qemu: Do not reattach PCI device used by other domain when shutdown

When failing on starting a domain, it tries to reattach all the PCI
devices defined in the domain conf, regardless of whether the devices
are still used by other domain. This will cause the devices to be deleted
from the list qemu_driver->activePciHostdevs, thus the devices will be
thought as usable even if it's not true. And following commands
nodedev-{reattach,reset} will be successful.

How to reproduce:
  1) Define two domains with same PCI device defined in the confs.
  2) # virsh start domain1
  3) # virsh start domain2
  4) # virsh nodedev-reattach $pci_device

You will see the device will be reattached to host successfully.
As pciDeviceReattach just check if the device is still used by
other domain via checking if the device is in list driver->activePciHostdevs,
however, the device is deleted from the list by step 2).

This patch is to prohibit the bug by:
  1) Prohibit a domain starting or device attachment right at
     preparation period (qemuPrepareHostdevPCIDevices) if the
     device is in list driver->activePciHostdevs, which means
     it's used by other domain.

  2) Introduces a new field for struct _pciDevice, (const char *used_by),
     it will be set as the domain name at preparation period,
     (qemuPrepareHostdevPCIDevices). Thus we can prohibit deleting
     the device from driver->activePciHostdevs if it's still used by
     other domain when stopping the domain process.

* src/pci.h (define two internal functions, pciDeviceSetUsedBy and
    pciDevceGetUsedBy)
* src/pci.c (new field "const char *used_by" for struct _pciDevice,
    implementations for the two new functions)
* src/libvirt_private.syms (Add the two new internal functions)
* src/qemu_hostdev.h (Modify the definition of functions
    qemuPrepareHostdevPCIDevices, and qemuDomainReAttachHostdevDevices)
* src/qemu_hostdev.c (Prohibit preparation and don't delete the
    device from activePciHostdevs list if it's still used by other domain)
* src/qemu_hotplug.c (Update function usage, as the definitions are
    changed)

Signed-off-by: Eric Blake <eblake@redhat.com>

diff --git a/src/libvirt_private.syms b/src/libvirt_private.syms
index 189c5975fd10d36a536ffb0789fbe0db85d012b6..1e03e3376f79acc1d1799d770d0b698a573788b9 100644 (file)
--- a/src/libvirt_private.syms
+++ b/src/libvirt_private.syms
@@ -881,6 +881,8 @@ virNWFilterHashTableRemoveEntry;
 pciDettachDevice;
 pciDeviceFileIterate;
 pciDeviceGetManaged;
+pciDeviceGetName;
+pciDeviceGetUsedBy;
 pciDeviceIsAssignable;
 pciDeviceIsVirtualFunction;
 pciDeviceListAdd;
@@ -893,6 +895,7 @@ pciDeviceListSteal;
 pciDeviceNetName;
 pciDeviceReAttachInit;
 pciDeviceSetManaged;
+pciDeviceSetUsedBy;
 pciFreeDevice;
 pciGetDevice;
 pciGetPhysicalFunction;

diff --git a/src/qemu/qemu_hostdev.c b/src/qemu/qemu_hostdev.c
index 6f77717dd8c62652e8d124048cd468b6149da30c..c82c5124db83b35aad97d809c1a58cf78eff91fd 100644 (file)
--- a/src/qemu/qemu_hostdev.c
+++ b/src/qemu/qemu_hostdev.c
@@ -1,7 +1,7 @@
 /*
  * qemu_hostdev.c: QEMU hostdev management
  *
- * Copyright (C) 2006-2007, 2009-2010 Red Hat, Inc.
+ * Copyright (C) 2006-2007, 2009-2011 Red Hat, Inc.
  * Copyright (C) 2006 Daniel P. Berrange
  *
  * This library is free software; you can redistribute it and/or
@@ -101,6 +101,7 @@ cleanup:
 
 
 int qemuPrepareHostdevPCIDevices(struct qemud_driver *driver,
+                                 const char *name,
                                  virDomainHostdevDefPtr *hostdevs,
                                  int nhostdevs)
 {
@@ -111,37 +112,63 @@ int qemuPrepareHostdevPCIDevices(struct qemud_driver *driver,
     if (!(pcidevs = qemuGetPciHostDeviceList(hostdevs, nhostdevs)))
         return -1;
 
