[PATCH v3] qemu: kvm: Enable XSAVE live migration support

[Sheng Yang <sheng@linux.intel.com>]

Signed-off-by: Sheng Yang <sheng@linux.intel.com>
---
 qemu-kvm-x86.c        |  109 ++++++++++++++++++++++++++++++++++++++++---------
 qemu-kvm.c            |   24 +++++++++++
 qemu-kvm.h            |   28 +++++++++++++
 target-i386/cpu.h     |    5 ++
 target-i386/kvm.c     |    2 +
 target-i386/machine.c |   20 +++++++++
 6 files changed, 169 insertions(+), 19 deletions(-)

diff --git a/qemu-kvm-x86.c b/qemu-kvm-x86.c
index 3c33e64..4f0b1d0 100644
--- a/qemu-kvm-x86.c
+++ b/qemu-kvm-x86.c
@@ -772,10 +772,20 @@ static void get_seg(SegmentCache *lhs, const struct kvm_segment *rhs)
 	| (rhs->avl * DESC_AVL_MASK);
 }
 
+#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
+
 void kvm_arch_load_regs(CPUState *env, int level)
 {
     struct kvm_regs regs;
     struct kvm_fpu fpu;
+    struct kvm_xsave* xsave;
+    struct kvm_xcrs xcrs;
     struct kvm_sregs sregs;
     struct kvm_msr_entry msrs[100];
     int rc, n, i;
@@ -806,16 +816,47 @@ 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);
+    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);
+        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);
+        }
+    } else {
+        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);
+    }
 
     memset(sregs.interrupt_bitmap, 0, sizeof(sregs.interrupt_bitmap));
     if (env->interrupt_injected >= 0) {
@@ -934,6 +975,8 @@ void kvm_arch_save_regs(CPUState *env)
 {
     struct kvm_regs regs;
     struct kvm_fpu fpu;
+    struct kvm_xsave* xsave;
+    struct kvm_xcrs xcrs;
     struct kvm_sregs sregs;
     struct kvm_msr_entry msrs[100];
     uint32_t hflags;
@@ -965,15 +1008,43 @@ 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;
+    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);
+        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;
+        }
+    } else {
+        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_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
  *
diff --git a/target-i386/cpu.h b/target-i386/cpu.h
index e989040..c32f854 100644
--- a/target-i386/cpu.h
+++ b/target-i386/cpu.h
@@ -736,6 +736,11 @@ typedef struct CPUX86State {
     uint16_t fpregs_format_vmstate;
 
     int kvm_vcpu_update_vapic;
+
+    uint64_t xstate_bv;
+    XMMReg ymmh_regs[CPU_NB_REGS];
+
+    uint64_t xcr0;
 } CPUX86State;
 
 CPUX86State *cpu_x86_init(const char *cpu_model);
diff --git a/target-i386/kvm.c b/target-i386/kvm.c
index f0f3252..57327f5 100644
--- a/target-i386/kvm.c
+++ b/target-i386/kvm.c
@@ -294,6 +294,8 @@ void kvm_arch_reset_vcpu(CPUState *env)
     env->interrupt_injected = -1;
     env->nmi_injected = 0;
     env->nmi_pending = 0;
+    /* Legal xcr0 for loading */
+    env->xcr0 = 1;
 }
 #ifdef KVM_UPSTREAM
 
diff --git a/target-i386/machine.c b/target-i386/machine.c
index b547e2a..6c89a08 100644
--- a/target-i386/machine.c
+++ b/target-i386/machine.c
@@ -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,
@@ -453,6 +469,10 @@ static const VMStateDescription vmstate_cpu = {
         /* KVM pvclock msr */
         VMSTATE_UINT64_V(system_time_msr, CPUState, 11),
         VMSTATE_UINT64_V(wall_clock_msr, CPUState, 11),
+
+        VMSTATE_UINT64_V(xcr0, CPUState, 12),
+        VMSTATE_UINT64_V(xstate_bv, CPUState, 12),
+        VMSTATE_YMMH_REGS_VARS(ymmh_regs, CPUState, CPU_NB_REGS, 12),
         VMSTATE_END_OF_LIST()
         /* The above list is not sorted /wrt version numbers, watch out! */
     }
-- 
1.7.0.1