ppc/pnv: Better big-core model, lpar-per-core, PC unit
PATCH v3 1/19 target/ppc: Fix msgsnd for POWER8
In reply to Nicholas PigginPOWER8 (ISA v2.07S) introduced the doorbell facility, the msgsnd instruction behaved mostly like msgsndp, it was addressed by TIR and could only send interrupts between threads on the core.
ISA v3.0 changed msgsnd to be addressed by PIR and can interrupt any thread in the system.
msgsnd only implements the v3.0 semantics, which can make multi-threaded POWER8 hang when booting Linux (due to IPIs failing). This change adds v2.07 semantics.
--- target/ppc/excp_helper.c | 74 ++++++++++++++++++++++++---------------- 1 file changed, 44 insertions(+), 30 deletions(-)
target/ppc/excp_helper.c +44 -30
@@ -3007,6 +3007,41 @@ static inline bool dbell_bcast_subproc(target_ulong rb)return (rb &DBELL_BRDCAST_MASK ) ==DBELL_BRDCAST_SUBPROC ; } +/* +* Send an interrupt to a thread in the same core as env). +*/ +static void msgsnd_core_tir (CPUPPCState *env,uint32_t target_tir,int irq) +{ +PowerPCCPU *cpu =env_archcpu (env); +CPUState *cs =env_cpu (env); +uint32_t nr_threads = cs->nr_threads; + +if (!(env->flags &POWERPC_FLAG_SMT_1LPAR )) { + nr_threads =1 ;/* msgsndp behaves as 1-thread in LPAR-per-thread mode*/ + } + +if (target_tir >= nr_threads) { +return ; + } + +if (nr_threads ==1 ) { +ppc_set_irq (cpu, irq,1 ); + }else { +CPUState *ccs; + +/* Does iothread need to be locked for walking CPU list? */ +bql_lock (); + THREAD_SIBLING_FOREACH(cs, ccs) { +PowerPCCPU *ccpu =POWERPC_CPU (ccs); +if (target_tir ==ppc_cpu_tir (ccpu)) { +ppc_set_irq (ccpu, irq,1 ); +break ; + } + } +bql_unlock (); + } +} +void helper_book3s_msgclr (CPUPPCState *env,target_ulong rb) {if (!dbell_type_server (rb)) {
@@ -3027,6 +3062,13 @@ void helper_book3s_msgsnd(CPUPPCState *env, target_ulong rb)return ; } +/* POWER8 msgsnd is like msgsndp (targets a thread within core) */ +if (!(env->insns_flags2 &PPC2_ISA300 )) { +msgsnd_core_tir (env, rb &PPC_BITMASK (57 ,63 ),PPC_INTERRUPT_HDOORBELL ); +return ; + } + +/* POWER9 and later msgsnd is a global (targets any thread) */ cpu =ppc_get_vcpu_by_pir (pir);if (!cpu) {return ;
@@ -3073,41 +3115,13 @@ void helper_book3s_msgclrp(CPUPPCState *env, target_ulong rb)*/ void helper_book3s_msgsndp (CPUPPCState *env,target_ulong rb) { -CPUState *cs =env_cpu (env); -PowerPCCPU *cpu =env_archcpu (env); -CPUState *ccs; -uint32_t nr_threads = cs->nr_threads; -int ttir = rb &PPC_BITMASK (57 ,63 ); -helper_hfscr_facility_check (env,HFSCR_MSGP ,"msgsndp" ,HFSCR_IC_MSGP ); -if (!(env->flags &POWERPC_FLAG_SMT_1LPAR )) { - nr_threads =1 ;/* msgsndp behaves as 1-thread in LPAR-per-thread mode*/ - } - -if (!dbell_type_server (rb) || ttir >= nr_threads) { -return ; - } - -if (nr_threads ==1 ) { -ppc_set_irq (cpu,PPC_INTERRUPT_DOORBELL ,1 ); +if (!dbell_type_server (rb)) {return ; } -/* Does iothread need to be locked for walking CPU list? */ -bql_lock (); - THREAD_SIBLING_FOREACH(cs, ccs) { -PowerPCCPU *ccpu =POWERPC_CPU (ccs); -uint32_t thread_id =ppc_cpu_tir (ccpu); - -if (ttir == thread_id) { -ppc_set_irq (ccpu,PPC_INTERRUPT_DOORBELL ,1 ); -bql_unlock (); -return ; - } - } - -g_assert_not_reached (); +msgsnd_core_tir (env, rb &PPC_BITMASK (57 ,63 ),PPC_INTERRUPT_DOORBELL ); }#endif /* TARGET_PPC64 */
Signature · 1 line
2.45.1
v3 cover ppc/pnv: Better big-core model, lpar-per-core, PC unit
Primary motivation for this series is to improve big-core support.
This also fixes POWER8 SMT running Linux with the msgsnd fix and setting lpar-per-core mode (which is always true on POWER8).
Since v2:
- Converted big-core, lpar-per-core, and big-core tb quirk to object properties APIs in PnvChip and PnvCore, suggested by Cedric.
- Removed a stray cleanup hunk noticed by clg.
Since v1:
- Remove chip->pnv_machine pointer addition.
- Split cpu_pause() function into its own patch.
- Remove the _CORE_ID macro.
- Add has_lpar_per_thread machine class attribute to initialize the lpar mode to per-core on POWER8 machines instead of testing presence of machine state property.
Since rfc:
- Fixed POWER8 SMT so it doesn't have to be disabled.
- Fixed inadvertent spapr SMT bug.
- Renamed PnvCPUState.core pointer to pnv_core. (Harsh)
- Moved where it is initialised (clg)
- Avoided most qdev_get_machine() calls by adding a PnvMachineState pointer from PnvChip, new patch 3 (clg).
- Rename TB state to use camel case (Harsh and clg)
- Add comment to explain SPRC/SPRD is only accessed with powernv.
- Use mc->desc for error messages and avoid splitting machine init handlers (Harsh).
- Add max_smt_threads class attribute to avoid duplicating checks (clg)
- Rename processor_id() class method to get_pir_tir (Harsh and clg)
- Add a comment for get_pir_tir() (clg)
- Allow get_pir_tir() to be passed NULL pointers to avoid dummy pir/tir variables (Harsh)
- Move the PPC_CPU_HAS_CORE_SIBLINGS macros to inline functions (clg)
- Invert them (test for single-thread rather than for siblings) because the callers read a little better that way (Harsh).
- Propagate lpar and big-core options down to chip and core levels rather than having to test machine (clg)
- Significantly split the big-core patch (clg).
- Rework big-core device-tree handling to simplify it (clg).
- Make new has_smt_siblings property bool (Harsh)
- Make the big-core timebase tod quirk a machine class property rather than machine state (Harsh).
Thanks,
Nick
Nicholas Piggin (19):
target/ppc: Fix msgsnd for POWER8
ppc/pnv: Add pointer from PnvCPUState to PnvCore ppc/pnv: Move timebase state into PnvCore
target/ppc: Move SPR indirect registers into PnvCore ppc/pnv: use class attribute to limit SMT threads for different
machines
ppc/pnv: Extend chip_pir class method to TIR as well
ppc: Add a core_index to CPUPPCState for SMT vCPUs target/ppc: Add helpers to check for SMT sibling threads
ppc: Add has_smt_siblings property to CPUPPCState ppc/pnv: Add a big-core mode that joins two regular cores ppc/pnv: Add allow for big-core differences in DT generation ppc/pnv: Implement big-core PVR for Power9/10
ppc/pnv: Implement Power9 CPU core thread state indirect register ppc/pnv: Add POWER10 ChipTOD quirk for big-core ppc/pnv: Add big-core machine property
system/cpus: Add cpu_pause() function
ppc/pnv: Add a CPU nmi and resume function
ppc/pnv: Implement POWER10 PC xscom registers for direct controls ppc/pnv: Add an LPAR per core machine option
include/hw/core/cpu.h | 8 + include/hw/ppc/pnv.h | 8 + include/hw/ppc/pnv_chip.h | 6 +- include/hw/ppc/pnv_core.h | 31 ++++ target/ppc/cpu.h | 45 ++--- hw/ppc/pnv.c | 310 ++++++++++++++++++++++++++++------- hw/ppc/pnv_chiptod.c | 7 +- hw/ppc/pnv_core.c | 127 +++++++++++++- hw/ppc/spapr_cpu_core.c | 16 +- system/cpus.c | 30 ++-- target/ppc/cpu_init.c | 26 +-- target/ppc/excp_helper.c | 69 ++++---- target/ppc/misc_helper.c | 104 ++++++------ target/ppc/timebase_helper.c | 82 ++++----- 14 files changed, 620 insertions(+), 249 deletions(-)
Signature · 1 line
2.45.1
PATCH v3 2/19 ppc/pnv: Add pointer from PnvCPUState to PnvCore
This helps move core state from CPU to core structures.
--- include/hw/ppc/pnv_core.h | 1 + hw/ppc/pnv_core.c | 3 +++ 2 files changed, 4 insertions(+)
include/hw/ppc/pnv_core.h +1 -0
@@ -54,6 +54,7 @@ struct PnvCoreClass {#define PNV_CORE_TYPE_NAME (cpu_model) cpu_model PNV_CORE_TYPE_SUFFIXtypedef struct PnvCPUState { +PnvCore *pnv_core;Object *intc; }PnvCPUState ;
hw/ppc/pnv_core.c +3 -0
@@ -278,6 +278,7 @@ static void pnv_core_realize(DeviceState *dev, Error **errp) pc->threads = g_new(PowerPCCPU *, cc->nr_threads);for (i =0 ; i < cc->nr_threads; i++) {PowerPCCPU *cpu; +PnvCPUState *pnv_cpu; obj =object_new (typename); cpu =POWERPC_CPU (obj);
@@ -288,6 +289,8 @@ static void pnv_core_realize(DeviceState *dev, Error **errp)object_property_add_child (OBJECT (pc), name, obj); cpu->machine_data =g_new0 (PnvCPUState,1 ); + pnv_cpu =pnv_cpu_state (cpu); + pnv_cpu->pnv_core = pc;object_unref (obj); }
Signature · 1 line
2.45.1
PATCH v3 5/19 ppc/pnv: use class attribute to limit SMT threads for different machines
In reply to Nicholas PigginUse a class attribute to specify the number of SMT threads per core permitted for different machines, 8 for powernv8 and 4 for powernv9/10.
--- include/hw/ppc/pnv.h | 1 + hw/ppc/pnv.c | 12 +++++++++--- 2 files changed, 10 insertions(+), 3 deletions(-)
include/hw/ppc/pnv.h +1 -0
@@ -76,6 +76,7 @@ struct PnvMachineClass {/*< public >*/ const char *compat;int compat_size; +int max_smt_threads;void (*dt_power_mgt)(PnvMachineState *pnv,void *fdt);void (*i2c_init)(PnvMachineState *pnv);
hw/ppc/pnv.c +9 -3
@@ -899,6 +899,7 @@ static void pnv_init(MachineState *machine)PnvMachineState *pnv =PNV_MACHINE (machine);MachineClass *mc =MACHINE_GET_CLASS (machine);PnvMachineClass *pmc =PNV_MACHINE_GET_CLASS (machine); +int max_smt_threads = pmc->max_smt_threads;char *fw_filename;long fw_size;uint64_t chip_ram_start =0 ;
@@ -997,17 +998,19 @@ static void pnv_init(MachineState *machine) pnv->num_chips = machine->smp.max_cpus / (machine->smp.cores * machine->smp.threads); -if (machine->smp.threads >8 ) { -error_report ("Cannot support more than 8 threads/core " -"on a powernv machine" ); +if (machine->smp.threads > max_smt_threads) { +error_report ("Cannot support more than %d threads/core " +"on %s machine" , max_smt_threads, mc->desc);exit (1 ); } +if (!is_power_of_2 (machine->smp.threads)) {error_report ("Cannot support %d threads/core on a powernv" "machine because it must be a power of 2" , machine->smp.threads);exit (1 ); } +/* * TODO: should we decide on how many chips we can create based * on #cores and Venice vs. Murano vs. Naples chip type etc...,
@@ -2490,6 +2493,7 @@ static void pnv_machine_power8_class_init(ObjectClass *oc, void *data) pmc->compat = compat; pmc->compat_size =sizeof (compat); + pmc->max_smt_threads =8 ;machine_class_allow_dynamic_sysbus_dev (mc,TYPE_PNV_PHB ); }
@@ -2514,6 +2518,7 @@ static void pnv_machine_power9_class_init(ObjectClass *oc, void *data) pmc->compat = compat; pmc->compat_size =sizeof (compat); + pmc->max_smt_threads =4 ; pmc->dt_power_mgt = pnv_dt_power_mgt;machine_class_allow_dynamic_sysbus_dev (mc,TYPE_PNV_PHB );
@@ -2538,6 +2543,7 @@ static void pnv_machine_p10_common_class_init(ObjectClass *oc, void *data) pmc->compat = compat; pmc->compat_size =sizeof (compat); + pmc->max_smt_threads =4 ; pmc->dt_power_mgt = pnv_dt_power_mgt; xfc->match_nvt = pnv10_xive_match_nvt;
Signature · 1 line
2.45.1
PATCH v3 9/19 ppc: Add has_smt_siblings property to CPUPPCState
In reply to Nicholas PigginThe decision to branch out to a slower SMT path in instruction emulation will become a bit more complicated with the way that "big-core" topology that will be implemented in subsequent changes. Hide these details from the wider CPU emulation code with a bool has_smt_siblings flag that can be set by machine initialisation.
