diff mbox series

[v2,3/7] device-core: use RCU for list of childs of a bus

Message ID 20200511160951.8733-4-mlevitsk@redhat.com (mailing list archive)
State New, archived
Headers show
Series RFC/WIP: Fix scsi devices plug/unplug races w.r.t virtio-scsi iothread | expand

Commit Message

Maxim Levitsky May 11, 2020, 4:09 p.m. UTC
This fixes the race between device emulation code that tries to find
a child device to dispatch the request to (e.g a scsi disk),
and hotplug of a new device to that bus.

Note that this doesn't convert all the readers of the list
but only these that might go over that list without BQL held.

This is a very small first step to make this code thread safe.

Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
---
 hw/core/bus.c          | 36 +++++++++++++++++++++++-------------
 hw/core/qdev.c         | 37 +++++++++++++++++++++++--------------
 hw/scsi/scsi-bus.c     | 17 ++++++++++++++---
 hw/scsi/virtio-scsi.c  |  6 +++++-
 include/hw/qdev-core.h |  3 +++
 5 files changed, 68 insertions(+), 31 deletions(-)

Comments

Stefan Hajnoczi May 27, 2020, 2:45 p.m. UTC | #1
On Mon, May 11, 2020 at 07:09:47PM +0300, Maxim Levitsky wrote:
> diff --git a/include/hw/qdev-core.h b/include/hw/qdev-core.h
> index d87d989e72..ef47cb2d9c 100644
> --- a/include/hw/qdev-core.h
> +++ b/include/hw/qdev-core.h
> @@ -3,6 +3,8 @@
>  
>  #include "qemu/queue.h"
>  #include "qemu/bitmap.h"
> +#include "qemu/rcu.h"
> +#include "qemu/rcu_queue.h"
>  #include "qom/object.h"
>  #include "hw/hotplug.h"
>  #include "hw/resettable.h"
> @@ -230,6 +232,7 @@ struct BusClass {
>  };
>  
>  typedef struct BusChild {
> +    struct rcu_head rcu;
>      DeviceState *child;
>      int index;
>      QTAILQ_ENTRY(BusChild) sibling;

Please add a doc comment to struct BusState saying the children field is
an RCU QTAILQ and writers must hold the QEMU global mutex.

Stefan
Maxim Levitsky July 9, 2020, 9:40 a.m. UTC | #2
On Wed, 2020-05-27 at 15:45 +0100, Stefan Hajnoczi wrote:
> On Mon, May 11, 2020 at 07:09:47PM +0300, Maxim Levitsky wrote:
> > diff --git a/include/hw/qdev-core.h b/include/hw/qdev-core.h
> > index d87d989e72..ef47cb2d9c 100644
> > --- a/include/hw/qdev-core.h
> > +++ b/include/hw/qdev-core.h
> > @@ -3,6 +3,8 @@
> >  
> >  #include "qemu/queue.h"
> >  #include "qemu/bitmap.h"
> > +#include "qemu/rcu.h"
> > +#include "qemu/rcu_queue.h"
> >  #include "qom/object.h"
> >  #include "hw/hotplug.h"
> >  #include "hw/resettable.h"
> > @@ -230,6 +232,7 @@ struct BusClass {
> >  };
> >  
> >  typedef struct BusChild {
> > +    struct rcu_head rcu;
> >      DeviceState *child;
> >      int index;
> >      QTAILQ_ENTRY(BusChild) sibling;
> 
> Please add a doc comment to struct BusState saying the children field is
> an RCU QTAILQ and writers must hold the QEMU global mutex.
> 
> Stefan
Done.


Best regards,
	Maxim Levitsky
diff mbox series

Patch

diff --git a/hw/core/bus.c b/hw/core/bus.c
index 3dc0a825f0..dd6b155ff1 100644
--- a/hw/core/bus.c
+++ b/hw/core/bus.c
@@ -49,12 +49,14 @@  int qbus_walk_children(BusState *bus,
         }
     }
 
-    QTAILQ_FOREACH(kid, &bus->children, sibling) {
-        err = qdev_walk_children(kid->child,
-                                 pre_devfn, pre_busfn,
-                                 post_devfn, post_busfn, opaque);
-        if (err < 0) {
-            return err;
+    WITH_RCU_READ_LOCK_GUARD() {
+        QTAILQ_FOREACH_RCU(kid, &bus->children, sibling) {
+            err = qdev_walk_children(kid->child,
+                                     pre_devfn, pre_busfn,
+                                     post_devfn, post_busfn, opaque);
+            if (err < 0) {
+                return err;
+            }
         }
     }
 
