Pass pre-opened PCI device sysfs config file to QEMU

This allows libvirt to open the PCI device sysfs config file prior
to dropping privileges so qemu can access the full config space.
Without this, a de-privileged qemu can only access the first 64
bytes of config space.

* src/qemu/qemu_conf.c, src/qemu/qemu_conf.h: Detect support
  for pci-assign.configfd option. Use this option when formatting
  PCI device string if possible
* src/qemu/qemu_driver.c: Pre-open PCI sysfs config file and pass
  to QEMU

diff --git a/src/qemu/qemu_conf.c b/src/qemu/qemu_conf.c
index 08d811b18ffd0578e5cf3c422b289ddcb1a037af..66a949e6e43fd00675daf4c0fed7262c4f36e266 100644 (file)
--- a/src/qemu/qemu_conf.c
+++ b/src/qemu/qemu_conf.c
@@ -1354,6 +1354,48 @@ fail:
     return -1;
 }
 
+static void qemudParsePCIDeviceStrs(const char *qemu, unsigned long long *flags)
+{
+    const char *const qemuarg[] = { qemu, "-device", "pci-assign,?", NULL };
+    const char *const qemuenv[] = { "LC_ALL=C", NULL };
+    pid_t child;
+    int status;
+    int newstderr = -1;
+
+    if (virExec(qemuarg, qemuenv, NULL,
+                &child, -1, NULL, &newstderr, VIR_EXEC_CLEAR_CAPS) < 0)
+        return;
+
+    char *pciassign = NULL;
+    enum { MAX_PCI_OUTPUT_SIZE = 1024*4 };
+    int len = virFileReadLimFD(newstderr, MAX_PCI_OUTPUT_SIZE, &pciassign);
+    if (len < 0) {
+        virReportSystemError(errno,
+                             _("Unable to read %s pci-assign device output"),
+                             qemu);
+        goto cleanup;
+    }
+
+    if (strstr(pciassign, "pci-assign.configfd"))
+        *flags |= QEMUD_CMD_FLAG_PCI_CONFIGFD;
+
+cleanup:
+    VIR_FREE(pciassign);
+    close(newstderr);
+rewait:
+    if (waitpid(child, &status, 0) != child) {
+        if (errno == EINTR)
+            goto rewait;
+
+        VIR_ERROR(_("Unexpected exit status from qemu %d pid %lu"),
+                  WEXITSTATUS(status), (unsigned long)child);
+    }
+    if (WEXITSTATUS(status) != 0) {
+        VIR_WARN("Unexpected exit status '%d', qemu probably failed",
+                 WEXITSTATUS(status));
+    }
+}
+
 int qemudExtractVersionInfo(const char *qemu,
                             unsigned int *retversion,
                             unsigned long long *retflags) {
@@ -1387,6 +1429,9 @@ int qemudExtractVersionInfo(const char *qemu,
                           &version, &is_kvm, &kvm_version) == -1)
         goto cleanup2;
 
+    if (flags & QEMUD_CMD_FLAG_DEVICE)
+        qemudParsePCIDeviceStrs(qemu, &flags);
+
     if (retversion)
         *retversion = version;
     if (retflags)
@@ -2896,8 +2941,33 @@ error:
 }
 
 
+int
+qemudOpenPCIConfig(virDomainHostdevDefPtr dev)
+{
+    char *path = NULL;
+    int configfd = -1;
+
+    if (virAsprintf(&path, "/sys/bus/pci/devices/%04x:%02x:%02x.%01x/config",
+                    dev->source.subsys.u.pci.domain,
+                    dev->source.subsys.u.pci.bus,
+                    dev->source.subsys.u.pci.slot,
+                    dev->source.subsys.u.pci.function) < 0) {
+        virReportOOMError();
+        return -1;
+    }
+
+    configfd = open(path, O_RDWR, 0);
+
+    if (configfd < 0)
+        virReportSystemError(errno, _("Failed opening %s"), path);
+
+    VIR_FREE(path);
+
+    return configfd;
+}
+
 char *
-qemuBuildPCIHostdevDevStr(virDomainHostdevDefPtr dev)
+qemuBuildPCIHostdevDevStr(virDomainHostdevDefPtr dev, const char *configfd)
 {
     virBuffer buf = VIR_BUFFER_INITIALIZER;
 
@@ -2907,6 +2977,8 @@ qemuBuildPCIHostdevDevStr(virDomainHostdevDefPtr dev)
                       dev->source.subsys.u.pci.slot,
                       dev->source.subsys.u.pci.function);
     virBufferVSprintf(&buf, ",id=%s", dev->info.alias);
+    if (configfd && *configfd)
+        virBufferVSprintf(&buf, ",configfd=%s", configfd);
     if (qemuBuildDeviceAddressStr(&buf, &dev->info) < 0)
         goto error;
 
