XSAVE enabling in QEmu

Signed-off-by Sheng Yang <[email protected]>

---
 target-i386/cpu.h     |    5 ++
 target-i386/kvm.c     |  134 +++++++++++++++++++++++++++++++++++++++++++++++++
 target-i386/machine.c |   20 +++++++
 3 files changed, 159 insertions(+), 0 deletions(-)

target-i386/cpu.h +5 -0

index 548ab80..75070d3 100644
@@ -718,6 +718,11 @@ typedef struct CPUX86State {
     uint16_t fpus_vmstate;
     uint16_t fptag_vmstate;
     uint16_t fpregs_format_vmstate;
+
+    uint64_t xstate_bv;
+    XMMReg ymmh_regs[CPU_NB_REGS];
+
+    uint64_t xcr0;
 } CPUX86State;
 
 CPUX86State *cpu_x86_init(const char *cpu_model);

target-i386/kvm.c +112 -0

index bb6a12f..90ff323 100644
@@ -289,6 +289,8 @@ void kvm_arch_reset_vcpu(CPUState *env)
     } else {
         env->mp_state = KVM_MP_STATE_RUNNABLE;
     }
+    /* Legal xcr0 for loading */
+    env->xcr0 = 1;
 }
 
 static int kvm_has_msr_star(CPUState *env)

@@ -504,6 +506,57 @@ static int kvm_put_fpu(CPUState *env)
     return kvm_vcpu_ioctl(env, KVM_SET_FPU, &fpu);
 }
 
+#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
+
+static int kvm_put_xsave(CPUState *env)
+{
+    int i;
+    struct kvm_xsave* 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);
+    return kvm_vcpu_ioctl(env, KVM_SET_XSAVE, xsave);
+}
+#endif
+
+#ifdef KVM_CAP_XCRS
+static int kvm_put_xcrs(CPUState *env)
+{
+    struct kvm_xcrs xcrs;
+
+    xcrs.nr_xcrs = 1;
+    xcrs.flags = 0;
+    xcrs.xcrs[0].xcr = 0;
+    xcrs.xcrs[0].value = env->xcr0;
+    return kvm_vcpu_ioctl(env, KVM_SET_XCRS, &xcrs);
+}
+#endif
+
 static int kvm_put_sregs(CPUState *env)
 {
     struct kvm_sregs sregs;

@@ -621,6 +674,59 @@ static int kvm_get_fpu(CPUState *env)
     return 0;
 }
 
+#ifdef KVM_CAP_XSAVE
+static int kvm_get_xsave(CPUState *env)
+{
+    struct kvm_xsave* xsave;
+    int ret, i;
+    uint16_t cwd, swd, twd, fop;
+
+    xsave = qemu_memalign(4096, sizeof(struct kvm_xsave));
+    ret = kvm_vcpu_ioctl(env, KVM_GET_XSAVE, xsave);
+    if (ret < 0)
+        return ret;
+
+    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);
+    return 0;
+}
+#endif
+
+#ifdef KVM_CAP_XCRS
+static int kvm_get_xcrs(CPUState *env)
+{
+    int i, ret;
+    struct kvm_xcrs xcrs;
+
+    ret = kvm_vcpu_ioctl(env, KVM_GET_XCRS, &xcrs);
+    if (ret < 0)
+        return ret;
+
+    for (i = 0; i < xcrs.nr_xcrs; i++)
+        /* Only support xcr0 now */
+        if (xcrs.xcrs[0].xcr == 0) {
+            env->xcr0 = xcrs.xcrs[0].value;
+            break;
+        }
+    return 0;
+}
+#endif
+
 static int kvm_get_sregs(CPUState *env)
 {
     struct kvm_sregs sregs;

@@ -965,9 +1071,23 @@ int kvm_arch_put_registers(CPUState *env, int level)
     if (ret < 0)
         return ret;
 
+#ifdef KVM_CAP_XSAVE
+    if (kvm_check_extension(env->kvm_state, KVM_CAP_XSAVE))
+        ret = kvm_put_xsave(env);
+    else
+        ret = kvm_put_fpu(env);
+#else
     ret = kvm_put_fpu(env);

target-i386/kvm.c +14 -0

     ret = kvm_put_sregs(env);
     if (ret < 0)

