[PATCH v3 2/2] accel/tcg: Register a force_rcu notifier

[Greg Kurz <groug@kaod.org>]

A TCG vCPU doing a busy loop systematicaly hangs the QEMU monitor
if the user passes 'device_add' without argument. This is because
drain_cpu_all() which is called from qmp_device_add() cannot return
if readers don't exit read-side critical sections. That is typically
what busy-looping TCG vCPUs do:

int cpu_exec(CPUState *cpu)
{
[...]
    rcu_read_lock();
[...]
    while (!cpu_handle_exception(cpu, &ret)) {
        // Busy loop keeps vCPU here
    }
[...]
    rcu_read_unlock();

    return ret;
}

Have all vCPU threads register a force_rcu notifier that will kick them
out of the loop using async_run_on_cpu(). The notifier is called with the
rcu_registry_lock mutex held, using async_run_on_cpu() ensures there are
no deadlocks.

Note that when running in round-robin mode, this means that we register
only one notifier which corresponds to the first vCPU. This is okay
since calling async_run_on_cpu() on any vCPU is enough to kick any
other vCPU from execution.

Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Fixes: 7bed89958bfb ("device_core: use drain_call_rcu in in qmp_device_add")
Resolves: https://gitlab.com/qemu-project/qemu/-/issues/650
Signed-off-by: Greg Kurz <groug@kaod.org>
---
 accel/tcg/tcg-accel-ops-mttcg.c | 26 ++++++++++++++++++++++++++
 accel/tcg/tcg-accel-ops-rr.c    | 18 ++++++++++++++++++
 2 files changed, 44 insertions(+)

diff --git a/accel/tcg/tcg-accel-ops-mttcg.c b/accel/tcg/tcg-accel-ops-mttcg.c
index 847d2079d21f..29632bd4c0af 100644
--- a/accel/tcg/tcg-accel-ops-mttcg.c
+++ b/accel/tcg/tcg-accel-ops-mttcg.c
@@ -28,6 +28,7 @@
 #include "sysemu/tcg.h"
 #include "sysemu/replay.h"
 #include "qemu/main-loop.h"
+#include "qemu/notify.h"
 #include "qemu/guest-random.h"
 #include "exec/exec-all.h"
 #include "hw/boards.h"
@@ -35,6 +36,26 @@
 #include "tcg-accel-ops.h"
 #include "tcg-accel-ops-mttcg.h"
 
+typedef struct MttcgForceRcuNotifier {
+    Notifier notifier;
+    CPUState *cpu;
+} MttcgForceRcuNotifier;
+
+static void do_nothing(CPUState *cpu, run_on_cpu_data d)
+{
+}
+
+static void mttcg_force_rcu(Notifier *notify, void *data)
+{
+    CPUState *cpu = container_of(notify, MttcgForceRcuNotifier, notifier)->cpu;
+
+    /*
+     * Called with rcu_registry_lock held, using async_run_on_cpu() ensures
+     * that there are no deadlocks.
+     */
+    async_run_on_cpu(cpu, do_nothing, RUN_ON_CPU_NULL);
+}
+
 /*
  * In the multi-threaded case each vCPU has its own thread. The TLS
  * variable current_cpu can be used deep in the code to find the
@@ -43,12 +64,16 @@
 
 static void *mttcg_cpu_thread_fn(void *arg)
 {
+    MttcgForceRcuNotifier force_rcu;
     CPUState *cpu = arg;
 
     assert(tcg_enabled());
     g_assert(!icount_enabled());
 
     rcu_register_thread();
+    force_rcu.notifier.notify = mttcg_force_rcu;
+    force_rcu.cpu = cpu;
+    rcu_add_force_rcu_notifier(&force_rcu.notifier);
     tcg_register_thread();
 
     qemu_mutex_lock_iothread();
@@ -100,6 +125,7 @@ static void *mttcg_cpu_thread_fn(void *arg)
 
     tcg_cpus_destroy(cpu);
     qemu_mutex_unlock_iothread();
+    rcu_remove_force_rcu_notifier(&force_rcu.notifier);
     rcu_unregister_thread();
     return NULL;
 }
diff --git a/accel/tcg/tcg-accel-ops-rr.c b/accel/tcg/tcg-accel-ops-rr.c
index a5fd26190e20..934ac21d79b5 100644
--- a/accel/tcg/tcg-accel-ops-rr.c
+++ b/accel/tcg/tcg-accel-ops-rr.c
@@ -28,6 +28,7 @@
 #include "sysemu/tcg.h"
 #include "sysemu/replay.h"
 #include "qemu/main-loop.h"
+#include "qemu/notify.h"
 #include "qemu/guest-random.h"
 #include "exec/exec-all.h"
 
@@ -133,6 +134,19 @@ static void rr_deal_with_unplugged_cpus(void)
     }
 }
 
+static void do_nothing(CPUState *cpu, run_on_cpu_data d)
+{
+}
+
+static void rr_force_rcu(Notifier *notify, void *data)
+{
+    /*
+     * Called with rcu_registry_lock held, using async_run_on_cpu() ensures
+     * that there are no deadlocks.
+     */
+    async_run_on_cpu(first_cpu, do_nothing, RUN_ON_CPU_NULL);
+}
+
 /*
  * In the single-threaded case each vCPU is simulated in turn. If
  * there is more than a single vCPU we create a simple timer to kick
@@ -143,10 +157,13 @@ static void rr_deal_with_unplugged_cpus(void)
 
 static void *rr_cpu_thread_fn(void *arg)
 {
+    Notifier force_rcu;
     CPUState *cpu = arg;
 
     assert(tcg_enabled());
     rcu_register_thread();
+    force_rcu.notify = rr_force_rcu;
+    rcu_add_force_rcu_notifier(&force_rcu);
     tcg_register_thread();
 
     qemu_mutex_lock_iothread();
@@ -255,6 +272,7 @@ static void *rr_cpu_thread_fn(void *arg)
         rr_deal_with_unplugged_cpus();
     }
 
+    rcu_remove_force_rcu_notifier(&force_rcu);
     rcu_unregister_thread();
     return NULL;
 }
-- 
2.31.1