--- target/ppc/cpu.h | 3 ++- hw/ppc/pnv_core.c | 3 +++ hw/ppc/spapr_cpu_core.c | 12 +++++++++--- 3 files changed, 14 insertions(+), 4 deletions(-)
target/ppc/cpu.h +2 -1
@@ -1248,6 +1248,7 @@ struct CPUArchState {int access_type;/* For SMT processors */ +bool has_smt_siblings;int core_index;#if !defined(CONFIG_USER_ONLY )
@@ -1514,7 +1515,7 @@ struct PowerPCCPUClass {static inline bool ppc_cpu_core_single_threaded (CPUState *cs) { -return cs->nr_threads ==1 ; +return !POWERPC_CPU (cs)->env.has_smt_siblings; }static inline bool ppc_cpu_lpar_single_threaded (CPUState *cs)
hw/ppc/pnv_core.c +3 -0
@@ -288,6 +288,9 @@ static void pnv_core_realize(DeviceState *dev, Error **errp) cpu =POWERPC_CPU (obj); pc->threads[i] =POWERPC_CPU (obj); +if (cc->nr_threads >1 ) { + cpu->env.has_smt_siblings = true; + }snprintf (name,sizeof (name),"thread[%d]" , i);object_property_add_child (OBJECT (pc), name, obj);
hw/ppc/spapr_cpu_core.c +9 -3
@@ -351,9 +351,15 @@ static void spapr_cpu_core_realize(DeviceState *dev, Error **errp)qemu_register_reset (spapr_cpu_core_reset_handler, sc); sc->threads = g_new0(PowerPCCPU *, cc->nr_threads);for (i =0 ; i < cc->nr_threads; i++) { - sc->threads[i] =spapr_create_vcpu (sc, i, errp); -if (!sc->threads[i] || - !spapr_realize_vcpu (sc->threads[i], spapr, sc, i, errp)) { +PowerPCCPU *cpu; + + cpu =spapr_create_vcpu (sc, i, errp); + sc->threads[i] = cpu; +if (cpu && cc->nr_threads >1 ) { + cpu->env.has_smt_siblings = true; + } + +if (!cpu || !spapr_realize_vcpu (cpu, spapr, sc, i, errp)) {spapr_cpu_core_unrealize (dev);return ; }
Signature · 1 line
2.45.1
PATCH v3 10/19 ppc/pnv: Add a big-core mode that joins two regular cores
In reply to Nicholas PigginPOWER9 and POWER10 machines come in two variants, big-core and small-core. Big-core machines are SMT8 from software's point of view, but the low level platform topology ("xscom registers and pervasive addressing"), these look more like a pair of small cores ganged together.
Presently the way this is modelled is to create one SMT8 PnvCore and add special cases to xscom and pervasive for big-core mode that tries to split this into two small cores, but this is becoming too complicated to manage.
A better approach is to create 2 core structures and ganging them together to look like an SMT8 core in TCG. Then the xscom and pervasive models mostly do not need to differentiate big and small core modes.
This change adds initial mode bits and QEMU topology handling to split SMT8 cores into 2xSMT4 cores.
--- include/hw/ppc/pnv.h | 2 + include/hw/ppc/pnv_chip.h | 1 + include/hw/ppc/pnv_core.h | 1 + hw/ppc/pnv.c | 80 ++++++++++++++++++++++++++++++++------- hw/ppc/pnv_core.c | 8 +++- 5 files changed, 78 insertions(+), 14 deletions(-)
include/hw/ppc/pnv.h +2 -0
@@ -101,6 +101,8 @@ struct PnvMachineState {PnvPnor *pnor;hwaddr fw_load_addr; + +bool big_core; };PnvChip *pnv_get_chip (PnvMachineState *pnv,uint32_t chip_id);
include/hw/ppc/pnv_chip.h +1 -0
@@ -27,6 +27,7 @@ struct PnvChip {uint64_t ram_start;uint64_t ram_size; +bool big_core;uint32_t nr_cores;uint32_t nr_threads;uint64_t cores_mask;
include/hw/ppc/pnv_core.h +1 -0
@@ -49,6 +49,7 @@ struct PnvCore {/*< public >*/ PowerPCCPU **threads; +bool big_core;uint32_t pir;uint32_t hwid;uint64_t hrmor;
hw/ppc/pnv.c +67 -13
141 lines not on this page · raw message
hw/ppc/pnv_core.c +7 -1
@@ -249,7 +249,12 @@ static void pnv_core_cpu_realize(PnvCore *pc, PowerPCCPU *cpu, Error **errp, pir_spr->default_value = pir; tir_spr->default_value = tir; - env->core_index = core_hwid; +if (pc->big_core) { +/* 2 "small cores" get the same core index for SMT operations */ + env->core_index = core_hwid >>1 ; + }else { + env->core_index = core_hwid; + }/* Set time-base frequency to 512 MHz */ cpu_ppc_tb_init (env,PNV_TIMEBASE_FREQ );
@@ -354,6 +359,7 @@ static void pnv_core_unrealize(DeviceState *dev)static Property pnv_core_properties[] = {DEFINE_PROP_UINT32 ("hwid" , PnvCore, hwid,0 ),DEFINE_PROP_UINT64 ("hrmor" , PnvCore, hrmor,0 ), +DEFINE_PROP_BOOL ("big-core" , PnvCore, big_core, false), DEFINE_PROP_LINK("chip", PnvCore, chip, TYPE_PNV_CHIP, PnvChip *),DEFINE_PROP_END_OF_LIST (), };
Signature · 1 line
2.45.1
PATCH v3 6/19 ppc/pnv: Extend chip_pir class method to TIR as well
In reply to Nicholas PigginThe chip_pir chip class method allows the platform to set the PIR processor identification register. Extend this to a more general ID function which also allows the TIR to be set. This is in preparation for "big core", which is a more complicated topology of cores and threads.
--- include/hw/ppc/pnv_chip.h | 4 +- hw/ppc/pnv.c | 85 +++++++++++++++++++++++++-------------- hw/ppc/pnv_core.c | 10 +++-- 3 files changed, 64 insertions(+), 35 deletions(-)
include/hw/ppc/pnv_chip.h +3 -1
@@ -150,7 +150,9 @@ struct PnvChipClass {DeviceRealize parent_realize; -uint32_t (*chip_pir)(PnvChip *chip,uint32_t core_id,uint32_t thread_id); +/* Get PIR and TIR values for a CPU thread identified by core/thread id */ +void (*get_pir_tir)(PnvChip *chip,uint32_t core_id,uint32_t thread_id, +uint32_t *pir,uint32_t *tir);void (*intc_create)(PnvChip *chip,PowerPCCPU *cpu,Error **errp);void (*intc_reset)(PnvChip *chip,PowerPCCPU *cpu);void (*intc_destroy)(PnvChip *chip,PowerPCCPU *cpu);
hw/ppc/pnv.c +55 -30
164 lines not on this page · raw message
hw/ppc/pnv_core.c +6 -4
@@ -227,8 +227,9 @@ static void pnv_core_cpu_realize(PnvCore *pc, PowerPCCPU *cpu, Error **errp, {CPUPPCState *env = &cpu->env;int core_hwid; -ppc_spr_t *pir = &env->spr_cb[SPR_PIR ]; -ppc_spr_t *tir = &env->spr_cb[SPR_TIR ]; +ppc_spr_t *pir_spr = &env->spr_cb[SPR_PIR ]; +ppc_spr_t *tir_spr = &env->spr_cb[SPR_TIR ]; +uint32_t pir, tir;Error *local_err =NULL ;PnvChipClass *pcc =PNV_CHIP_GET_CLASS (pc->chip);
@@ -244,8 +245,9 @@ static void pnv_core_cpu_realize(PnvCore *pc, PowerPCCPU *cpu, Error **errp, core_hwid =object_property_get_uint (OBJECT (pc),"hwid" , &error_abort); - tir->default_value = thread_index; - pir->default_value = pcc->chip_pir (pc->chip, core_hwid, thread_index); + pcc->get_pir_tir (pc->chip, core_hwid, thread_index, &pir, &tir); + pir_spr->default_value = pir; + tir_spr->default_value = tir;/* Set time-base frequency to 512 MHz */ cpu_ppc_tb_init (env,PNV_TIMEBASE_FREQ );
Signature · 1 line
2.45.1
PATCH v3 15/19 ppc/pnv: Add big-core machine property
In reply to Nicholas PigginBig-core implementation is complete, so expose it as a machine property that may be set with big-core=on option on powernv9 and powernv10 machines.
--- hw/ppc/pnv.c | 61 ++++++++++++++++++++++++++++++++++++++-------------- 1 file changed, 45 insertions(+), 16 deletions(-)
hw/ppc/pnv.c +45 -16
@@ -2581,6 +2581,34 @@ static int pnv10_xive_match_nvt(XiveFabric *xfb, uint8_t format,return total_count; } +static bool pnv_machine_get_big_core (Object *obj,Error **errp) +{ +PnvMachineState *pnv =PNV_MACHINE (obj); +return pnv->big_core; +} + +static void pnv_machine_set_big_core (Object *obj,bool value,Error **errp) +{ +PnvMachineState *pnv =PNV_MACHINE (obj); + pnv->big_core = value; +} + +static bool pnv_machine_get_hb (Object *obj,Error **errp) +{ +PnvMachineState *pnv =PNV_MACHINE (obj); + +return !!pnv->fw_load_addr; +} + +static void pnv_machine_set_hb (Object *obj,bool value,Error **errp) +{ +PnvMachineState *pnv =PNV_MACHINE (obj); + +if (value) { + pnv->fw_load_addr =0x8000000 ; + } +} +static void pnv_machine_power8_class_init (ObjectClass *oc,void *data) {MachineClass *mc =MACHINE_CLASS (oc);
@@ -2632,6 +2660,12 @@ static void pnv_machine_power9_class_init(ObjectClass *oc, void *data) pmc->dt_power_mgt = pnv_dt_power_mgt;machine_class_allow_dynamic_sysbus_dev (mc,TYPE_PNV_PHB ); + +object_class_property_add_bool (oc,"big-core" , + pnv_machine_get_big_core, + pnv_machine_set_big_core); +object_class_property_set_description (oc,"big-core" , +"Use big-core (aka fused-core) mode" ); }static void pnv_machine_p10_common_class_init (ObjectClass *oc,void *data)
@@ -2668,6 +2702,17 @@ static void pnv_machine_power10_class_init(ObjectClass *oc, void *data)pnv_machine_p10_common_class_init (oc, data); mc->desc ="IBM PowerNV (Non-Virtualized) POWER10" ; + +/* +* This is the parent of POWER10 Rainier class, so properies go here +* rather than common init (which would add them to both parent and +* child which is invalid). +*/ +object_class_property_add_bool (oc,"big-core" , + pnv_machine_get_big_core, + pnv_machine_set_big_core); +object_class_property_set_description (oc,"big-core" , +"Use big-core (aka fused-core) mode" ); }static void pnv_machine_p10_rainier_class_init (ObjectClass *oc,void *data)
@@ -2680,22 +2725,6 @@ static void pnv_machine_p10_rainier_class_init(ObjectClass *oc, void *data) pmc->i2c_init = pnv_rainier_i2c_init; } -static bool pnv_machine_get_hb (Object *obj,Error **errp) -{ -PnvMachineState *pnv =PNV_MACHINE (obj); - -return !!pnv->fw_load_addr; -} - -static void pnv_machine_set_hb (Object *obj,bool value,Error **errp) -{ -PnvMachineState *pnv =PNV_MACHINE (obj); - -if (value) { - pnv->fw_load_addr =0x8000000 ; - } -} -static void pnv_cpu_do_nmi_on_cpu (CPUState *cs,run_on_cpu_data arg) {CPUPPCState *env =cpu_env (cs);
Signature · 1 line
2.45.1
PATCH v3 3/19 ppc/pnv: Move timebase state into PnvCore
In reply to Nicholas PigginThe timebase state machine is per per-core state and can be driven by any thread in the core. It is currently implemented as a hack where the state is in a CPU structure and only thread 0's state is accessed by the chiptod, which limits programming the timebase side of the state machine to thread 0 of a core.
