[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [PATCH v6 5/9] target/arm/kvm64: Add kvm_arch_get/put_sve
From: |
Masayoshi Mizuma |
Subject: |
Re: [PATCH v6 5/9] target/arm/kvm64: Add kvm_arch_get/put_sve |
Date: |
Thu, 17 Oct 2019 12:43:41 -0400 |
User-agent: |
NeoMutt/20180716 |
On Wed, Oct 16, 2019 at 10:54:04AM +0200, 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.
>
> Signed-off-by: Andrew Jones <address@hidden>
> Reviewed-by: Richard Henderson <address@hidden>
> Reviewed-by: Eric Auger <address@hidden>
This patch works well on aarch64 with SVE machine, thanks!
Please feel free to add:
Tested-by: Masayoshi Mizuma <address@hidden>
- Masa
> ---
> target/arm/kvm64.c | 183 ++++++++++++++++++++++++++++++++++++++-------
> 1 file changed, 155 insertions(+), 28 deletions(-)
>
> diff --git a/target/arm/kvm64.c b/target/arm/kvm64.c
> index 28f6db57d5ee..4c0b11d105a4 100644
> --- a/target/arm/kvm64.c
> +++ b/target/arm/kvm64.c
> @@ -671,11 +671,12 @@ 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;
> @@ -721,10 +722,8 @@ int kvm_arm_cpreg_level(uint64_t regidx)
>
> static int kvm_arch_put_fpsimd(CPUState *cs)
> {
> - ARMCPU *cpu = ARM_CPU(cs);
> - CPUARMState *env = &cpu->env;
> + CPUARMState *env = &ARM_CPU(cs)->env;
> struct kvm_one_reg reg;
> - uint32_t fpr;
> int i, ret;
>
> for (i = 0; i < 32; i++) {
> @@ -742,17 +741,73 @@ static int kvm_arch_put_fpsimd(CPUState *cs)
> }
> }
>
> - reg.addr = (uintptr_t)(&fpr);
> - fpr = vfp_get_fpsr(env);
> - reg.id = AARCH64_SIMD_CTRL_REG(fp_regs.fpsr);
> - ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, ®);
> - if (ret) {
> - return ret;
> + return 0;
> +}
> +
> +/*
> + * SVE registers are encoded in KVM's memory in an endianness-invariant
> format.
> + * The byte at offset i from the start of the in-memory representation
> contains
> + * the bits [(7 + 8 * i) : (8 * i)] of the register value. As this means the
> + * lowest offsets are stored in the lowest memory addresses, then that nearly
> + * matches QEMU's representation, which is to use an array of host-endian
> + * uint64_t's, where the lower offsets are at the lower indices. To complete
> + * the translation we just need to byte swap the uint64_t's on big-endian
> hosts.
> + */
> +static uint64_t *sve_bswap64(uint64_t *dst, uint64_t *src, int nr)
> +{
> +#ifdef HOST_WORDS_BIGENDIAN
> + int i;
> +
> + for (i = 0; i < nr; ++i) {
> + dst[i] = bswap64(src[i]);
> + }
> +
> + return dst;
> +#else
> + return src;
> +#endif
> +}
> +
> +/*
> + * KVM SVE registers come in slices where ZREGs have a slice size of 2048
> bits
> + * and PREGS and the FFR have a slice size of 256 bits. However we simply
> hard
> + * code the slice index to zero for now as it's unlikely we'll need more than
> + * one slice for quite some time.
