Re: [Qemu-devel] [PATCH v2 10/14] target/arm/kvm64: Add kvm_arch_get/put_sve

[Andrew Jones]

On Thu, Jun 27, 2019 at 08:56:21AM +0200, Auger Eric wrote:
> Hi,
> 
> On 6/21/19 6:34 PM, Andrew Jones wrote:
> > These are the SVE equivalents to kvm_arch_get/put_fpsimd. Note, the
> > swabbing is different than it is for fpsmid because the vector format
> > is a little-endian stream of words.
> 
> some cosmetic changes besides Richard's comments
> > 
> > Signed-off-by: Andrew Jones <address@hidden>
> > ---
> >  target/arm/kvm64.c | 135 +++++++++++++++++++++++++++++++++++++++++++--
> >  1 file changed, 131 insertions(+), 4 deletions(-)
> > 
> > diff --git a/target/arm/kvm64.c b/target/arm/kvm64.c
> > index a2485d447e6a..706541327491 100644
> > --- a/target/arm/kvm64.c
> > +++ b/target/arm/kvm64.c
> > @@ -673,11 +673,12 @@ int kvm_arch_destroy_vcpu(CPUState *cs)
> >  bool kvm_arm_reg_syncs_via_cpreg_list(uint64_t regidx)
> >  {
> >      /* Return true if the regidx is a register we should synchronize
> > -     * via the cpreg_tuples array (ie is not a core reg we sync by
> > -     * hand in kvm_arch_get/put_registers())
> > +     * via the cpreg_tuples array (ie is not a core or sve reg that
> > +     * we sync by hand in kvm_arch_get/put_registers())
> >       */
> >      switch (regidx & KVM_REG_ARM_COPROC_MASK) {
> >      case KVM_REG_ARM_CORE:
> > +    case KVM_REG_ARM64_SVE:
> >          return false;
> >      default:
> >          return true;
> > @@ -763,6 +764,70 @@ static int kvm_arch_put_fpsimd(CPUState *cs)
> >      return 0;
> >  }
> >  
> > +/*
> > + * If ARM_MAX_VQ is increased to be greater than 16, then we can no
> > + * longer hard code slices to 1 in kvm_arch_put/get_sve().
> > + */
> > +QEMU_BUILD_BUG_ON(ARM_MAX_VQ > 16);
> if the code is ready to support slices, I guess you could have a define
> and compute the slice number from ARM_MAX_VQ?

Yeah, that should be do-able. Thanks for the suggestion.

