Thread: [kvm-devel] [PATCH] qemu-kvm: fix guest resetting

SourceForge Headquarters 225 Broadway Suite 1600 San Diego, CA 92101 +1 (858) 422-6466

Resetting guests used to be racy, deadlock-prone, or simply broken (for
SMP). This patch fixes the issues - at least for me on x86 (tested on
Intel SMP host, UP and SMP guest, in-kernel und user space irqchip,
guest- and monitor-issued resets). Note that ia64 and powerpc may need
to look into the SMP thing as well (=>kvm_arch_cpu_reset).

At this chance, the patch also cleans up some unneeded reset fragments.

Signed-off-by: Jan Kiszka <jan...@si...>
---
 qemu/qemu-kvm-ia64.c    |    4 ++++
 qemu/qemu-kvm-powerpc.c |    4 ++++
 qemu/qemu-kvm-x86.c     |   16 ++++++++++++++++
 qemu/qemu-kvm.c         |   38 ++++++++++++++++++--------------------
 qemu/qemu-kvm.h         |    1 +
 qemu/vl.c               |   11 ++++++-----
 6 files changed, 49 insertions(+), 25 deletions(-)

Index: b/qemu/qemu-kvm.c
===================================================================

--- a/qemu/qemu-kvm.c
+++ b/qemu/qemu-kvm.c
@@ -28,8 +28,6 @@ kvm_context_t kvm_context;
 
 extern int smp_cpus;
 
-static int qemu_kvm_reset_requested;
-
 pthread_mutex_t qemu_mutex = PTHREAD_MUTEX_INITIALIZER;
 pthread_cond_t qemu_aio_cond = PTHREAD_COND_INITIALIZER;
 pthread_cond_t qemu_vcpu_cond = PTHREAD_COND_INITIALIZER;
@@ -56,7 +54,6 @@ struct vcpu_info {
     int signalled;
     int stop;
     int stopped;
-    int reload_regs;
     int created;
 } vcpu_info[256];
 
@@ -257,17 +254,20 @@ static int all_threads_paused(void)
 
 static void pause_all_threads(void)
 {
+    CPUState *cpu_single = cpu_single_env;
     int i;
 
-    for (i = 0; i < smp_cpus; ++i) {
-	vcpu_info[i].stop = 1;
-	pthread_kill(vcpu_info[i].thread, SIG_IPI);
-    }
+    for (i = 0; i < smp_cpus; ++i)
+	if (!cpu_single || cpu_single->cpu_index != i) {
+	    vcpu_info[i].stop = 1;
+	    pthread_kill(vcpu_info[i].thread, SIG_IPI);
+	}
+
     while (!all_threads_paused()) {
 	pthread_mutex_unlock(&qemu_mutex);
-	kvm_eat_signal(&io_signal_table, NULL, 1000);
+	kvm_eat_signal(&io_signal_table, cpu_single, 1000);
 	pthread_mutex_lock(&qemu_mutex);
-	cpu_single_env = NULL;
+	cpu_single_env = cpu_single;
     }
 }
 
@@ -317,11 +317,18 @@ void qemu_kvm_system_reset_request(void)
 {
     int i;
 
+    pause_all_threads();
+
+    qemu_system_reset();
+
+    for (i = 0; i < smp_cpus; ++i)
+	kvm_arch_cpu_reset(vcpu_info[i].env);
+
     for (i = 0; i < smp_cpus; ++i) {
-	vcpu_info[i].reload_regs = 1;
+	vcpu_info[i].stop = 0;
+	vcpu_info[i].stopped = 0;
 	pthread_kill(vcpu_info[i].thread, SIG_IPI);
     }
-    qemu_system_reset();
 }
 