@@ -1009,9 +1129,23 @@ int kvm_arch_get_registers(CPUState *env)
     if (ret < 0)
         return ret;
 
+#ifdef KVM_CAP_XSAVE
+    if (kvm_check_extension(env->kvm_state, KVM_CAP_XSAVE))
+        ret = kvm_get_xsave(env);
+    else
+        ret = kvm_get_fpu(env);
+#else
     ret = kvm_get_fpu(env);
+#endif
+    if (ret < 0)
+        return ret;
+
+#ifdef KVM_CAP_XCRS
+    if (kvm_check_extension(env->kvm_state, KVM_CAP_XCRS))
+        ret = kvm_get_xcrs(env);
     if (ret < 0)
         return ret;
+#endif
 
     ret = kvm_get_sregs(env);
     if (ret < 0)

target-i386/machine.c +16 -0

index b547e2a..5f8376c 100644
@@ -47,6 +47,22 @@ static const VMStateDescription vmstate_xmm_reg = {
 #define VMSTATE_XMM_REGS(_field, _state, _n)                         \
     VMSTATE_STRUCT_ARRAY(_field, _state, _n, 0, vmstate_xmm_reg, XMMReg)
 
+/* YMMH format is the same as XMM */
+static const VMStateDescription vmstate_ymmh_reg = {
+    .name = "ymmh_reg",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .minimum_version_id_old = 1,
+    .fields      = (VMStateField []) {
+        VMSTATE_UINT64(XMM_Q(0), XMMReg),
+        VMSTATE_UINT64(XMM_Q(1), XMMReg),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
+#define VMSTATE_YMMH_REGS_VARS(_field, _state, _n, _v)                         \
+    VMSTATE_STRUCT_ARRAY(_field, _state, _n, _v, vmstate_ymmh_reg, XMMReg)
+
 static const VMStateDescription vmstate_mtrr_var = {
     .name = "mtrr_var",
     .version_id = 1,

Signed-off-by Sheng Yang <[email protected]>

---
 target-i386/cpu.h     |    7 ++-
 target-i386/kvm.c     |  139 ++++++++++++++++++++++++++++++++++++++++++++++++-
 target-i386/machine.c |   20 +++++++
 3 files changed, 163 insertions(+), 3 deletions(-)

target-i386/cpu.h +6 -1

index 548ab80..680eed1 100644
@@ -718,6 +718,11 @@ typedef struct CPUX86State {
     uint16_t fpus_vmstate;
     uint16_t fptag_vmstate;
     uint16_t fpregs_format_vmstate;
+
+    uint64_t xstate_bv;
+    XMMReg ymmh_regs[CPU_NB_REGS];
+
+    uint64_t xcr0;
 } CPUX86State;
 
 CPUX86State *cpu_x86_init(const char *cpu_model);

@@ -895,7 +900,7 @@ uint64_t cpu_get_tsc(CPUX86State *env);
 #define cpu_list_id x86_cpu_list
 #define cpudef_setup	x86_cpudef_setup
 
-#define CPU_SAVE_VERSION 11
+#define CPU_SAVE_VERSION 12
 
 /* MMU modes definitions */
 #define MMU_MODE0_SUFFIX _kernel

target-i386/kvm.c +10 -0

index bb6a12f..e490c0a 100644
@@ -289,6 +289,8 @@ void kvm_arch_reset_vcpu(CPUState *env)
     } else {
         env->mp_state = KVM_MP_STATE_RUNNABLE;
     }
+    /* Legal xcr0 for loading */
+    env->xcr0 = 1;
 }
 
 static int kvm_has_msr_star(CPUState *env)

@@ -504,6 +506,68 @@ static int kvm_put_fpu(CPUState *env)
     return kvm_vcpu_ioctl(env, KVM_SET_FPU, &fpu);
 }
 
+#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

target-i386/kvm.c +117 -2

+        return kvm_put_fpu(env);
+
+    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);
+    return kvm_vcpu_ioctl(env, KVM_SET_XSAVE, xsave);
+#else
+    return kvm_put_fpu(env);
+#endif
+}
+
+static int kvm_put_xcrs(CPUState *env)
+{
+#ifdef KVM_CAP_XCRS
+    struct kvm_xcrs xcrs;
+
+    if (!kvm_check_extension(env->kvm_state, KVM_CAP_XCRS))
+        return 0;
+
+    xcrs.nr_xcrs = 1;
+    xcrs.flags = 0;
+    xcrs.xcrs[0].xcr = 0;
+    xcrs.xcrs[0].value = env->xcr0;
+    return kvm_vcpu_ioctl(env, KVM_SET_XCRS, &xcrs);
+#else
+    return 0;
+#endif
+}
+
 static int kvm_put_sregs(CPUState *env)
 {
     struct kvm_sregs sregs;

