +"handler may run and log hardware error on the destination" ); + } + +return 0 ; +} + +static const VMStateDescription vmstate_spapr_machine_check = { + .name ="spapr_machine_check" , + .version_id =1 , + .minimum_version_id =1 , + .needed = spapr_fwnmi_needed, + .pre_save = spapr_fwnmi_pre_save, + .fields = (VMStateField []) { +VMSTATE_UINT64 (guest_machine_check_addr, SpaprMachineState), +VMSTATE_INT32 (mc_status, SpaprMachineState), +VMSTATE_END_OF_LIST () + }, +}; +static const VMStateDescription vmstate_spapr = { .name ="spapr" , .version_id =3 ,@@ -2075,6 +2115,7 @@ static const VMStateDescription vmstate_spapr = { &vmstate_spapr_cap_large_decr, &vmstate_spapr_cap_ccf_assist, &vmstate_spapr_cap_fwnmi, + &vmstate_spapr_machine_check, NULL } };hw/ppc/spapr_events.c +8
-1@@ -43,6 +43,7 @@#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@@ -842,6 +843,8 @@ 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 ) {/* @@ -871,8 +874,19 @@ void spapr_mce_req_event(PowerPCCPU *cpu, bool recovered)return ; } } - spapr->mc_status = cpu->vcpu_id; + 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. Quoted 8 lines
hw/ppc/spapr_events.c void spapr_mce_req_event(PowerPCCPU *cpu, bool recovered) · line 886
Quoted 4 lines
hw/ppc/spapr_events.c +4
-0+* Though this is not preferable, it is better than aborting +* the migration or killing the VM. +*/ +warn_report_err (local_err);I suspect the error message in
local_errwon't be particularly meaningful on its own. Perhaps you need to add a prefix to clarify that the problem is you've received a fwnmi after migration has commenced?ok
Quoted 30 lines
Quoted 17 lines
hw/ppc/spapr_events.c +3
-0+ } + + spapr->mc_status = cpu->vcpu_id;spapr_mce_dispatch_elog (cpu, recovered); }hw/ppc/spapr_rtas.c +1
-0@@ -50,6 +50,7 @@#include "hw/ppc/fdt.h" #include "target/ppc/mmu-hash64.h" #include "target/ppc/mmu-book3s-v3.h" +#include "migration/blocker.h" static void rtas_display_character(PowerPCCPU *cpu, SpaprMachineState *spapr, uint32_t token, uint32_t nargs,hw/ppc/spapr_rtas.c static void rtas_ibm_nmi_interlock(PowerPCCPU *cpu, · line 450
Quoted 4 lines
hw/ppc/spapr_rtas.c +1
-0@@ -446,6 +447,7 @@ static void rtas_ibm_nmi_interlock(PowerPCCPU *cpu,*/ spapr->mc_status =-1 ;qemu_cond_signal (&spapr->mc_delivery_cond); +migrate_del_blocker (spapr->fwnmi_migration_blocker);Oh... damn. I suggested using a static
fwnmi_migration_blockerinstance, but I just realized there's a problem with it.If we do receive multiple fwnmi events on different cpus at roughly the same time, this will break: I think we'll try to add the same migration blocker instance multiple times, which won't be good. Even if that doesn't do anything *too* bad, then we'll unblock the migration on the first interlock, rather than waiting for all pending fwnmi events to complete.
Quoted 4 lines
Quoted 1 line
Ok, not sure how to handle this, ill look into it.
Well, you can do it by reverting to the old approach of dynamically creating the Error object before adding it as blocker (and freeing it when the blocker is removed). It's a bit ugly, but it will suffice.
Sure, Thanks
Quoted 14 lines
Quoted 14 lines
Quoted 14 lines
Quoted 14 lines
hw/ppc/spapr_rtas.c +0
-0rtas_st (rets,0 ,RTAS_OUT_SUCCESS ); }include/hw/ppc/spapr.h +2
-0@@ -215,6 +215,8 @@ struct SpaprMachineState {unsigned gpu_numa_id;SpaprTpmProxy *tpm_proxy; + +Error *fwnmi_migration_blocker; };#define H_SUCCESS 0
Re: [PATCH v17 5/7] ppc: spapr: Handle "ibm,nmi-register" and "ibm,nmi-interlock" RTAS calls
In reply to GaneshQuoted 50 lines · Ganesh
Quoted 19 lines · David Gibson
Quoted 18 lines · Ganesh Goudar
From: Aravinda Prasad <[email protected]>
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.
Quoted 2 lines
Quoted 1 line
[Move fwnmi registeration to .apply hook]
s/registeration/registration/
Thanks
Quoted 10 lines
Quoted 10 lines
Signed-off-by Ganesh Goudar <[email protected]>Signed-off-by Aravinda Prasad <[email protected]>---
hw/ppc/spapr_caps.c | 9 +++++--
hw/ppc/spapr_rtas.c | 57
++++++++++++++++++++++++++++++++++++++++++
include/hw/ppc/spapr.h| 5 +++-3 files changed, 68 insertions(+), 3 deletions(-)Quoted 16 lines
hw/ppc/spapr_caps.c static void · line 512
Quoted 9 lines
hw/ppc/spapr_caps.c +0
-0@@ -509,9 +509,14 @@ static voidcap_fwnmi_mce_apply(SpaprMachineState *spapr, uint8_t val, * of software injected faults like duplicate SLBs). */ warn_report("Firmware Assisted Non-Maskable Interrupts not supported in TCG");This logic still isn't quite right. To start with the
warn_report()above possible wants to be more weakly worded. With TCG, FWNMI won't generally *do* anything, and there are some edge cases where the behaviour is arguably incorrect. However there's no reason we can't make the RTAS calls work basically as expected and in almost all cases things will behave correctly - at least according to the case where no fwnmi events are delivered...
