1 files changed, 161 insertions, 83 deletions

diff --git a/hw/s390x/s390-pci-bus.c b/hw/s390x/s390-pci-bus.c
index f017c1d..80ff1ce 100644
--- a/hw/s390x/s390-pci-bus.c
+++ b/hw/s390x/s390-pci-bus.c
@@ -148,6 +148,22 @@ out:
     psccb->header.response_code = cpu_to_be16(rc);
 }
 
+static void s390_pci_perform_unplug(S390PCIBusDevice *pbdev)
+{
+    HotplugHandler *hotplug_ctrl;
+
+    /* Unplug the PCI device */
+    if (pbdev->pdev) {
+        hotplug_ctrl = qdev_get_hotplug_handler(DEVICE(pbdev->pdev));
+        hotplug_handler_unplug(hotplug_ctrl, DEVICE(pbdev->pdev),
+                               &error_abort);
+    }
+
+    /* Unplug the zPCI device */
+    hotplug_ctrl = qdev_get_hotplug_handler(DEVICE(pbdev));
+    hotplug_handler_unplug(hotplug_ctrl, DEVICE(pbdev), &error_abort);
+}
+
 void s390_pci_sclp_deconfigure(SCCB *sccb)
 {
     IoaCfgSccb *psccb = (IoaCfgSccb *)sccb;
@@ -178,8 +194,8 @@ void s390_pci_sclp_deconfigure(SCCB *sccb)
         pbdev->state = ZPCI_FS_STANDBY;
         rc = SCLP_RC_NORMAL_COMPLETION;
 
-        if (pbdev->release_timer) {
-            qdev_unplug(DEVICE(pbdev->pdev), NULL);
+        if (pbdev->unplug_requested) {
+            s390_pci_perform_unplug(pbdev);
         }
     }
 out:
@@ -217,6 +233,24 @@ S390PCIBusDevice *s390_pci_find_dev_by_target(S390pciState *s,
     return NULL;
 }
 
+static S390PCIBusDevice *s390_pci_find_dev_by_pci(S390pciState *s,
+                                                  PCIDevice *pci_dev)
+{
+    S390PCIBusDevice *pbdev;
+
+    if (!pci_dev) {
+        return NULL;
+    }
+
+    QTAILQ_FOREACH(pbdev, &s->zpci_devs, link) {
+        if (pbdev->pdev == pci_dev) {
+            return pbdev;
+        }
+    }
+
+    return NULL;
+}
+
 S390PCIBusDevice *s390_pci_find_dev_by_idx(S390pciState *s, uint32_t idx)
 {
     return g_hash_table_lookup(s->zpci_table, &idx);
@@ -826,6 +860,12 @@ static void s390_pcihost_pre_plug(HotplugHandler *hotplug_dev, DeviceState *dev,
 {
     S390pciState *s = S390_PCI_HOST_BRIDGE(hotplug_dev);
 
+    if (!s390_has_feat(S390_FEAT_ZPCI)) {
+        warn_report("Plugging a PCI/zPCI device without the 'zpci' CPU "
+                    "feature enabled; the guest will not be able to see/use "
+                    "this device");
+    }
+
     if (object_dynamic_cast(OBJECT(dev), TYPE_PCI_DEVICE)) {
         PCIDevice *pdev = PCI_DEVICE(dev);
 
@@ -843,6 +883,21 @@ static void s390_pcihost_pre_plug(HotplugHandler *hotplug_dev, DeviceState *dev,
     }
 }
 
+static void s390_pci_update_subordinate(PCIDevice *dev, uint32_t nr)
+{
+    uint32_t old_nr;
+
+    pci_default_write_config(dev, PCI_SUBORDINATE_BUS, nr, 1);
+    while (!pci_bus_is_root(pci_get_bus(dev))) {
+        dev = pci_get_bus(dev)->parent_dev;
+
+        old_nr = pci_default_read_config(dev, PCI_SUBORDINATE_BUS, 1);
+        if (old_nr < nr) {
+            pci_default_write_config(dev, PCI_SUBORDINATE_BUS, nr, 1);
+        }
+    }
+}
+
 static void s390_pcihost_plug(HotplugHandler *hotplug_dev, DeviceState *dev,
                               Error **errp)
 {
@@ -851,25 +906,21 @@ static void s390_pcihost_plug(HotplugHandler *hotplug_dev, DeviceState *dev,
     S390PCIBusDevice *pbdev = NULL;
 
     if (object_dynamic_cast(OBJECT(dev), TYPE_PCI_BRIDGE)) {
-        BusState *bus;
         PCIBridge *pb = PCI_BRIDGE(dev);
-        PCIDevice *pdev = PCI_DEVICE(dev);
 