@@ -621,6 +685,69 @@ static int kvm_get_fpu(CPUState *env)
     return 0;
 }
 
+static int kvm_get_xsave(CPUState *env)
+{
+#ifdef KVM_CAP_XSAVE
+    struct kvm_xsave* xsave;
+    int ret, i;
+    uint16_t cwd, swd, twd, fop;
+
+    if (!kvm_check_extension(env->kvm_state, KVM_CAP_XSAVE))
+        return kvm_get_fpu(env);
+
+    xsave = qemu_memalign(4096, sizeof(struct kvm_xsave));
+    ret = kvm_vcpu_ioctl(env, KVM_GET_XSAVE, xsave);
+    if (ret < 0)
+        return ret;
+
+    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);
+    return 0;
+#else
+    return kvm_get_fpu(env);
+#endif
+}
+
+static int kvm_get_xcrs(CPUState *env)
+{
+#ifdef KVM_CAP_XCRS
+    int i, ret;
+    struct kvm_xcrs xcrs;
+
+    if (!kvm_check_extension(env->kvm_state, KVM_CAP_XCRS))
+        return 0;
+
+    ret = kvm_vcpu_ioctl(env, KVM_GET_XCRS, &xcrs);
+    if (ret < 0)
+        return ret;
+
+    for (i = 0; i < xcrs.nr_xcrs; i++)
+        /* Only support xcr0 now */
+        if (xcrs.xcrs[0].xcr == 0) {
+            env->xcr0 = xcrs.xcrs[0].value;
+            break;
+        }
+    return 0;
+#else
+    return 0;
+#endif
+}
+
 static int kvm_get_sregs(CPUState *env)
 {
     struct kvm_sregs sregs;

@@ -965,7 +1092,11 @@ int kvm_arch_put_registers(CPUState *env, int level)
     if (ret < 0)
         return ret;
 
-    ret = kvm_put_fpu(env);
+    ret = kvm_put_xsave(env);
+    if (ret < 0)
+        return ret;
+
+    ret = kvm_put_xcrs(env);
     if (ret < 0)
         return ret;
 

@@ -1009,7 +1140,11 @@ int kvm_arch_get_registers(CPUState *env)
     if (ret < 0)
         return ret;
 
-    ret = kvm_get_fpu(env);
+    ret = kvm_get_xsave(env);
+    if (ret < 0)
+        return ret;
+
+    ret = kvm_get_xcrs(env);
     if (ret < 0)
         return ret;
 

target-i386/machine.c +16 -0

index b547e2a..5f8376c 100644
@@ -47,6 +47,22 @@ static const VMStateDescription vmstate_xmm_reg = {
 #define VMSTATE_XMM_REGS(_field, _state, _n)                         \
     VMSTATE_STRUCT_ARRAY(_field, _state, _n, 0, vmstate_xmm_reg, XMMReg)
 
+/* YMMH format is the same as XMM */
+static const VMStateDescription vmstate_ymmh_reg = {
+    .name = "ymmh_reg",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .minimum_version_id_old = 1,
+    .fields      = (VMStateField []) {
+        VMSTATE_UINT64(XMM_Q(0), XMMReg),
+        VMSTATE_UINT64(XMM_Q(1), XMMReg),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
+#define VMSTATE_YMMH_REGS_VARS(_field, _state, _n, _v)                         \
+    VMSTATE_STRUCT_ARRAY(_field, _state, _n, _v, vmstate_ymmh_reg, XMMReg)
+
 static const VMStateDescription vmstate_mtrr_var = {
     .name = "mtrr_var",
     .version_id = 1,