Move the state out into PnvCore and share it among all threads.
--- include/hw/ppc/pnv_core.h | 17 ++++++++++++ target/ppc/cpu.h | 21 -------------- hw/ppc/pnv_chiptod.c | 7 ++--- target/ppc/timebase_helper.c | 53 ++++++++++++++++++++---------------- 4 files changed, 49 insertions(+), 49 deletions(-)
include/hw/ppc/pnv_core.h +17 -0
@@ -25,6 +25,20 @@#include "hw/ppc/pnv.h" #include "qom/object.h" +/* Per-core ChipTOD / TimeBase state */ +typedef struct PnvCoreTODState { +int tb_ready_for_tod;/* core TB ready to receive TOD from chiptod */ +int tod_sent_to_tb;/* chiptod sent TOD to the core TB */ + +/* +* "Timers" for async TBST events are simulated by mfTFAC because TFAC +* is polled for such events. These are just used to ensure firmware +* performs the polling at least a few times. +*/ +int tb_state_timer; +int tb_sync_pulse_timer; +}PnvCoreTODState ; +#define TYPE_PNV_CORE "powernv-cpu-core"OBJECT_DECLARE_TYPE (PnvCore, PnvCoreClass,PNV_CORE )
@@ -38,6 +52,9 @@ struct PnvCore {uint32_t pir;uint32_t hwid;uint64_t hrmor; + +PnvCoreTODState tod_state; +PnvChip *chip;MemoryRegion xscom_regs;
target/ppc/cpu.h +0 -21
@@ -1196,21 +1196,6 @@ DEXCR_ASPECT(SRAPD, 4) DEXCR_ASPECT(NPHIE, 5)DEXCR_ASPECT (PHIE ,6 ) -/*****************************************************************************/ -/* PowerNV ChipTOD and TimeBase State Machine */ -struct pnv_tod_tbst { -int tb_ready_for_tod;/* core TB ready to receive TOD from chiptod */ -int tod_sent_to_tb;/* chiptod sent TOD to the core TB */ - -/* -* "Timers" for async TBST events are simulated by mfTFAC because TFAC -* is polled for such events. These are just used to ensure firmware -* performs the polling at least a few times. -*/ -int tb_state_timer; -int tb_sync_pulse_timer; -}; -/*****************************************************************************/ /* The whole PowerPC CPU context */
@@ -1291,12 +1276,6 @@ struct CPUArchState {uint32_t tlb_need_flush;/* Delayed flush needed */ #define TLB_NEED_LOCAL_FLUSH 0x1#define TLB_NEED_GLOBAL_FLUSH 0x2 - -#if defined(TARGET_PPC64 ) -/* PowerNV chiptod / timebase facility state. */ -/* Would be nice to put these into PnvCore */ -struct pnv_tod_tbst pnv_tod_tbst; -#endif #endif /* Other registers */
hw/ppc/pnv_chiptod.c +3 -4
@@ -364,8 +364,7 @@ static void pnv_chiptod_xscom_write(void *opaque, hwaddr addr,qemu_log_mask (LOG_GUEST_ERROR ,"pnv_chiptod: xscom write reg" " TOD_MOVE_TOD_TO_TB_REG with no slave target\n" ); }else { -PowerPCCPU *cpu = chiptod->slave_pc_target->threads[0 ]; -CPUPPCState *env = &cpu->env; +PnvCore *pc = chiptod->slave_pc_target;/* * Moving TOD to TB will set the TB of all threads in a
@@ -377,8 +376,8 @@ static void pnv_chiptod_xscom_write(void *opaque, hwaddr addr,* thread 0. */ -if (env->pnv_tod_tbst.tb_ready_for_tod) { - env->pnv_tod_tbst.tod_sent_to_tb =1 ; +if (pc->tod_state.tb_ready_for_tod) { + pc->tod_state.tod_sent_to_tb =1 ; }else {qemu_log_mask (LOG_GUEST_ERROR ,"pnv_chiptod: xscom write reg" " TOD_MOVE_TOD_TO_TB_REG with TB not ready to"
target/ppc/timebase_helper.c +29 -24
132 lines not on this page · raw message
Signature · 1 line
2.45.1
PATCH v3 12/19 ppc/pnv: Implement big-core PVR for Power9/10
In reply to Nicholas PigginPower9/10 CPUs have PVR[51] set in small-core mode and clear in big-core mode. This is used by skiboot firmware.
PVR is not hypervisor-privileged but it is not so important that spapr to implement this because it's generally masked out of PVR matching code in kernels, and only used by firmware.
--- hw/ppc/pnv_core.c | 4 ++++ 1 file changed, 4 insertions(+)
hw/ppc/pnv_core.c +4 -0
@@ -58,6 +58,10 @@ static void pnv_core_cpu_reset(PnvCore *pc, PowerPCCPU *cpu) env->nip =0x10 ; env->msr |=MSR_HVB ;/* Hypervisor mode */ env->spr[SPR_HRMOR ] = pc->hrmor; +if (pc->big_core) { +/* Clear "small core" bit on Power9/10 (this is set in default PVR) */ + env->spr[SPR_PVR ] &= ~PPC_BIT (51 ); + }hreg_compute_hflags (env);ppc_maybe_interrupt (env);
Signature · 1 line
2.45.1
PATCH v3 4/19 target/ppc: Move SPR indirect registers into PnvCore
In reply to Nicholas PigginSPRC/SPRD were recently added to all BookS CPUs supported, but they are only tested on POWER9 and POWER10, so restrict them to those CPUs.
SPR indirect scratch registers presently replicated per-CPU like SMT SPRs, but the PnvCore is a better place for them since they are restricted to P9/P10.
Also add SPR indirect read access to core thread state for POWER9 since skiboot accesses that when booting to check for big-core mode.
--- include/hw/ppc/pnv_core.h | 1 + target/ppc/cpu.h | 3 -- target/ppc/cpu_init.c | 21 +++++++------- target/ppc/misc_helper.c | 60 ++++++++++++++++++--------------------- 4 files changed, 39 insertions(+), 46 deletions(-)
include/hw/ppc/pnv_core.h +1 -0
@@ -53,6 +53,7 @@ struct PnvCore {uint32_t hwid;uint64_t hrmor; +target_ulong scratch[8 ];/* SPRC/SPRD indirect SCRATCH registers */ PnvCoreTODState tod_state;PnvChip *chip;
target/ppc/cpu.h +0 -3
@@ -1253,9 +1253,6 @@ struct CPUArchState {ppc_slb_t slb[MAX_SLB_ENTRIES ];/* PowerPC 64 SLB area */ struct CPUBreakpoint *ciabr_breakpoint;struct CPUWatchpoint *dawr0_watchpoint; - -/* POWER CPU regs/state */ -target_ulong scratch[8 ];/* SCRATCH registers (shared across core) */ #endif target_ulong sr[32 ];/* segment registers */ uint32_t nb_BATs;/* number of BATs */
target/ppc/cpu_init.c +11 -10
@@ -5777,16 +5777,6 @@ static void register_power_common_book4_sprs(CPUPPCState *env)SPR_NOACCESS ,SPR_NOACCESS , &spr_read_generic, &spr_core_write_generic, 0x00000000); -spr_register_hv (env,SPR_POWER_SPRC ,"SPRC" , -SPR_NOACCESS ,SPR_NOACCESS , -SPR_NOACCESS ,SPR_NOACCESS , - &spr_read_generic, &spr_write_sprc, -0x00000000 ); -spr_register_hv (env,SPR_POWER_SPRD ,"SPRD" , -SPR_NOACCESS ,SPR_NOACCESS , -SPR_NOACCESS ,SPR_NOACCESS , - &spr_read_sprd, &spr_write_sprd, -0x00000000 );#endif }
@@ -5799,6 +5789,17 @@ static void register_power9_book4_sprs(CPUPPCState *env)SPR_NOACCESS ,SPR_NOACCESS , &spr_read_generic, &spr_write_generic, KVM_REG_PPC_WORT, 0); +/* SPRC/SPRD exist in earlier CPUs but only tested on POWER9/10 */ +spr_register_hv (env,SPR_POWER_SPRC ,"SPRC" , +SPR_NOACCESS ,SPR_NOACCESS , +SPR_NOACCESS ,SPR_NOACCESS , + &spr_read_generic, &spr_write_sprc, +0x00000000 ); +spr_register_hv (env,SPR_POWER_SPRD ,"SPRD" , +SPR_NOACCESS ,SPR_NOACCESS , +SPR_NOACCESS ,SPR_NOACCESS , + &spr_read_sprd, &spr_write_sprd, +0x00000000 );#endif }
target/ppc/misc_helper.c +27 -33
85 lines not on this page · raw message
Signature · 1 line
2.45.1
PATCH v3 16/19 system/cpus: Add cpu_pause() function
In reply to Nicholas PigginThis factors the CPU pause function from pause_all_vcpus() into a new cpu_pause() function, similarly to cpu_resume(). cpu_resume() is moved to keep it next to cpu_pause().
--- include/hw/core/cpu.h | 8 ++++++++ system/cpus.c | 30 +++++++++++++++++------------- 2 files changed, 25 insertions(+), 13 deletions(-)
include/hw/core/cpu.h +8 -0
@@ -984,6 +984,14 @@ void cpu_reset_interrupt(CPUState *cpu, int mask);*/ void cpu_exit (CPUState *cpu); +/** +* cpu_pause: +* @cpu: The CPU to pause. +* +* Pauses CPU, i.e. puts CPU into stopped state. +*/ +void cpu_pause (CPUState *cpu); +/** * cpu_resume: * @cpu: The CPU to resume.
system/cpus.c +17 -13
@@ -568,6 +568,22 @@ void cpu_thread_signal_destroyed(CPUState *cpu)qemu_cond_signal (&qemu_cpu_cond); } +void cpu_pause (CPUState *cpu) +{ +if (qemu_cpu_is_self (cpu)) { +qemu_cpu_stop (cpu, true); + }else { + cpu->stop = true; +qemu_cpu_kick (cpu); + } +} + +void cpu_resume (CPUState *cpu) +{ + cpu->stop = false; + cpu->stopped = false; +qemu_cpu_kick (cpu); +}static bool all_vcpus_paused (void ) {
@@ -588,12 +604,7 @@ void pause_all_vcpus(void)qemu_clock_enable (QEMU_CLOCK_VIRTUAL , false);CPU_FOREACH (cpu) { -if (qemu_cpu_is_self (cpu)) { -qemu_cpu_stop (cpu, true); - }else { - cpu->stop = true; -qemu_cpu_kick (cpu); - } +cpu_pause (cpu); }/* We need to drop the replay_lock so any vCPU threads woken up
@@ -613,13 +624,6 @@ void pause_all_vcpus(void)bql_lock (); } -void cpu_resume (CPUState *cpu) -{ - cpu->stop = false; - cpu->stopped = false; -qemu_cpu_kick (cpu); -} -void resume_all_vcpus (void ) {CPUState *cpu;
Signature · 1 line
2.45.1
PATCH v3 19/19 ppc/pnv: Add an LPAR per core machine option
In reply to Nicholas PigginRecent POWER CPUs can operate in "LPAR per core" or "LPAR per thread" modes. In per-core mode, some SPRs and IPI doorbells are shared between threads in a core. In per-thread mode, supervisor and user state is not shared between threads.
OpenPOWER systems after POWER8 use LPAR per thread mode, and it is required for KVM. Enterprise systems use LPAR per core mode, as they partition the machine by core.
Implement a lpar-per-core machine option for powernv machines. This is fixed true for POWER8 machines, and defaults off for P9 and P10.
