rcu: completely disable pthread_atfork callbacks as soon as possible

Because of -daemonize, system mode QEMU sometimes needs to fork() and
keep RCU enabled in the child.  However, there is a possible deadlock
with synchronize_rcu:

- the CPU thread is inside a RCU critical section and wants to take
  the BQL in order to do MMIO

- the monitor thread, which is owning the BQL, calls rcu_init_lock
  which tries to take the rcu_sync_lock

- the call_rcu thread has taken rcu_sync_lock in synchronize_rcu, but
  synchronize_rcu needs the CPU thread to end the critical section
  before returning.

This cannot happen for user-mode emulation, because it does not have
a BQL.

To fix it, assume that system mode QEMU only forks in preparation for
exec (except when daemonizing) and disable pthread_atfork as soon as
the double fork has happened.

Reported-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Tested-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

diff --git a/include/qemu/rcu.h b/include/qemu/rcu.h
index 83ae2808be1917af846173c02d18734747501269..c0da9907e88d817cc4ee9675f9c14519452e508b 100644 (file)
--- a/include/qemu/rcu.h
+++ b/include/qemu/rcu.h
@@ -105,6 +105,12 @@ extern void synchronize_rcu(void);
  */
 extern void rcu_register_thread(void);
 extern void rcu_unregister_thread(void);
+
+/*
+ * Support for fork().  fork() support is enabled at startup.
+ */
+extern void rcu_enable_atfork(void);
+extern void rcu_disable_atfork(void);
 extern void rcu_after_fork(void);
 
 struct rcu_head;

diff --git a/util/rcu.c b/util/rcu.c
index 9adc5e4a368ab600d1c53f7076840b51093d9624..2142ddd93baf4e82725799d25f2a394f3cc93b64 100644 (file)
--- a/util/rcu.c
+++ b/util/rcu.c
@@ -318,15 +318,35 @@ static void rcu_init_complete(void)
     rcu_register_thread();
 }
 
+static int atfork_depth = 1;
+
+void rcu_enable_atfork(void)
+{
+    atfork_depth++;
+}
+
+void rcu_disable_atfork(void)
+{
+    atfork_depth--;
+}
+
 #ifdef CONFIG_POSIX
 static void rcu_init_lock(void)
 {
+    if (atfork_depth < 1) {
+        return;
+    }
+
     qemu_mutex_lock(&rcu_sync_lock);
     qemu_mutex_lock(&rcu_registry_lock);
 }
 
 static void rcu_init_unlock(void)
 {
+    if (atfork_depth < 1) {
+        return;
+    }
+
     qemu_mutex_unlock(&rcu_registry_lock);
     qemu_mutex_unlock(&rcu_sync_lock);
 }

diff --git a/vl.c b/vl.c
index 99fcfa04421a59100e1df6a3f47e30834d960f71..8967115514a0a790c9b5dde2336881596e51a02b 100644 (file)
--- a/vl.c
+++ b/vl.c
@@ -4121,6 +4121,7 @@ int main(int argc, char **argv, char **envp)
     set_memory_options(&ram_slots, &maxram_size, machine_class);
 
     os_daemonize();
+    rcu_disable_atfork();
 
     if (pid_file && qemu_create_pidfile(pid_file) != 0) {
         error_report("could not acquire pid file: %s", strerror(errno));