Signed-off-by Sheng Yang <[email protected]>

---
 kvm-all.c             |   21 +++++++
 kvm.h                 |    2 +
 target-i386/cpu.h     |    7 ++-
 target-i386/kvm.c     |  139 ++++++++++++++++++++++++++++++++++++++++++++++++-
 target-i386/machine.c |   20 +++++++
 5 files changed, 186 insertions(+), 3 deletions(-)

kvm-all.c +21 -0

index 43704b8..343c06e 100644
@@ -71,6 +71,7 @@ struct KVMState
 #endif
     int irqchip_in_kernel;
     int pit_in_kernel;
+    int xsave, xcrs;
 };
 
 static KVMState *kvm_state;

@@ -685,6 +686,16 @@ int kvm_init(int smp_cpus)
     s->debugregs = kvm_check_extension(s, KVM_CAP_DEBUGREGS);
 #endif
 
+    s->xsave = 0;
+#ifdef KVM_CAP_XSAVE
+    s->xsave = kvm_check_extension(s, KVM_CAP_XSAVE);
+#endif
+
+    s->xcrs = 0;
+#ifdef KVM_CAP_XCRS
+    s->xcrs = kvm_check_extension(s, KVM_CAP_XCRS);
+#endif
+
     ret = kvm_arch_init(s, smp_cpus);
     if (ret < 0)
         goto err;

@@ -1013,6 +1024,16 @@ int kvm_has_debugregs(void)
     return kvm_state->debugregs;
 }
 
+int kvm_has_xsave(void)
+{
+    return kvm_state->xsave;
+}
+
+int kvm_has_xcrs(void)
+{
+    return kvm_state->xcrs;
+}
+
 void kvm_setup_guest_memory(void *start, size_t size)
 {
     if (!kvm_has_sync_mmu()) {

kvm.h +2 -0

index 7975e87..50c4192 100644
@@ -41,6 +41,8 @@ int kvm_has_sync_mmu(void);
 int kvm_has_vcpu_events(void);
 int kvm_has_robust_singlestep(void);
 int kvm_has_debugregs(void);
+int kvm_has_xsave(void);
+int kvm_has_xcrs(void);
 
 #ifdef NEED_CPU_H
 int kvm_init_vcpu(CPUState *env);

target-i386/cpu.h +6 -1

index 548ab80..680eed1 100644
@@ -718,6 +718,11 @@ typedef struct CPUX86State {
     uint16_t fpus_vmstate;
     uint16_t fptag_vmstate;
     uint16_t fpregs_format_vmstate;
+
+    uint64_t xstate_bv;
+    XMMReg ymmh_regs[CPU_NB_REGS];
+
+    uint64_t xcr0;
 } CPUX86State;
 
 CPUX86State *cpu_x86_init(const char *cpu_model);

@@ -895,7 +900,7 @@ uint64_t cpu_get_tsc(CPUX86State *env);
 #define cpu_list_id x86_cpu_list
 #define cpudef_setup	x86_cpudef_setup
 
-#define CPU_SAVE_VERSION 11
+#define CPU_SAVE_VERSION 12
 
 /* MMU modes definitions */
 #define MMU_MODE0_SUFFIX _kernel

target-i386/kvm.c +137 -2

index bb6a12f..db1f21d 100644
@@ -289,6 +289,8 @@ void kvm_arch_reset_vcpu(CPUState *env)
     } else {
         env->mp_state = KVM_MP_STATE_RUNNABLE;
     }
+    /* Legal xcr0 for loading */
+    env->xcr0 = 1;
 }
 
 static int kvm_has_msr_star(CPUState *env)

@@ -504,6 +506,68 @@ static int kvm_put_fpu(CPUState *env)
     return kvm_vcpu_ioctl(env, KVM_SET_FPU, &fpu);
 }
 
+#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
+
+static int kvm_put_xsave(CPUState *env)
+{
+#ifdef KVM_CAP_XSAVE
+    int i;
+    struct kvm_xsave* xsave;
+    uint16_t cwd, swd, twd, fop;
+
+    if (!kvm_has_xsave())
+        return kvm_put_fpu(env);
+
+    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);
+    return kvm_vcpu_ioctl(env, KVM_SET_XSAVE, xsave);
+#else
+    return kvm_put_fpu(env);
+#endif
+}
+
+static int kvm_put_xcrs(CPUState *env)
+{
+#ifdef KVM_CAP_XCRS
+    struct kvm_xcrs xcrs;
+
+    if (!kvm_has_xcrs())
+        return 0;
+
+    xcrs.nr_xcrs = 1;
+    xcrs.flags = 0;
+    xcrs.xcrs[0].xcr = 0;
+    xcrs.xcrs[0].value = env->xcr0;
+    return kvm_vcpu_ioctl(env, KVM_SET_XCRS, &xcrs);
+#else
+    return 0;
+#endif
+}
+
 static int kvm_put_sregs(CPUState *env)
 {
     struct kvm_sregs sregs;

