Patchwork [4/4] qemu-kvm: Enable XSAVE live migration support

login
register
mail settings
Submitter Sheng Yang
Date June 17, 2010, 7:18 a.m.
Message ID <1276759096-29104-5-git-send-email-sheng@linux.intel.com>
Download mbox | patch
Permalink /patch/55980/
State New
Headers show

Comments

Sheng Yang - June 17, 2010, 7:18 a.m.
Based on upstream xsave related fields.

Signed-off-by: Sheng Yang <sheng@linux.intel.com>
---
 qemu-kvm-x86.c |   95 +++++++++++++++++++++++++++++++++++++++++++++++++++++++-
 qemu-kvm.c     |   24 ++++++++++++++
 qemu-kvm.h     |   28 ++++++++++++++++
 3 files changed, 146 insertions(+), 1 deletions(-)
Jan Kiszka - June 17, 2010, 7:41 a.m.
Sheng Yang wrote:
> Based on upstream xsave related fields.
> 
> Signed-off-by: Sheng Yang <sheng@linux.intel.com>
> ---
>  qemu-kvm-x86.c |   95 +++++++++++++++++++++++++++++++++++++++++++++++++++++++-
>  qemu-kvm.c     |   24 ++++++++++++++
>  qemu-kvm.h     |   28 ++++++++++++++++
>  3 files changed, 146 insertions(+), 1 deletions(-)
> 
> diff --git a/qemu-kvm-x86.c b/qemu-kvm-x86.c
> index 3c33e64..dcef8b5 100644
> --- a/qemu-kvm-x86.c
> +++ b/qemu-kvm-x86.c
> @@ -772,10 +772,26 @@ static void get_seg(SegmentCache *lhs, const struct kvm_segment *rhs)
>  	| (rhs->avl * DESC_AVL_MASK);
>  }
>  
> +#ifdef KVM_CAP_XSAVE
> +#define XSAVE_CWD_RIP     2
> +#define XSAVE_CWD_RDP     4
> +#define XSAVE_MXCSR       6
> +#define XSAVE_ST_SPACE    8
> +#define XSAVE_XMM_SPACE   40
> +#define XSAVE_XSTATE_BV   128
> +#define XSAVE_YMMH_SPACE  144
> +#endif
> +
>  void kvm_arch_load_regs(CPUState *env, int level)
>  {
>      struct kvm_regs regs;
>      struct kvm_fpu fpu;
> +#ifdef KVM_CAP_XSAVE
> +    struct kvm_xsave* xsave;
> +#endif
> +#ifdef KVM_CAP_XCRS
> +    struct kvm_xcrs xcrs;
> +#endif
>      struct kvm_sregs sregs;
>      struct kvm_msr_entry msrs[100];
>      int rc, n, i;
> @@ -806,16 +822,53 @@ void kvm_arch_load_regs(CPUState *env, int level)
>  
>      kvm_set_regs(env, &regs);
>  
> +#ifdef KVM_CAP_XSAVE
> +    if (kvm_check_extension(kvm_state, KVM_CAP_XSAVE)) {
> +        uint16_t cwd, swd, twd, fop;
> +
> +        xsave = qemu_memalign(4096, sizeof(struct kvm_xsave));
> +        memset(xsave, 0, sizeof(struct kvm_xsave));
> +        cwd = swd = twd = fop = 0;
> +        swd = env->fpus & ~(7 << 11);
> +        swd |= (env->fpstt & 7) << 11;
> +        cwd = env->fpuc;
> +        for (i = 0; i < 8; ++i)
> +            twd |= (!env->fptags[i]) << i;
> +        xsave->region[0] = (uint32_t)(swd << 16) + cwd;
> +        xsave->region[1] = (uint32_t)(fop << 16) + twd;
> +        memcpy(&xsave->region[XSAVE_ST_SPACE], env->fpregs,
> +                sizeof env->fpregs);
> +        memcpy(&xsave->region[XSAVE_XMM_SPACE], env->xmm_regs,
> +                sizeof env->xmm_regs);
> +        xsave->region[XSAVE_MXCSR] = env->mxcsr;
> +        *(uint64_t *)&xsave->region[XSAVE_XSTATE_BV] = env->xstate_bv;
> +        memcpy(&xsave->region[XSAVE_YMMH_SPACE], env->ymmh_regs,
> +                sizeof env->ymmh_regs);
> +        kvm_set_xsave(env, xsave);
> +#ifdef KVM_CAP_XCRS
> +        if (kvm_check_extension(kvm_state, KVM_CAP_XCRS)) {
> +            xcrs.nr_xcrs = 1;
> +            xcrs.flags = 0;
> +            xcrs.xcrs[0].xcr = 0;
> +            xcrs.xcrs[0].value = env->xcr0;
> +            kvm_set_xcrs(env, &xcrs);
> +        }
> +#endif /* KVM_CAP_XCRS */
> +    } else {
> +#endif /* KVM_CAP_XSAVE */

Why not reusing kvm_put/get_xsave as defined for upstream? There should
be enough examples for that pattern. The result will be a tiny qemu-kvm
patch.

