spapr: reset DRCs after devices

A DRC with a pending unplug request releases its associated device at
machine reset time.

In the case of LMB, when all DRCs for a DIMM device have been reset,
the DIMM gets unplugged, causing guest memory to disappear. This may
be very confusing for anything still using this memory.

This is exactly what happens with vhost backends, and QEMU aborts
with:

qemu-system-ppc64: used ring relocated for ring 2
qemu-system-ppc64: qemu/hw/virtio/vhost.c:649: vhost_commit: Assertion
 `r >= 0' failed.

The issue is that each DRC registers a QEMU reset handler, and we
don't control the order in which these handlers are called (ie,
a LMB DRC will unplug a DIMM before the virtio device using the
memory on this DIMM could stop its vhost backend).

To avoid such situations, let's reset DRCs after all devices
have been reset.

Reported-by: Mallesh N. Koti <mallesh@linux.vnet.ibm.com>
Signed-off-by: Greg Kurz <groug@kaod.org>
Reviewed-by: Daniel Henrique Barboza <danielhb@linux.vnet.ibm.com>
Reviewed-by: Michael Roth <mdroth@linux.vnet.ibm.com>
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
(cherry picked from commit 82512483940c756e2db1bd67ea91b02bc29c5e01)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>

diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c
index 954fd1a747686ad32ba2216a4600612d5c0388fe..8630281d0ee24c0940e89e2ce5c006c68284d789 100644 (file)
--- a/hw/ppc/spapr.c
+++ b/hw/ppc/spapr.c
@@ -1393,6 +1393,19 @@ static void find_unknown_sysbus_device(SysBusDevice *sbdev, void *opaque)
     }
 }
 
+static int spapr_reset_drcs(Object *child, void *opaque)
+{
+    sPAPRDRConnector *drc =
+        (sPAPRDRConnector *) object_dynamic_cast(child,
+                                                 TYPE_SPAPR_DR_CONNECTOR);
+
+    if (drc) {
+        spapr_drc_reset(drc);
+    }
+
+    return 0;
+}
+
 static void ppc_spapr_reset(void)
 {
     MachineState *machine = MACHINE(qdev_get_machine());
@@ -1416,6 +1429,14 @@ static void ppc_spapr_reset(void)
     }
 
     qemu_devices_reset();
+
+    /* DRC reset may cause a device to be unplugged. This will cause troubles
+     * if this device is used by another device (eg, a running vhost backend
+     * will crash QEMU if the DIMM holding the vring goes away). To avoid such
+     * situations, we reset DRCs after all devices have been reset.
+     */
+    object_child_foreach_recursive(object_get_root(), spapr_reset_drcs, NULL);
+
     spapr_clear_pending_events(spapr);
 
     /*

diff --git a/hw/ppc/spapr_drc.c b/hw/ppc/spapr_drc.c
index 50df36118701c88609ff55ddc76ec05f9be2ec1a..85f4e7d3246c323051ea7cfcf665d2b83379d40a 100644 (file)
--- a/hw/ppc/spapr_drc.c
+++ b/hw/ppc/spapr_drc.c
@@ -455,11 +455,6 @@ void spapr_drc_reset(sPAPRDRConnector *drc)
     }
 }
 
-static void drc_reset(void *opaque)
-{
-    spapr_drc_reset(SPAPR_DR_CONNECTOR(opaque));
-}
-
 bool spapr_drc_needed(void *opaque)
 {
     sPAPRDRConnector *drc = (sPAPRDRConnector *)opaque;
@@ -518,7 +513,6 @@ static void realize(DeviceState *d, Error **errp)
     }
     vmstate_register(DEVICE(drc), spapr_drc_index(drc), &vmstate_spapr_drc,
                      drc);
-    qemu_register_reset(drc_reset, drc);
     trace_spapr_drc_realize_complete(spapr_drc_index(drc));
 }
 
@@ -529,7 +523,6 @@ static void unrealize(DeviceState *d, Error **errp)
     char name[256];
 
     trace_spapr_drc_unrealize(spapr_drc_index(drc));
-    qemu_unregister_reset(drc_reset, drc);
     vmstate_unregister(DEVICE(drc), &vmstate_spapr_drc, drc);
     root_container = container_get(object_get_root(), DRC_CONTAINER_PATH);
     snprintf(name, sizeof(name), "%x", spapr_drc_index(drc));