diff --git a/exec.c b/exec.c
index f41518e8a35b0ccf220bd534754d80186c70b434..891e0eee03b44fa737c2c007546784c0df441e82 100644
--- a/exec.c
+++ b/exec.c
@@ -512,21 +512,6 @@ void cpu_exec_init_all(unsigned long tb_size)
 
 #if defined(CPU_SAVE_VERSION) && !defined(CONFIG_USER_ONLY)
 
-static void cpu_common_pre_save(void *opaque)
-{
-    CPUState *env = opaque;
-
-    cpu_synchronize_state(env);
-}
-
-static int cpu_common_pre_load(void *opaque)
-{
-    CPUState *env = opaque;
-
-    cpu_synchronize_state(env);
-    return 0;
-}
-
 static int cpu_common_post_load(void *opaque, int version_id)
 {
     CPUState *env = opaque;
@@ -544,8 +529,6 @@ static const VMStateDescription vmstate_cpu_common = {
     .version_id = 1,
     .minimum_version_id = 1,
     .minimum_version_id_old = 1,
-    .pre_save = cpu_common_pre_save,
-    .pre_load = cpu_common_pre_load,
     .post_load = cpu_common_post_load,
     .fields      = (VMStateField []) {
         VMSTATE_UINT32(halted, CPUState),
diff --git a/hw/apic.c b/hw/apic.c
index 87e7dc0ba9e4a5d1ee11faa462ffebafd7f2bfe9..3c90f4c84536593d2e73411243d779bc836cd388 100644
--- a/hw/apic.c
+++ b/hw/apic.c
@@ -938,8 +938,6 @@ static void apic_reset(void *opaque)
     APICState *s = opaque;
     int bsp;
 
-    cpu_synchronize_state(s->cpu_env);
-
     bsp = cpu_is_bsp(s->cpu_env);
     s->apicbase = 0xfee00000 |
         (bsp ? MSR_IA32_APICBASE_BSP : 0) | MSR_IA32_APICBASE_ENABLE;
diff --git a/hw/ppc_newworld.c b/hw/ppc_newworld.c
index bc86c851e72b01de4cc0080508007f78894fdaa7..d4f9013fe521e73fe39c5cead400117e9f64f997 100644
--- a/hw/ppc_newworld.c
+++ b/hw/ppc_newworld.c
@@ -167,9 +167,6 @@ static void ppc_core99_init (ram_addr_t ram_size,
         envs[i] = env;
     }
 
-    /* Make sure all register sets take effect */
-    cpu_synchronize_state(env);
-
     /* allocate RAM */
     ram_offset = qemu_ram_alloc(ram_size);
     cpu_register_physical_memory(0, ram_size, ram_offset);
diff --git a/hw/ppc_oldworld.c b/hw/ppc_oldworld.c
index 04a78358dddaf9cc5dfe258deea3f118ad4cd280..93c95ba6593d01998551625e1b01dc7ca6afd07c 100644
--- a/hw/ppc_oldworld.c
+++ b/hw/ppc_oldworld.c
@@ -165,9 +165,6 @@ static void ppc_heathrow_init (ram_addr_t ram_size,
         envs[i] = env;
     }
 
-    /* Make sure all register sets take effect */
-    cpu_synchronize_state(env);
-
     /* allocate RAM */
     if (ram_size > (2047 << 20)) {
         fprintf(stderr,
diff --git a/hw/s390-virtio.c b/hw/s390-virtio.c
index 358272837847834965059bf82b67a8bc28cb1994..ad3386f6076f6308bb6b6e03df080faf172879a3 100644
--- a/hw/s390-virtio.c
+++ b/hw/s390-virtio.c
@@ -185,7 +185,6 @@ static void s390_init(ram_addr_t ram_size,
             exit(1);
         }
 