Jan

>      memset(&fpu, 0, sizeof fpu);
>      fpu.fsw = env->fpus & ~(7 << 11);
>      fpu.fsw |= (env->fpstt & 7) << 11;
>      fpu.fcw = env->fpuc;
>      for (i = 0; i < 8; ++i)
> -	fpu.ftwx |= (!env->fptags[i]) << i;
> +        fpu.ftwx |= (!env->fptags[i]) << i;
>      memcpy(fpu.fpr, env->fpregs, sizeof env->fpregs);
>      memcpy(fpu.xmm, env->xmm_regs, sizeof env->xmm_regs);
>      fpu.mxcsr = env->mxcsr;
>      kvm_set_fpu(env, &fpu);
> +#ifdef KVM_CAP_XSAVE
> +    }
> +#endif
>  
>      memset(sregs.interrupt_bitmap, 0, sizeof(sregs.interrupt_bitmap));
>      if (env->interrupt_injected >= 0) {
> @@ -934,6 +987,12 @@ void kvm_arch_save_regs(CPUState *env)
>  {
>      struct kvm_regs regs;
>      struct kvm_fpu fpu;
> +#ifdef KVM_CAP_XSAVE
> +    struct kvm_xsave* xsave;
> +#endif
> +#ifdef KVM_CAP_XCRS
> +    struct kvm_xcrs xcrs;
> +#endif
>      struct kvm_sregs sregs;
>      struct kvm_msr_entry msrs[100];
>      uint32_t hflags;
> @@ -965,6 +1024,37 @@ void kvm_arch_save_regs(CPUState *env)
>      env->eflags = regs.rflags;
>      env->eip = regs.rip;
>  
> +#ifdef KVM_CAP_XSAVE
> +    if (kvm_check_extension(kvm_state, KVM_CAP_XSAVE)) {
> +        uint16_t cwd, swd, twd, fop;
> +        xsave = qemu_memalign(4096, sizeof(struct kvm_xsave));
> +        kvm_get_xsave(env, xsave);
> +        cwd = (uint16_t)xsave->region[0];
> +        swd = (uint16_t)(xsave->region[0] >> 16);
> +        twd = (uint16_t)xsave->region[1];
> +        fop = (uint16_t)(xsave->region[1] >> 16);
> +        env->fpstt = (swd >> 11) & 7;
> +        env->fpus = swd;
> +        env->fpuc = cwd;
> +        for (i = 0; i < 8; ++i)
> +            env->fptags[i] = !((twd >> i) & 1);
> +        env->mxcsr = xsave->region[XSAVE_MXCSR];
> +        memcpy(env->fpregs, &xsave->region[XSAVE_ST_SPACE],
> +                sizeof env->fpregs);
> +        memcpy(env->xmm_regs, &xsave->region[XSAVE_XMM_SPACE],
> +                sizeof env->xmm_regs);
> +        env->xstate_bv = *(uint64_t *)&xsave->region[XSAVE_XSTATE_BV];
> +        memcpy(env->ymmh_regs, &xsave->region[XSAVE_YMMH_SPACE],
> +                sizeof env->ymmh_regs);
> +#ifdef KVM_CAP_XCRS
> +        if (kvm_check_extension(kvm_state, KVM_CAP_XCRS)) {
> +            kvm_get_xcrs(env, &xcrs);
> +            if (xcrs.xcrs[0].xcr == 0)
> +                env->xcr0 = xcrs.xcrs[0].value;
> +        }
> +#endif
> +    } else {
> +#endif
>      kvm_get_fpu(env, &fpu);
>      env->fpstt = (fpu.fsw >> 11) & 7;
>      env->fpus = fpu.fsw;
> @@ -974,6 +1064,9 @@ void kvm_arch_save_regs(CPUState *env)
>      memcpy(env->fpregs, fpu.fpr, sizeof env->fpregs);
>      memcpy(env->xmm_regs, fpu.xmm, sizeof env->xmm_regs);
>      env->mxcsr = fpu.mxcsr;
> +#ifdef KVM_CAP_XSAVE
> +    }
> +#endif
>  
>      kvm_get_sregs(env, &sregs);
>  
> diff --git a/qemu-kvm.c b/qemu-kvm.c
> index 96d458c..be1dac2 100644
> --- a/qemu-kvm.c
> +++ b/qemu-kvm.c
> @@ -503,6 +503,30 @@ int kvm_set_mpstate(CPUState *env, struct kvm_mp_state *mp_state)
>  }
>  #endif
>  
> +#ifdef KVM_CAP_XSAVE
> +int kvm_get_xsave(CPUState *env, struct kvm_xsave *xsave)
> +{
> +    return kvm_vcpu_ioctl(env, KVM_GET_XSAVE, xsave);
> +}
> +
> +int kvm_set_xsave(CPUState *env, struct kvm_xsave *xsave)
> +{
> +    return kvm_vcpu_ioctl(env, KVM_SET_XSAVE, xsave);
> +}
> +#endif
> +
> +#ifdef KVM_CAP_XCRS
> +int kvm_get_xcrs(CPUState *env, struct kvm_xcrs *xcrs)
> +{
> +    return kvm_vcpu_ioctl(env, KVM_GET_XCRS, xcrs);
> +}
> +
> +int kvm_set_xcrs(CPUState *env, struct kvm_xcrs *xcrs)
> +{
> +    return kvm_vcpu_ioctl(env, KVM_SET_XCRS, xcrs);
> +}
> +#endif
> +
>  static int handle_mmio(CPUState *env)
>  {
>      unsigned long addr = env->kvm_run->mmio.phys_addr;
> diff --git a/qemu-kvm.h b/qemu-kvm.h
> index 6f6c6d8..3ace503 100644
> --- a/qemu-kvm.h
> +++ b/qemu-kvm.h
> @@ -300,6 +300,34 @@ int kvm_get_mpstate(CPUState *env, struct kvm_mp_state *mp_state);
