commit 73c6e4013b4cd92d3d531bc22cc29e6036ef42e0
author Paolo Bonzini <pbonzini@redhat.com> Wed Jan 27 08:49:21 2016 +0100
committer Paolo Bonzini <pbonzini@redhat.com> Tue Aug 08 10:40:09 2017 +0200
tree a6eda7dbf2e2dfb39507cefd5cd0cb95cbe8a640
parent c233a35d3d91af666aa95a6a3ba8244d4ce728c6

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>

include/qemu/rcu.h

diff --git a/include/qemu/rcu.h b/include/qemu/rcu.h
index 83ae280..c0da990 100644
--- a/include/qemu/rcu.h
+++ b/include/qemu/rcu.h
@@ -105,6 +105,12 @@
  */
 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;

util/rcu.c

diff --git a/util/rcu.c b/util/rcu.c
index 9adc5e4..2142ddd 100644
--- a/util/rcu.c
+++ b/util/rcu.c
@@ -318,15 +318,35 @@
     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);
 }

vl.c

diff --git a/vl.c b/vl.c
index 99fcfa0..8967115 100644
--- a/vl.c
+++ b/vl.c
@@ -4121,6 +4121,7 @@
     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));