-        cpu_synchronize_state(env);
         env->psw.addr = KERN_IMAGE_START;
         env->psw.mask = 0x0000000180000000ULL;
     }
diff --git a/kvm-all.c b/kvm-all.c
index 2f7e33a6cd07cc73caca6b17df5f78c3d02406a4..534ead060d81b593a7a3725e183c71bd9d7adde0 100644
--- a/kvm-all.c
+++ b/kvm-all.c
@@ -156,10 +156,6 @@ static void kvm_reset_vcpu(void *opaque)
     CPUState *env = opaque;
 
     kvm_arch_reset_vcpu(env);
-    if (kvm_arch_put_registers(env)) {
-        fprintf(stderr, "Fatal: kvm vcpu reset failed\n");
-        abort();
-    }
 }
 
 int kvm_irqchip_in_kernel(void)
@@ -214,7 +210,6 @@ int kvm_init_vcpu(CPUState *env)
     if (ret == 0) {
         qemu_register_reset(kvm_reset_vcpu, env);
         kvm_arch_reset_vcpu(env);
-        ret = kvm_arch_put_registers(env);
     }
 err:
     return ret;
@@ -753,6 +748,18 @@ void kvm_cpu_synchronize_state(CPUState *env)
     }
 }
 
+void kvm_cpu_synchronize_post_reset(CPUState *env)
+{
+    kvm_arch_put_registers(env, KVM_PUT_RESET_STATE);
+    env->kvm_vcpu_dirty = 0;
+}
+
+void kvm_cpu_synchronize_post_init(CPUState *env)
+{
+    kvm_arch_put_registers(env, KVM_PUT_FULL_STATE);
+    env->kvm_vcpu_dirty = 0;
+}
+
 int kvm_cpu_exec(CPUState *env)
 {
     struct kvm_run *run = env->kvm_run;
@@ -770,7 +777,7 @@ int kvm_cpu_exec(CPUState *env)
 #endif
 
         if (env->kvm_vcpu_dirty) {
-            kvm_arch_put_registers(env);
+            kvm_arch_put_registers(env, KVM_PUT_RUNTIME_STATE);
             env->kvm_vcpu_dirty = 0;
         }
 
diff --git a/kvm.h b/kvm.h
index a602e4552ab0af94ee2c5c3c2423401c25f952b6..b2937b9956f5f57badb1735f3e1d3b7a1dc5552f 100644
--- a/kvm.h
+++ b/kvm.h
@@ -82,7 +82,14 @@ int kvm_arch_pre_run(CPUState *env, struct kvm_run *run);
 
 int kvm_arch_get_registers(CPUState *env);
 
-int kvm_arch_put_registers(CPUState *env);
+/* state subset only touched by the VCPU itself during runtime */
+#define KVM_PUT_RUNTIME_STATE   1
+/* state subset modified during VCPU reset */
+#define KVM_PUT_RESET_STATE     2
+/* full state set, modified during initialization or on vmload */
+#define KVM_PUT_FULL_STATE      3
+
+int kvm_arch_put_registers(CPUState *env, int level);
 
 int kvm_arch_init(KVMState *s, int smp_cpus);
 
@@ -126,6 +133,8 @@ int kvm_check_extension(KVMState *s, unsigned int extension);
 uint32_t kvm_arch_get_supported_cpuid(CPUState *env, uint32_t function,
                                       int reg);
 void kvm_cpu_synchronize_state(CPUState *env);
+void kvm_cpu_synchronize_post_reset(CPUState *env);
+void kvm_cpu_synchronize_post_init(CPUState *env);
 
 /* generic hooks - to be moved/refactored once there are more users */
 
@@ -136,4 +145,18 @@ static inline void cpu_synchronize_state(CPUState *env)
     }
 }
 
+static inline void cpu_synchronize_post_reset(CPUState *env)
+{
+    if (kvm_enabled()) {
+        kvm_cpu_synchronize_post_reset(env);
+    }
+}
+
+static inline void cpu_synchronize_post_init(CPUState *env)
+{
+    if (kvm_enabled()) {
+        kvm_cpu_synchronize_post_init(env);
+    }
+}
+
 #endif
diff --git a/savevm.c b/savevm.c
index 4b5866396035fcc55eb94f47a704d335c0301779..a6e774b4d0f297505e3074216da04011db3a40e3 100644
--- a/savevm.c
+++ b/savevm.c
@@ -1345,6 +1345,8 @@ int qemu_savevm_state_complete(Monitor *mon, QEMUFile *f)
 {
     SaveStateEntry *se;
 
