kvm: Enable XSAVE live migration support

Signed-off-by: Sheng Yang <sheng@linux.intel.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

5 files changed, 186 insertions, 3 deletions

diff --git a/kvm-all.c b/kvm-all.c
index 5684e51..9380302 100644
--- a/kvm-all.c
+++ b/kvm-all.c
@@ -71,6 +71,7 @@ struct KVMState
 #endif
     int irqchip_in_kernel;
     int pit_in_kernel;
+    int xsave, xcrs;
 };
 
 static KVMState *kvm_state;
@@ -686,6 +687,16 @@ 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;
@@ -1014,6 +1025,16 @@ 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()) {
diff --git a/kvm.h b/kvm.h
index 500e7e4..93f8187 100644
--- a/kvm.h
+++ b/kvm.h
@@ -40,6 +40,8 @@ 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);
diff --git a/target-i386/cpu.h b/target-i386/cpu.h
index 8dafa0d..4de486e 100644
--- a/target-i386/cpu.h
+++ b/target-i386/cpu.h
@@ -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);
@@ -899,7 +904,7 @@ 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
diff --git a/target-i386/kvm.c b/target-i386/kvm.c
index 2b14ff5..436c0c4 100644
--- a/target-i386/kvm.c
+++ b/target-i386/kvm.c
@@ -497,6 +497,68 @@ 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;
@@ -614,6 +676,69 @@ 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;
@@ -958,7 +1083,11 @@ 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;
 
@@ -1002,7 +1131,11 @@ 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;
 
@@ -1290,6 +1423,8 @@ void kvm_arch_update_guest_debug(CPUState *env, struct kvm_guest_debug *dbg)
                 (len_code[hw_breakpoint[n].len] << (18 + n*4));
         }
     }
+    /* Legal xcr0 for loading */
+    env->xcr0 = 1;
 }
 #endif /* KVM_CAP_SET_GUEST_DEBUG */
 
diff --git a/target-i386/machine.c b/target-i386/machine.c
index b547e2a..5f8376c 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),
+        /* XSAVE related fields */
+        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! */
     }