Set the TIR default value with the SMT thread index, and place some
standard limits on SMT configurations. Now powernv is able to boot
skiboot and Linux with a SMT topology, including booting a KVM guest.

There are several other per-core SPRs, but they are not so important to
run OPAL/Linux. Some important per-LPAR ones to convert before powernv
could run in 1LPAR mode. Broadcast msgsnd is not yet implemented either,
but skiboot/Linux does not use that. KVM uses an implementation-specific
detail of POWER9/10 TLBs where TLBIEL invalidates translations of all
threads on a core, but that is not required here because KVM does not
cache translations across PID or LPID switch. Most of these I have or
aren't too hard to implement, but I start with a small bare bones for
comments.

Not-yet-Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 hw/ppc/pnv.c      | 12 ++++++++++++
 hw/ppc/pnv_core.c | 13 +++++--------
 2 files changed, 17 insertions(+), 8 deletions(-)

diff --git a/hw/ppc/pnv.c b/hw/ppc/pnv.c
index fc083173f3..f599ccad1d 100644
--- a/hw/ppc/pnv.c
+++ b/hw/ppc/pnv.c
@@ -887,6 +887,18 @@ 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");
+        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...,
diff --git a/hw/ppc/pnv_core.c b/hw/ppc/pnv_core.c
index 0bc3ad41c8..acd83caee8 100644
--- a/hw/ppc/pnv_core.c
+++ b/hw/ppc/pnv_core.c
@@ -167,12 +167,13 @@ static const MemoryRegionOps pnv_core_power9_xscom_ops = {
     .endianness = DEVICE_BIG_ENDIAN,
 };
 
-static void pnv_core_cpu_realize(PnvCore *pc, PowerPCCPU *cpu, Error **errp)
+static void pnv_core_cpu_realize(PnvCore *pc, PowerPCCPU *cpu, Error **errp,
+                                 int thread_index)
 {
     CPUPPCState *env = &cpu->env;
     int core_pir;
-    int thread_index = 0; /* TODO: TCG supports only one thread */
     ppc_spr_t *pir = &env->spr_cb[SPR_PIR];
+    ppc_spr_t *tir = &env->spr_cb[SPR_TIR];
     Error *local_err = NULL;
     PnvChipClass *pcc = PNV_CHIP_GET_CLASS(pc->chip);
 
@@ -188,11 +189,7 @@ static void pnv_core_cpu_realize(PnvCore *pc, PowerPCCPU *cpu, Error **errp)
 
     core_pir = object_property_get_uint(OBJECT(pc), "pir", &error_abort);
 
-    /*
-     * The PIR of a thread is the core PIR + the thread index. We will
-     * need to find a way to get the thread index when TCG supports
-     * more than 1. We could use the object name ?
-     */
+    tir->default_value = thread_index;
     pir->default_value = core_pir + thread_index;
 
     /* Set time-base frequency to 512 MHz */
@@ -241,7 +238,7 @@ static void pnv_core_realize(DeviceState *dev, Error **errp)
     }
 
     for (j = 0; j < cc->nr_threads; j++) {
-        pnv_core_cpu_realize(pc, pc->threads[j], &local_err);
+        pnv_core_cpu_realize(pc, pc->threads[j], &local_err, j);
         if (local_err) {
             goto err;
         }
-- 
2.40.1

On 6/29/23 04:16, Nicholas Piggin wrote:
> Set the TIR default value with the SMT thread index, and place some
> standard limits on SMT configurations. Now powernv is able to boot
> skiboot and Linux with a SMT topology, including booting a KVM guest.
> 
> There are several other per-core SPRs, but they are not so important to
> run OPAL/Linux. Some important per-LPAR ones to convert before powernv
> could run in 1LPAR mode. Broadcast msgsnd is not yet implemented either,
> but skiboot/Linux does not use that. KVM uses an implementation-specific
> detail of POWER9/10 TLBs where TLBIEL invalidates translations of all
> threads on a core, but that is not required here because KVM does not
> cache translations across PID or LPID switch. Most of these I have or
> aren't too hard to implement, but I start with a small bare bones for
> comments.
> 
> Not-yet-Signed-off-by: Nicholas Piggin <npiggin@gmail.com>

I am glad this becoming possible. You can model the missing parts
later on.

Reviewed-by: Cédric Le Goater <clg@kaod.org>

Thanks,

C.

> ---
>   hw/ppc/pnv.c      | 12 ++++++++++++
>   hw/ppc/pnv_core.c | 13 +++++--------
>   2 files changed, 17 insertions(+), 8 deletions(-)
> 
> diff --git a/hw/ppc/pnv.c b/hw/ppc/pnv.c
> index fc083173f3..f599ccad1d 100644
> --- a/hw/ppc/pnv.c
> +++ b/hw/ppc/pnv.c
> @@ -887,6 +887,18 @@ 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");
> +        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...,
> diff --git a/hw/ppc/pnv_core.c b/hw/ppc/pnv_core.c
> index 0bc3ad41c8..acd83caee8 100644
> --- a/hw/ppc/pnv_core.c
> +++ b/hw/ppc/pnv_core.c
> @@ -167,12 +167,13 @@ static const MemoryRegionOps pnv_core_power9_xscom_ops = {
>       .endianness = DEVICE_BIG_ENDIAN,
>   };
>   
> -static void pnv_core_cpu_realize(PnvCore *pc, PowerPCCPU *cpu, Error **errp)
> +static void pnv_core_cpu_realize(PnvCore *pc, PowerPCCPU *cpu, Error **errp,
> +                                 int thread_index)
>   {
>       CPUPPCState *env = &cpu->env;
>       int core_pir;
> -    int thread_index = 0; /* TODO: TCG supports only one thread */
>       ppc_spr_t *pir = &env->spr_cb[SPR_PIR];
> +    ppc_spr_t *tir = &env->spr_cb[SPR_TIR];
>       Error *local_err = NULL;
>       PnvChipClass *pcc = PNV_CHIP_GET_CLASS(pc->chip);
>   
> @@ -188,11 +189,7 @@ static void pnv_core_cpu_realize(PnvCore *pc, PowerPCCPU *cpu, Error **errp)
>   
>       core_pir = object_property_get_uint(OBJECT(pc), "pir", &error_abort);
>   
> -    /*
> -     * The PIR of a thread is the core PIR + the thread index. We will
> -     * need to find a way to get the thread index when TCG supports
> -     * more than 1. We could use the object name ?
> -     */
> +    tir->default_value = thread_index;
>       pir->default_value = core_pir + thread_index;
>   
>       /* Set time-base frequency to 512 MHz */
> @@ -241,7 +238,7 @@ static void pnv_core_realize(DeviceState *dev, Error **errp)
>       }
>   
>       for (j = 0; j < cc->nr_threads; j++) {
> -        pnv_core_cpu_realize(pc, pc->threads[j], &local_err);
> +        pnv_core_cpu_realize(pc, pc->threads[j], &local_err, j);
>           if (local_err) {
>               goto err;
>           }