>  int kvm_set_mpstate(CPUState *env, struct kvm_mp_state *mp_state);
>  #endif
>  
> +#ifdef KVM_CAP_XSAVE
> +/*!
> + *  * \brief Read VCPU xsave state
> + *
> + */
> +int kvm_get_xsave(CPUState *env, struct kvm_xsave *xsave);
> +
> +/*!
> + *  * \brief Write VCPU xsave state
> + *
> + */
> +int kvm_set_xsave(CPUState *env, struct kvm_xsave *xsave);
> +#endif
> +
> +#ifdef KVM_CAP_XCRS
> +/*!
> + *  * \brief Read VCPU XCRs
> + *
> + */
> +int kvm_get_xcrs(CPUState *env, struct kvm_xcrs *xcrs);
> +
> +/*!
> + *  * \brief Write VCPU XCRs
> + *
> + */
> +int kvm_set_xcrs(CPUState *env, struct kvm_xcrs *xcrs);
> +#endif
> +
>  /*!
>   * \brief Simulate an external vectored interrupt
>   *
Sheng Yang - June 17, 2010, 8:32 a.m.
On Thursday 17 June 2010 15:41:43 Jan Kiszka wrote:
> Sheng Yang wrote:
> > Based on upstream xsave related fields.
> > 
> > Signed-off-by: Sheng Yang <sheng@linux.intel.com>
> > ---
> > 
> >  qemu-kvm-x86.c |   95
> >  +++++++++++++++++++++++++++++++++++++++++++++++++++++++- qemu-kvm.c    
> >  |   24 ++++++++++++++
> >  qemu-kvm.h     |   28 ++++++++++++++++
> >  3 files changed, 146 insertions(+), 1 deletions(-)
> > 
> > diff --git a/qemu-kvm-x86.c b/qemu-kvm-x86.c
> > index 3c33e64..dcef8b5 100644
> > --- a/qemu-kvm-x86.c
> > +++ b/qemu-kvm-x86.c
> > @@ -772,10 +772,26 @@ static void get_seg(SegmentCache *lhs, const struct
> > kvm_segment *rhs)
> > 
> >  	| (rhs->avl * DESC_AVL_MASK);
> >  
> >  }
> > 
> > +#ifdef KVM_CAP_XSAVE
> > +#define XSAVE_CWD_RIP     2
> > +#define XSAVE_CWD_RDP     4
> > +#define XSAVE_MXCSR       6
> > +#define XSAVE_ST_SPACE    8
> > +#define XSAVE_XMM_SPACE   40
> > +#define XSAVE_XSTATE_BV   128
> > +#define XSAVE_YMMH_SPACE  144
> > +#endif
> > +
> > 
> >  void kvm_arch_load_regs(CPUState *env, int level)
> >  {
> >  
> >      struct kvm_regs regs;
> >      struct kvm_fpu fpu;
> > 
> > +#ifdef KVM_CAP_XSAVE
> > +    struct kvm_xsave* xsave;
> > +#endif
> > +#ifdef KVM_CAP_XCRS
> > +    struct kvm_xcrs xcrs;
> > +#endif
> > 
> >      struct kvm_sregs sregs;
> >      struct kvm_msr_entry msrs[100];
> >      int rc, n, i;
> > 
> > @@ -806,16 +822,53 @@ void kvm_arch_load_regs(CPUState *env, int level)
> > 
> >      kvm_set_regs(env, &regs);
> > 
> > +#ifdef KVM_CAP_XSAVE
> > +    if (kvm_check_extension(kvm_state, KVM_CAP_XSAVE)) {
> > +        uint16_t cwd, swd, twd, fop;
> > +
> > +        xsave = qemu_memalign(4096, sizeof(struct kvm_xsave));
> > +        memset(xsave, 0, sizeof(struct kvm_xsave));
> > +        cwd = swd = twd = fop = 0;
> > +        swd = env->fpus & ~(7 << 11);
> > +        swd |= (env->fpstt & 7) << 11;
> > +        cwd = env->fpuc;
> > +        for (i = 0; i < 8; ++i)
> > +            twd |= (!env->fptags[i]) << i;
> > +        xsave->region[0] = (uint32_t)(swd << 16) + cwd;
> > +        xsave->region[1] = (uint32_t)(fop << 16) + twd;
> > +        memcpy(&xsave->region[XSAVE_ST_SPACE], env->fpregs,
> > +                sizeof env->fpregs);
> > +        memcpy(&xsave->region[XSAVE_XMM_SPACE], env->xmm_regs,
> > +                sizeof env->xmm_regs);
> > +        xsave->region[XSAVE_MXCSR] = env->mxcsr;
> > +        *(uint64_t *)&xsave->region[XSAVE_XSTATE_BV] = env->xstate_bv;
> > +        memcpy(&xsave->region[XSAVE_YMMH_SPACE], env->ymmh_regs,
> > +                sizeof env->ymmh_regs);
> > +        kvm_set_xsave(env, xsave);
> > +#ifdef KVM_CAP_XCRS
> > +        if (kvm_check_extension(kvm_state, KVM_CAP_XCRS)) {
> > +            xcrs.nr_xcrs = 1;
> > +            xcrs.flags = 0;
> > +            xcrs.xcrs[0].xcr = 0;
> > +            xcrs.xcrs[0].value = env->xcr0;
> > +            kvm_set_xcrs(env, &xcrs);
> > +        }
> > +#endif /* KVM_CAP_XCRS */
> > +    } else {
> > +#endif /* KVM_CAP_XSAVE */
> 
> Why not reusing kvm_put/get_xsave as defined for upstream? There should
> be enough examples for that pattern. The result will be a tiny qemu-kvm
> patch.

