rcu: Introduce force_rcu notifier

The drain_rcu_call() function can be blocked as long as an RCU reader
stays in a read-side critical section. This is typically what happens
when a TCG vCPU is executing a busy loop. It can deadlock the QEMU
monitor as reported in https://gitlab.com/qemu-project/qemu/-/issues/650 .

This can be avoided by allowing drain_rcu_call() to enforce an RCU grace
period. Since each reader might need to do specific actions to end a
read-side critical section, do it with notifiers.

Prepare ground for this by adding a notifier list to the RCU reader
struct and use it in wait_for_readers() if drain_rcu_call() is in
progress. An API is added for readers to register their notifiers.

This is largely based on a draft from Paolo Bonzini.

Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Greg Kurz <groug@kaod.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20211109183523.47726-2-groug@kaod.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

include/qemu/rcu.h

@@ -27,6 +27,7 @@
 #include "qemu/thread.h"
 #include "qemu/queue.h"
 #include "qemu/atomic.h"
+#include "qemu/notify.h"
 #include "qemu/sys_membarrier.h"
 
 #ifdef __cplusplus
@@ -66,6 +67,13 @@ struct rcu_reader_data {
 
     /* Data used for registry, protected by rcu_registry_lock */
     QLIST_ENTRY(rcu_reader_data) node;
+
+    /*
+     * NotifierList used to force an RCU grace period.  Accessed under
+     * rcu_registry_lock.  Note that the notifier is called _outside_
+     * the thread!
+     */
+    NotifierList force_rcu;
 };
 
 extern __thread struct rcu_reader_data rcu_reader;
@@ -180,6 +188,13 @@ G_DEFINE_AUTOPTR_CLEANUP_FUNC(RCUReadAuto, rcu_read_auto_unlock)
 #define RCU_READ_LOCK_GUARD() \
     g_autoptr(RCUReadAuto) _rcu_read_auto __attribute__((unused)) = rcu_read_auto_lock()
 
+/*
+ * Force-RCU notifiers tell readers that they should exit their
+ * read-side critical section.
+ */
+void rcu_add_force_rcu_notifier(Notifier *n);
+void rcu_remove_force_rcu_notifier(Notifier *n);
+
 #ifdef __cplusplus
 }
 #endif

util/rcu.c

@@ -46,6 +46,7 @@
 unsigned long rcu_gp_ctr = RCU_GP_LOCKED;
 
 QemuEvent rcu_gp_event;
+static int in_drain_call_rcu;
 static QemuMutex rcu_registry_lock;
 static QemuMutex rcu_sync_lock;
 
@@ -107,6 +108,8 @@ static void wait_for_readers(void)
                  * get some extra futex wakeups.
                  */
                 qatomic_set(&index->waiting, false);
+            } else if (qatomic_read(&in_drain_call_rcu)) {
+                notifier_list_notify(&index->force_rcu, NULL);
             }
         }
 
@@ -339,8 +342,10 @@ void drain_call_rcu(void)
      * assumed.
      */
 
+    qatomic_inc(&in_drain_call_rcu);
     call_rcu1(&rcu_drain.rcu, drain_rcu_callback);
     qemu_event_wait(&rcu_drain.drain_complete_event);
+    qatomic_dec(&in_drain_call_rcu);
 
     if (locked) {
         qemu_mutex_lock_iothread();
@@ -363,6 +368,20 @@ void rcu_unregister_thread(void)
     qemu_mutex_unlock(&rcu_registry_lock);
 }
 
+void rcu_add_force_rcu_notifier(Notifier *n)
+{
+    qemu_mutex_lock(&rcu_registry_lock);
+    notifier_list_add(&rcu_reader.force_rcu, n);
+    qemu_mutex_unlock(&rcu_registry_lock);
+}
+
+void rcu_remove_force_rcu_notifier(Notifier *n)
+{
+    qemu_mutex_lock(&rcu_registry_lock);
+    notifier_remove(n);
+    qemu_mutex_unlock(&rcu_registry_lock);
+}
+
 static void rcu_init_complete(void)
 {
     QemuThread thread;