> + */
> +static int kvm_arch_put_sve(CPUState *cs)
> +{
> + ARMCPU *cpu = ARM_CPU(cs);
> + CPUARMState *env = &cpu->env;
> + uint64_t tmp[ARM_MAX_VQ * 2];
> + uint64_t *r;
> + struct kvm_one_reg reg;
> + int n, ret;
> +
> + for (n = 0; n < KVM_ARM64_SVE_NUM_ZREGS; ++n) {
> + r = sve_bswap64(tmp, &env->vfp.zregs[n].d[0], cpu->sve_max_vq * 2);
> + reg.addr = (uintptr_t)r;
> + reg.id = KVM_REG_ARM64_SVE_ZREG(n, 0);
> + ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, ®);
> + if (ret) {
> + return ret;
> + }
> + }
> +
> + for (n = 0; n < KVM_ARM64_SVE_NUM_PREGS; ++n) {
> + r = sve_bswap64(tmp, r = &env->vfp.pregs[n].p[0],
> + DIV_ROUND_UP(cpu->sve_max_vq * 2, 8));
> + reg.addr = (uintptr_t)r;
> + reg.id = KVM_REG_ARM64_SVE_PREG(n, 0);
> + ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, ®);
> + if (ret) {
> + return ret;
> + }
> }
>
> - reg.addr = (uintptr_t)(&fpr);
> - fpr = vfp_get_fpcr(env);
> - reg.id = AARCH64_SIMD_CTRL_REG(fp_regs.fpcr);
> + r = sve_bswap64(tmp, &env->vfp.pregs[FFR_PRED_NUM].p[0],
> + DIV_ROUND_UP(cpu->sve_max_vq * 2, 8));
> + reg.addr = (uintptr_t)r;
> + reg.id = KVM_REG_ARM64_SVE_FFR(0);
> ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, ®);
> if (ret) {
> return ret;
> @@ -765,6 +820,7 @@ int kvm_arch_put_registers(CPUState *cs, int level)
> {
> struct kvm_one_reg reg;
> uint64_t val;
> + uint32_t fpr;
> int i, ret;
> unsigned int el;
>
> @@ -855,7 +911,27 @@ int kvm_arch_put_registers(CPUState *cs, int level)
> }
> }
>
> - ret = kvm_arch_put_fpsimd(cs);
> + if (cpu_isar_feature(aa64_sve, cpu)) {
> + ret = kvm_arch_put_sve(cs);
> + } else {
> + ret = kvm_arch_put_fpsimd(cs);
> + }
> + if (ret) {
> + return ret;
> + }
> +
> + reg.addr = (uintptr_t)(&fpr);
> + fpr = vfp_get_fpsr(env);
> + reg.id = AARCH64_SIMD_CTRL_REG(fp_regs.fpsr);
> + ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, ®);
> + if (ret) {
> + return ret;
> + }
> +
> + reg.addr = (uintptr_t)(&fpr);
> + fpr = vfp_get_fpcr(env);
> + reg.id = AARCH64_SIMD_CTRL_REG(fp_regs.fpcr);
> + ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, ®);
> if (ret) {
> return ret;
> }
> @@ -878,10 +954,8 @@ int kvm_arch_put_registers(CPUState *cs, int level)
>
> static int kvm_arch_get_fpsimd(CPUState *cs)
> {
> - ARMCPU *cpu = ARM_CPU(cs);
> - CPUARMState *env = &cpu->env;
> + CPUARMState *env = &ARM_CPU(cs)->env;
> struct kvm_one_reg reg;
> - uint32_t fpr;
> int i, ret;
>
> for (i = 0; i < 32; i++) {
> @@ -899,21 +973,53 @@ static int kvm_arch_get_fpsimd(CPUState *cs)
> }
> }
>
> - reg.addr = (uintptr_t)(&fpr);
> - reg.id = AARCH64_SIMD_CTRL_REG(fp_regs.fpsr);
> - ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, ®);
> - if (ret) {
> - return ret;
> + return 0;
> +}
> +
> +/*
> + * KVM SVE registers come in slices where ZREGs have a slice size of 2048
> bits
> + * and PREGS and the FFR have a slice size of 256 bits. However we simply
> hard
> + * code the slice index to zero for now as it's unlikely we'll need more than
> + * one slice for quite some time.