+        pdev = PCI_DEVICE(dev);
         pci_bridge_map_irq(pb, dev->id, s390_pci_map_irq);
         pci_setup_iommu(&pb->sec_bus, s390_pci_dma_iommu, s);
 
-        bus = BUS(&pb->sec_bus);
-        qbus_set_hotplug_handler(bus, DEVICE(s), errp);
+        qbus_set_hotplug_handler(BUS(&pb->sec_bus), DEVICE(s), errp);
 
         if (dev->hotplugged) {
-            pci_default_write_config(pdev, PCI_PRIMARY_BUS, s->bus_no, 1);
+            pci_default_write_config(pdev, PCI_PRIMARY_BUS,
+                                     pci_dev_bus_num(pdev), 1);
             s->bus_no += 1;
             pci_default_write_config(pdev, PCI_SECONDARY_BUS, s->bus_no, 1);
-            do {
-                pdev = pci_get_bus(pdev)->parent_dev;
-                pci_default_write_config(pdev, PCI_SUBORDINATE_BUS,
-                                         s->bus_no, 1);
-            } while (pci_get_bus(pdev) && pci_dev_bus_num(pdev));
+
+            s390_pci_update_subordinate(pdev, s->bus_no);
         }
     } else if (object_dynamic_cast(OBJECT(dev), TYPE_PCI_DEVICE)) {
         pdev = PCI_DEVICE(dev);
@@ -925,99 +976,96 @@ static void s390_pcihost_plug(HotplugHandler *hotplug_dev, DeviceState *dev,
     }
 }
 
-static void s390_pcihost_timer_cb(void *opaque)
+static void s390_pcihost_unplug(HotplugHandler *hotplug_dev, DeviceState *dev,
+                                Error **errp)
 {
-    S390PCIBusDevice *pbdev = opaque;
+    S390pciState *s = S390_PCI_HOST_BRIDGE(hotplug_dev);
+    S390PCIBusDevice *pbdev = NULL;
 
-    if (pbdev->summary_ind) {
-        pci_dereg_irqs(pbdev);
-    }
-    if (pbdev->iommu->enabled) {
-        pci_dereg_ioat(pbdev->iommu);
-    }
+    if (object_dynamic_cast(OBJECT(dev), TYPE_PCI_DEVICE)) {
+        PCIDevice *pci_dev = PCI_DEVICE(dev);
+        PCIBus *bus;
+        int32_t devfn;
 
-    pbdev->state = ZPCI_FS_STANDBY;
-    s390_pci_generate_plug_event(HP_EVENT_CONFIGURED_TO_STBRES,
-                                 pbdev->fh, pbdev->fid);
-    qdev_unplug(DEVICE(pbdev), NULL);
+        pbdev = s390_pci_find_dev_by_pci(s, PCI_DEVICE(dev));
+        g_assert(pbdev);
+
+        s390_pci_generate_plug_event(HP_EVENT_STANDBY_TO_RESERVED,
+                                     pbdev->fh, pbdev->fid);
+        bus = pci_get_bus(pci_dev);
+        devfn = pci_dev->devfn;
+        object_unparent(OBJECT(pci_dev));
+
+        s390_pci_msix_free(pbdev);
+        s390_pci_iommu_free(s, bus, devfn);
+        pbdev->pdev = NULL;
+        pbdev->state = ZPCI_FS_RESERVED;
+    } else if (object_dynamic_cast(OBJECT(dev), TYPE_S390_PCI_DEVICE)) {
+        pbdev = S390_PCI_DEVICE(dev);
+        pbdev->fid = 0;
+        QTAILQ_REMOVE(&s->zpci_devs, pbdev, link);
+        g_hash_table_remove(s->zpci_table, &pbdev->idx);
+        object_unparent(OBJECT(pbdev));
+    }
 }
 
