> From: Zhong, Yang <yang.zh...@intel.com>
> Sent: Friday, January 7, 2022 5:32 PM
>
> From: Jing Liu <jing2....@intel.com>
>
> Extended feature has large state while current
> kvm_xsave only allows 4KB. Use new XSAVE ioctls
> if the xstate size is large than kvm_xsave.
shouldn't we always use the new xsave ioctls as long as
CAP_XSAVE2 is available?
>
> Signed-off-by: Jing Liu <jing2....@intel.com>
> Signed-off-by: Zeng Guang <guang.z...@intel.com>
> Signed-off-by: Wei Wang <wei.w.w...@intel.com>
> Signed-off-by: Yang Zhong <yang.zh...@intel.com>
> ---
> linux-headers/asm-x86/kvm.h | 14 ++++++++++++++
> linux-headers/linux/kvm.h | 2 ++
> target/i386/cpu.h | 5 +++++
> target/i386/kvm/kvm.c | 16 ++++++++++++++--
> target/i386/xsave_helper.c | 35 +++++++++++++++++++++++++++++++++++
> 5 files changed, 70 insertions(+), 2 deletions(-)
>
> diff --git a/linux-headers/asm-x86/kvm.h b/linux-headers/asm-x86/kvm.h
> index 5a776a08f7..32f2a921e8 100644
> --- a/linux-headers/asm-x86/kvm.h
> +++ b/linux-headers/asm-x86/kvm.h
> @@ -376,6 +376,20 @@ struct kvm_debugregs {
> /* for KVM_CAP_XSAVE */
> struct kvm_xsave {
> __u32 region[1024];
> + /*
> + * KVM_GET_XSAVE2 and KVM_SET_XSAVE write and read as many
> bytes
> + * as are returned by KVM_CHECK_EXTENSION(KVM_CAP_XSAVE2)
> + * respectively, when invoked on the vm file descriptor.
> + *
> + * The size value returned by
> KVM_CHECK_EXTENSION(KVM_CAP_XSAVE2)
> + * will always be at least 4096. Currently, it is only greater
> + * than 4096 if a dynamic feature has been enabled with
> + * ``arch_prctl()``, but this may change in the future.
> + *
> + * The offsets of the state save areas in struct kvm_xsave follow
> + * the contents of CPUID leaf 0xD on the host.
> + */
> + __u32 extra[0];
> };
>
> #define KVM_MAX_XCRS 16
> diff --git a/linux-headers/linux/kvm.h b/linux-headers/linux/kvm.h
> index 02c5e7b7bb..97d5b6d81d 100644
> --- a/linux-headers/linux/kvm.h
> +++ b/linux-headers/linux/kvm.h
> @@ -1130,6 +1130,7 @@ struct kvm_ppc_resize_hpt {
> #define KVM_CAP_BINARY_STATS_FD 203
> #define KVM_CAP_EXIT_ON_EMULATION_FAILURE 204
> #define KVM_CAP_ARM_MTE 205
> +#define KVM_CAP_XSAVE2 207
>
> #ifdef KVM_CAP_IRQ_ROUTING
>
> @@ -1550,6 +1551,7 @@ struct kvm_s390_ucas_mapping {
> /* Available with KVM_CAP_XSAVE */
> #define KVM_GET_XSAVE _IOR(KVMIO, 0xa4, struct
> kvm_xsave)
> #define KVM_SET_XSAVE _IOW(KVMIO, 0xa5, struct
> kvm_xsave)
> +#define KVM_GET_XSAVE2 _IOR(KVMIO, 0xcf, struct
> kvm_xsave)
> /* Available with KVM_CAP_XCRS */
> #define KVM_GET_XCRS _IOR(KVMIO, 0xa6, struct kvm_xcrs)
> #define KVM_SET_XCRS _IOW(KVMIO, 0xa7, struct kvm_xcrs)
> diff --git a/target/i386/cpu.h b/target/i386/cpu.h
> index 245e8b5a1a..6153c4ab1a 100644
> --- a/target/i386/cpu.h
> +++ b/target/i386/cpu.h
> @@ -1519,6 +1519,11 @@ typedef struct CPUX86State {
> YMMReg zmmh_regs[CPU_NB_REGS];
> ZMMReg hi16_zmm_regs[CPU_NB_REGS];
>
> +#ifdef TARGET_X86_64
> + uint8_t xtilecfg[64];
> + uint8_t xtiledata[8192];
> +#endif
> +
> /* sysenter registers */