Still lots of codes in kvm_arch_load/save_regs() duplicate with ones in kvm.c, 
e.g. kvm_get/put_sregs, kvm_get/put_msrs. So would like to wait for merging.

--
regards
Yang, Sheng

> 
> Jan
> 
> >      memset(&fpu, 0, sizeof fpu);
> >      fpu.fsw = env->fpus & ~(7 << 11);
> >      fpu.fsw |= (env->fpstt & 7) << 11;
> >      fpu.fcw = env->fpuc;
> >      for (i = 0; i < 8; ++i)
> > 
> > -	fpu.ftwx |= (!env->fptags[i]) << i;
> > +        fpu.ftwx |= (!env->fptags[i]) << i;
> > 
> >      memcpy(fpu.fpr, env->fpregs, sizeof env->fpregs);
> >      memcpy(fpu.xmm, env->xmm_regs, sizeof env->xmm_regs);
> >      fpu.mxcsr = env->mxcsr;
> >      kvm_set_fpu(env, &fpu);
> > 
> > +#ifdef KVM_CAP_XSAVE
> > +    }
> > +#endif
> > 
> >      memset(sregs.interrupt_bitmap, 0, sizeof(sregs.interrupt_bitmap));
> >      if (env->interrupt_injected >= 0) {
> > 
> > @@ -934,6 +987,12 @@ void kvm_arch_save_regs(CPUState *env)
> > 
> >  {
> >  
> >      struct kvm_regs regs;
> >      struct kvm_fpu fpu;
> > 
> > +#ifdef KVM_CAP_XSAVE
> > +    struct kvm_xsave* xsave;
> > +#endif
> > +#ifdef KVM_CAP_XCRS
> > +    struct kvm_xcrs xcrs;
> > +#endif
> > 
> >      struct kvm_sregs sregs;
> >      struct kvm_msr_entry msrs[100];
> >      uint32_t hflags;
> > 
> > @@ -965,6 +1024,37 @@ void kvm_arch_save_regs(CPUState *env)
> > 
> >      env->eflags = regs.rflags;
> >      env->eip = regs.rip;
> > 
> > +#ifdef KVM_CAP_XSAVE
> > +    if (kvm_check_extension(kvm_state, KVM_CAP_XSAVE)) {
> > +        uint16_t cwd, swd, twd, fop;
> > +        xsave = qemu_memalign(4096, sizeof(struct kvm_xsave));
> > +        kvm_get_xsave(env, xsave);
> > +        cwd = (uint16_t)xsave->region[0];
> > +        swd = (uint16_t)(xsave->region[0] >> 16);
> > +        twd = (uint16_t)xsave->region[1];
> > +        fop = (uint16_t)(xsave->region[1] >> 16);
> > +        env->fpstt = (swd >> 11) & 7;
> > +        env->fpus = swd;
> > +        env->fpuc = cwd;
> > +        for (i = 0; i < 8; ++i)
> > +            env->fptags[i] = !((twd >> i) & 1);
> > +        env->mxcsr = xsave->region[XSAVE_MXCSR];
> > +        memcpy(env->fpregs, &xsave->region[XSAVE_ST_SPACE],
> > +                sizeof env->fpregs);
> > +        memcpy(env->xmm_regs, &xsave->region[XSAVE_XMM_SPACE],
> > +                sizeof env->xmm_regs);
> > +        env->xstate_bv = *(uint64_t *)&xsave->region[XSAVE_XSTATE_BV];
> > +        memcpy(env->ymmh_regs, &xsave->region[XSAVE_YMMH_SPACE],
> > +                sizeof env->ymmh_regs);
> > +#ifdef KVM_CAP_XCRS
> > +        if (kvm_check_extension(kvm_state, KVM_CAP_XCRS)) {
> > +            kvm_get_xcrs(env, &xcrs);
> > +            if (xcrs.xcrs[0].xcr == 0)
> > +                env->xcr0 = xcrs.xcrs[0].value;
> > +        }
> > +#endif
> > +    } else {
> > +#endif
> > 
> >      kvm_get_fpu(env, &fpu);
> >      env->fpstt = (fpu.fsw >> 11) & 7;