-static void s390_pcihost_unplug(HotplugHandler *hotplug_dev, DeviceState *dev,
-                                Error **errp)
+static void s390_pcihost_unplug_request(HotplugHandler *hotplug_dev,
+                                        DeviceState *dev,
+                                        Error **errp)
 {
     S390pciState *s = S390_PCI_HOST_BRIDGE(hotplug_dev);
-    PCIDevice *pci_dev = NULL;
-    PCIBus *bus;
-    int32_t devfn;
-    S390PCIBusDevice *pbdev = NULL;
+    S390PCIBusDevice *pbdev;
 
     if (object_dynamic_cast(OBJECT(dev), TYPE_PCI_BRIDGE)) {
         error_setg(errp, "PCI bridge hot unplug currently not supported");
-        return;
     } else if (object_dynamic_cast(OBJECT(dev), TYPE_PCI_DEVICE)) {
-        pci_dev = PCI_DEVICE(dev);
-
-        QTAILQ_FOREACH(pbdev, &s->zpci_devs, link) {
-            if (pbdev->pdev == pci_dev) {
-                break;
-            }
-        }
-        assert(pbdev != NULL);
+        /*
+         * Redirect the unplug request to the zPCI device and remember that
+         * we've checked the PCI device already (to prevent endless recursion).
+         */
+        pbdev = s390_pci_find_dev_by_pci(s, PCI_DEVICE(dev));
+        g_assert(pbdev);
+        pbdev->pci_unplug_request_processed = true;
+        qdev_unplug(DEVICE(pbdev), errp);
     } else if (object_dynamic_cast(OBJECT(dev), TYPE_S390_PCI_DEVICE)) {
         pbdev = S390_PCI_DEVICE(dev);
-        pci_dev = pbdev->pdev;
-    } else {
-        g_assert_not_reached();
-    }
 
-    switch (pbdev->state) {
-    case ZPCI_FS_RESERVED:
-        goto out;
-    case ZPCI_FS_STANDBY:
-        break;
-    default:
-        if (pbdev->release_timer) {
+        /*
+         * If unplug was initially requested for the zPCI device, we
+         * first have to redirect to the PCI device, which will in return
+         * redirect back to us after performing its checks (if the request
+         * is not blocked, e.g. because it's a PCI bridge).
+         */
+        if (pbdev->pdev && !pbdev->pci_unplug_request_processed) {
+            qdev_unplug(DEVICE(pbdev->pdev), errp);
             return;
         }
-        s390_pci_generate_plug_event(HP_EVENT_DECONFIGURE_REQUEST,
-                                     pbdev->fh, pbdev->fid);
-        pbdev->release_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL,
-                                            s390_pcihost_timer_cb,
-                                            pbdev);
-        timer_mod(pbdev->release_timer,
-                  qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + HOT_UNPLUG_TIMEOUT);
-        return;
-    }
+        pbdev->pci_unplug_request_processed = false;
 
-    if (pbdev->release_timer) {
-        timer_del(pbdev->release_timer);
-        timer_free(pbdev->release_timer);
-        pbdev->release_timer = NULL;
+        switch (pbdev->state) {
+        case ZPCI_FS_STANDBY:
+        case ZPCI_FS_RESERVED:
+            s390_pci_perform_unplug(pbdev);
+            break;
+        default:
+            /*
+             * Allow to send multiple requests, e.g. if the guest crashed
+             * before releasing the device, we would not be able to send
+             * another request to the same VM (e.g. fresh OS).
+             */
+            pbdev->unplug_requested = true;
+            s390_pci_generate_plug_event(HP_EVENT_DECONFIGURE_REQUEST,
+                                         pbdev->fh, pbdev->fid);
+        }
+    } else {
+        g_assert_not_reached();
     }
-
-    s390_pci_generate_plug_event(HP_EVENT_STANDBY_TO_RESERVED,
-                                 pbdev->fh, pbdev->fid);
-    bus = pci_get_bus(pci_dev);
-    devfn = pci_dev->devfn;
-    object_unparent(OBJECT(pci_dev));
-    fmb_timer_free(pbdev);
-    s390_pci_msix_free(pbdev);
-    s390_pci_iommu_free(s, bus, devfn);
-    pbdev->pdev = NULL;
-    pbdev->state = ZPCI_FS_RESERVED;
-out:
-    pbdev->fid = 0;
-    QTAILQ_REMOVE(&s->zpci_devs, pbdev, link);
-    g_hash_table_remove(s->zpci_table, &pbdev->idx);
-    object_unparent(OBJECT(pbdev));
 }
 
