[2/3] PPC: Enable to use PAPR with PR style KVM

When running PR style KVM, we need to tell the kernel that we want
to run in PAPR mode now. This means that we need to pass some more
register information down and enable papr mode. We also need to align
the HTAB to htab_size boundary.

Using this patch, -M pseries works with kvm even on non-hv kvm
implementations, as long as the preceding kernel patches are in.

Signed-off-by: Alexander Graf <agraf@suse.de>
---
 hw/spapr.c           |   14 ++++++++++++-
 target-ppc/kvm.c     |   53 ++++++++++++++++++++++++++++++++++++++++++++++++++
 target-ppc/kvm_ppc.h |    5 ++++
 3 files changed, 71 insertions(+), 1 deletions(-)

On Tue, Aug 09, 2011 at 06:39:29PM +0200, Alexander Graf wrote:
> When running PR style KVM, we need to tell the kernel that we want
> to run in PAPR mode now. This means that we need to pass some more
> register information down and enable papr mode. We also need to align
> the HTAB to htab_size boundary.
> 
> Using this patch, -M pseries works with kvm even on non-hv kvm
> implementations, as long as the preceding kernel patches are in.
> 
> Signed-off-by: Alexander Graf <agraf@suse.de>
> ---
>  hw/spapr.c           |   14 ++++++++++++-
>  target-ppc/kvm.c     |   53 ++++++++++++++++++++++++++++++++++++++++++++++++++
>  target-ppc/kvm_ppc.h |    5 ++++
>  3 files changed, 71 insertions(+), 1 deletions(-)
> 
> diff --git a/hw/spapr.c b/hw/spapr.c
> index 07b2165..d56697a 100644
> --- a/hw/spapr.c
> +++ b/hw/spapr.c
> @@ -38,6 +38,9 @@
>  #include "hw/spapr_vio.h"
>  #include "hw/xics.h"
>  
> +#include "kvm.h"
> +#include "kvm_ppc.h"
> +
>  #include <libfdt.h>
>  
>  #define KERNEL_LOAD_ADDR        0x00000000
> @@ -336,12 +339,21 @@ static void ppc_spapr_init(ram_addr_t ram_size,
>       * later we should probably make it scale to the size of guest
>       * RAM */
>      spapr->htab_size = 1ULL << (pteg_shift + 7);
> -    spapr->htab = qemu_malloc(spapr->htab_size);
> +    spapr->htab = qemu_memalign(spapr->htab_size, spapr->htab_size);
>  
>      for (env = first_cpu; env != NULL; env = env->next_cpu) {
>          env->external_htab = spapr->htab;
>          env->htab_base = -1;
>          env->htab_mask = spapr->htab_size - 1;
> +
> +        /* Tell KVM that we're in PAPR mode */
> +        env->spr[SPR_SDR1] = (unsigned long)spapr->htab |
> +                             ((pteg_shift + 7) - 18);
> +        env->spr[SPR_HIOR] = 0;
> +
> +        if (kvm_enabled()) {
> +            kvmppc_set_papr(env);
> +        }
>      }
>  
>      filename = qemu_find_file(QEMU_FILE_TYPE_BIOS, "spapr-rtas.bin");
> diff --git a/target-ppc/kvm.c b/target-ppc/kvm.c
> index 219e7a7..02f958f 100644
> --- a/target-ppc/kvm.c
> +++ b/target-ppc/kvm.c
> @@ -29,6 +29,10 @@
>  #include "cpu.h"
>  #include "device_tree.h"
>  
> +#include "hw/sysbus.h"
> +#include "hw/spapr.h"
> +#include "hw/spapr_vio.h"
> +
>  //#define DEBUG_KVM
>  
>  #ifdef DEBUG_KVM
> @@ -455,6 +459,14 @@ int kvm_arch_handle_exit(CPUState *env, struct kvm_run *run)
>          dprintf("handle halt\n");
>          ret = kvmppc_handle_halt(env);
>          break;
> +#if defined(CONFIG_FDT) && defined(TARGET_PPC64)

We should hack up configure to give us a CONFIG_PSERIES variable,
instead of duplicating this horrid logic in multiple places
(especially since it will later become CONFIG_FDT && TARGET_PPC64 &&
CONFIG_IOMMU.

> +    case KVM_EXIT_PAPR_HCALL:
> +        dprintf("handle PAPR hypercall\n");
> +        run->papr_hcall.ret = spapr_hypercall(env, run->papr_hcall.nr,
> +                                              run->papr_hcall.args);
> +        ret = 1;
> +        break;
> +#endif
>      default:
>          fprintf(stderr, "KVM: unknown exit reason %d\n", run->exit_reason);
>          ret = -1;
> @@ -606,6 +618,47 @@ int kvmppc_get_hypercall(CPUState *env, uint8_t *buf, int buf_len)
>      return 0;
>  }
>  
> +void kvmppc_set_papr(CPUState *env)
> +{
> +    struct kvm_enable_cap cap;
> +    struct kvm_sregs sregs;
> +    int ret;
> +
> +    memset(&cap, 0, sizeof(cap));
> +    cap.cap = KVM_CAP_PPC_PAPR;
> +    ret = kvm_vcpu_ioctl(env, KVM_ENABLE_CAP, &cap);
> +
> +    if (ret) {
> +        goto fail;
> +    }
> +
> +    /*
> +     * XXX We set HIOR here. It really should be a qdev property of
> +     *     the CPU node, but we don't have CPUs converted to qdev yet.
> +     *
> +     *     Once we have qdev CPUs, move HIOR to a qdev property and
> +     *     remove this chunk.
> +     */
> +    memset(&sregs, 0, sizeof(sregs));
> +    ret = kvm_vcpu_ioctl(env, KVM_GET_SREGS, &sregs);
> +    if (ret) {
> +        goto fail;
> +    }
> +
> +    sregs.u.s.flags |= KVM_SREGS_S_HIOR;
> +    sregs.u.s.hior = env->spr[SPR_HIOR];
> +    sregs.u.s.sdr1 = env->spr[SPR_SDR1];
> +    ret = kvm_vcpu_ioctl(env, KVM_SET_SREGS, &sregs);
> +    if (ret) {
> +        goto fail;
> +    }
> +
> +    return;
> +
> +fail:
> +    cpu_abort(env, "This KVM version does not support PAPR\n");
> +}
> +
>  bool kvm_arch_stop_on_emulation_error(CPUState *env)
>  {
>      return true;
> diff --git a/target-ppc/kvm_ppc.h b/target-ppc/kvm_ppc.h
> index 76f98d9..809b8b4 100644
> --- a/target-ppc/kvm_ppc.h
> +++ b/target-ppc/kvm_ppc.h
> @@ -17,6 +17,7 @@ uint32_t kvmppc_get_tbfreq(void);
>  uint64_t kvmppc_get_clockfreq(void);
>  int kvmppc_get_hypercall(CPUState *env, uint8_t *buf, int buf_len);
>  int kvmppc_set_interrupt(CPUState *env, int irq, int level);
> +void kvmppc_set_papr(CPUState *env);
>  
>  #else
>  
> @@ -40,6 +41,10 @@ static inline int kvmppc_set_interrupt(CPUState *env, int irq, int level)
>      return -1;
>  }
>  
> +static void kvmppc_set_papr(CPUState *env)
> +{

Shouldn't this have a cpu_error or assert or something, since it
should never be called if !kvm_enabled().

> +}
> +
>  #endif
>  
>  #ifndef CONFIG_KVM