+    cpu_synchronize_all_states();
+
     QTAILQ_FOREACH(se, &savevm_handlers, entry) {
         if (se->save_live_state == NULL)
             continue;
@@ -1545,6 +1547,8 @@ int qemu_loadvm_state(QEMUFile *f)
         }
     }
 
+    cpu_synchronize_all_post_init();
+
     ret = 0;
 
 out:
diff --git a/sysemu.h b/sysemu.h
index 8ba618e54fc669a31fb2a24f789fad9828a2b6fc..d77344c1b9df5f3c1b2da5cd17dd8854be8114a0 100644
--- a/sysemu.h
+++ b/sysemu.h
@@ -58,6 +58,10 @@ int load_vmstate(Monitor *mon, const char *name);
 void do_delvm(Monitor *mon, const QDict *qdict);
 void do_info_snapshots(Monitor *mon);
 
+void cpu_synchronize_all_states(void);
+void cpu_synchronize_all_post_reset(void);
+void cpu_synchronize_all_post_init(void);
+
 void qemu_announce_self(void);
 
 void main_loop_wait(int timeout);
diff --git a/target-i386/kvm.c b/target-i386/kvm.c
index e0247ea631cfa57afa553a2c2766ab4fb7ab3c91..2c834dfdcc6147a868b9969f1143ecc6449c9785 100644
--- a/target-i386/kvm.c
+++ b/target-i386/kvm.c
@@ -883,7 +883,7 @@ static int kvm_guest_debug_workarounds(CPUState *env)
     return ret;
 }
 
-int kvm_arch_put_registers(CPUState *env)
+int kvm_arch_put_registers(CPUState *env, int level)
 {
     int ret;
 
diff --git a/target-i386/machine.c b/target-i386/machine.c
index 87704918beec94aaed2bace1cc57bc124fa4a3d0..b547e2ac7ac4fa97444634f317ec516caba3c1c2 100644
--- a/target-i386/machine.c
+++ b/target-i386/machine.c
@@ -321,8 +321,6 @@ static void cpu_pre_save(void *opaque)
     CPUState *env = opaque;
     int i;
 
-    cpu_synchronize_state(env);
-
     /* FPU */
     env->fpus_vmstate = (env->fpus & ~0x3800) | (env->fpstt & 0x7) << 11;
     env->fptag_vmstate = 0;
@@ -337,14 +335,6 @@ static void cpu_pre_save(void *opaque)
 #endif
 }
 
-static int cpu_pre_load(void *opaque)
-{
-    CPUState *env = opaque;
-
-    cpu_synchronize_state(env);
-    return 0;
-}
-
 static int cpu_post_load(void *opaque, int version_id)
 {
     CPUState *env = opaque;
@@ -373,7 +363,6 @@ static const VMStateDescription vmstate_cpu = {
     .minimum_version_id = 3,
     .minimum_version_id_old = 3,
     .pre_save = cpu_pre_save,
-    .pre_load = cpu_pre_load,
     .post_load = cpu_post_load,
     .fields      = (VMStateField []) {
         VMSTATE_UINTTL_ARRAY(regs, CPUState, CPU_NB_REGS),
diff --git a/target-ppc/kvm.c b/target-ppc/kvm.c
index 8ad003799c8c66d1af990b52812436783eef565a..aa3d43247bb80ebef19e8e6e5f8bcf9e60f27662 100644
--- a/target-ppc/kvm.c
+++ b/target-ppc/kvm.c
@@ -73,7 +73,7 @@ void kvm_arch_reset_vcpu(CPUState *env)
 {
 }
 