> > +
> > +static int kvm_arch_put_sve(CPUState *cs)
> > +{
> > +    ARMCPU *cpu = ARM_CPU(cs);
> > +    CPUARMState *env = &cpu->env;
> > +    struct kvm_one_reg reg;
> > +    int slices = 1;
> > +    int i, n, ret;
> > +
> > +    for (i = 0; i < slices; i++) {
> > +        for (n = 0; n < KVM_ARM64_SVE_NUM_ZREGS; n++) {
> > +            uint64_t *q = aa64_vfp_qreg(env, n);
> > +#ifdef HOST_WORDS_BIGENDIAN
> > +            uint64_t d[ARM_MAX_VQ * 2];
> > +            int j;
> line to be added
> > +            for (j = 0; j < cpu->sve_max_vq * 2; j++) {
> > +                d[j] = bswap64(q[j]);
> > +            }
> > +            reg.addr = (uintptr_t)d;
> > +#else
> > +            reg.addr = (uintptr_t)q;
> > +#endif
> > +            reg.id = KVM_REG_ARM64_SVE_ZREG(n, i);
> > +            ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, &reg);
> > +            if (ret) {
> > +                return ret;
> > +            }
> > +        }
> > +
> > +        for (n = 0; n < KVM_ARM64_SVE_NUM_PREGS; n++) {
> > +            uint64_t *q = &env->vfp.pregs[n].p[0];
> > +#ifdef HOST_WORDS_BIGENDIAN
> > +            uint64_t d[ARM_MAX_VQ * 2 / 8];
> > +            int j;
> line
> > +            for (j = 0; j < cpu->sve_max_vq * 2 / 8; j++) {
> > +                d[j] = bswap64(q[j]);
> > +            }
> > +            reg.addr = (uintptr_t)d;
> > +#else
> > +            reg.addr = (uintptr_t)q;
> > +#endif
> > +            reg.id = KVM_REG_ARM64_SVE_PREG(n, i);
> > +            ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, &reg);
> > +            if (ret) {
> > +                return ret;
> > +            }
> > +        }
> > +
> > +        reg.addr = (uintptr_t)&env->vfp.pregs[FFR_PRED_NUM].p[0];
> > +        reg.id = KVM_REG_ARM64_SVE_FFR(i);
> > +        ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, &reg);
> > +        if (ret) {
> > +            return ret;
> > +        }
> > +    }
> > +
> > +    return 0;
> > +}
> > +
> >  int kvm_arch_put_registers(CPUState *cs, int level)
> >  {
> >      struct kvm_one_reg reg;
> > @@ -857,7 +922,11 @@ int kvm_arch_put_registers(CPUState *cs, int level)
> >          }
> >      }
> >  
> > -    ret = kvm_arch_put_fpsimd(cs);
> > +    if (!cpu->sve_max_vq) {
> > +        ret = kvm_arch_put_fpsimd(cs);
> > +    } else {
> > +        ret = kvm_arch_put_sve(cs);
> > +    }
> >      if (ret) {
> >          return ret;
> >      }
> > @@ -920,6 +989,60 @@ static int kvm_arch_get_fpsimd(CPUState *cs)
> >      return 0;
> >  }
> >  
> > +static int kvm_arch_get_sve(CPUState *cs)
> > +{
> > +    ARMCPU *cpu = ARM_CPU(cs);
> > +    CPUARMState *env = &cpu->env;
> > +    struct kvm_one_reg reg;
> > +    int slices = 1;
> > +    int i, n, ret;
> > +
> > +    for (i = 0; i < slices; i++) {
> > +        for (n = 0; n < KVM_ARM64_SVE_NUM_ZREGS; n++) {
> > +            uint64_t *q = aa64_vfp_qreg(env, n);
> extra line needed
> > +            reg.id = KVM_REG_ARM64_SVE_ZREG(n, i);
> > +            reg.addr = (uintptr_t)q;
> > +            ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, &reg);
> > +            if (ret) {
> > +                return ret;
> > +            } else {> +#ifdef HOST_WORDS_BIGENDIAN
> > +                int j;
> line
> > +                for (j = 0; j < cpu->sve_max_vq * 2; j++) {
> > +                    q[j] = bswap64(q[j]);
> > +                }
> > +#endif
> > +            }
> > +        }
> > +
> > +        for (n = 0; n < KVM_ARM64_SVE_NUM_PREGS; n++) {
> > +            uint64_t *q = &env->vfp.pregs[n].p[0];
> extra line needed
> > +            reg.id = KVM_REG_ARM64_SVE_PREG(n, i);
> > +            reg.addr = (uintptr_t)q;
> > +            ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, &reg);
> > +            if (ret) {
> > +                return ret;
> > +            } else {> +#ifdef HOST_WORDS_BIGENDIAN
> > +                int j;
> line
> > +                for (j = 0; j < cpu->sve_max_vq * 2 / 8; j++) {
> > +                    q[j] = bswap64(q[j]);
> > +                }
> > +#endif
> > +            }
> > +        }
> > +
> > +        reg.addr = (uintptr_t)&env->vfp.pregs[FFR_PRED_NUM].p[0];
> > +        reg.id = KVM_REG_ARM64_SVE_FFR(i);
> > +        ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, &reg);
> > +        if (ret) {
> > +            return ret;
> > +        }
> > +    }
> > +
> > +    return 0;
> > +}
> > +
> >  int kvm_arch_get_registers(CPUState *cs)
> >  {
> >      struct kvm_one_reg reg;
> > @@ -1014,7 +1137,11 @@ int kvm_arch_get_registers(CPUState *cs)
> >          env->spsr = env->banked_spsr[i];
> >      }
> >  
> > -    ret = kvm_arch_get_fpsimd(cs);
> > +    if (!cpu->sve_max_vq) {
> > +        ret = kvm_arch_get_fpsimd(cs);
> > +    } else {
> > +        ret = kvm_arch_get_sve(cs);
> > +    }
> >      if (ret) {
> >          return ret;
> >      }
> > 
> 
>

I'll see if I can clean/improve this patch with yours and Richard's
suggestions.

Thanks,
drew