@@ -90,9 +92,13 @@  static void bus_reset_child_foreach(Object *obj, ResettableChildCallback cb,
     BusState *bus = BUS(obj);
     BusChild *kid;
 
-    QTAILQ_FOREACH(kid, &bus->children, sibling) {
+    rcu_read_lock();
+
+    QTAILQ_FOREACH_RCU(kid, &bus->children, sibling) {
         cb(OBJECT(kid->child), opaque, type);
     }
+
+    rcu_read_unlock();
 }
 
 static void qbus_realize(BusState *bus, DeviceState *parent, const char *name)
@@ -185,14 +191,18 @@  static void bus_set_realized(Object *obj, bool value, Error **errp)
 
         /* TODO: recursive realization */
     } else if (!value && bus->realized) {
-        QTAILQ_FOREACH(kid, &bus->children, sibling) {
-            DeviceState *dev = kid->child;
-            object_property_set_bool(OBJECT(dev), false, "realized",
-                                     &local_err);
-            if (local_err != NULL) {
-                break;
+
+        WITH_RCU_READ_LOCK_GUARD() {
+            QTAILQ_FOREACH_RCU(kid, &bus->children, sibling) {
+                DeviceState *dev = kid->child;
+                object_property_set_bool(OBJECT(dev), false, "realized",
+                                         &local_err);
+                if (local_err != NULL) {
+                    break;
+                }
             }
         }
+
         if (bc->unrealize && local_err == NULL) {
             bc->unrealize(bus, &local_err);
         }
diff --git a/hw/core/qdev.c b/hw/core/qdev.c
index dd77a56067..732789e2b7 100644
--- a/hw/core/qdev.c
+++ b/hw/core/qdev.c
@@ -51,6 +51,12 @@  const VMStateDescription *qdev_get_vmsd(DeviceState *dev)
     return dc->vmsd;
 }
 
+static void bus_free_bus_child(BusChild *kid)
+{
+    object_unref(OBJECT(kid->child));
+    g_free(kid);
+}
+
 static void bus_remove_child(BusState *bus, DeviceState *child)
 {
     BusChild *kid;
@@ -60,15 +66,16 @@  static void bus_remove_child(BusState *bus, DeviceState *child)
             char name[32];
 
             snprintf(name, sizeof(name), "child[%d]", kid->index);
-            QTAILQ_REMOVE(&bus->children, kid, sibling);
+            QTAILQ_REMOVE_RCU(&bus->children, kid, sibling);
 
             bus->num_children--;
 
             /* This gives back ownership of kid->child back to us.  */
             object_property_del(OBJECT(bus), name, NULL);
-            object_unref(OBJECT(kid->child));
-            g_free(kid);
-            return;
+
+            /* free the bus kid, when it is safe to do so*/
+            call_rcu(kid, bus_free_bus_child, rcu);
+            break;
         }
     }
 }
@@ -83,7 +90,7 @@  static void bus_add_child(BusState *bus, DeviceState *child)
     kid->child = child;
     object_ref(OBJECT(kid->child));
 
-    QTAILQ_INSERT_HEAD(&bus->children, kid, sibling);
+    QTAILQ_INSERT_HEAD_RCU(&bus->children, kid, sibling);
 
     /* This transfers ownership of kid->child to the property.  */
     snprintf(name, sizeof(name), "child[%d]", kid->index);
@@ -682,17 +689,19 @@  DeviceState *qdev_find_recursive(BusState *bus, const char *id)
     DeviceState *ret;
     BusState *child;
 
-    QTAILQ_FOREACH(kid, &bus->children, sibling) {
-        DeviceState *dev = kid->child;
+    WITH_RCU_READ_LOCK_GUARD() {
+        QTAILQ_FOREACH_RCU(kid, &bus->children, sibling) {
+            DeviceState *dev = kid->child;
 
-        if (dev->id && strcmp(dev->id, id) == 0) {
-            return dev;
-        }
+            if (dev->id && strcmp(dev->id, id) == 0) {
+                return dev;
+            }
 
