s390x/pci: reset ISM passthrough devices on shutdown and system reset

ISM device firmware stores unique state information that can
can cause a wholesale unmap of the associated IOMMU (e.g. when
we get a termination signal for QEMU) to trigger firmware errors
because firmware believes we are attempting to invalidate entries
that are still in-use by the guest OS (when in fact that guest is
in the process of being terminated or rebooted).
To alleviate this, register both a shutdown notifier (for unexpected
termination cases e.g. virsh destroy) as well as a reset callback
(for cases like guest OS reboot).  For each of these scenarios, trigger
PCI device reset; this is enough to indicate to firmware that the IOMMU
is no longer in-use by the guest OS, making it safe to invalidate any
associated IOMMU entries.

Fixes: 15d0e7942d3b ("s390x/pci: don't fence interpreted devices without MSI-X")
Signed-off-by: Matthew Rosato <mjrosato@linux.ibm.com>
Message-Id: <20221209195700.263824-1-mjrosato@linux.ibm.com>
Reviewed-by: Eric Farman <farman@linux.ibm.com>
[thuth: Adjusted the hunk in s390-pci-vfio.c due to different context]
Signed-off-by: Thomas Huth <thuth@redhat.com>

1 files changed, 28 insertions, 0 deletions

diff --git a/hw/s390x/s390-pci-bus.c b/hw/s390x/s390-pci-bus.c
index 977e7daa15..02751f3597 100644
--- a/hw/s390x/s390-pci-bus.c
+++ b/hw/s390x/s390-pci-bus.c
@@ -24,6 +24,8 @@
 #include "hw/pci/msi.h"
 #include "qemu/error-report.h"
 #include "qemu/module.h"
+#include "sysemu/reset.h"
+#include "sysemu/runstate.h"
 
 #ifndef DEBUG_S390PCI_BUS
 #define DEBUG_S390PCI_BUS  0
@@ -150,10 +152,30 @@ out:
     psccb->header.response_code = cpu_to_be16(rc);
 }
 
+static void s390_pci_shutdown_notifier(Notifier *n, void *opaque)
+{
+    S390PCIBusDevice *pbdev = container_of(n, S390PCIBusDevice,
+                                           shutdown_notifier);
+
+    pci_device_reset(pbdev->pdev);
+}
+
+static void s390_pci_reset_cb(void *opaque)
+{
+    S390PCIBusDevice *pbdev = opaque;
+
+    pci_device_reset(pbdev->pdev);
+}
+
 static void s390_pci_perform_unplug(S390PCIBusDevice *pbdev)
 {
     HotplugHandler *hotplug_ctrl;
 
+    if (pbdev->pft == ZPCI_PFT_ISM) {
+        notifier_remove(&pbdev->shutdown_notifier);
+        qemu_unregister_reset(s390_pci_reset_cb, pbdev);
+    }
+
     /* Unplug the PCI device */
     if (pbdev->pdev) {
         DeviceState *pdev = DEVICE(pbdev->pdev);
@@ -1111,6 +1133,12 @@ static void s390_pcihost_plug(HotplugHandler *hotplug_dev, DeviceState *dev,
                 pbdev->fh |= FH_SHM_VFIO;
                 pbdev->forwarding_assist = false;
             }
+            /* Register shutdown notifier and reset callback for ISM devices */
+            if (pbdev->pft == ZPCI_PFT_ISM) {
+                pbdev->shutdown_notifier.notify = s390_pci_shutdown_notifier;
+                qemu_register_shutdown_notifier(&pbdev->shutdown_notifier);
+                qemu_register_reset(s390_pci_reset_cb, pbdev);
+            }
         } else {
             pbdev->fh |= FH_SHM_EMUL;
             /* Always intercept emulated devices */