-    /* We have to use 4 loops here. *All* devices must
+    /* We have to use 6 loops here. *All* devices must
      * be detached before we reset any of them, because
      * in some cases you have to reset the whole PCI,
      * which impacts all devices on it. Also, all devices
      * must be reset before being marked as active.
      */
 
-    /* XXX validate that non-managed device isn't in use, eg
+    /* Loop 1: validate that non-managed device isn't in use, eg
      * by checking that device is either un-bound, or bound
      * to pci-stub.ko
      */
 
     for (i = 0; i < pciDeviceListCount(pcidevs); i++) {
         pciDevice *dev = pciDeviceListGet(pcidevs, i);
-        if (!pciDeviceIsAssignable(dev, !driver->relaxedACS))
-            goto reattachdevs;
+        pciDevice *other;
 
+        if (!pciDeviceIsAssignable(dev, !driver->relaxedACS)) {
+            qemuReportError(VIR_ERR_OPERATION_INVALID,
+                            _("PCI device %s is not assignable"),
+                            pciDeviceGetName(dev));
+            goto cleanup;
+        }
+        /* The device is in use by other active domain if
+         * the dev is in list driver->activePciHostdevs.
+         */
+        if ((other = pciDeviceListFind(driver->activePciHostdevs, dev))) {
+            const char *other_name = pciDeviceGetUsedBy(other);
+
+            if (other_name)
+                qemuReportError(VIR_ERR_OPERATION_INVALID,
+                                _("PCI device %s is in use by domain %s"),
+                                pciDeviceGetName(dev), other_name);
+            else
+                qemuReportError(VIR_ERR_OPERATION_INVALID,
+                                _("PCI device %s is already in use"),
+                                pciDeviceGetName(dev));
+            goto cleanup;
+        }
+    }
+
+    /* Loop 2: detach managed devices */
+    for (i = 0; i < pciDeviceListCount(pcidevs); i++) {
+        pciDevice *dev = pciDeviceListGet(pcidevs, i);
         if (pciDeviceGetManaged(dev) &&
             pciDettachDevice(dev, driver->activePciHostdevs) < 0)
             goto reattachdevs;
     }
 
-    /* Now that all the PCI hostdevs have be dettached, we can safely
-     * reset them */
+    /* Loop 3: Now that all the PCI hostdevs have been detached, we
+     * can safely reset them */
     for (i = 0; i < pciDeviceListCount(pcidevs); i++) {
         pciDevice *dev = pciDeviceListGet(pcidevs, i);
         if (pciResetDevice(dev, driver->activePciHostdevs, pcidevs) < 0)
             goto reattachdevs;
     }
 
-    /* Now mark all the devices as active */
+    /* Loop 4: Now mark all the devices as active */
     for (i = 0; i < pciDeviceListCount(pcidevs); i++) {
         pciDevice *dev = pciDeviceListGet(pcidevs, i);
         if (pciDeviceListAdd(driver->activePciHostdevs, dev) < 0) {
@@ -150,7 +177,19 @@ int qemuPrepareHostdevPCIDevices(struct qemud_driver *driver,
         }
     }
 