> + */
> +static int kvm_arch_get_sve(CPUState *cs)
> +{
> + ARMCPU *cpu = ARM_CPU(cs);
> + CPUARMState *env = &cpu->env;
> + struct kvm_one_reg reg;
> + uint64_t *r;
> + int n, ret;
> +
> + for (n = 0; n < KVM_ARM64_SVE_NUM_ZREGS; ++n) {
> + r = &env->vfp.zregs[n].d[0];
> + reg.addr = (uintptr_t)r;
> + reg.id = KVM_REG_ARM64_SVE_ZREG(n, 0);
> + ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, ®);
> + if (ret) {
> + return ret;
> + }
> + sve_bswap64(r, r, cpu->sve_max_vq * 2);
> + }
> +
> + for (n = 0; n < KVM_ARM64_SVE_NUM_PREGS; ++n) {
> + r = &env->vfp.pregs[n].p[0];
> + reg.addr = (uintptr_t)r;
> + reg.id = KVM_REG_ARM64_SVE_PREG(n, 0);
> + ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, ®);
> + if (ret) {
> + return ret;
> + }
> + sve_bswap64(r, r, DIV_ROUND_UP(cpu->sve_max_vq * 2, 8));
> }
> - vfp_set_fpsr(env, fpr);
>
> - reg.addr = (uintptr_t)(&fpr);
> - reg.id = AARCH64_SIMD_CTRL_REG(fp_regs.fpcr);
> + r = &env->vfp.pregs[FFR_PRED_NUM].p[0];
> + reg.addr = (uintptr_t)r;
> + reg.id = KVM_REG_ARM64_SVE_FFR(0);
> ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, ®);
> if (ret) {
> return ret;
> }
> - vfp_set_fpcr(env, fpr);
> + sve_bswap64(r, r, DIV_ROUND_UP(cpu->sve_max_vq * 2, 8));
>
> return 0;
> }
> @@ -923,6 +1029,7 @@ int kvm_arch_get_registers(CPUState *cs)
> struct kvm_one_reg reg;
> uint64_t val;
> unsigned int el;
> + uint32_t fpr;
> int i, ret;
>
> ARMCPU *cpu = ARM_CPU(cs);
> @@ -1012,10 +1119,30 @@ int kvm_arch_get_registers(CPUState *cs)
> env->spsr = env->banked_spsr[i];
> }
>
> - ret = kvm_arch_get_fpsimd(cs);
> + if (cpu_isar_feature(aa64_sve, cpu)) {
> + ret = kvm_arch_get_sve(cs);
> + } else {
> + ret = kvm_arch_get_fpsimd(cs);
> + }
> + if (ret) {
> + return ret;
> + }
> +
> + reg.addr = (uintptr_t)(&fpr);
> + reg.id = AARCH64_SIMD_CTRL_REG(fp_regs.fpsr);
> + ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, ®);
> + if (ret) {
> + return ret;
> + }
> + vfp_set_fpsr(env, fpr);
> +
> + reg.addr = (uintptr_t)(&fpr);
> + reg.id = AARCH64_SIMD_CTRL_REG(fp_regs.fpcr);
> + ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, ®);
> if (ret) {
> return ret;
> }
> + vfp_set_fpcr(env, fpr);
>
> ret = kvm_get_vcpu_events(cpu);
> if (ret) {
> --
> 2.21.0
>
>
- Re: [PATCH v6 2/9] tests: arm: Introduce cpu feature tests, (continued)
[PATCH v6 3/9] target/arm: Allow SVE to be disabled via a CPU property, Andrew Jones, 2019/10/16
[PATCH v6 4/9] target/arm/cpu64: max cpu: Introduce sve<N> properties, Andrew Jones, 2019/10/16
[PATCH v6 5/9] target/arm/kvm64: Add kvm_arch_get/put_sve, Andrew Jones, 2019/10/16
- Re: [PATCH v6 5/9] target/arm/kvm64: Add kvm_arch_get/put_sve,
Masayoshi Mizuma <=
[PATCH v6 6/9] target/arm/kvm64: max cpu: Enable SVE when available, Andrew Jones, 2019/10/16
[PATCH v6 7/9] target/arm/kvm: scratch vcpu: Preserve input kvm_vcpu_init features, Andrew Jones, 2019/10/16
[PATCH v6 8/9] target/arm/cpu64: max cpu: Support sve properties with KVM, Andrew Jones, 2019/10/16
[PATCH v6 9/9] target/arm/kvm: host cpu: Add support for sve<N> properties, Andrew Jones, 2019/10/16