[Qemu-devel] [PATCH] 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        |   77 +++++++++++++++++++++++++++++++++++++------------
 qemu-kvm.c            |   12 +++++++
 qemu-kvm.h            |   14 +++++++++
 target-i386/cpu.h     |    5 +++
 target-i386/machine.c |   20 +++++++++++++
 5 files changed, 109 insertions(+), 19 deletions(-)

diff --git a/qemu-kvm-x86.c b/qemu-kvm-x86.c
index 73b4af7..a2e2896 100644
--- a/qemu-kvm-x86.c
+++ b/qemu-kvm-x86.c
@@ -776,6 +776,7 @@ void kvm_arch_load_regs(CPUState *env, int level)
 {
     struct kvm_regs regs;
     struct kvm_fpu fpu;
+    struct kvm_xsave xsave;
     struct kvm_sregs sregs;
     struct kvm_msr_entry msrs[100];
     int rc, n, i;
@@ -806,16 +807,35 @@ 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)) {
+        memset(&xsave, 0, sizeof xsave);
+        xsave.i387.swd = env->fpus & ~(7 << 11);
+        xsave.i387.swd |= (env->fpstt & 7) << 11;
+        xsave.i387.cwd = env->fpuc;
+        for (i = 0; i < 8; ++i)
+            xsave.i387.twd |= (!env->fptags[i]) << i;
+        memcpy(xsave.i387.st_space, env->fpregs,
+                sizeof env->fpregs);
+        memcpy(xsave.i387.xmm_space, env->xmm_regs,
+                sizeof env->xmm_regs);
+        xsave.i387.mxcsr = env->mxcsr;
+        xsave.xsave_hdr.xstate_bv = env->xstate_bv;
+        memcpy(xsave.ymmh.ymmh_space, env->ymmh_regs,
+                sizeof env->ymmh_regs);
+        xsave.xcr0 = env->xcr0;
+        kvm_set_xsave(env, &xsave);
+    } 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) {
@@ -938,6 +958,7 @@ void kvm_arch_save_regs(CPUState *env)
 {
     struct kvm_regs regs;
     struct kvm_fpu fpu;
+    struct kvm_xsave xsave;
     struct kvm_sregs sregs;
     struct kvm_msr_entry msrs[100];
     uint32_t hflags;
@@ -969,15 +990,33 @@ 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)) {
+        kvm_get_xsave(env, &xsave);
+        env->fpstt = (xsave.i387.swd >> 11) & 7;
+        env->fpus = xsave.i387.swd;
+        env->fpuc = xsave.i387.cwd;
+        for (i = 0; i < 8; ++i)
+            env->fptags[i] = !((xsave.i387.twd >> i) & 1);
+        memcpy(env->fpregs, xsave.i387.st_space,
+                sizeof env->fpregs);
+        memcpy(env->xmm_regs, xsave.i387.xmm_space,
+                sizeof env->xmm_regs);
+        env->mxcsr = xsave.i387.mxcsr;
+        env->xstate_bv = xsave.xsave_hdr.xstate_bv;
+        memcpy(env->ymmh_regs, xsave.ymmh.ymmh_space,
+                sizeof env->ymmh_regs);
+        env->xcr0 = xsave.xcr0;
+    } 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 35a4c8a..c472b96 100644
--- a/qemu-kvm.c
+++ b/qemu-kvm.c
@@ -485,6 +485,18 @@ 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
+
 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..0fb4638 100644
--- a/qemu-kvm.h
+++ b/qemu-kvm.h
@@ -300,6 +300,20 @@ 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
+
 /*!
  * \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/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