@@ -621,6 +685,69 @@ static int kvm_get_fpu(CPUState *env)
     return 0;
 }
 
+static int kvm_get_xsave(CPUState *env)
+{
+#ifdef KVM_CAP_XSAVE
+    struct kvm_xsave* xsave;
+    int ret, i;
+    uint16_t cwd, swd, twd, fop;
+
+    if (!kvm_has_xsave())
+        return kvm_get_fpu(env);
+
+    xsave = qemu_memalign(4096, sizeof(struct kvm_xsave));
+    ret = kvm_vcpu_ioctl(env, KVM_GET_XSAVE, xsave);
+    if (ret < 0)
+        return ret;
+
+    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);
+    return 0;
+#else
+    return kvm_get_fpu(env);
+#endif
+}
+
+static int kvm_get_xcrs(CPUState *env)
+{
+#ifdef KVM_CAP_XCRS
+    int i, ret;
+    struct kvm_xcrs xcrs;
+
+    if (!kvm_has_xcrs())
+        return 0;
+
+    ret = kvm_vcpu_ioctl(env, KVM_GET_XCRS, &xcrs);
+    if (ret < 0)
+        return ret;
+
+    for (i = 0; i < xcrs.nr_xcrs; i++)
+        /* Only support xcr0 now */
+        if (xcrs.xcrs[0].xcr == 0) {
+            env->xcr0 = xcrs.xcrs[0].value;
+            break;
+        }
+    return 0;
+#else
+    return 0;
+#endif
+}
+
 static int kvm_get_sregs(CPUState *env)
 {
     struct kvm_sregs sregs;

@@ -965,7 +1092,11 @@ int kvm_arch_put_registers(CPUState *env, int level)
     if (ret < 0)
         return ret;
 
-    ret = kvm_put_fpu(env);
+    ret = kvm_put_xsave(env);
+    if (ret < 0)
+        return ret;
+
+    ret = kvm_put_xcrs(env);
     if (ret < 0)
         return ret;
 

@@ -1009,7 +1140,11 @@ int kvm_arch_get_registers(CPUState *env)
     if (ret < 0)
         return ret;
 
-    ret = kvm_get_fpu(env);
+    ret = kvm_get_xsave(env);
+    if (ret < 0)
+        return ret;
+
+    ret = kvm_get_xcrs(env);
     if (ret < 0)
         return ret;
 

target-i386/machine.c +16 -0

index b547e2a..5f8376c 100644
@@ -47,6 +47,22 @@ static const VMStateDescription vmstate_xmm_reg = {
 #define VMSTATE_XMM_REGS(_field, _state, _n)                         \
     VMSTATE_STRUCT_ARRAY(_field, _state, _n, 0, vmstate_xmm_reg, XMMReg)
 
+/* YMMH format is the same as XMM */
+static const VMStateDescription vmstate_ymmh_reg = {
+    .name = "ymmh_reg",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .minimum_version_id_old = 1,
+    .fields      = (VMStateField []) {
+        VMSTATE_UINT64(XMM_Q(0), XMMReg),
+        VMSTATE_UINT64(XMM_Q(1), XMMReg),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
+#define VMSTATE_YMMH_REGS_VARS(_field, _state, _n, _v)                         \
+    VMSTATE_STRUCT_ARRAY(_field, _state, _n, _v, vmstate_ymmh_reg, XMMReg)
+
 static const VMStateDescription vmstate_mtrr_var = {
     .name = "mtrr_var",
     .version_id = 1,

Based on upstream xsave related fields.