-        QLIST_FOREACH(child, &dev->child_bus, sibling) {
-            ret = qdev_find_recursive(child, id);
-            if (ret) {
-                return ret;
+            QLIST_FOREACH(child, &dev->child_bus, sibling) {
+                ret = qdev_find_recursive(child, id);
+                if (ret) {
+                    return ret;
+                }
             }
         }
     }
diff --git a/hw/scsi/scsi-bus.c b/hw/scsi/scsi-bus.c
index 7bbc37acec..2bf6d005f3 100644
--- a/hw/scsi/scsi-bus.c
+++ b/hw/scsi/scsi-bus.c
@@ -412,7 +412,10 @@  static bool scsi_target_emulate_report_luns(SCSITargetReq *r)
     id = r->req.dev->id;
     found_lun0 = false;
     n = 0;
-    QTAILQ_FOREACH(kid, &r->req.bus->qbus.children, sibling) {
+
+    rcu_read_lock();
+
+    QTAILQ_FOREACH_RCU(kid, &r->req.bus->qbus.children, sibling) {
         DeviceState *qdev = kid->child;
         SCSIDevice *dev = SCSI_DEVICE(qdev);
 
@@ -433,7 +436,7 @@  static bool scsi_target_emulate_report_luns(SCSITargetReq *r)
     memset(r->buf, 0, len);
     stl_be_p(&r->buf[0], n);
     i = found_lun0 ? 8 : 16;
-    QTAILQ_FOREACH(kid, &r->req.bus->qbus.children, sibling) {
+    QTAILQ_FOREACH_RCU(kid, &r->req.bus->qbus.children, sibling) {
         DeviceState *qdev = kid->child;
         SCSIDevice *dev = SCSI_DEVICE(qdev);
 
@@ -442,6 +445,9 @@  static bool scsi_target_emulate_report_luns(SCSITargetReq *r)
             i += 8;
         }
     }
+
+    rcu_read_unlock();
+
     assert(i == n + 8);
     r->len = len;
     return true;
@@ -1584,12 +1590,15 @@  SCSIDevice *scsi_device_find(SCSIBus *bus, int channel, int id, int lun)
     BusChild *kid;
     SCSIDevice *target_dev = NULL;
 
-    QTAILQ_FOREACH(kid, &bus->qbus.children, sibling) {
+    rcu_read_lock();
+
+    QTAILQ_FOREACH_RCU(kid, &bus->qbus.children, sibling) {
         DeviceState *qdev = kid->child;
         SCSIDevice *dev = SCSI_DEVICE(qdev);
 
         if (dev->channel == channel && dev->id == id) {
             if (dev->lun == lun) {
+                rcu_read_unlock();
                 return dev;
             }
 
@@ -1603,6 +1612,8 @@  SCSIDevice *scsi_device_find(SCSIBus *bus, int channel, int id, int lun)
             }
         }
     }
+
+    rcu_read_unlock();
     return target_dev;
 }
 
diff --git a/hw/scsi/virtio-scsi.c b/hw/scsi/virtio-scsi.c
index 472bbd233b..b0f4a35f81 100644
--- a/hw/scsi/virtio-scsi.c
+++ b/hw/scsi/virtio-scsi.c
@@ -367,12 +367,16 @@  static int virtio_scsi_do_tmf(VirtIOSCSI *s, VirtIOSCSIReq *req)
     case VIRTIO_SCSI_T_TMF_I_T_NEXUS_RESET:
         target = req->req.tmf.lun[1];
         s->resetting++;
-        QTAILQ_FOREACH(kid, &s->bus.qbus.children, sibling) {
+
+        rcu_read_lock();
+        QTAILQ_FOREACH_RCU(kid, &s->bus.qbus.children, sibling) {
              d = SCSI_DEVICE(kid->child);
              if (d->channel == 0 && d->id == target) {
                 qdev_reset_all(&d->qdev);
              }
         }
+        rcu_read_unlock();
+
         s->resetting--;
         break;
 
diff --git a/include/hw/qdev-core.h b/include/hw/qdev-core.h
index d87d989e72..ef47cb2d9c 100644
--- a/include/hw/qdev-core.h
+++ b/include/hw/qdev-core.h
@@ -3,6 +3,8 @@ 
 
 #include "qemu/queue.h"
 #include "qemu/bitmap.h"
+#include "qemu/rcu.h"
+#include "qemu/rcu_queue.h"
 #include "qom/object.h"
 #include "hw/hotplug.h"
 #include "hw/resettable.h"
@@ -230,6 +232,7 @@  struct BusClass {
 };
 
 typedef struct BusChild {
+    struct rcu_head rcu;
     DeviceState *child;
     int index;
     QTAILQ_ENTRY(BusChild) sibling;