With this change, powernv8 SMT now works sufficiently to run Linux, with a single socket. Multi-threaded KVM guests still have problems, as does multi-socket Linux boot.
--- include/hw/ppc/pnv.h | 2 ++ include/hw/ppc/pnv_chip.h | 1 + include/hw/ppc/pnv_core.h | 1 + hw/ppc/pnv.c | 38 ++++++++++++++++++++++++++++++++++++++ hw/ppc/pnv_core.c | 8 ++++++++ target/ppc/cpu_init.c | 3 ++- 6 files changed, 52 insertions(+), 1 deletion(-)
include/hw/ppc/pnv.h +2 -0
@@ -77,6 +77,7 @@ struct PnvMachineClass {const char *compat;int compat_size;int max_smt_threads; +bool has_lpar_per_thread;bool quirk_tb_big_core;void (*dt_power_mgt)(PnvMachineState *pnv,void *fdt);
@@ -104,6 +105,7 @@ struct PnvMachineState {hwaddr fw_load_addr;bool big_core; +bool lpar_per_core; };PnvChip *pnv_get_chip (PnvMachineState *pnv,uint32_t chip_id);
include/hw/ppc/pnv_chip.h +1 -0
@@ -28,6 +28,7 @@ struct PnvChip {uint64_t ram_size;bool big_core; +bool lpar_per_core;uint32_t nr_cores;uint32_t nr_threads;uint64_t cores_mask;
include/hw/ppc/pnv_core.h +1 -0
@@ -57,6 +57,7 @@ struct PnvCore {/*< public >*/ PowerPCCPU **threads;bool big_core; +bool lpar_per_core;uint32_t pir;uint32_t hwid;uint64_t hrmor;
hw/ppc/pnv.c +38 -0
@@ -1026,6 +1026,11 @@ static void pnv_init(MachineState *machine)exit (1 ); } +/* Set lpar-per-core mode if lpar-per-thread is not supported */ +if (!pmc->has_lpar_per_thread) { + pnv->lpar_per_core = true; + } + pnv->num_chips = machine->smp.max_cpus / (machine->smp.cores * machine->smp.threads);
@@ -1102,6 +1107,8 @@ static void pnv_init(MachineState *machine) &error_fatal);object_property_set_bool (chip,"big-core" , pnv->big_core, &error_fatal); +object_property_set_bool (chip,"lpar-per-core" , pnv->lpar_per_core, + &error_fatal);/* * The POWER8 machine use the XICS interrupt interface. * Propagate the XICS fabric to the chip and its controllers.
@@ -2338,6 +2345,8 @@ static void pnv_chip_core_realize(PnvChip *chip, Error **errp) &error_fatal);object_property_set_bool (OBJECT (pnv_core),"quirk-tb-big-core" , pmc->quirk_tb_big_core, &error_fatal); +object_property_set_bool (OBJECT (pnv_core),"lpar-per-core" , + chip->lpar_per_core, &error_fatal);object_property_set_link (OBJECT (pnv_core),"chip" ,OBJECT (chip), &error_abort);
@@ -2373,6 +2382,7 @@ static Property pnv_chip_properties[] = {DEFINE_PROP_UINT64 ("cores-mask" , PnvChip, cores_mask,0x0 ),DEFINE_PROP_UINT32 ("nr-threads" , PnvChip, nr_threads,1 ),DEFINE_PROP_BOOL ("big-core" , PnvChip, big_core, false), +DEFINE_PROP_BOOL ("lpar-per-core" , PnvChip, lpar_per_core, false), DEFINE_PROP_END_OF_LIST(), };
@@ -2593,6 +2603,18 @@ static void pnv_machine_set_big_core(Object *obj, bool value, Error **errp) pnv->big_core = value; } +static bool pnv_machine_get_lpar_per_core (Object *obj,Error **errp) +{ +PnvMachineState *pnv =PNV_MACHINE (obj); +return pnv->lpar_per_core; +} + +static void pnv_machine_set_lpar_per_core (Object *obj,bool value,Error **errp) +{ +PnvMachineState *pnv =PNV_MACHINE (obj); + pnv->lpar_per_core = value; +} +static bool pnv_machine_get_hb (Object *obj,Error **errp) {PnvMachineState *pnv =PNV_MACHINE (obj);
@@ -2632,6 +2654,8 @@ static void pnv_machine_power8_class_init(ObjectClass *oc, void *data) pmc->compat = compat; pmc->compat_size =sizeof (compat); pmc->max_smt_threads =8 ; +/* POWER8 is always lpar-per-core mode */ + pmc->has_lpar_per_thread = false;machine_class_allow_dynamic_sysbus_dev (mc,TYPE_PNV_PHB ); }
@@ -2657,6 +2681,7 @@ static void pnv_machine_power9_class_init(ObjectClass *oc, void *data) pmc->compat = compat; pmc->compat_size =sizeof (compat); pmc->max_smt_threads =4 ; + pmc->has_lpar_per_thread = true; pmc->dt_power_mgt = pnv_dt_power_mgt;machine_class_allow_dynamic_sysbus_dev (mc,TYPE_PNV_PHB );
@@ -2666,6 +2691,12 @@ static void pnv_machine_power9_class_init(ObjectClass *oc, void *data) pnv_machine_set_big_core);object_class_property_set_description (oc,"big-core" ,"Use big-core (aka fused-core) mode" ); + +object_class_property_add_bool (oc,"lpar-per-core" , + pnv_machine_get_lpar_per_core, + pnv_machine_set_lpar_per_core); +object_class_property_set_description (oc,"lpar-per-core" , +"Use 1 LPAR per core mode" ); }static void pnv_machine_p10_common_class_init (ObjectClass *oc,void *data)
@@ -2688,6 +2719,7 @@ static void pnv_machine_p10_common_class_init(ObjectClass *oc, void *data) pmc->compat = compat; pmc->compat_size =sizeof (compat); pmc->max_smt_threads =4 ; + pmc->has_lpar_per_thread = true; pmc->quirk_tb_big_core = true; pmc->dt_power_mgt = pnv_dt_power_mgt;
@@ -2713,6 +2745,12 @@ static void pnv_machine_power10_class_init(ObjectClass *oc, void *data) pnv_machine_set_big_core);object_class_property_set_description (oc,"big-core" ,"Use big-core (aka fused-core) mode" ); + +object_class_property_add_bool (oc,"lpar-per-core" , + pnv_machine_get_lpar_per_core, + pnv_machine_set_lpar_per_core); +object_class_property_set_description (oc,"lpar-per-core" , +"Use 1 LPAR per core mode" ); }static void pnv_machine_p10_rainier_class_init (ObjectClass *oc,void *data)
hw/ppc/pnv_core.c +8 -0
@@ -208,6 +208,9 @@ static uint64_t pnv_core_power10_xscom_read(void *opaque, hwaddr addr, val |=PPC_BIT (56 + i); } } +if (pc->lpar_per_core) { + val |=PPC_BIT (62 ); + }break ;case PNV10_XSCOM_EC_CORE_THREAD_INFO :break ;
@@ -321,6 +324,10 @@ static void pnv_core_cpu_realize(PnvCore *pc, PowerPCCPU *cpu, Error **errp, env->core_index = core_hwid; } +if (pc->lpar_per_core) { +cpu_ppc_set_1lpar (cpu); + } +/* Set time-base frequency to 512 MHz */ cpu_ppc_tb_init (env,PNV_TIMEBASE_FREQ ); }
@@ -427,6 +434,7 @@ static Property pnv_core_properties[] = {DEFINE_PROP_BOOL ("big-core" , PnvCore, big_core, false),DEFINE_PROP_BOOL ("quirk-tb-big-core" , PnvCore, tod_state.big_core_quirk, false), +DEFINE_PROP_BOOL ("lpar-per-core" , PnvCore, lpar_per_core, false), DEFINE_PROP_LINK("chip", PnvCore, chip, TYPE_PNV_CHIP, PnvChip *), DEFINE_PROP_END_OF_LIST(), };
target/ppc/cpu_init.c +2 -1
@@ -6803,7 +6803,8 @@ void cpu_ppc_set_1lpar(PowerPCCPU *cpu)/* * pseries SMT means "LPAR per core" mode, e.g., msgsndp is usable -* between threads. +* between threads. powernv be in either mode, and it mostly affects +* supervisor visible registers and instructions. */ if (env->flags &POWERPC_FLAG_SMT ) { env->flags |=POWERPC_FLAG_SMT_1LPAR ;
Signature · 1 line
2.45.1
PATCH v3 11/19 ppc/pnv: Add allow for big-core differences in DT generation
In reply to Nicholas Piggindevice-tree building needs to account for big-core mode, because it is driven by qemu cores (small cores). Every second core should be skipped, and every core should describe threads for both small-cores that make up the big core.
--- hw/ppc/pnv.c | 43 +++++++++++++++++++++++++++++++++++-------- 1 file changed, 35 insertions(+), 8 deletions(-)
hw/ppc/pnv.c +35 -8
@@ -141,9 +141,9 @@ static int pnv_dt_core(PnvChip *chip, PnvCore *pc, void *fdt)CPUPPCState *env = &cpu->env;PowerPCCPUClass *pcc =POWERPC_CPU_GET_CLASS (cs);PnvChipClass *pnv_cc =PNV_CHIP_GET_CLASS (chip); - g_autofree uint32_t *servers_prop = g_new(uint32_t, smt_threads); +uint32_t *servers_prop;int i; -uint32_t pir; +uint32_t pir, tir;uint32_t segs[] = {cpu_to_be32 (28 ),cpu_to_be32 (40 ),0xffffffff ,0xffffffff };uint32_t tbfreq =PNV_TIMEBASE_FREQ ;
@@ -154,7 +154,10 @@ static int pnv_dt_core(PnvChip *chip, PnvCore *pc, void *fdt)char *nodename;int cpus_offset =get_cpus_node (fdt); - pnv_cc->get_pir_tir (chip, pc->hwid,0 , &pir,NULL ); + pnv_cc->get_pir_tir (chip, pc->hwid,0 , &pir, &tir); + +/* Only one DT node per (big) core */ +g_assert (tir ==0 ); nodename =g_strdup_printf ("%s@%x" , dc->fw_name, pir); offset =fdt_add_subnode (fdt, cpus_offset, nodename);
@@ -235,12 +238,28 @@ static int pnv_dt_core(PnvChip *chip, PnvCore *pc, void *fdt) }/* Build interrupt servers properties */ -for (i =0 ; i < smt_threads; i++) { - pnv_cc->get_pir_tir (chip, pc->hwid, i, &pir,NULL ); - servers_prop[i] =cpu_to_be32 (pir); +if (pc->big_core) { + servers_prop =g_new (uint32_t, smt_threads *2 ); +for (i =0 ; i < smt_threads; i++) { + pnv_cc->get_pir_tir (chip, pc->hwid, i, &pir,NULL ); + servers_prop[i *2 ] =cpu_to_be32 (pir); + + pnv_cc->get_pir_tir (chip, pc->hwid +1 , i, &pir,NULL ); + servers_prop[i *2 +1 ] =cpu_to_be32 (pir); + } +_FDT ((fdt_setprop (fdt, offset,"ibm,ppc-interrupt-server#s" , + servers_prop,sizeof (*servers_prop) * smt_threads + *2 ))); + }else { + servers_prop =g_new (uint32_t, smt_threads); +for (i =0 ; i < smt_threads; i++) { + pnv_cc->get_pir_tir (chip, pc->hwid, i, &pir,NULL ); + servers_prop[i] =cpu_to_be32 (pir); + } +_FDT ((fdt_setprop (fdt, offset,"ibm,ppc-interrupt-server#s" , + servers_prop,sizeof (*servers_prop) * smt_threads))); } -_FDT ((fdt_setprop (fdt, offset,"ibm,ppc-interrupt-server#s" , - servers_prop,sizeof (*servers_prop) * smt_threads))); +g_free (servers_prop);return offset; }
@@ -389,6 +408,10 @@ static void pnv_chip_power9_dt_populate(PnvChip *chip, void *fdt)_FDT ((fdt_setprop (fdt, offset,"ibm,pa-features" , pa_features_300,sizeof (pa_features_300)))); + +if (pnv_core->big_core) { + i++;/* Big-core groups two QEMU cores */ + } }if (chip->ram_size) {
@@ -450,6 +473,10 @@ static void pnv_chip_power10_dt_populate(PnvChip *chip, void *fdt)_FDT ((fdt_setprop (fdt, offset,"ibm,pa-features" , pa_features_31,sizeof (pa_features_31)))); + +if (pnv_core->big_core) { + i++;/* Big-core groups two QEMU cores */ + } }if (chip->ram_size) {
Signature · 1 line
2.45.1
PATCH v3 13/19 ppc/pnv: Implement Power9 CPU core thread state indirect register
In reply to Nicholas PigginPower9 CPUs have a core thread state register accessible via SPRC/SPRD indirect registers. This register includes a bit for big-core mode, which skiboot requires.