Quoted 12 lines
ok
Quoted 11 lines
Quoted 8 lines
hw/ppc/spapr_caps.c +3
-2- } else if (kvm_enabled() && (kvmppc_set_fwnmi() != 0)) { - error_setg(errp, + } else if (kvm_enabled()) { + if (!kvmppc_set_fwnmi()) { + /* Register ibm,nmi-register and ibm,nmi-interlock RTAScalls */
+spapr_fwnmi_register();..but here you only register the RTAS calls in the KVM case, which breaks that. If there really is a strong reason to do this, then the
warn_report()above should beerror_setg()and fail the apply.
Also I found a side effect of moving this fwnmi registration to apply hook, I see the following assert
when I reboot the guest. may be I must have a member to indicate if the registration is already done.
Requesting system reboot
[ 186.368745] sd 0:0:0:0: [sda] Synchronizing SCSI cache
[ 186.370222] reboot: Restarting system
#######MACHINE RESET######
#####SPAPR_FWNMI_REGISTER######
qemu-system-ppc64: /home/jupit/qemu/hw/ppc/spapr_rtas.c:510: spapr_rtas_register: Assertion `!name || !rtas_table[token].name' failed. Aborted
Quoted 109 lines
Quoted 26 lines
Quoted 26 lines
+ } else {
+ error_setg(errp,
"Firmware Assisted Non-Maskable Interrupts not supported by KVM, try cap-fwnmi-mce=off"); + }
}
}
diff --gita/hw/ppc/spapr_rtas.cb/hw/ppc/spapr_rtas.c
index2c066a372d..0328b1f341100644hw/ppc/spapr_rtas.c +10
-0@@ -400,6 +400,55 @@ 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) +{ + hwaddr rtas_addr = spapr_get_rtas_addr(); + + if (!rtas_addr) { + rtas_st(rets, 0, RTAS_OUT_NOT_SUPPORTED); + return;Quoted 8 lines
hw/ppc/spapr_rtas.c static void rtas_get_power_level(PowerPCCPU *cpu, SpaprMachineState *spapr, · line 417
Quoted 4 lines
hw/ppc/spapr_rtas.c +4
-0+ } + + if (spapr_get_cap(spapr, SPAPR_CAP_FWNMI_MCE) == SPAPR_CAP_OFF) { + rtas_st(rets, 0, RTAS_OUT_NOT_SUPPORTED);Actually, since you explicitly test for the cap being enabled here, there's no reason not to *always* register this RTAS call. Also this test for the feature flag should go first, before delving into the device tree for the RTAS address.
Sure, will do
Quoted 74 lines
Quoted 74 lines
hw/ppc/spapr_rtas.c +21
-0+ return; + } + + 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 == -1) { + /* NMI register not called */ + rtas_st(rets, 0, RTAS_OUT_PARAM_ERROR); + return; + } + + if (spapr->mc_status != cpu->vcpu_id) { + /* The vCPU that hit the NMI should invoke"ibm,nmi-interlock" */
+rtas_st(rets, 0, RTAS_OUT_PARAM_ERROR);
+ return;
+ }hw/ppc/spapr_rtas.c +10
-0+ + /* + * 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_fnfn;hw/ppc/spapr_rtas.c +7
-0@@ -503,6 +552,14 @@ hwaddr spapr_get_rtas_addr(void) return (hwaddr)fdt32_to_cpu(*rtas_data); } +void spapr_fwnmi_register(void) +{ + 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); +} + static void core_rtas_register_types(void) { spapr_rtas_register(RTAS_DISPLAY_CHARACTER, "display-character",include/hw/ppc/spapr.h +4
-0@@ -653,8 +653,10 @@ target_ulong spapr_hypercall(PowerPCCPU *cpu, target_ulong opcode, #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_SUSPEND_ME (RTAS_TOKEN_BASE + 0x2A) +#define RTAS_IBM_NMI_REGISTER (RTAS_TOKEN_BASE + 0x2B) +#define RTAS_IBM_NMI_INTERLOCK (RTAS_TOKEN_BASE + 0x2C) -#define RTAS_TOKEN_MAX (RTAS_TOKEN_BASE + 0x2B) +#define RTAS_TOKEN_MAX (RTAS_TOKEN_BASE + 0x2D) /* RTAS ibm,get-system-parameter token values */ #define RTAS_SYSPARM_SPLPAR_CHARACTERISTICS 20@@ -907,4 +909,5 @@ void spapr_check_pagesize(SpaprMachineState *spapr, hwaddr pagesize, void spapr_set_all_lpcrs(target_ulong value, target_ulong mask); hwaddr spapr_get_rtas_addr(void); +void spapr_fwnmi_register (void ); #endif /* HW_SPAPR_H */