> >      env->fpus = fpu.fsw;
> > 
> > @@ -974,6 +1064,9 @@ void kvm_arch_save_regs(CPUState *env)
> > 
> >      memcpy(env->fpregs, fpu.fpr, sizeof env->fpregs);
> >      memcpy(env->xmm_regs, fpu.xmm, sizeof env->xmm_regs);
> >      env->mxcsr = fpu.mxcsr;
> > 
> > +#ifdef KVM_CAP_XSAVE
> > +    }
> > +#endif
> > 
> >      kvm_get_sregs(env, &sregs);
> > 
> > diff --git a/qemu-kvm.c b/qemu-kvm.c
> > index 96d458c..be1dac2 100644
> > --- a/qemu-kvm.c
> > +++ b/qemu-kvm.c
> > @@ -503,6 +503,30 @@ int kvm_set_mpstate(CPUState *env, struct
> > kvm_mp_state *mp_state)
> > 
> >  }
> >  #endif
> > 
> > +#ifdef KVM_CAP_XSAVE
> > +int kvm_get_xsave(CPUState *env, struct kvm_xsave *xsave)
> > +{
> > +    return kvm_vcpu_ioctl(env, KVM_GET_XSAVE, xsave);
> > +}
> > +
> > +int kvm_set_xsave(CPUState *env, struct kvm_xsave *xsave)
> > +{
> > +    return kvm_vcpu_ioctl(env, KVM_SET_XSAVE, xsave);
> > +}
> > +#endif
> > +
> > +#ifdef KVM_CAP_XCRS
> > +int kvm_get_xcrs(CPUState *env, struct kvm_xcrs *xcrs)
> > +{
> > +    return kvm_vcpu_ioctl(env, KVM_GET_XCRS, xcrs);
> > +}
> > +
> > +int kvm_set_xcrs(CPUState *env, struct kvm_xcrs *xcrs)
> > +{
> > +    return kvm_vcpu_ioctl(env, KVM_SET_XCRS, xcrs);
> > +}
> > +#endif
> > +
> > 
> >  static int handle_mmio(CPUState *env)
> >  {
> >  
> >      unsigned long addr = env->kvm_run->mmio.phys_addr;
> > 
> > diff --git a/qemu-kvm.h b/qemu-kvm.h
> > index 6f6c6d8..3ace503 100644
> > --- a/qemu-kvm.h
> > +++ b/qemu-kvm.h
> > @@ -300,6 +300,34 @@ int kvm_get_mpstate(CPUState *env, struct
> > kvm_mp_state *mp_state);
> > 
> >  int kvm_set_mpstate(CPUState *env, struct kvm_mp_state *mp_state);
> >  #endif
> > 
> > +#ifdef KVM_CAP_XSAVE
> > +/*!
> > + *  * \brief Read VCPU xsave state
> > + *
> > + */
> > +int kvm_get_xsave(CPUState *env, struct kvm_xsave *xsave);
> > +
> > +/*!
> > + *  * \brief Write VCPU xsave state
> > + *
> > + */
> > +int kvm_set_xsave(CPUState *env, struct kvm_xsave *xsave);
> > +#endif
> > +
> > +#ifdef KVM_CAP_XCRS
> > +/*!
> > + *  * \brief Read VCPU XCRs
> > + *
> > + */
> > +int kvm_get_xcrs(CPUState *env, struct kvm_xcrs *xcrs);
> > +
> > +/*!
> > + *  * \brief Write VCPU XCRs
> > + *
> > + */
> > +int kvm_set_xcrs(CPUState *env, struct kvm_xcrs *xcrs);
> > +#endif
> > +
> > 
> >  /*!
> >  
> >   * \brief Simulate an external vectored interrupt
> >   *
Jan Kiszka - June 17, 2010, 8:44 a.m.
Sheng Yang wrote:
> On Thursday 17 June 2010 15:41:43 Jan Kiszka wrote:
>> Sheng Yang wrote:
>>> Based on upstream xsave related fields.
>>>
>>> Signed-off-by: Sheng Yang <sheng@linux.intel.com>
>>> ---
>>>
>>>  qemu-kvm-x86.c |   95
>>>  +++++++++++++++++++++++++++++++++++++++++++++++++++++++- qemu-kvm.c    
>>>  |   24 ++++++++++++++
>>>  qemu-kvm.h     |   28 ++++++++++++++++
>>>  3 files changed, 146 insertions(+), 1 deletions(-)
>>>
>>> diff --git a/qemu-kvm-x86.c b/qemu-kvm-x86.c