--- target/ppc/misc_helper.c | 17 +++++++++++++++++ 1 file changed, 17 insertions(+)
target/ppc/misc_helper.c +17 -0
@@ -319,6 +319,23 @@ target_ulong helper_load_sprd(CPUPPCState *env)case 0 :/* SCRATCH0-3 */ case 1 :/* SCRATCH4-7 */ return pc->scratch[(sprc >>3 ) &0x7 ]; + +case 0x1e0 :/* core thread state */ +if (env->excp_model ==POWERPC_EXCP_POWER9 ) { +/* +* Only implement for POWER9 because skiboot uses it to check +* big-core mode. Other bits are unimplemented so we would +* prefer to get unimplemented message on POWER10 if it were +* used anywhere. +*/ +if (pc->big_core) { +return PPC_BIT (63 ); + }else { +return 0 ; + } + } +/* fallthru */ +default :qemu_log_mask (LOG_UNIMP ,"mfSPRD: Unimplemented SPRC:0x" TARGET_FMT_lx"\n" , sprc);
Signature · 1 line
2.45.1
PATCH v3 17/19 ppc/pnv: Add a CPU nmi and resume function
In reply to Nicholas PigginPower CPUs have an execution control facility that can pause, resume, and cause NMIs, among other things. Add a function that will nmi a CPU and resume it if it was paused, in preparation for implementing the control facility.
--- include/hw/ppc/pnv.h | 2 ++ hw/ppc/pnv.c | 14 +++++++++++++- 2 files changed, 15 insertions(+), 1 deletion(-)
include/hw/ppc/pnv.h +2 -0
@@ -112,6 +112,8 @@ PnvChip *pnv_chip_add_phb(PnvChip *chip, PnvPHB *phb);#define PNV_FDT_ADDR 0x01000000#define PNV_TIMEBASE_FREQ 512000000ULL +void pnv_cpu_do_nmi_resume (CPUState *cs); +/* * BMC helpers */
hw/ppc/pnv.c +13 -1
@@ -2751,11 +2751,23 @@ static void pnv_cpu_do_nmi_on_cpu(CPUState *cs, run_on_cpu_data arg)*/ env->spr[SPR_SRR1 ] |=SRR1_WAKESCOM ; } +if (arg.host_int ==1 ) { +cpu_resume (cs); + } +} + +/* +* Send a SRESET (NMI) interrupt to the CPU, and resume execution if it was +* paused. +*/ +void pnv_cpu_do_nmi_resume (CPUState *cs) +{ +async_run_on_cpu (cs, pnv_cpu_do_nmi_on_cpu,RUN_ON_CPU_HOST_INT (1 )); }static void pnv_cpu_do_nmi (PnvChip *chip,PowerPCCPU *cpu,void *opaque) { -async_run_on_cpu (CPU (cpu), pnv_cpu_do_nmi_on_cpu,RUN_ON_CPU_NULL ); +async_run_on_cpu (CPU (cpu), pnv_cpu_do_nmi_on_cpu,RUN_ON_CPU_HOST_INT (0 )); }static void pnv_nmi (NMIState *n,int cpu_index,Error **errp)
Signature · 1 line
2.45.1
PATCH v3 7/19 ppc: Add a core_index to CPUPPCState for SMT vCPUs
In reply to Nicholas PigginThe way SMT thread siblings are matched is clunky, using hard-coded logic that checks the PIR SPR.
Change that to use a new core_index variable in the CPUPPCState, where all siblings have the same core_index. CPU realize routines have flexibility in setting core/sibling topology.
--- target/ppc/cpu.h | 9 +++++---- hw/ppc/pnv_core.c | 2 ++ hw/ppc/spapr_cpu_core.c | 4 ++++ 3 files changed, 11 insertions(+), 4 deletions(-)
target/ppc/cpu.h +5 -4
@@ -1247,6 +1247,9 @@ struct CPUArchState {/* when a memory exception occurs, the access type is stored here */ int access_type; +/* For SMT processors */ +int core_index; +#if !defined(CONFIG_USER_ONLY )/* MMU context, only relevant for full system emulation */ #if defined(TARGET_PPC64 )
@@ -1402,12 +1405,10 @@ struct CPUArchState {uint64_t pmu_base_time; }; -#define _CORE_ID (cs) \ - (POWERPC_CPU(cs)->env.spr_cb[SPR_PIR].default_value & ~(cs->nr_threads - 1)) -#define THREAD_SIBLING_FOREACH (cs, cs_sibling) \ CPU_FOREACH(cs_sibling) \ - if (_CORE_ID(cs) == _CORE_ID(cs_sibling)) + if (POWERPC_CPU(cs)->env.core_index == \ + POWERPC_CPU(cs_sibling)->env.core_index)#define SET_FIT_PERIOD (a_, b_, c_, d_) \ do { \
hw/ppc/pnv_core.c +2 -0
@@ -249,6 +249,8 @@ static void pnv_core_cpu_realize(PnvCore *pc, PowerPCCPU *cpu, Error **errp, pir_spr->default_value = pir; tir_spr->default_value = tir; + env->core_index = core_hwid; +/* Set time-base frequency to 512 MHz */ cpu_ppc_tb_init (env,PNV_TIMEBASE_FREQ ); }
hw/ppc/spapr_cpu_core.c +4 -0
@@ -302,11 +302,13 @@ static PowerPCCPU *spapr_create_vcpu(SpaprCpuCore *sc, int i, Error **errp) g_autofree char *id = NULL;CPUState *cs;PowerPCCPU *cpu; +CPUPPCState *env; obj =object_new (scc->cpu_type); cs =CPU (obj); cpu =POWERPC_CPU (obj); + env = &cpu->env;/* * All CPUs start halted. CPU0 is unhalted from the machine level reset code * and the rest are explicitly started up by the guest using an RTAS call.
@@ -317,6 +319,8 @@ static PowerPCCPU *spapr_create_vcpu(SpaprCpuCore *sc, int i, Error **errp)return NULL ; } + env->core_index = cc->core_id; + cpu->node_id = sc->node_id; id =g_strdup_printf ("thread[%d]" , i);
Signature · 1 line
2.45.1
PATCH v3 8/19 target/ppc: Add helpers to check for SMT sibling threads
In reply to Nicholas PigginAdd helpers for TCG code to determine if there are SMT siblings sharing per-core and per-lpar registers. This simplifies the callers and makes SMT register topology simpler to modify with later changes.
--- target/ppc/cpu.h | 11 +++++++++++ target/ppc/cpu_init.c | 2 +- target/ppc/excp_helper.c | 17 +++++------------ target/ppc/misc_helper.c | 27 ++++++--------------------- target/ppc/timebase_helper.c | 20 +++++++------------- 5 files changed, 30 insertions(+), 47 deletions(-)
target/ppc/cpu.h +11 -0
@@ -1512,6 +1512,17 @@ struct PowerPCCPUClass {int (*check_attn)(CPUPPCState *env); }; +static inline bool ppc_cpu_core_single_threaded (CPUState *cs) +{ +return cs->nr_threads ==1 ; +} + +static inline bool ppc_cpu_lpar_single_threaded (CPUState *cs) +{ +return !(POWERPC_CPU (cs)->env.flags &POWERPC_FLAG_SMT_1LPAR ) || +ppc_cpu_core_single_threaded (cs); +} +ObjectClass *ppc_cpu_class_by_name (const char *name);PowerPCCPUClass *ppc_cpu_class_by_pvr (uint32_t pvr);PowerPCCPUClass *ppc_cpu_class_by_pvr_mask (uint32_t pvr);
target/ppc/cpu_init.c +1 -1
@@ -6993,7 +6993,7 @@ static void ppc_cpu_realize(DeviceState *dev, Error **errp) pcc->parent_realize (dev, errp); -if (env_cpu (env)->nr_threads >1 ) { +if (!ppc_cpu_core_single_threaded (cs)) { env->flags |=POWERPC_FLAG_SMT ; }
target/ppc/excp_helper.c +5 -12
@@ -3014,18 +3014,11 @@ static void msgsnd_core_tir(CPUPPCState *env, uint32_t target_tir, int irq) {PowerPCCPU *cpu =env_archcpu (env);CPUState *cs =env_cpu (env); -uint32_t nr_threads = cs->nr_threads; -if (!(env->flags &POWERPC_FLAG_SMT_1LPAR )) { - nr_threads =1 ;/* msgsndp behaves as 1-thread in LPAR-per-thread mode*/ - } - -if (target_tir >= nr_threads) { -return ; - } - -if (nr_threads ==1 ) { -ppc_set_irq (cpu, irq,1 ); +if (ppc_cpu_lpar_single_threaded (cs)) { +if (target_tir ==0 ) { +ppc_set_irq (cpu, irq,1 ); + } }else {CPUState *ccs;
@@ -3080,7 +3073,7 @@ void helper_book3s_msgsnd(CPUPPCState *env, target_ulong rb) brdcast = true; } -if (cs->nr_threads ==1 || !brdcast) { +if (ppc_cpu_core_single_threaded (cs) || !brdcast) {ppc_set_irq (cpu,PPC_INTERRUPT_HDOORBELL ,1 );return ; }
target/ppc/misc_helper.c +6 -21
@@ -49,9 +49,8 @@ void helper_spr_core_write_generic(CPUPPCState *env, uint32_t sprn, {CPUState *cs =env_cpu (env);CPUState *ccs; -uint32_t nr_threads = cs->nr_threads; -if (nr_threads ==1 ) { +if (ppc_cpu_core_single_threaded (cs)) { env->spr[sprn] = val;return ; }
@@ -196,7 +195,7 @@ void helper_store_ptcr(CPUPPCState *env, target_ulong val)return ; } -if (cs->nr_threads ==1 || !(env->flags &POWERPC_FLAG_SMT_1LPAR )) { +if (ppc_cpu_lpar_single_threaded (cs)) { env->spr[SPR_PTCR ] = val;tlb_flush (cs); }else {
@@ -243,16 +242,12 @@ target_ulong helper_load_dpdes(CPUPPCState *env) {CPUState *cs =env_cpu (env);CPUState *ccs; -uint32_t nr_threads = cs->nr_threads;target_ulong dpdes =0 ;helper_hfscr_facility_check (env,HFSCR_MSGP ,"load DPDES" ,HFSCR_IC_MSGP ); -if (!(env->flags &POWERPC_FLAG_SMT_1LPAR )) { - nr_threads =1 ;/* DPDES behaves as 1-thread in LPAR-per-thread mode */ - } - -if (nr_threads ==1 ) { +/* DPDES behaves as 1-thread in LPAR-per-thread mode */ +if (ppc_cpu_lpar_single_threaded (cs)) {if (env->pending_interrupts &PPC_INTERRUPT_DOORBELL ) { dpdes =1 ; }
@@ -279,21 +274,11 @@ void helper_store_dpdes(CPUPPCState *env, target_ulong val)PowerPCCPU *cpu =env_archcpu (env);CPUState *cs =env_cpu (env);CPUState *ccs; -uint32_t nr_threads = cs->nr_threads;helper_hfscr_facility_check (env,HFSCR_MSGP ,"store DPDES" ,HFSCR_IC_MSGP ); -if (!(env->flags &POWERPC_FLAG_SMT_1LPAR )) { - nr_threads =1 ;/* DPDES behaves as 1-thread in LPAR-per-thread mode */ - } - -if (val & ~(nr_threads -1 )) { -qemu_log_mask (LOG_GUEST_ERROR ,"Invalid DPDES register value " - TARGET_FMT_lx"\n" , val); - val &= (nr_threads -1 );/* Ignore the invalid bits */ - } - -if (nr_threads ==1 ) { +/* DPDES behaves as 1-thread in LPAR-per-thread mode */ +if (ppc_cpu_lpar_single_threaded (cs)) {ppc_set_irq (cpu,PPC_INTERRUPT_DOORBELL , val &0x1 );return ; }
target/ppc/timebase_helper.c +7 -13
@@ -63,9 +63,8 @@ void helper_store_purr(CPUPPCState *env, target_ulong val) {CPUState *cs =env_cpu (env);CPUState *ccs; -uint32_t nr_threads = cs->nr_threads; -if (nr_threads ==1 || !(env->flags &POWERPC_FLAG_SMT_1LPAR )) { +if (ppc_cpu_lpar_single_threaded (cs)) {cpu_ppc_store_purr (env, val);return ; }
@@ -82,9 +81,8 @@ void helper_store_tbl(CPUPPCState *env, target_ulong val) {CPUState *cs =env_cpu (env);CPUState *ccs; -uint32_t nr_threads = cs->nr_threads; -if (nr_threads ==1 || !(env->flags &POWERPC_FLAG_SMT_1LPAR )) { +if (ppc_cpu_lpar_single_threaded (cs)) {cpu_ppc_store_tbl (env, val);return ; }
@@ -99,9 +97,8 @@ void helper_store_tbu(CPUPPCState *env, target_ulong val) {CPUState *cs =env_cpu (env);CPUState *ccs; -uint32_t nr_threads = cs->nr_threads; -if (nr_threads ==1 || !(env->flags &POWERPC_FLAG_SMT_1LPAR )) { +if (ppc_cpu_lpar_single_threaded (cs)) {cpu_ppc_store_tbu (env, val);return ; }
@@ -141,9 +138,8 @@ void helper_store_hdecr(CPUPPCState *env, target_ulong val) {CPUState *cs =env_cpu (env);CPUState *ccs; -uint32_t nr_threads = cs->nr_threads; -if (nr_threads ==1 || !(env->flags &POWERPC_FLAG_SMT_1LPAR )) { +if (ppc_cpu_lpar_single_threaded (cs)) {cpu_ppc_store_hdecr (env, val);return ; }
@@ -158,9 +154,8 @@ void helper_store_vtb(CPUPPCState *env, target_ulong val) {CPUState *cs =env_cpu (env);CPUState *ccs; -uint32_t nr_threads = cs->nr_threads; -if (nr_threads ==1 || !(env->flags &POWERPC_FLAG_SMT_1LPAR )) { +if (ppc_cpu_lpar_single_threaded (cs)) {cpu_ppc_store_vtb (env, val);return ; }
@@ -175,9 +170,8 @@ void helper_store_tbu40(CPUPPCState *env, target_ulong val) {CPUState *cs =env_cpu (env);CPUState *ccs; -uint32_t nr_threads = cs->nr_threads; -if (nr_threads ==1 || !(env->flags &POWERPC_FLAG_SMT_1LPAR )) { +if (ppc_cpu_lpar_single_threaded (cs)) {cpu_ppc_store_tbu40 (env, val);return ; }
@@ -288,7 +282,7 @@ static void write_tfmr(CPUPPCState *env, target_ulong val) {CPUState *cs =env_cpu (env); -if (cs->nr_threads ==1 ) { +if (ppc_cpu_core_single_threaded (cs)) { env->spr[SPR_TFMR ] = val; }else {CPUState *ccs;
Signature · 1 line
2.45.1
PATCH v3 14/19 ppc/pnv: Add POWER10 ChipTOD quirk for big-core
In reply to Nicholas PigginPOWER10 has a quirk in its ChipTOD addressing that requires the even small-core to be selected even when programming the odd small-core. This allows skiboot chiptod init to run in big-core mode.