Signed-off-by Sheng Yang <[email protected]>

---
 qemu-kvm-x86.c |   95 +++++++++++++++++++++++++++++++++++++++++++++++++++++++-
 qemu-kvm.c     |   24 ++++++++++++++
 qemu-kvm.h     |   28 ++++++++++++++++
 3 files changed, 146 insertions(+), 1 deletions(-)

qemu-kvm-x86.c +40 -0

index 3c33e64..dcef8b5 100644
@@ -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

qemu-kvm-x86.c +44 -1

     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);
 

qemu-kvm.c +24 -0

index 96d458c..be1dac2 100644
@@ -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;

qemu-kvm.h +28 -0

index 6f6c6d8..3ace503 100644
@@ -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
  *

Quoted 84 lines · Sheng Yang

Based on upstream xsave related fields.

Signed-off-by Sheng Yang <[email protected]>

---

 qemu-kvm-x86.c |   95
 +++++++++++++++++++++++++++++++++++++++++++++++++++++++- qemu-kvm.c    
 |   24 ++++++++++++++
 qemu-kvm.h     |   28 ++++++++++++++++
 3 files changed, 146 insertions(+), 1 deletions(-)

qemu-kvm-x86.c +46 -0

index 3c33e64..dcef8b5 100644
@@ -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);

qemu-kvm-x86.c void kvm_arch_load_regs(CPUState *env, int level) · line 858

Quoted 4 lines

qemu-kvm-x86.c +4 -0

+        }
+#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

Quoted 175 lines

qemu-kvm-x86.c +4 -1

     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) {

qemu-kvm-x86.c +6 -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;

qemu-kvm-x86.c +31 -0

@@ -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;

qemu-kvm-x86.c +3 -0

@@ -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);

qemu-kvm.c +24 -0

index 96d458c..be1dac2 100644
@@ -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;

qemu-kvm.h +28 -0

index 6f6c6d8..3ace503 100644
@@ -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 *

Quoted 84 lines · On Thursday 17 June 2010 15:41:43 Jan Kiszka wrote:

Quoted 83 lines · Sheng Yang

Based on upstream xsave related fields.

Signed-off-by Sheng Yang <[email protected]>

---

 qemu-kvm-x86.c |   95
 +++++++++++++++++++++++++++++++++++++++++++++++++++++++- qemu-kvm.c    
 |   24 ++++++++++++++
 qemu-kvm.h     |   28 ++++++++++++++++
 3 files changed, 146 insertions(+), 1 deletions(-)

qemu-kvm-x86.c +45 -0

index 3c33e64..dcef8b5 100644
@@ -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;

Quoted 8 lines

qemu-kvm-x86.c void kvm_arch_load_regs(CPUState *env, int level) · line 858

Quoted 5 lines

qemu-kvm-x86.c +5 -0

+            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.

Signed-off-by Sheng Yang <[email protected]>

---

Would send out XSAVE patch after the upstream ones have been merged, since the patch would be affected by the merge.

 qemu-kvm-x86.c    |   23 ++---------------------
 qemu-kvm.c        |   10 ----------
 qemu-kvm.h        |   30 ------------------------------
 target-i386/kvm.c |    5 ++++-
 4 files changed, 6 insertions(+), 62 deletions(-)

qemu-kvm-x86.c +2 -21

index 3c33e64..49218ae 100644
@@ -775,7 +775,6 @@ static void get_seg(SegmentCache *lhs, const struct kvm_segment *rhs)
 void kvm_arch_load_regs(CPUState *env, int level)
 {
     struct kvm_regs regs;
-    struct kvm_fpu fpu;
     struct kvm_sregs sregs;
     struct kvm_msr_entry msrs[100];
     int rc, n, i;

@@ -806,16 +805,7 @@ void kvm_arch_load_regs(CPUState *env, int level)
 
     kvm_set_regs(env, &regs);
 
-    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;
-    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);
+    kvm_put_fpu(env);
 
     memset(sregs.interrupt_bitmap, 0, sizeof(sregs.interrupt_bitmap));
     if (env->interrupt_injected >= 0) {

@@ -933,7 +923,6 @@ void kvm_arch_load_regs(CPUState *env, int level)
 void kvm_arch_save_regs(CPUState *env)
 {
     struct kvm_regs regs;
-    struct kvm_fpu fpu;
     struct kvm_sregs sregs;
     struct kvm_msr_entry msrs[100];
     uint32_t hflags;

@@ -965,15 +954,7 @@ void kvm_arch_save_regs(CPUState *env)
     env->eflags = regs.rflags;
     env->eip = regs.rip;
 