>>> index 3c33e64..dcef8b5 100644
>>> --- a/qemu-kvm-x86.c
>>> +++ b/qemu-kvm-x86.c
>>> @@ -772,10 +772,26 @@ static void get_seg(SegmentCache *lhs, const struct
>>> kvm_segment *rhs)
>>>
>>>  	| (rhs->avl * DESC_AVL_MASK);
>>>  
>>>  }
>>>
>>> +#ifdef KVM_CAP_XSAVE
>>> +#define XSAVE_CWD_RIP     2
>>> +#define XSAVE_CWD_RDP     4
>>> +#define XSAVE_MXCSR       6
>>> +#define XSAVE_ST_SPACE    8
>>> +#define XSAVE_XMM_SPACE   40
>>> +#define XSAVE_XSTATE_BV   128
>>> +#define XSAVE_YMMH_SPACE  144
>>> +#endif
>>> +
>>>
>>>  void kvm_arch_load_regs(CPUState *env, int level)
>>>  {
>>>  
>>>      struct kvm_regs regs;
>>>      struct kvm_fpu fpu;
>>>
>>> +#ifdef KVM_CAP_XSAVE
>>> +    struct kvm_xsave* xsave;
>>> +#endif
>>> +#ifdef KVM_CAP_XCRS
>>> +    struct kvm_xcrs xcrs;
>>> +#endif
>>>
>>>      struct kvm_sregs sregs;
>>>      struct kvm_msr_entry msrs[100];
>>>      int rc, n, i;
>>>
>>> @@ -806,16 +822,53 @@ void kvm_arch_load_regs(CPUState *env, int level)
>>>
>>>      kvm_set_regs(env, &regs);
>>>
>>> +#ifdef KVM_CAP_XSAVE
>>> +    if (kvm_check_extension(kvm_state, KVM_CAP_XSAVE)) {
>>> +        uint16_t cwd, swd, twd, fop;
>>> +
>>> +        xsave = qemu_memalign(4096, sizeof(struct kvm_xsave));
>>> +        memset(xsave, 0, sizeof(struct kvm_xsave));
>>> +        cwd = swd = twd = fop = 0;
>>> +        swd = env->fpus & ~(7 << 11);
>>> +        swd |= (env->fpstt & 7) << 11;
>>> +        cwd = env->fpuc;
>>> +        for (i = 0; i < 8; ++i)
>>> +            twd |= (!env->fptags[i]) << i;
>>> +        xsave->region[0] = (uint32_t)(swd << 16) + cwd;
>>> +        xsave->region[1] = (uint32_t)(fop << 16) + twd;
>>> +        memcpy(&xsave->region[XSAVE_ST_SPACE], env->fpregs,
>>> +                sizeof env->fpregs);
>>> +        memcpy(&xsave->region[XSAVE_XMM_SPACE], env->xmm_regs,
>>> +                sizeof env->xmm_regs);
>>> +        xsave->region[XSAVE_MXCSR] = env->mxcsr;
>>> +        *(uint64_t *)&xsave->region[XSAVE_XSTATE_BV] = env->xstate_bv;
>>> +        memcpy(&xsave->region[XSAVE_YMMH_SPACE], env->ymmh_regs,
>>> +                sizeof env->ymmh_regs);
>>> +        kvm_set_xsave(env, xsave);
>>> +#ifdef KVM_CAP_XCRS
>>> +        if (kvm_check_extension(kvm_state, KVM_CAP_XCRS)) {
>>> +            xcrs.nr_xcrs = 1;
>>> +            xcrs.flags = 0;
>>> +            xcrs.xcrs[0].xcr = 0;
>>> +            xcrs.xcrs[0].value = env->xcr0;
>>> +            kvm_set_xcrs(env, &xcrs);
>>> +        }
>>> +#endif /* KVM_CAP_XCRS */
>>> +    } else {
>>> +#endif /* KVM_CAP_XSAVE */
>> Why not reusing kvm_put/get_xsave as defined for upstream? There should
>> be enough examples for that pattern. The result will be a tiny qemu-kvm
>> patch.
> 
> Still lots of codes in kvm_arch_load/save_regs() duplicate with ones in kvm.c, 
> e.g. kvm_get/put_sregs, kvm_get/put_msrs. So would like to wait for merging.