--- include/hw/ppc/pnv.h | 1 + include/hw/ppc/pnv_core.h | 7 +++++++ hw/ppc/pnv.c | 7 ++++++- hw/ppc/pnv_core.c | 2 ++ target/ppc/timebase_helper.c | 9 +++++++++ 5 files changed, 25 insertions(+), 1 deletion(-)
include/hw/ppc/pnv.h +1 -0
@@ -77,6 +77,7 @@ struct PnvMachineClass {const char *compat;int compat_size;int max_smt_threads; +bool quirk_tb_big_core;void (*dt_power_mgt)(PnvMachineState *pnv,void *fdt);void (*i2c_init)(PnvMachineState *pnv);
include/hw/ppc/pnv_core.h +7 -0
@@ -27,6 +27,13 @@/* Per-core ChipTOD / TimeBase state */ typedef struct PnvCoreTODState { + /* + * POWER10 DD2.0 - big core TFMR drives the state machine on the even + * small core. Skiboot has a workaround that targets the even small core + * for CHIPTOD_TO_TB ops. + */ + bool big_core_quirk; + int tb_ready_for_tod; /* core TB ready to receive TOD from chiptod */ int tod_sent_to_tb; /* chiptod sent TOD to the core TB */
hw/ppc/pnv.c +6 -1
@@ -2290,11 +2290,12 @@ static void pnv_chip_core_sanitize(PnvMachineState *pnv, PnvChip *chip,static void pnv_chip_core_realize (PnvChip *chip,Error **errp) { +PnvMachineState *pnv =PNV_MACHINE (qdev_get_machine ()); +PnvMachineClass *pmc =PNV_MACHINE_GET_CLASS (pnv);Error *error =NULL ;PnvChipClass *pcc =PNV_CHIP_GET_CLASS (chip);const char *typename =pnv_chip_core_typename (chip);int i, core_hwid; -PnvMachineState *pnv =PNV_MACHINE (qdev_get_machine ());if (!object_class_by_name (typename)) {error_setg (errp,"Unable to find PowerNV CPU Core '%s'" , typename);
@@ -2335,8 +2336,11 @@ static void pnv_chip_core_realize(PnvChip *chip, Error **errp) &error_fatal);object_property_set_bool (OBJECT (pnv_core),"big-core" , chip->big_core, &error_fatal); +object_property_set_bool (OBJECT (pnv_core),"quirk-tb-big-core" , + pmc->quirk_tb_big_core, &error_fatal);object_property_set_link (OBJECT (pnv_core),"chip" ,OBJECT (chip), &error_abort); +qdev_realize (DEVICE (pnv_core),NULL , &error_fatal);/* Each core has an XSCOM MMIO region */
@@ -2650,6 +2654,7 @@ static void pnv_machine_p10_common_class_init(ObjectClass *oc, void *data) pmc->compat = compat; pmc->compat_size =sizeof (compat); pmc->max_smt_threads =4 ; + pmc->quirk_tb_big_core = true; pmc->dt_power_mgt = pnv_dt_power_mgt; xfc->match_nvt = pnv10_xive_match_nvt;
hw/ppc/pnv_core.c +2 -0
@@ -364,6 +364,8 @@ static Property pnv_core_properties[] = {DEFINE_PROP_UINT32 ("hwid" , PnvCore, hwid,0 ),DEFINE_PROP_UINT64 ("hrmor" , PnvCore, hrmor,0 ),DEFINE_PROP_BOOL ("big-core" , PnvCore, big_core, false), +DEFINE_PROP_BOOL ("quirk-tb-big-core" , PnvCore, tod_state.big_core_quirk, + false), DEFINE_PROP_LINK("chip", PnvCore, chip, TYPE_PNV_CHIP, PnvChip *), DEFINE_PROP_END_OF_LIST(), };
target/ppc/timebase_helper.c +9 -0
@@ -20,6 +20,7 @@#include "cpu.h" #include "hw/ppc/ppc.h" #include "hw/ppc/pnv_core.h" +#include "hw/ppc/pnv_chip.h" #include "exec/helper-proto.h" #include "exec/exec-all.h" #include "qemu/log.h"
@@ -297,6 +298,14 @@ static PnvCoreTODState *cpu_get_tbst(PowerPCCPU *cpu) {PnvCore *pc =pnv_cpu_state (cpu)->pnv_core; +if (pc->big_core && pc->tod_state.big_core_quirk) { +/* Must operate on the even small core */ +int core_id =CPU_CORE (pc)->core_id; +if (core_id &1 ) { + pc = pc->chip->cores[core_id & ~1 ]; + } + } +return &pc->tod_state; }
Signature · 1 line
2.45.1
PATCH v3 18/19 ppc/pnv: Implement POWER10 PC xscom registers for direct controls
In reply to Nicholas PigginThe PC unit in the processor core contains xscom registers that provide low level status and control of the CPU.
This implements "direct controls", sufficient for skiboot firmware, which uses it to send NMI IPIs between CPUs.
POWER10 is sufficiently different from POWER9 (particularly with respect to QME and special wakeup) that it is not trivial to implement POWER9 support by reusing the code.
--- include/hw/ppc/pnv_core.h | 3 ++ hw/ppc/pnv_core.c | 89 ++++++++++++++++++++++++++++++++++++--- 2 files changed, 87 insertions(+), 5 deletions(-)
include/hw/ppc/pnv_core.h +3 -0
@@ -109,6 +109,9 @@ OBJECT_DECLARE_TYPE(PnvQuad, PnvQuadClass, PNV_QUAD)struct PnvQuad {DeviceState parent_obj; +bool special_wakeup_done; +bool special_wakeup[4 ]; +uint32_t quad_id;MemoryRegion xscom_regs;MemoryRegion xscom_qme_regs;
hw/ppc/pnv_core.c +84 -5
134 lines not on this page · raw message
Signature · 1 line
2.45.1
Re: [PATCH v3 15/19] ppc/pnv: Add big-core machine property
In reply to Nicholas PigginQuoted 5 lines · Nicholas Piggin
Big-core implementation is complete, so expose it as a machine property that may be set with big-core=on option on powernv9 and powernv10 machines.
Signed-off-by Nicholas Piggin <[email protected]>
Thanks,
C.
Quoted 97 lines
--- hw/ppc/pnv.c | 61 ++++++++++++++++++++++++++++++++++++++-------------- 1 file changed, 45 insertions(+), 16 deletions(-)hw/ppc/pnv.c +45
-16@@ -2581,6 +2581,34 @@ static int pnv10_xive_match_nvt(XiveFabric *xfb, uint8_t format,return total_count; } +static bool pnv_machine_get_big_core (Object *obj,Error **errp) +{ +PnvMachineState *pnv =PNV_MACHINE (obj); +return pnv->big_core; +} + +static void pnv_machine_set_big_core (Object *obj,bool value,Error **errp) +{ +PnvMachineState *pnv =PNV_MACHINE (obj); + pnv->big_core = value; +} + +static bool pnv_machine_get_hb (Object *obj,Error **errp) +{ +PnvMachineState *pnv =PNV_MACHINE (obj); + +return !!pnv->fw_load_addr; +} + +static void pnv_machine_set_hb (Object *obj,bool value,Error **errp) +{ +PnvMachineState *pnv =PNV_MACHINE (obj); + +if (value) { + pnv->fw_load_addr =0x8000000 ; + } +} +static void pnv_machine_power8_class_init (ObjectClass *oc,void *data) {MachineClass *mc =MACHINE_CLASS (oc);@@ -2632,6 +2660,12 @@ static void pnv_machine_power9_class_init(ObjectClass *oc, void *data) pmc->dt_power_mgt = pnv_dt_power_mgt;machine_class_allow_dynamic_sysbus_dev (mc,TYPE_PNV_PHB ); + +object_class_property_add_bool (oc,"big-core" , + pnv_machine_get_big_core, + pnv_machine_set_big_core); +object_class_property_set_description (oc,"big-core" , +"Use big-core (aka fused-core) mode" ); }static void pnv_machine_p10_common_class_init (ObjectClass *oc,void *data)@@ -2668,6 +2702,17 @@ static void pnv_machine_power10_class_init(ObjectClass *oc, void *data)pnv_machine_p10_common_class_init (oc, data); mc->desc ="IBM PowerNV (Non-Virtualized) POWER10" ; + +/* +* This is the parent of POWER10 Rainier class, so properies go here +* rather than common init (which would add them to both parent and +* child which is invalid). +*/ +object_class_property_add_bool (oc,"big-core" , + pnv_machine_get_big_core, + pnv_machine_set_big_core); +object_class_property_set_description (oc,"big-core" , +"Use big-core (aka fused-core) mode" ); }static void pnv_machine_p10_rainier_class_init (ObjectClass *oc,void *data)@@ -2680,22 +2725,6 @@ static void pnv_machine_p10_rainier_class_init(ObjectClass *oc, void *data) pmc->i2c_init = pnv_rainier_i2c_init; } -static bool pnv_machine_get_hb (Object *obj,Error **errp) -{ -PnvMachineState *pnv =PNV_MACHINE (obj); - -return !!pnv->fw_load_addr; -} - -static void pnv_machine_set_hb (Object *obj,bool value,Error **errp) -{ -PnvMachineState *pnv =PNV_MACHINE (obj); - -if (value) { - pnv->fw_load_addr =0x8000000 ; - } -} -static void pnv_cpu_do_nmi_on_cpu (CPUState *cs,run_on_cpu_data arg) {CPUPPCState *env =cpu_env (cs);
Re: [PATCH v3 14/19] ppc/pnv: Add POWER10 ChipTOD quirk for big-core
In reply to Nicholas PigginQuoted 5 lines · Nicholas Piggin
POWER10 has a quirk in its ChipTOD addressing that requires the even small-core to be selected even when programming the odd small-core. This allows skiboot chiptod init to run in big-core mode.