> uint32_t sysenter_cs;
> target_ulong sysenter_esp;
> diff --git a/target/i386/kvm/kvm.c b/target/i386/kvm/kvm.c
> index 3fb3ddbe2b..97520e9dff 100644
> --- a/target/i386/kvm/kvm.c
> +++ b/target/i386/kvm/kvm.c
> @@ -1983,7 +1983,12 @@ int kvm_arch_init_vcpu(CPUState *cs)
> }
>
> if (has_xsave) {
> - env->xsave_buf_len = sizeof(struct kvm_xsave);
> + uint32_t size = kvm_vm_check_extension(cs->kvm_state,
> KVM_CAP_XSAVE2);
> + if (!size) {
> + size = sizeof(struct kvm_xsave);
> + }
> +
> + env->xsave_buf_len = QEMU_ALIGN_UP(size, 4096);
> env->xsave_buf = qemu_memalign(4096, env->xsave_buf_len);
> memset(env->xsave_buf, 0, env->xsave_buf_len);
>
> @@ -2580,6 +2585,7 @@ static int kvm_put_xsave(X86CPU *cpu)
> if (!has_xsave) {
> return kvm_put_fpu(cpu);
> }
> +
> x86_cpu_xsave_all_areas(cpu, xsave, env->xsave_buf_len);
>
> return kvm_vcpu_ioctl(CPU(cpu), KVM_SET_XSAVE, xsave);
> @@ -3247,10 +3253,16 @@ static int kvm_get_xsave(X86CPU *cpu)
> return kvm_get_fpu(cpu);
> }
>
> - ret = kvm_vcpu_ioctl(CPU(cpu), KVM_GET_XSAVE, xsave);
> + if (env->xsave_buf_len <= sizeof(struct kvm_xsave)) {
> + ret = kvm_vcpu_ioctl(CPU(cpu), KVM_GET_XSAVE, xsave);
> + } else {
> + ret = kvm_vcpu_ioctl(CPU(cpu), KVM_GET_XSAVE2, xsave);
> + }
> +
> if (ret < 0) {
> return ret;
> }
> +
> x86_cpu_xrstor_all_areas(cpu, xsave, env->xsave_buf_len);
>
> return 0;
> diff --git a/target/i386/xsave_helper.c b/target/i386/xsave_helper.c
> index ac61a96344..090424e820 100644
> --- a/target/i386/xsave_helper.c
> +++ b/target/i386/xsave_helper.c
> @@ -5,6 +5,7 @@
> #include "qemu/osdep.h"
>
> #include "cpu.h"
> +#include <asm/kvm.h>
>
> void x86_cpu_xsave_all_areas(X86CPU *cpu, void *buf, uint32_t buflen)
> {
> @@ -126,6 +127,23 @@ void x86_cpu_xsave_all_areas(X86CPU *cpu, void
> *buf, uint32_t buflen)
>
> memcpy(pkru, &env->pkru, sizeof(env->pkru));
> }
> +
> + e = &x86_ext_save_areas[XSTATE_XTILE_CFG_BIT];
> + if (e->size && e->offset) {
> + XSaveXTILE_CFG *tilecfg = buf + e->offset;
> +
> + memcpy(tilecfg, &env->xtilecfg, sizeof(env->xtilecfg));
> + }
> +
> + if (buflen > sizeof(struct kvm_xsave)) {
> + e = &x86_ext_save_areas[XSTATE_XTILE_DATA_BIT];
> +
> + if (e->size && e->offset) {
> + XSaveXTILE_DATA *tiledata = buf + e->offset;
> +
> + memcpy(tiledata, &env->xtiledata, sizeof(env->xtiledata));
> + }
> + }
> #endif
> }
>
> @@ -247,5 +265,22 @@ void x86_cpu_xrstor_all_areas(X86CPU *cpu, const
> void *buf, uint32_t buflen)
> pkru = buf + e->offset;
> memcpy(&env->pkru, pkru, sizeof(env->pkru));
> }
> +
> + e = &x86_ext_save_areas[XSTATE_XTILE_CFG_BIT];
> + if (e->size && e->offset) {
> + const XSaveXTILE_CFG *tilecfg = buf + e->offset;
> +
> + memcpy(&env->xtilecfg, tilecfg, sizeof(env->xtilecfg));
> + }
> +
> + if (buflen > sizeof(struct kvm_xsave)) {
> + e = &x86_ext_save_areas[XSTATE_XTILE_DATA_BIT];
> +
> + if (e->size && e->offset) {
> + const XSaveXTILE_DATA *tiledata = buf + e->offset;
> +
> + memcpy(&env->xtiledata, tiledata, sizeof(env->xtiledata));
> + }
> + }
> #endif
> }