-    kvm_get_fpu(env, &fpu);
-    env->fpstt = (fpu.fsw >> 11) & 7;
-    env->fpus = fpu.fsw;
-    env->fpuc = fpu.fcw;
-    for (i = 0; i < 8; ++i)
-	env->fptags[i] = !((fpu.ftwx >> i) & 1);
-    memcpy(env->fpregs, fpu.fpr, sizeof env->fpregs);
-    memcpy(env->xmm_regs, fpu.xmm, sizeof env->xmm_regs);
-    env->mxcsr = fpu.mxcsr;
+    kvm_get_fpu(env);
 
     kvm_get_sregs(env, &sregs);
 

qemu-kvm.c +0 -10

index 96d458c..114cb5e 100644
@@ -461,16 +461,6 @@ int kvm_set_regs(CPUState *env, struct kvm_regs *regs)
     return kvm_vcpu_ioctl(env, KVM_SET_REGS, regs);
 }
 
-int kvm_get_fpu(CPUState *env, struct kvm_fpu *fpu)
-{
-    return kvm_vcpu_ioctl(env, KVM_GET_FPU, fpu);
-}
-
-int kvm_set_fpu(CPUState *env, struct kvm_fpu *fpu)
-{
-    return kvm_vcpu_ioctl(env, KVM_SET_FPU, fpu);
-}
-
 int kvm_get_sregs(CPUState *env, struct kvm_sregs *sregs)
 {
     return kvm_vcpu_ioctl(env, KVM_GET_SREGS, sregs);

qemu-kvm.h +0 -30

index 6f6c6d8..ebe7893 100644
@@ -222,36 +222,6 @@ int kvm_get_regs(CPUState *env, struct kvm_regs *regs);
  * \return 0 on success
  */
 int kvm_set_regs(CPUState *env, struct kvm_regs *regs);
-/*!
- * \brief Read VCPU fpu registers
- *
- * This gets the FPU registers from the VCPU and outputs them
- * into a kvm_fpu structure
- *
- * \note This function returns a \b copy of the VCPUs registers.\n
- * If you wish to modify the VCPU FPU registers, you should call kvm_set_fpu()
- *
- * \param kvm Pointer to the current kvm_context
- * \param vcpu Which virtual CPU should get dumped
- * \param fpu Pointer to a kvm_fpu which will be populated with the VCPUs
- * fpu registers values
- * \return 0 on success
- */
-int kvm_get_fpu(CPUState *env, struct kvm_fpu *fpu);
-
-/*!
- * \brief Write VCPU fpu registers
- *
- * This sets the FPU registers on the VCPU from a kvm_fpu structure
- *
- * \note When this function returns, the fpu pointer and the data it points to
- * can be discarded
- * \param kvm Pointer to the current kvm_context
- * \param vcpu Which virtual CPU should get dumped
- * \param fpu Pointer to a kvm_fpu which holds the new vcpu fpu state
- * \return 0 on success
- */
-int kvm_set_fpu(CPUState *env, struct kvm_fpu *fpu);
 
 /*!
  * \brief Read VCPU system registers

target-i386/kvm.c +3 -1

index 9cb9cf4..9c13f62 100644
@@ -488,6 +488,7 @@ static int kvm_getput_regs(CPUState *env, int set)
 
     return ret;
 }
+#endif /* KVM_UPSTREAM */
 
 static int kvm_put_fpu(CPUState *env)
 {

@@ -507,6 +508,7 @@ static int kvm_put_fpu(CPUState *env)
     return kvm_vcpu_ioctl(env, KVM_SET_FPU, &fpu);
 }
 
+#ifdef KVM_UPSTREAM
 static int kvm_put_sregs(CPUState *env)
 {
     struct kvm_sregs sregs;

@@ -605,7 +607,7 @@ static int kvm_put_msrs(CPUState *env, int level)
     return kvm_vcpu_ioctl(env, KVM_SET_MSRS, &msr_data);
 
 }
-
+#endif /* KVM_UPSTREAM */
 
 static int kvm_get_fpu(CPUState *env)
 {

Notice the first three patches applied to uq/master branch of qemu-kvm, the last one applied to qemu-kvm master branch. And the last one would only apply after the first three merged in master branch.