Signed-off-by Nicholas Piggin <[email protected]>
Thanks,
C.
Quoted 116 lines
--- include/hw/ppc/pnv.h | 1 + include/hw/ppc/pnv_core.h | 7 +++++++ hw/ppc/pnv.c | 7 ++++++- hw/ppc/pnv_core.c | 2 ++ target/ppc/timebase_helper.c | 9 +++++++++ 5 files changed, 25 insertions(+), 1 deletion(-)include/hw/ppc/pnv.h +1
-0@@ -77,6 +77,7 @@ struct PnvMachineClass {const char *compat;int compat_size;int max_smt_threads; +bool quirk_tb_big_core;void (*dt_power_mgt)(PnvMachineState *pnv,void *fdt);void (*i2c_init)(PnvMachineState *pnv);include/hw/ppc/pnv_core.h +7
-0@@ -27,6 +27,13 @@/* Per-core ChipTOD / TimeBase state */ typedef struct PnvCoreTODState { + /* + * POWER10 DD2.0 - big core TFMR drives the state machine on the even + * small core. Skiboot has a workaround that targets the even small core + * for CHIPTOD_TO_TB ops. + */ + bool big_core_quirk; + int tb_ready_for_tod; /* core TB ready to receive TOD from chiptod */ int tod_sent_to_tb; /* chiptod sent TOD to the core TB */hw/ppc/pnv.c +6
-1@@ -2290,11 +2290,12 @@ static void pnv_chip_core_sanitize(PnvMachineState *pnv, PnvChip *chip,static void pnv_chip_core_realize (PnvChip *chip,Error **errp) { +PnvMachineState *pnv =PNV_MACHINE (qdev_get_machine ()); +PnvMachineClass *pmc =PNV_MACHINE_GET_CLASS (pnv);Error *error =NULL ;PnvChipClass *pcc =PNV_CHIP_GET_CLASS (chip);const char *typename =pnv_chip_core_typename (chip);int i, core_hwid; -PnvMachineState *pnv =PNV_MACHINE (qdev_get_machine ());if (!object_class_by_name (typename)) {error_setg (errp,"Unable to find PowerNV CPU Core '%s'" , typename);@@ -2335,8 +2336,11 @@ static void pnv_chip_core_realize(PnvChip *chip, Error **errp) &error_fatal);object_property_set_bool (OBJECT (pnv_core),"big-core" , chip->big_core, &error_fatal); +object_property_set_bool (OBJECT (pnv_core),"quirk-tb-big-core" , + pmc->quirk_tb_big_core, &error_fatal);object_property_set_link (OBJECT (pnv_core),"chip" ,OBJECT (chip), &error_abort); +qdev_realize (DEVICE (pnv_core),NULL , &error_fatal);/* Each core has an XSCOM MMIO region */ @@ -2650,6 +2654,7 @@ static void pnv_machine_p10_common_class_init(ObjectClass *oc, void *data) pmc->compat = compat; pmc->compat_size =sizeof (compat); pmc->max_smt_threads =4 ; + pmc->quirk_tb_big_core = true; pmc->dt_power_mgt = pnv_dt_power_mgt; xfc->match_nvt = pnv10_xive_match_nvt;hw/ppc/pnv_core.c +2
-0@@ -364,6 +364,8 @@ static Property pnv_core_properties[] = {DEFINE_PROP_UINT32 ("hwid" , PnvCore, hwid,0 ),DEFINE_PROP_UINT64 ("hrmor" , PnvCore, hrmor,0 ),DEFINE_PROP_BOOL ("big-core" , PnvCore, big_core, false), +DEFINE_PROP_BOOL ("quirk-tb-big-core" , PnvCore, tod_state.big_core_quirk, + false), DEFINE_PROP_LINK("chip", PnvCore, chip, TYPE_PNV_CHIP, PnvChip *), DEFINE_PROP_END_OF_LIST(), };target/ppc/timebase_helper.c +9
-0@@ -20,6 +20,7 @@#include "cpu.h" #include "hw/ppc/ppc.h" #include "hw/ppc/pnv_core.h" +#include "hw/ppc/pnv_chip.h" #include "exec/helper-proto.h" #include "exec/exec-all.h" #include "qemu/log.h" @@ -297,6 +298,14 @@ static PnvCoreTODState *cpu_get_tbst(PowerPCCPU *cpu) {PnvCore *pc =pnv_cpu_state (cpu)->pnv_core; +if (pc->big_core && pc->tod_state.big_core_quirk) { +/* Must operate on the even small core */ +int core_id =CPU_CORE (pc)->core_id; +if (core_id &1 ) { + pc = pc->chip->cores[core_id & ~1 ]; + } + } +return &pc->tod_state; }
Re: [PATCH v3 19/19] ppc/pnv: Add an LPAR per core machine option
In reply to Nicholas PigginQuoted 9 lines · Nicholas Piggin
Recent POWER CPUs can operate in "LPAR per core" or "LPAR per thread" modes. In per-core mode, some SPRs and IPI doorbells are shared between threads in a core. In per-thread mode, supervisor and user state is not shared between threads.
OpenPOWER systems after POWER8 use LPAR per thread mode, and it is required for KVM. Enterprise systems use LPAR per core mode, as they partition the machine by core.
Quoted 8 lines
Implement a lpar-per-core machine option for powernv machines. This is fixed true for POWER8 machines, and defaults off for P9 and P10.
With this change, powernv8 SMT now works sufficiently to run Linux, with a single socket. Multi-threaded KVM guests still have problems, as does multi-socket Linux boot.
Signed-off-by Nicholas Piggin <[email protected]>
Thanks,
C.
Quoted 212 lines
--- include/hw/ppc/pnv.h | 2 ++ include/hw/ppc/pnv_chip.h | 1 + include/hw/ppc/pnv_core.h | 1 + hw/ppc/pnv.c | 38 ++++++++++++++++++++++++++++++++++++++ hw/ppc/pnv_core.c | 8 ++++++++ target/ppc/cpu_init.c | 3 ++- 6 files changed, 52 insertions(+), 1 deletion(-)include/hw/ppc/pnv.h +2
-0@@ -77,6 +77,7 @@ struct PnvMachineClass {const char *compat;int compat_size;int max_smt_threads; +bool has_lpar_per_thread;bool quirk_tb_big_core;void (*dt_power_mgt)(PnvMachineState *pnv,void *fdt);@@ -104,6 +105,7 @@ struct PnvMachineState {hwaddr fw_load_addr;bool big_core; +bool lpar_per_core; };PnvChip *pnv_get_chip (PnvMachineState *pnv,uint32_t chip_id);include/hw/ppc/pnv_chip.h +1
-0@@ -28,6 +28,7 @@ struct PnvChip {uint64_t ram_size;bool big_core; +bool lpar_per_core;uint32_t nr_cores;uint32_t nr_threads;uint64_t cores_mask;include/hw/ppc/pnv_core.h +1
-0@@ -57,6 +57,7 @@ struct PnvCore {/*< public >*/ PowerPCCPU **threads;bool big_core; +bool lpar_per_core;uint32_t pir;uint32_t hwid;uint64_t hrmor;hw/ppc/pnv.c +38
-0@@ -1026,6 +1026,11 @@ static void pnv_init(MachineState *machine)exit (1 ); } +/* Set lpar-per-core mode if lpar-per-thread is not supported */ +if (!pmc->has_lpar_per_thread) { + pnv->lpar_per_core = true; + } + pnv->num_chips = machine->smp.max_cpus / (machine->smp.cores * machine->smp.threads);@@ -1102,6 +1107,8 @@ static void pnv_init(MachineState *machine) &error_fatal);object_property_set_bool (chip,"big-core" , pnv->big_core, &error_fatal); +object_property_set_bool (chip,"lpar-per-core" , pnv->lpar_per_core, + &error_fatal);/* * The POWER8 machine use the XICS interrupt interface. * Propagate the XICS fabric to the chip and its controllers. @@ -2338,6 +2345,8 @@ static void pnv_chip_core_realize(PnvChip *chip, Error **errp) &error_fatal);object_property_set_bool (OBJECT (pnv_core),"quirk-tb-big-core" , pmc->quirk_tb_big_core, &error_fatal); +object_property_set_bool (OBJECT (pnv_core),"lpar-per-core" , + chip->lpar_per_core, &error_fatal);object_property_set_link (OBJECT (pnv_core),"chip" ,OBJECT (chip), &error_abort);@@ -2373,6 +2382,7 @@ static Property pnv_chip_properties[] = {DEFINE_PROP_UINT64 ("cores-mask" , PnvChip, cores_mask,0x0 ),DEFINE_PROP_UINT32 ("nr-threads" , PnvChip, nr_threads,1 ),DEFINE_PROP_BOOL ("big-core" , PnvChip, big_core, false), +DEFINE_PROP_BOOL ("lpar-per-core" , PnvChip, lpar_per_core, false), DEFINE_PROP_END_OF_LIST(), };@@ -2593,6 +2603,18 @@ static void pnv_machine_set_big_core(Object *obj, bool value, Error **errp) pnv->big_core = value; } +static bool pnv_machine_get_lpar_per_core (Object *obj,Error **errp) +{ +PnvMachineState *pnv =PNV_MACHINE (obj); +return pnv->lpar_per_core; +} + +static void pnv_machine_set_lpar_per_core (Object *obj,bool value,Error **errp) +{ +PnvMachineState *pnv =PNV_MACHINE (obj); + pnv->lpar_per_core = value; +} +static bool pnv_machine_get_hb (Object *obj,Error **errp) {PnvMachineState *pnv =PNV_MACHINE (obj);@@ -2632,6 +2654,8 @@ static void pnv_machine_power8_class_init(ObjectClass *oc, void *data) pmc->compat = compat; pmc->compat_size =sizeof (compat); pmc->max_smt_threads =8 ; +/* POWER8 is always lpar-per-core mode */ + pmc->has_lpar_per_thread = false;machine_class_allow_dynamic_sysbus_dev (mc,TYPE_PNV_PHB ); }@@ -2657,6 +2681,7 @@ static void pnv_machine_power9_class_init(ObjectClass *oc, void *data) pmc->compat = compat; pmc->compat_size =sizeof (compat); pmc->max_smt_threads =4 ; + pmc->has_lpar_per_thread = true; pmc->dt_power_mgt = pnv_dt_power_mgt;machine_class_allow_dynamic_sysbus_dev (mc,TYPE_PNV_PHB );@@ -2666,6 +2691,12 @@ static void pnv_machine_power9_class_init(ObjectClass *oc, void *data) pnv_machine_set_big_core);object_class_property_set_description (oc,"big-core" ,"Use big-core (aka fused-core) mode" ); + +object_class_property_add_bool (oc,"lpar-per-core" , + pnv_machine_get_lpar_per_core, + pnv_machine_set_lpar_per_core); +object_class_property_set_description (oc,"lpar-per-core" , +"Use 1 LPAR per core mode" ); }static void pnv_machine_p10_common_class_init (ObjectClass *oc,void *data)@@ -2688,6 +2719,7 @@ static void pnv_machine_p10_common_class_init(ObjectClass *oc, void *data) pmc->compat = compat; pmc->compat_size =sizeof (compat); pmc->max_smt_threads =4 ; + pmc->has_lpar_per_thread = true; pmc->quirk_tb_big_core = true; pmc->dt_power_mgt = pnv_dt_power_mgt;@@ -2713,6 +2745,12 @@ static void pnv_machine_power10_class_init(ObjectClass *oc, void *data) pnv_machine_set_big_core);object_class_property_set_description (oc,"big-core" ,"Use big-core (aka fused-core) mode" ); + +object_class_property_add_bool (oc,"lpar-per-core" , + pnv_machine_get_lpar_per_core, + pnv_machine_set_lpar_per_core); +object_class_property_set_description (oc,"lpar-per-core" , +"Use 1 LPAR per core mode" ); }static void pnv_machine_p10_rainier_class_init (ObjectClass *oc,void *data)hw/ppc/pnv_core.c +8
-0@@ -208,6 +208,9 @@ static uint64_t pnv_core_power10_xscom_read(void *opaque, hwaddr addr, val |=PPC_BIT (56 + i); } } +if (pc->lpar_per_core) { + val |=PPC_BIT (62 ); + }break ;case PNV10_XSCOM_EC_CORE_THREAD_INFO :break ;@@ -321,6 +324,10 @@ static void pnv_core_cpu_realize(PnvCore *pc, PowerPCCPU *cpu, Error **errp, env->core_index = core_hwid; } +if (pc->lpar_per_core) { +cpu_ppc_set_1lpar (cpu); + } +/* Set time-base frequency to 512 MHz */ cpu_ppc_tb_init (env,PNV_TIMEBASE_FREQ ); }@@ -427,6 +434,7 @@ static Property pnv_core_properties[] = {DEFINE_PROP_BOOL ("big-core" , PnvCore, big_core, false),DEFINE_PROP_BOOL ("quirk-tb-big-core" , PnvCore, tod_state.big_core_quirk, false), +DEFINE_PROP_BOOL ("lpar-per-core" , PnvCore, lpar_per_core, false), DEFINE_PROP_LINK("chip", PnvCore, chip, TYPE_PNV_CHIP, PnvChip *), DEFINE_PROP_END_OF_LIST(), };target/ppc/cpu_init.c +2
-1@@ -6803,7 +6803,8 @@ void cpu_ppc_set_1lpar(PowerPCCPU *cpu)/* * pseries SMT means "LPAR per core" mode, e.g., msgsndp is usable -* between threads. +* between threads. powernv be in either mode, and it mostly affects +* supervisor visible registers and instructions. */ if (env->flags &POWERPC_FLAG_SMT ) { env->flags |=POWERPC_FLAG_SMT_1LPAR ;
Re: [PATCH v3 13/19] ppc/pnv: Implement Power9 CPU core thread state indirect register
In reply to Nicholas PigginQuoted 5 lines · Nicholas Piggin
Power9 CPUs have a core thread state register accessible via SPRC/SPRD indirect registers. This register includes a bit for big-core mode, which skiboot requires.