-    /* Now steal all the devices from pcidevs */
+    /* Loop 5: Now set the used_by_domain of the device in
+     * driver->activePciHostdevs as domain name.
+     */
+    for (i = 0; i < pciDeviceListCount(pcidevs); i++) {
+        pciDevice *dev, *activeDev;
+
+        dev = pciDeviceListGet(pcidevs, i);
+        activeDev = pciDeviceListFind(driver->activePciHostdevs, dev);
+
+        pciDeviceSetUsedBy(activeDev, name);
+    }
+
+    /* Loop 6: Now steal all the devices from pcidevs */
     while (pciDeviceListCount(pcidevs) > 0) {
         pciDevice *dev = pciDeviceListGet(pcidevs, 0);
         pciDeviceListSteal(pcidevs, dev);
@@ -183,7 +222,7 @@ static int
 qemuPrepareHostPCIDevices(struct qemud_driver *driver,
                           virDomainDefPtr def)
 {
-    return qemuPrepareHostdevPCIDevices(driver, def->hostdevs, def->nhostdevs);
+    return qemuPrepareHostdevPCIDevices(driver, def->name, def->hostdevs, def->nhostdevs);
 }
 
 
@@ -258,6 +297,7 @@ void qemuReattachPciDevice(pciDevice *dev, struct qemud_driver *driver)
 
 
 void qemuDomainReAttachHostdevDevices(struct qemud_driver *driver,
+                                      const char *name,
                                       virDomainHostdevDefPtr *hostdevs,
                                       int nhostdevs)
 {
@@ -277,6 +317,16 @@ void qemuDomainReAttachHostdevDevices(struct qemud_driver *driver,
 
     for (i = 0; i < pciDeviceListCount(pcidevs); i++) {
         pciDevice *dev = pciDeviceListGet(pcidevs, i);
+        pciDevice *activeDev = NULL;
+
+        /* Never delete the dev from list driver->activePciHostdevs
+         * if it's used by other domain.
+         */
+        activeDev = pciDeviceListFind(driver->activePciHostdevs, dev);
+        if (activeDev &&
+            STRNEQ_NULLABLE(name, pciDeviceGetUsedBy(activeDev)))
+            continue;
+
         pciDeviceListDel(driver->activePciHostdevs, dev);
     }
 
@@ -305,5 +355,5 @@ void qemuDomainReAttachHostDevices(struct qemud_driver *driver,
     if (!def->nhostdevs)
         return;
 
-    qemuDomainReAttachHostdevDevices(driver, def->hostdevs, def->nhostdevs);
+    qemuDomainReAttachHostdevDevices(driver, def->name, def->hostdevs, def->nhostdevs);
 }

diff --git a/src/qemu/qemu_hostdev.h b/src/qemu/qemu_hostdev.h
index 1f3d1bc16e17b4f474833e29e2bf7c4350abd9de..07d7de27a20c25c36391c75c5bf5819a5f42acaa 100644 (file)
--- a/src/qemu/qemu_hostdev.h
+++ b/src/qemu/qemu_hostdev.h
@@ -30,12 +30,14 @@
 int qemuUpdateActivePciHostdevs(struct qemud_driver *driver,
                                 virDomainDefPtr def);
 int qemuPrepareHostdevPCIDevices(struct qemud_driver *driver,
+                                 const char *name,
                                  virDomainHostdevDefPtr *hostdevs,
                                  int nhostdevs);
 int qemuPrepareHostDevices(struct qemud_driver *driver,
                            virDomainDefPtr def);
 void qemuReattachPciDevice(pciDevice *dev, struct qemud_driver *driver);
 void qemuDomainReAttachHostdevDevices(struct qemud_driver *driver,
+                                      const char *name,
                                       virDomainHostdevDefPtr *hostdevs,
                                       int nhostdevs);
 void qemuDomainReAttachHostDevices(struct qemud_driver *driver,

diff --git a/src/qemu/qemu_hotplug.c b/src/qemu/qemu_hotplug.c
index 4c1705deb7c23cde843b6ba6b321fc97d489d5e1..bfa524b9b486dbf1038ca9c991d6f4fdd73811d4 100644 (file)
--- a/src/qemu/qemu_hotplug.c
+++ b/src/qemu/qemu_hotplug.c
@@ -893,7 +893,7 @@ int qemuDomainAttachHostPciDevice(struct qemud_driver *driver,
         return -1;
     }
 