-int kvm_arch_put_registers(CPUState *env)
+int kvm_arch_put_registers(CPUState *env, int level)
 {
     struct kvm_regs regs;
     int ret;
diff --git a/target-ppc/machine.c b/target-ppc/machine.c
index 4897c8a4d304cbbabb3b33df6eb9a54eecb3448d..67de951959aa01d605d9a7b7e0b705deb1be348a 100644
--- a/target-ppc/machine.c
+++ b/target-ppc/machine.c
@@ -7,8 +7,6 @@ void cpu_save(QEMUFile *f, void *opaque)
     CPUState *env = (CPUState *)opaque;
     unsigned int i, j;
 
-    cpu_synchronize_state(env);
-
     for (i = 0; i < 32; i++)
         qemu_put_betls(f, &env->gpr[i]);
 #if !defined(TARGET_PPC64)
@@ -96,8 +94,6 @@ int cpu_load(QEMUFile *f, void *opaque, int version_id)
     CPUState *env = (CPUState *)opaque;
     unsigned int i, j;
 
-    cpu_synchronize_state(env);
-
     for (i = 0; i < 32; i++)
         qemu_get_betls(f, &env->gpr[i]);
 #if !defined(TARGET_PPC64)
diff --git a/target-s390x/kvm.c b/target-s390x/kvm.c
index 0199a650f611d74a57942c84f5da80cd8be1e550..72e77b0cdae628e8d094940705da6a83f542397d 100644
--- a/target-s390x/kvm.c
+++ b/target-s390x/kvm.c
@@ -91,7 +91,7 @@ void kvm_arch_reset_vcpu(CPUState *env)
     /* FIXME: add code to reset vcpu. */
 }
 
-int kvm_arch_put_registers(CPUState *env)
+int kvm_arch_put_registers(CPUState *env, int level)
 {
     struct kvm_regs regs;
     int ret;
@@ -296,7 +296,6 @@ static int handle_hypercall(CPUState *env, struct kvm_run *run)
 
     cpu_synchronize_state(env);
     r = s390_virtio_hypercall(env);
-    kvm_arch_put_registers(env);
 
     return r;
 }
diff --git a/vl.c b/vl.c
index 274d8472942a9737ddf51af7e485f39ae44e0c07..10d8e34e50300c5d16c5dd62c6a40833ab345b4d 100644
--- a/vl.c
+++ b/vl.c
@@ -3002,6 +3002,33 @@ static void nographic_update(void *opaque)
     qemu_mod_timer(nographic_timer, interval + qemu_get_clock(rt_clock));
 }
 
+void cpu_synchronize_all_states(void)
+{
+    CPUState *cpu;
+
+    for (cpu = first_cpu; cpu; cpu = cpu->next_cpu) {
+        cpu_synchronize_state(cpu);
+    }
+}
+
+void cpu_synchronize_all_post_reset(void)
+{
+    CPUState *cpu;
+
+    for (cpu = first_cpu; cpu; cpu = cpu->next_cpu) {
+        cpu_synchronize_post_reset(cpu);
+    }
+}
+
+void cpu_synchronize_all_post_init(void)
+{
+    CPUState *cpu;
+
+    for (cpu = first_cpu; cpu; cpu = cpu->next_cpu) {
+        cpu_synchronize_post_init(cpu);
+    }
+}
+
 struct vm_change_state_entry {
     VMChangeStateHandler *cb;
     void *opaque;
@@ -3143,6 +3170,7 @@ void qemu_system_reset(void)
     QTAILQ_FOREACH_SAFE(re, &reset_handlers, entry, nre) {
         re->func(re->opaque);
     }
+    cpu_synchronize_all_post_reset();
 }
 
 void qemu_system_reset_request(void)
@@ -5928,6 +5956,7 @@ int main(int argc, char **argv, char **envp)
     machine->init(ram_size, boot_devices,
                   kernel_filename, kernel_cmdline, initrd_filename, cpu_model);
 
+    cpu_synchronize_all_post_init();
 
 #ifndef _WIN32
     /* must be after terminal init, SDL library changes signal handlers */