That we still have some legacy here is no good reason to increase it.
Just check how debugregs were introduced.

Jan

Patch

diff --git a/qemu-kvm-x86.c b/qemu-kvm-x86.c
index 3c33e64..dcef8b5 100644
--- a/qemu-kvm-x86.c
+++ b/qemu-kvm-x86.c
@@ -772,10 +772,26 @@  static void get_seg(SegmentCache *lhs, const struct kvm_segment *rhs)
 	| (rhs->avl * DESC_AVL_MASK);
 }
 
+#ifdef KVM_CAP_XSAVE
+#define XSAVE_CWD_RIP     2
+#define XSAVE_CWD_RDP     4
+#define XSAVE_MXCSR       6
+#define XSAVE_ST_SPACE    8
+#define XSAVE_XMM_SPACE   40
+#define XSAVE_XSTATE_BV   128
+#define XSAVE_YMMH_SPACE  144
+#endif
+
 void kvm_arch_load_regs(CPUState *env, int level)
 {
     struct kvm_regs regs;
     struct kvm_fpu fpu;
+#ifdef KVM_CAP_XSAVE
+    struct kvm_xsave* xsave;
+#endif
+#ifdef KVM_CAP_XCRS
+    struct kvm_xcrs xcrs;
+#endif
     struct kvm_sregs sregs;
     struct kvm_msr_entry msrs[100];
     int rc, n, i;
@@ -806,16 +822,53 @@  void kvm_arch_load_regs(CPUState *env, int level)
 
     kvm_set_regs(env, &regs);
 
+#ifdef KVM_CAP_XSAVE
+    if (kvm_check_extension(kvm_state, KVM_CAP_XSAVE)) {
+        uint16_t cwd, swd, twd, fop;
+
+        xsave = qemu_memalign(4096, sizeof(struct kvm_xsave));
+        memset(xsave, 0, sizeof(struct kvm_xsave));
+        cwd = swd = twd = fop = 0;
+        swd = env->fpus & ~(7 << 11);
+        swd |= (env->fpstt & 7) << 11;
+        cwd = env->fpuc;
+        for (i = 0; i < 8; ++i)
+            twd |= (!env->fptags[i]) << i;
+        xsave->region[0] = (uint32_t)(swd << 16) + cwd;
+        xsave->region[1] = (uint32_t)(fop << 16) + twd;
+        memcpy(&xsave->region[XSAVE_ST_SPACE], env->fpregs,
+                sizeof env->fpregs);
+        memcpy(&xsave->region[XSAVE_XMM_SPACE], env->xmm_regs,
+                sizeof env->xmm_regs);
+        xsave->region[XSAVE_MXCSR] = env->mxcsr;
+        *(uint64_t *)&xsave->region[XSAVE_XSTATE_BV] = env->xstate_bv;
+        memcpy(&xsave->region[XSAVE_YMMH_SPACE], env->ymmh_regs,
+                sizeof env->ymmh_regs);
+        kvm_set_xsave(env, xsave);
+#ifdef KVM_CAP_XCRS
+        if (kvm_check_extension(kvm_state, KVM_CAP_XCRS)) {
+            xcrs.nr_xcrs = 1;
+            xcrs.flags = 0;
+            xcrs.xcrs[0].xcr = 0;
+            xcrs.xcrs[0].value = env->xcr0;
+            kvm_set_xcrs(env, &xcrs);
+        }
+#endif /* KVM_CAP_XCRS */
+    } else {
+#endif /* KVM_CAP_XSAVE */
     memset(&fpu, 0, sizeof fpu);
     fpu.fsw = env->fpus & ~(7 << 11);
     fpu.fsw |= (env->fpstt & 7) << 11;
     fpu.fcw = env->fpuc;
     for (i = 0; i < 8; ++i)
-	fpu.ftwx |= (!env->fptags[i]) << i;
+        fpu.ftwx |= (!env->fptags[i]) << i;
     memcpy(fpu.fpr, env->fpregs, sizeof env->fpregs);
     memcpy(fpu.xmm, env->xmm_regs, sizeof env->xmm_regs);
     fpu.mxcsr = env->mxcsr;
     kvm_set_fpu(env, &fpu);
+#ifdef KVM_CAP_XSAVE
+    }
+#endif
 
     memset(sregs.interrupt_bitmap, 0, sizeof(sregs.interrupt_bitmap));
     if (env->interrupt_injected >= 0) {
@@ -934,6 +987,12 @@  void kvm_arch_save_regs(CPUState *env)
 {
     struct kvm_regs regs;
     struct kvm_fpu fpu;
+#ifdef KVM_CAP_XSAVE
+    struct kvm_xsave* xsave;
+#endif
+#ifdef KVM_CAP_XCRS
+    struct kvm_xcrs xcrs;
+#endif
     struct kvm_sregs sregs;
     struct kvm_msr_entry msrs[100];
     uint32_t hflags;
@@ -965,6 +1024,37 @@  void kvm_arch_save_regs(CPUState *env)
     env->eflags = regs.rflags;
     env->eip = regs.rip;
 