-    if (qemuPrepareHostdevPCIDevices(driver, &hostdev, 1) < 0)
+    if (qemuPrepareHostdevPCIDevices(driver, vm->def->name, &hostdev, 1) < 0)
         return -1;
 
     if (qemuCapsGet(priv->qemuCaps, QEMU_CAPS_DEVICE)) {
@@ -959,7 +959,7 @@ error:
                                         hostdev->info.addr.pci.slot) < 0)
         VIR_WARN("Unable to release PCI address on host device");
 
-    qemuDomainReAttachHostdevDevices(driver, &hostdev, 1);
+    qemuDomainReAttachHostdevDevices(driver, vm->def->name, &hostdev, 1);
 
     VIR_FREE(devstr);
     VIR_FREE(configfd_name);

diff --git a/src/util/pci.c b/src/util/pci.c
index 8d8e15727fcc07196fcf0eeb76cc93c165e793f8..2bbb90c0a6e92ad5be4a7ac267d4f56a3a565dd6 100644 (file)
--- a/src/util/pci.c
+++ b/src/util/pci.c
@@ -62,6 +62,7 @@ struct _pciDevice {
     char          name[PCI_ADDR_LEN]; /* domain:bus:slot.function */
     char          id[PCI_ID_LEN];     /* product vendor */
     char          *path;
+    const char    *used_by;           /* The domain which uses the device */
     int           fd;
 
     unsigned      initted;
@@ -1377,6 +1378,12 @@ pciFreeDevice(pciDevice *dev)
     VIR_FREE(dev);
 }
 
+const char *
+pciDeviceGetName(pciDevice *dev)
+{
+    return dev->name;
+}
+
 void pciDeviceSetManaged(pciDevice *dev, unsigned managed)
 {
     dev->managed = !!managed;
@@ -1387,6 +1394,18 @@ unsigned pciDeviceGetManaged(pciDevice *dev)
     return dev->managed;
 }
 
+void
+pciDeviceSetUsedBy(pciDevice *dev, const char *name)
+{
+    dev->used_by = name;
+}
+
+const char *
+pciDeviceGetUsedBy(pciDevice *dev)
+{
+    return dev->used_by;
+}
+
 void pciDeviceReAttachInit(pciDevice *pci)
 {
     pci->unbind_from_stub = 1;

diff --git a/src/util/pci.h b/src/util/pci.h
index a1600fe1fd5276a0a7beaf41320c96f0f565425a..ab29c0bfeaf763b1d74c87c4cab92a609c731bdb 100644 (file)
--- a/src/util/pci.h
+++ b/src/util/pci.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2009 Red Hat, Inc.
+ * Copyright (C) 2009, 2011 Red Hat, Inc.
  *
  * This library is free software; you can redistribute it and/or
  * modify it under the terms of the GNU Lesser General Public
@@ -39,6 +39,7 @@ pciDevice *pciGetDevice      (unsigned       domain,
                               unsigned       slot,
                               unsigned       function);
 void       pciFreeDevice     (pciDevice     *dev);
+const char *pciDeviceGetName (pciDevice     *dev);
 int        pciDettachDevice  (pciDevice     *dev, pciDeviceList *activeDevs);
 int        pciReAttachDevice (pciDevice     *dev, pciDeviceList *activeDevs);
 int        pciResetDevice    (pciDevice     *dev,
@@ -47,6 +48,9 @@ int        pciResetDevice    (pciDevice     *dev,
 void      pciDeviceSetManaged(pciDevice     *dev,
                               unsigned       managed);
 unsigned  pciDeviceGetManaged(pciDevice     *dev);
+void      pciDeviceSetUsedBy(pciDevice     *dev,
+                             const char *used_by);
+const char *pciDeviceGetUsedBy(pciDevice   *dev);
 void      pciDeviceReAttachInit(pciDevice   *dev);
 
 pciDeviceList *pciDeviceListNew  (void);