xen: implement unplug protocol in xen_platform

The unplug protocol is necessary to support PV drivers in the guest: the
drivers expect to be able to "unplug" emulated disks and nics before
initializing the Xen PV interfaces.
It is responsibility of the guest to make sure that the unplug is done
before the emulated devices or the PV interface start to be used.

We use pci_for_each_device to walk the PCI bus, identify the devices and
disks that we want to disable and dynamically unplug them.

Changes in v2:

- use PCI_CLASS constants;

- replace pci_unplug_device with qdev_unplug;

- do not import hw/ide/internal.h in xen_platform.c;

Changes in v3:

- introduce piix3-ide-xen, that support hot-unplug;

- move the unplug code to hw/ide/piix.c;

- just call qdev_unplug from xen_platform.c to unplug the IDE disks;

Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Acked-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Alexander Graf <agraf@suse.de>

hw/ide.h

@@ -13,6 +13,7 @@ ISADevice *isa_ide_init(int iobase, int iobase2, int isairq,
 /* ide-pci.c */
 void pci_cmd646_ide_init(PCIBus *bus, DriveInfo **hd_table,
                          int secondary_ide_enabled);
+PCIDevice *pci_piix3_xen_ide_init(PCIBus *bus, DriveInfo **hd_table, int devfn);
 PCIDevice *pci_piix3_ide_init(PCIBus *bus, DriveInfo **hd_table, int devfn);
 PCIDevice *pci_piix4_ide_init(PCIBus *bus, DriveInfo **hd_table, int devfn);
 void vt82c686b_ide_init(PCIBus *bus, DriveInfo **hd_table, int devfn);

hw/ide/piix.c

@@ -149,6 +149,42 @@ static int pci_piix_ide_initfn(PCIDevice *dev)
     return 0;
 }
 
+static int pci_piix3_xen_ide_unplug(DeviceState *dev)
+{
+    PCIDevice *pci_dev;
+    PCIIDEState *pci_ide;
+    DriveInfo *di;
+    int i = 0;
+
+    pci_dev = DO_UPCAST(PCIDevice, qdev, dev);
+    pci_ide = DO_UPCAST(PCIIDEState, dev, pci_dev);
+
+    for (; i < 3; i++) {
+        di = drive_get_by_index(IF_IDE, i);
+        if (di != NULL && di->bdrv != NULL && !di->bdrv->removable) {
+            DeviceState *ds = bdrv_get_attached(di->bdrv);
+            if (ds) {
+                bdrv_detach(di->bdrv, ds);
+            }
+            bdrv_close(di->bdrv);
+            pci_ide->bus[di->bus].ifs[di->unit].bs = NULL;
+            drive_put_ref(di);
+        }
+    }
+    qdev_reset_all(&(pci_ide->dev.qdev));
+    return 0;
+}
+
+PCIDevice *pci_piix3_xen_ide_init(PCIBus *bus, DriveInfo **hd_table, int devfn)
+{
+    PCIDevice *dev;
+
+    dev = pci_create_simple(bus, devfn, "piix3-ide-xen");
+    dev->qdev.info->unplug = pci_piix3_xen_ide_unplug;
+    pci_ide_create_devs(dev, hd_table);
+    return dev;
+}
+
 /* hd_table must contain 4 block drivers */
 /* NOTE: for the PIIX3, the IRQs and IOports are hardcoded */
 PCIDevice *pci_piix3_ide_init(PCIBus *bus, DriveInfo **hd_table, int devfn)
@@ -181,6 +217,14 @@ static PCIDeviceInfo piix_ide_info[] = {
         .vendor_id    = PCI_VENDOR_ID_INTEL,
         .device_id    = PCI_DEVICE_ID_INTEL_82371SB_1,
         .class_id     = PCI_CLASS_STORAGE_IDE,
+    },{
+        .qdev.name    = "piix3-ide-xen",
+        .qdev.size    = sizeof(PCIIDEState),
+        .qdev.no_user = 1,
+        .init         = pci_piix_ide_initfn,
+        .vendor_id    = PCI_VENDOR_ID_INTEL,
+        .device_id    = PCI_DEVICE_ID_INTEL_82371SB_1,
+        .class_id     = PCI_CLASS_STORAGE_IDE,
     },{
         .qdev.name    = "piix4-ide",
         .qdev.size    = sizeof(PCIIDEState),

hw/pc_piix.c

@@ -155,7 +155,11 @@ static void pc_init1(ram_addr_t ram_size,
     ide_drive_get(hd, MAX_IDE_BUS);
     if (pci_enabled) {
         PCIDevice *dev;
+        if (xen_enabled()) {
+            dev = pci_piix3_xen_ide_init(pci_bus, hd, piix3_devfn + 1);
+        } else {
             dev = pci_piix3_ide_init(pci_bus, hd, piix3_devfn + 1);
+        }
         idebus[0] = qdev_get_child_bus(&dev->qdev, "ide.0");
         idebus[1] = qdev_get_child_bus(&dev->qdev, "ide.1");
     } else {

hw/xen_platform.c

@@ -76,6 +76,35 @@ static void log_writeb(PCIXenPlatformState *s, char val)
 }
 
 /* Xen Platform, Fixed IOPort */
+#define UNPLUG_ALL_IDE_DISKS 1
+#define UNPLUG_ALL_NICS 2
+#define UNPLUG_AUX_IDE_DISKS 4
+
+static void unplug_nic(PCIBus *b, PCIDevice *d)
+{
+    if (pci_get_word(d->config + PCI_CLASS_DEVICE) ==
+            PCI_CLASS_NETWORK_ETHERNET) {
+        qdev_unplug(&(d->qdev));
+    }
+}
+
+static void pci_unplug_nics(PCIBus *bus)
+{
+    pci_for_each_device(bus, 0, unplug_nic);
+}
+
+static void unplug_disks(PCIBus *b, PCIDevice *d)
+{
+    if (pci_get_word(d->config + PCI_CLASS_DEVICE) ==
+            PCI_CLASS_STORAGE_IDE) {
+        qdev_unplug(&(d->qdev));
+    }
+}
+
+static void pci_unplug_disks(PCIBus *bus)
+{
+    pci_for_each_device(bus, 0, unplug_disks);
+}
 
 static void platform_fixed_ioport_writew(void *opaque, uint32_t addr, uint32_t val)
 {
@@ -83,10 +112,22 @@ static void platform_fixed_ioport_writew(void *opaque, uint32_t addr, uint32_t v
 
     switch (addr - XEN_PLATFORM_IOPORT) {
     case 0:
-        /* TODO: */
         /* Unplug devices.  Value is a bitmask of which devices to
            unplug, with bit 0 the IDE devices, bit 1 the network
            devices, and bit 2 the non-primary-master IDE devices. */
+        if (val & UNPLUG_ALL_IDE_DISKS) {
+            DPRINTF("unplug disks\n");
+            qemu_aio_flush();
+            bdrv_flush_all();
+            pci_unplug_disks(s->pci_dev.bus);
+        }
+        if (val & UNPLUG_ALL_NICS) {
+            DPRINTF("unplug nics\n");
+            pci_unplug_nics(s->pci_dev.bus);
+        }
+        if (val & UNPLUG_AUX_IDE_DISKS) {
+            DPRINTF("unplug auxiliary disks not supported\n");
+        }
         break;
     case 2:
         switch (val) {