+#ifdef KVM_CAP_XSAVE
+    if (kvm_check_extension(kvm_state, KVM_CAP_XSAVE)) {
+        uint16_t cwd, swd, twd, fop;
+        xsave = qemu_memalign(4096, sizeof(struct kvm_xsave));
+        kvm_get_xsave(env, xsave);
+        cwd = (uint16_t)xsave->region[0];
+        swd = (uint16_t)(xsave->region[0] >> 16);
+        twd = (uint16_t)xsave->region[1];
+        fop = (uint16_t)(xsave->region[1] >> 16);
+        env->fpstt = (swd >> 11) & 7;
+        env->fpus = swd;
+        env->fpuc = cwd;
+        for (i = 0; i < 8; ++i)
+            env->fptags[i] = !((twd >> i) & 1);
+        env->mxcsr = xsave->region[XSAVE_MXCSR];
+        memcpy(env->fpregs, &xsave->region[XSAVE_ST_SPACE],
+                sizeof env->fpregs);
+        memcpy(env->xmm_regs, &xsave->region[XSAVE_XMM_SPACE],
+                sizeof env->xmm_regs);
+        env->xstate_bv = *(uint64_t *)&xsave->region[XSAVE_XSTATE_BV];
+        memcpy(env->ymmh_regs, &xsave->region[XSAVE_YMMH_SPACE],
+                sizeof env->ymmh_regs);
+#ifdef KVM_CAP_XCRS
+        if (kvm_check_extension(kvm_state, KVM_CAP_XCRS)) {
+            kvm_get_xcrs(env, &xcrs);
+            if (xcrs.xcrs[0].xcr == 0)
+                env->xcr0 = xcrs.xcrs[0].value;
+        }
+#endif
+    } else {
+#endif
     kvm_get_fpu(env, &fpu);
     env->fpstt = (fpu.fsw >> 11) & 7;
     env->fpus = fpu.fsw;
@@ -974,6 +1064,9 @@  void kvm_arch_save_regs(CPUState *env)
     memcpy(env->fpregs, fpu.fpr, sizeof env->fpregs);
     memcpy(env->xmm_regs, fpu.xmm, sizeof env->xmm_regs);
     env->mxcsr = fpu.mxcsr;
+#ifdef KVM_CAP_XSAVE
+    }
+#endif
 
     kvm_get_sregs(env, &sregs);
 
diff --git a/qemu-kvm.c b/qemu-kvm.c
index 96d458c..be1dac2 100644
--- a/qemu-kvm.c
+++ b/qemu-kvm.c
@@ -503,6 +503,30 @@  int kvm_set_mpstate(CPUState *env, struct kvm_mp_state *mp_state)
 }
 #endif
 
+#ifdef KVM_CAP_XSAVE
+int kvm_get_xsave(CPUState *env, struct kvm_xsave *xsave)
+{
+    return kvm_vcpu_ioctl(env, KVM_GET_XSAVE, xsave);
+}
+
+int kvm_set_xsave(CPUState *env, struct kvm_xsave *xsave)
+{
+    return kvm_vcpu_ioctl(env, KVM_SET_XSAVE, xsave);
+}
+#endif
+
+#ifdef KVM_CAP_XCRS
+int kvm_get_xcrs(CPUState *env, struct kvm_xcrs *xcrs)
+{
+    return kvm_vcpu_ioctl(env, KVM_GET_XCRS, xcrs);
+}
+
+int kvm_set_xcrs(CPUState *env, struct kvm_xcrs *xcrs)
+{
+    return kvm_vcpu_ioctl(env, KVM_SET_XCRS, xcrs);
+}
+#endif
+
 static int handle_mmio(CPUState *env)
 {
     unsigned long addr = env->kvm_run->mmio.phys_addr;
diff --git a/qemu-kvm.h b/qemu-kvm.h
index 6f6c6d8..3ace503 100644
--- a/qemu-kvm.h
+++ b/qemu-kvm.h
@@ -300,6 +300,34 @@  int kvm_get_mpstate(CPUState *env, struct kvm_mp_state *mp_state);
 int kvm_set_mpstate(CPUState *env, struct kvm_mp_state *mp_state);
 #endif
 
+#ifdef KVM_CAP_XSAVE
+/*!
+ *  * \brief Read VCPU xsave state
+ *
+ */
+int kvm_get_xsave(CPUState *env, struct kvm_xsave *xsave);
+
+/*!
+ *  * \brief Write VCPU xsave state
+ *
+ */
+int kvm_set_xsave(CPUState *env, struct kvm_xsave *xsave);
+#endif
+
+#ifdef KVM_CAP_XCRS
+/*!
+ *  * \brief Read VCPU XCRs
+ *
+ */
+int kvm_get_xcrs(CPUState *env, struct kvm_xcrs *xcrs);
+
+/*!
+ *  * \brief Write VCPU XCRs
+ *
+ */
+int kvm_set_xcrs(CPUState *env, struct kvm_xcrs *xcrs);
+#endif
+
 /*!
  * \brief Simulate an external vectored interrupt
  *