 static void s390_pci_enumerate_bridge(PCIBus *bus, PCIDevice *pdev,
                                       void *opaque)
 {
     S390pciState *s = opaque;
-    unsigned int primary = s->bus_no;
-    unsigned int subordinate = 0xff;
     PCIBus *sec_bus = NULL;
 
     if ((pci_default_read_config(pdev, PCI_HEADER_TYPE, 1) !=
@@ -1026,7 +1074,7 @@ static void s390_pci_enumerate_bridge(PCIBus *bus, PCIDevice *pdev,
     }
 
     (s->bus_no)++;
-    pci_default_write_config(pdev, PCI_PRIMARY_BUS, primary, 1);
+    pci_default_write_config(pdev, PCI_PRIMARY_BUS, pci_dev_bus_num(pdev), 1);
     pci_default_write_config(pdev, PCI_SECONDARY_BUS, s->bus_no, 1);
     pci_default_write_config(pdev, PCI_SUBORDINATE_BUS, s->bus_no, 1);
 
@@ -1035,7 +1083,7 @@ static void s390_pci_enumerate_bridge(PCIBus *bus, PCIDevice *pdev,
         return;
     }
 
-    pci_default_write_config(pdev, PCI_SUBORDINATE_BUS, subordinate, 1);
+    /* Assign numbers to all child bridges. The last is the highest number. */
     pci_for_each_device(sec_bus, pci_bus_num(sec_bus),
                         s390_pci_enumerate_bridge, s);
     pci_default_write_config(pdev, PCI_SUBORDINATE_BUS, s->bus_no, 1);
@@ -1045,7 +1093,26 @@ static void s390_pcihost_reset(DeviceState *dev)
 {
     S390pciState *s = S390_PCI_HOST_BRIDGE(dev);
     PCIBus *bus = s->parent_obj.bus;
+    S390PCIBusDevice *pbdev, *next;
+
+    /* Process all pending unplug requests */
+    QTAILQ_FOREACH_SAFE(pbdev, &s->zpci_devs, link, next) {
+        if (pbdev->unplug_requested) {
+            if (pbdev->summary_ind) {
+                pci_dereg_irqs(pbdev);
+            }
+            if (pbdev->iommu->enabled) {
+                pci_dereg_ioat(pbdev->iommu);
+            }
+            pbdev->state = ZPCI_FS_STANDBY;
+            s390_pci_perform_unplug(pbdev);
+        }
+    }
 
+    /*
+     * When resetting a PCI bridge, the assigned numbers are set to 0. So
+     * on every system reset, we also have to reassign numbers.
+     */
     s->bus_no = 0;
     pci_for_each_device(bus, pci_bus_num(bus), s390_pci_enumerate_bridge, s);
 }
@@ -1059,6 +1126,7 @@ static void s390_pcihost_class_init(ObjectClass *klass, void *data)
     dc->realize = s390_pcihost_realize;
     hc->pre_plug = s390_pcihost_pre_plug;
     hc->plug = s390_pcihost_plug;
+    hc->unplug_request = s390_pcihost_unplug_request;
     hc->unplug = s390_pcihost_unplug;
     msi_nonbroken = true;
 }
@@ -1219,6 +1287,15 @@ static Property s390_pci_device_properties[] = {
     DEFINE_PROP_END_OF_LIST(),
 };
 
+static const VMStateDescription s390_pci_device_vmstate = {
+    .name = TYPE_S390_PCI_DEVICE,
+    /*
+     * TODO: add state handling here, so migration works at least with
+     * emulated pci devices on s390x
+     */
+    .unmigratable = 1,
+};
+
 static void s390_pci_device_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
@@ -1229,6 +1306,7 @@ static void s390_pci_device_class_init(ObjectClass *klass, void *data)
     dc->bus_type = TYPE_S390_PCI_BUS;
     dc->realize = s390_pci_device_realize;
     dc->props = s390_pci_device_properties;
+    dc->vmsd = &s390_pci_device_vmstate;
 }
 
 static const TypeInfo s390_pci_device_info = {