Re: [Qemu-devel] [PATCH v2 8/9] spapr: Implement processor compatibility in ibm, client-architecture-support

[Alexander Graf <agraf@suse.de>]

On 21.05.14 10:27, Alexey Kardashevskiy wrote:
> Modern Linux kernels support last POWERPC CPUs so when a kernel boots,
> in most cases it can find a matching cpu_spec in the kernel's cpu_specs
> list. However if the kernel is quite old, it may be missing a definition
> of the actual CPU. To provide an ability for old kernels to work on modern
> hardware, a Processor Compatibility Mode has been introduced
> by the PowerISA specification.
>
>  From the hardware prospective, it is supported by the Processor
> Compatibility Register (PCR) which is defined in PowerISA. The register
> enables one of the compatibility modes (2.05/2.06/2.07).
> Since PCR is a hypervisor privileged register and cannot be
> directly accessed from the guest, the mode selection is done via
> ibm,client-architecture-support (CAS) RTAS call using which the guest
> specifies what "raw" and "architected" CPU versions it supports.
> QEMU works out the best match, changes a "cpu-version" property of
> every CPU and notifies the guest about the change by setting these
> properties in the buffer passed as a response on a custom H_CAS hypercall.
>
> This implements ibm,client-architecture-support parameters parsing
> (now only for PVRs) and cooks the device tree diff with new values for
> "cpu-version", "ibm,ppc-interrupt-server#s" and
> "ibm,ppc-interrupt-server#s" properties.
>
> Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
> ---
>   hw/ppc/spapr.c       |  4 ++-
>   hw/ppc/spapr_hcall.c | 85 ++++++++++++++++++++++++++++++++++++++++++++++++++++
>   trace-events         |  4 +++
>   3 files changed, 92 insertions(+), 1 deletion(-)
>
> diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c
> index 14c72d9..020426a 100644
> --- a/hw/ppc/spapr.c
> +++ b/hw/ppc/spapr.c
> @@ -34,6 +34,7 @@
>   #include "sysemu/kvm.h"
>   #include "kvm_ppc.h"
>   #include "mmu-hash64.h"
> +#include "qom/cpu.h"
>   
>   #include "hw/boards.h"
>   #include "hw/ppc/ppc.h"
> @@ -601,7 +602,8 @@ int spapr_h_cas_compose_response(target_ulong addr, target_ulong size)
>       _FDT((fdt_open_into(fdt_skel, fdt, size)));
>       g_free(fdt_skel);
>   
> -    /* Place to make changes to the tree */
> +    /* Fix skeleton up */
> +    _FDT((spapr_fixup_cpu_dt(fdt, spapr)));
>   
>       /* Pack resulting tree */
>       _FDT((fdt_pack(fdt)));
> diff --git a/hw/ppc/spapr_hcall.c b/hw/ppc/spapr_hcall.c
> index 2f6aa5c..2e0a49c 100644
> --- a/hw/ppc/spapr_hcall.c
> +++ b/hw/ppc/spapr_hcall.c
> @@ -3,6 +3,9 @@
>   #include "helper_regs.h"
>   #include "hw/ppc/spapr.h"
>   #include "mmu-hash64.h"
> +#include "cpu-models.h"
> +#include "trace.h"
> +#include "kvm_ppc.h"
>   
>   struct SPRSyncState {
>       CPUState *cs;
> @@ -752,12 +755,94 @@ out:
>       return ret;
>   }
>   
> +#define get_compat_level(cpuver) ( \
> +    ((cpuver) == CPU_POWERPC_LOGICAL_2_05) ? 2050 : \
> +    ((cpuver) == CPU_POWERPC_LOGICAL_2_06) ? 2060 : \
> +    ((cpuver) == CPU_POWERPC_LOGICAL_2_06_PLUS) ? 2061 : \
> +    ((cpuver) == CPU_POWERPC_LOGICAL_2_07) ? 2070 : 0)
> +
>   static target_ulong h_client_architecture_support(PowerPCCPU *cpu_,
>                                                     sPAPREnvironment *spapr,
>                                                     target_ulong opcode,
>                                                     target_ulong *args)
>   {
>       target_ulong list = args[0];
> +    PowerPCCPUClass *pcc_ = POWERPC_CPU_GET_CLASS(cpu_);
> +    CPUState *cs;
> +    bool cpu_match = false;
> +    unsigned old_cpu_version = cpu_->cpu_version;
> +    unsigned compat_lvl = 0, cpu_version = 0;
> +    unsigned max_lvl = get_compat_level(cpu_->max_compat);
> +
> +    /* Parse PVR list */
> +    for ( ; ; ) {
> +        uint32_t pvr, pvr_mask;
> +
> +        pvr_mask = rtas_ld(list, 0);
> +        list += 4;
> +        pvr = rtas_ld(list, 0);
> +        list += 4;
> +
> +        trace_spapr_cas_pvr_try(pvr);
> +        if (!max_lvl &&
> +            ((cpu_->env.spr[SPR_PVR] & pvr_mask) == (pvr & pvr_mask))) {
> +            cpu_match = true;
> +            cpu_version = 0;
> +        } else if (pvr == cpu_->cpu_version) {
> +            cpu_match = true;
> +            cpu_version = cpu_->cpu_version;
> +        } else if (!cpu_match) {
> +            /* If it is a logical PVR, try to determine the highest level */
> +            unsigned lvl = get_compat_level(pvr);
> +            if (lvl) {
> +                bool is205 = (pcc_->pcr_mask & PCR_COMPAT_2_05) &&
> +                     (lvl == get_compat_level(CPU_POWERPC_LOGICAL_2_05));
> +                bool is206 = (pcc_->pcr_mask & PCR_COMPAT_2_06) &&
> +                    ((lvl == get_compat_level(CPU_POWERPC_LOGICAL_2_06)) ||
> +                    (lvl == get_compat_level(CPU_POWERPC_LOGICAL_2_06_PLUS)));
> +
> +                if (is205 || is206) {
> +                    if (!max_lvl) {
> +                        /* User did not set the level, choose the highest */
> +                        if (compat_lvl <= lvl) {
> +                            compat_lvl = lvl;
> +                            cpu_version = pvr;
> +                        }
> +                    } else if (max_lvl >= lvl) {
> +                        /* User chose the level, don't set higher than this */
> +                        compat_lvl = lvl;
> +                        cpu_version = pvr;
> +                    }
> +                }
> +            }
> +        }
> +        /* Terminator record */
> +        if (~pvr_mask & pvr) {

This loop can be used by the guest to stall QEMU for a long period of 
time, no? Better add a safety net check somewhere to allow for early abort.

> +            break;
> +        }
> +    }
> +
> +    /* For the future use: here @list points to the first capability */
> +
> +    /* Parsing finished */
> +    trace_spapr_cas_pvr(cpu_->cpu_version, cpu_match,
> +                        cpu_version, pcc_->pcr_mask);
> +
> +    /* Update CPUs */
> +    if (old_cpu_version != cpu_version) {
> +        CPU_FOREACH(cs) {
> +            PowerPCCPU *cpu = POWERPC_CPU(cs);
> +
> +            if (ppc_set_compat(cpu, cpu_version) < 0) {

Please run the updates on the vcpu threads themselves.


Alex