Signed-off-by Nicholas Piggin <[email protected]>
Thanks,
C.
Quoted 32 lines
--- target/ppc/misc_helper.c | 17 +++++++++++++++++ 1 file changed, 17 insertions(+)target/ppc/misc_helper.c +17
-0@@ -319,6 +319,23 @@ target_ulong helper_load_sprd(CPUPPCState *env)case 0 :/* SCRATCH0-3 */ case 1 :/* SCRATCH4-7 */ return pc->scratch[(sprc >>3 ) &0x7 ]; + +case 0x1e0 :/* core thread state */ +if (env->excp_model ==POWERPC_EXCP_POWER9 ) { +/* +* Only implement for POWER9 because skiboot uses it to check +* big-core mode. Other bits are unimplemented so we would +* prefer to get unimplemented message on POWER10 if it were +* used anywhere. +*/ +if (pc->big_core) { +return PPC_BIT (63 ); + }else { +return 0 ; + } + } +/* fallthru */ +default :qemu_log_mask (LOG_UNIMP ,"mfSPRD: Unimplemented SPRC:0x" TARGET_FMT_lx"\n" , sprc);
Re: [PATCH v3 11/19] ppc/pnv: Add allow for big-core differences in DT generation
In reply to Nicholas PigginQuoted 6 lines · Nicholas Piggin
device-tree building needs to account for big-core mode, because it is driven by qemu cores (small cores). Every second core should be skipped, and every core should describe threads for both small-cores that make up the big core.
Signed-off-by Nicholas Piggin <[email protected]>
Thanks,
C.
Quoted 88 lines
--- hw/ppc/pnv.c | 43 +++++++++++++++++++++++++++++++++++-------- 1 file changed, 35 insertions(+), 8 deletions(-)hw/ppc/pnv.c +35
-8@@ -141,9 +141,9 @@ static int pnv_dt_core(PnvChip *chip, PnvCore *pc, void *fdt)CPUPPCState *env = &cpu->env;PowerPCCPUClass *pcc =POWERPC_CPU_GET_CLASS (cs);PnvChipClass *pnv_cc =PNV_CHIP_GET_CLASS (chip); - g_autofree uint32_t *servers_prop = g_new(uint32_t, smt_threads); +uint32_t *servers_prop;int i; -uint32_t pir; +uint32_t pir, tir;uint32_t segs[] = {cpu_to_be32 (28 ),cpu_to_be32 (40 ),0xffffffff ,0xffffffff };uint32_t tbfreq =PNV_TIMEBASE_FREQ ;@@ -154,7 +154,10 @@ static int pnv_dt_core(PnvChip *chip, PnvCore *pc, void *fdt)char *nodename;int cpus_offset =get_cpus_node (fdt); - pnv_cc->get_pir_tir (chip, pc->hwid,0 , &pir,NULL ); + pnv_cc->get_pir_tir (chip, pc->hwid,0 , &pir, &tir); + +/* Only one DT node per (big) core */ +g_assert (tir ==0 ); nodename =g_strdup_printf ("%s@%x" , dc->fw_name, pir); offset =fdt_add_subnode (fdt, cpus_offset, nodename);@@ -235,12 +238,28 @@ static int pnv_dt_core(PnvChip *chip, PnvCore *pc, void *fdt) }/* Build interrupt servers properties */ -for (i =0 ; i < smt_threads; i++) { - pnv_cc->get_pir_tir (chip, pc->hwid, i, &pir,NULL ); - servers_prop[i] =cpu_to_be32 (pir); +if (pc->big_core) { + servers_prop =g_new (uint32_t, smt_threads *2 ); +for (i =0 ; i < smt_threads; i++) { + pnv_cc->get_pir_tir (chip, pc->hwid, i, &pir,NULL ); + servers_prop[i *2 ] =cpu_to_be32 (pir); + + pnv_cc->get_pir_tir (chip, pc->hwid +1 , i, &pir,NULL ); + servers_prop[i *2 +1 ] =cpu_to_be32 (pir); + } +_FDT ((fdt_setprop (fdt, offset,"ibm,ppc-interrupt-server#s" , + servers_prop,sizeof (*servers_prop) * smt_threads + *2 ))); + }else { + servers_prop =g_new (uint32_t, smt_threads); +for (i =0 ; i < smt_threads; i++) { + pnv_cc->get_pir_tir (chip, pc->hwid, i, &pir,NULL ); + servers_prop[i] =cpu_to_be32 (pir); + } +_FDT ((fdt_setprop (fdt, offset,"ibm,ppc-interrupt-server#s" , + servers_prop,sizeof (*servers_prop) * smt_threads))); } -_FDT ((fdt_setprop (fdt, offset,"ibm,ppc-interrupt-server#s" , - servers_prop,sizeof (*servers_prop) * smt_threads))); +g_free (servers_prop);return offset; }@@ -389,6 +408,10 @@ static void pnv_chip_power9_dt_populate(PnvChip *chip, void *fdt)_FDT ((fdt_setprop (fdt, offset,"ibm,pa-features" , pa_features_300,sizeof (pa_features_300)))); + +if (pnv_core->big_core) { + i++;/* Big-core groups two QEMU cores */ + } }if (chip->ram_size) {@@ -450,6 +473,10 @@ static void pnv_chip_power10_dt_populate(PnvChip *chip, void *fdt)_FDT ((fdt_setprop (fdt, offset,"ibm,pa-features" , pa_features_31,sizeof (pa_features_31)))); + +if (pnv_core->big_core) { + i++;/* Big-core groups two QEMU cores */ + } }if (chip->ram_size) {
Re: [PATCH v3 01/19] target/ppc: Fix msgsnd for POWER8
In reply to Nicholas PigginQuoted 4 lines · Nicholas Piggin
POWER8 (ISA v2.07S) introduced the doorbell facility, the msgsnd instruction behaved mostly like msgsndp, it was addressed by TIR and could only send interrupts between threads on the core.
Quoted 8 lines
ISA v3.0 changed msgsnd to be addressed by PIR and can interrupt any thread in the system.
msgsnd only implements the v3.0 semantics, which can make multi-threaded POWER8 hang when booting Linux (due to IPIs failing). This change adds v2.07 semantics.
Signed-off-by Nicholas Piggin <[email protected]>
Thanks,
C.
Quoted 108 lines
--- target/ppc/excp_helper.c | 74 ++++++++++++++++++++++++---------------- 1 file changed, 44 insertions(+), 30 deletions(-)target/ppc/excp_helper.c +44
-30@@ -3007,6 +3007,41 @@ static inline bool dbell_bcast_subproc(target_ulong rb)return (rb &DBELL_BRDCAST_MASK ) ==DBELL_BRDCAST_SUBPROC ; } +/* +* Send an interrupt to a thread in the same core as env). +*/ +static void msgsnd_core_tir (CPUPPCState *env,uint32_t target_tir,int irq) +{ +PowerPCCPU *cpu =env_archcpu (env); +CPUState *cs =env_cpu (env); +uint32_t nr_threads = cs->nr_threads; + +if (!(env->flags &POWERPC_FLAG_SMT_1LPAR )) { + nr_threads =1 ;/* msgsndp behaves as 1-thread in LPAR-per-thread mode*/ + } + +if (target_tir >= nr_threads) { +return ; + } + +if (nr_threads ==1 ) { +ppc_set_irq (cpu, irq,1 ); + }else { +CPUState *ccs; + +/* Does iothread need to be locked for walking CPU list? */ +bql_lock (); + THREAD_SIBLING_FOREACH(cs, ccs) { +PowerPCCPU *ccpu =POWERPC_CPU (ccs); +if (target_tir ==ppc_cpu_tir (ccpu)) { +ppc_set_irq (ccpu, irq,1 ); +break ; + } + } +bql_unlock (); + } +} +void helper_book3s_msgclr (CPUPPCState *env,target_ulong rb) {if (!dbell_type_server (rb)) {@@ -3027,6 +3062,13 @@ void helper_book3s_msgsnd(CPUPPCState *env, target_ulong rb)return ; } +/* POWER8 msgsnd is like msgsndp (targets a thread within core) */ +if (!(env->insns_flags2 &PPC2_ISA300 )) { +msgsnd_core_tir (env, rb &PPC_BITMASK (57 ,63 ),PPC_INTERRUPT_HDOORBELL ); +return ; + } + +/* POWER9 and later msgsnd is a global (targets any thread) */ cpu =ppc_get_vcpu_by_pir (pir);if (!cpu) {return ;@@ -3073,41 +3115,13 @@ void helper_book3s_msgclrp(CPUPPCState *env, target_ulong rb)*/ void helper_book3s_msgsndp (CPUPPCState *env,target_ulong rb) { -CPUState *cs =env_cpu (env); -PowerPCCPU *cpu =env_archcpu (env); -CPUState *ccs; -uint32_t nr_threads = cs->nr_threads; -int ttir = rb &PPC_BITMASK (57 ,63 ); -helper_hfscr_facility_check (env,HFSCR_MSGP ,"msgsndp" ,HFSCR_IC_MSGP ); -if (!(env->flags &POWERPC_FLAG_SMT_1LPAR )) { - nr_threads =1 ;/* msgsndp behaves as 1-thread in LPAR-per-thread mode*/ - } - -if (!dbell_type_server (rb) || ttir >= nr_threads) { -return ; - } - -if (nr_threads ==1 ) { -ppc_set_irq (cpu,PPC_INTERRUPT_DOORBELL ,1 ); +if (!dbell_type_server (rb)) {return ; } -/* Does iothread need to be locked for walking CPU list? */ -bql_lock (); - THREAD_SIBLING_FOREACH(cs, ccs) { -PowerPCCPU *ccpu =POWERPC_CPU (ccs); -uint32_t thread_id =ppc_cpu_tir (ccpu); - -if (ttir == thread_id) { -ppc_set_irq (ccpu,PPC_INTERRUPT_DOORBELL ,1 ); -bql_unlock (); -return ; - } - } - -g_assert_not_reached (); +msgsnd_core_tir (env, rb &PPC_BITMASK (57 ,63 ),PPC_INTERRUPT_DOORBELL ); }#endif /* TARGET_PPC64 */