 static int kvm_main_loop_cpu(CPUState *env)
@@ -354,11 +361,6 @@ static int kvm_main_loop_cpu(CPUState *e
 	    kvm_cpu_exec(env);
 	env->interrupt_request &= ~CPU_INTERRUPT_EXIT;
 	kvm_main_loop_wait(env, 0);
-        if (info->reload_regs) {
-	    info->reload_regs = 0;
-	    if (env->cpu_index == 0) /* ap needs to be placed in INIT */
-		kvm_arch_load_regs(env);
-	}
     }
     pthread_mutex_unlock(&qemu_mutex);
     return 0;
@@ -467,10 +469,6 @@ int kvm_main_loop(void)
             break;
         else if (qemu_powerdown_requested())
             qemu_system_powerdown();
-        else if (qemu_reset_requested()) {
-            pthread_kill(vcpu_info[0].thread, SIG_IPI);
-            qemu_kvm_reset_requested = 1;
-        }
         pthread_mutex_unlock(&qemu_mutex);
     }
 
Index: b/qemu/qemu-kvm-ia64.c
===================================================================
--- a/qemu/qemu-kvm-ia64.c
+++ b/qemu/qemu-kvm-ia64.c
@@ -61,3 +61,7 @@ int kvm_arch_try_push_interrupts(void *o
 void kvm_arch_update_regs_for_sipi(CPUState *env)
 {
 }
+
+void kvm_arch_cpu_reset(CPUState *env)
+{
+}
Index: b/qemu/qemu-kvm-powerpc.c
===================================================================
--- a/qemu/qemu-kvm-powerpc.c
+++ b/qemu/qemu-kvm-powerpc.c
@@ -213,3 +213,7 @@ int handle_powerpc_dcr_write(int vcpu, u
 
     return 0; /* XXX ignore failed DCR ops */
 }
+
+void kvm_arch_cpu_reset(CPUState *env)
+{
+}
Index: b/qemu/qemu-kvm-x86.c
===================================================================
--- a/qemu/qemu-kvm-x86.c
+++ b/qemu/qemu-kvm-x86.c
@@ -689,3 +689,19 @@ int handle_tpr_access(void *opaque, int 
     kvm_tpr_access_report(cpu_single_env, rip, is_write);
     return 0;
 }
+
+void kvm_arch_cpu_reset(CPUState *env)
+{
+    struct kvm_mp_state mp_state = { .mp_state = KVM_MP_STATE_UNINITIALIZED };
+
+    kvm_arch_load_regs(env);
+    if (env->cpu_index != 0) {
+	if (kvm_irqchip_in_kernel(kvm_context))
+	    kvm_set_mpstate(kvm_context, env->cpu_index, &mp_state);
+	else {
+	    env->interrupt_request &= ~CPU_INTERRUPT_HARD;
+	    env->hflags |= HF_HALTED_MASK;
+	    env->exception_index = EXCP_HLT;
+	}
+    }
+}
Index: b/qemu/qemu-kvm.h
===================================================================
--- a/qemu/qemu-kvm.h
+++ b/qemu/qemu-kvm.h
@@ -55,6 +55,7 @@ void kvm_arch_post_kvm_run(void *opaque,
 int kvm_arch_has_work(CPUState *env);
 int kvm_arch_try_push_interrupts(void *opaque);
 void kvm_arch_update_regs_for_sipi(CPUState *env);
+void kvm_arch_cpu_reset(CPUState *env);
 
 CPUState *qemu_kvm_cpu_env(int index);
 
Index: b/qemu/vl.c
===================================================================
--- a/qemu/vl.c
+++ b/qemu/vl.c
@@ -7235,6 +7235,12 @@ void qemu_system_reset(void)
 
 void qemu_system_reset_request(void)
 {
+#ifdef USE_KVM
+    if (kvm_allowed && !no_reboot) {
+        qemu_kvm_system_reset_request();
+        return;
+    }
+#endif
     if (no_reboot) {
         shutdown_requested = 1;
     } else {
@@ -7242,11 +7248,6 @@ void qemu_system_reset_request(void)
     }
     if (cpu_single_env)
         cpu_interrupt(cpu_single_env, CPU_INTERRUPT_EXIT);
-#ifdef USE_KVM
-    if (kvm_allowed)
-        if (!no_reboot)
-            qemu_kvm_system_reset_request();
-#endif
 }
 
 void qemu_system_shutdown_request(void)