@@ -4611,8 +4683,30 @@ int qemudBuildCommandLine(virConnectPtr conn,
         if (hostdev->mode == VIR_DOMAIN_HOSTDEV_MODE_SUBSYS &&
             hostdev->source.subsys.type == VIR_DOMAIN_HOSTDEV_SUBSYS_TYPE_PCI) {
             if (qemuCmdFlags & QEMUD_CMD_FLAG_DEVICE) {
+                char *configfd_name = NULL;
+                if (qemuCmdFlags & QEMUD_CMD_FLAG_PCI_CONFIGFD) {
+                    int configfd = qemudOpenPCIConfig(hostdev);
+
+                    if (configfd >= 0) {
+                        if (virAsprintf(&configfd_name, "%d", configfd) < 0) {
+                            close(configfd);
+                            virReportOOMError();
+                            goto no_memory;
+                        }
+
+                        if (VIR_REALLOC_N(*vmfds, (*nvmfds)+1) < 0) {
+                            VIR_FREE(configfd_name);
+                            close(configfd);
+                            goto no_memory;
+                        }
+
+                        (*vmfds)[(*nvmfds)++] = configfd;
+                    }
+                }
                 ADD_ARG_LIT("-device");
-                if (!(devstr = qemuBuildPCIHostdevDevStr(hostdev)))
+                devstr = qemuBuildPCIHostdevDevStr(hostdev, configfd_name);
+                VIR_FREE(configfd_name);
+                if (!devstr)
                     goto error;
                 ADD_ARG(devstr);
             } else if (qemuCmdFlags & QEMUD_CMD_FLAG_PCIDEVICE) {

diff --git a/src/qemu/qemu_conf.h b/src/qemu/qemu_conf.h
index 516a59bd0859fd4215e7367c7178b2c7d7260b85..7616d151b21f57453e6085ed91f0291b2d75ce86 100644 (file)
--- a/src/qemu/qemu_conf.h
+++ b/src/qemu/qemu_conf.h
@@ -89,6 +89,7 @@ enum qemud_cmd_flags {
     QEMUD_CMD_FLAG_NO_HPET       = (1LL << 33), /* -no-hpet flag is supported */
     QEMUD_CMD_FLAG_NO_KVM_PIT    = (1LL << 34), /* -no-kvm-pit-reinjection supported */
     QEMUD_CMD_FLAG_TDF           = (1LL << 35), /* -tdf flag (user-mode pit catchup) */
+    QEMUD_CMD_FLAG_PCI_CONFIGFD  = (1LL << 36), /* pci-assign.configfd */
 };
 
 /* Main driver state */
@@ -247,7 +248,10 @@ char * qemuBuildSoundDevStr(virDomainSoundDefPtr sound);
 /* Legacy, pre device support */
 char * qemuBuildPCIHostdevPCIDevStr(virDomainHostdevDefPtr dev);
 /* Current, best practice */
-char * qemuBuildPCIHostdevDevStr(virDomainHostdevDefPtr dev);
+char * qemuBuildPCIHostdevDevStr(virDomainHostdevDefPtr dev,
+                                 const char *configfd);
+
+int qemudOpenPCIConfig(virDomainHostdevDefPtr dev);
 
 /* Current, best practice */
 char * qemuBuildChrChardevStr(virDomainChrDefPtr dev);

diff --git a/src/qemu/qemu_driver.c b/src/qemu/qemu_driver.c
index 3b2b0d8dff5761c4e4fb0f5935bd1f06f6634108..76ec3bf5e2ca9b7d1e80a1816b541be7efa1a35c 100644 (file)
--- a/src/qemu/qemu_driver.c
+++ b/src/qemu/qemu_driver.c
@@ -7658,6 +7658,8 @@ static int qemudDomainAttachHostPciDevice(struct qemud_driver *driver,
     pciDevice *pci;
     int ret;
     char *devstr = NULL;
+    int configfd = -1;
+    char *configfd_name = NULL;
 
     if (VIR_REALLOC_N(vm->def->hostdevs, vm->def->nhostdevs+1) < 0) {
         virReportOOMError();
@@ -7688,8 +7690,32 @@ static int qemudDomainAttachHostPciDevice(struct qemud_driver *driver,
             goto error;
         if (qemuDomainPCIAddressEnsureAddr(priv->pciaddrs, &hostdev->info) < 0)
             goto error;
+        if (qemuCmdFlags & QEMUD_CMD_FLAG_PCI_CONFIGFD) {
+            configfd = qemudOpenPCIConfig(hostdev);
+            if (configfd >= 0) {
+                if (virAsprintf(&configfd_name, "fd-%s",
+                                hostdev->info.alias) < 0) {
+                    virReportOOMError();
+                    goto error;
+                }
+
+                qemuDomainObjEnterMonitorWithDriver(driver, vm);
+                if (qemuMonitorSendFileHandle(priv->mon, configfd_name,
+                                              configfd) < 0) {
+                    qemuDomainObjExitMonitorWithDriver(driver, vm);
+                    goto error;
+                }
+                qemuDomainObjExitMonitorWithDriver(driver, vm);
+            }
+        }
+
+        if (!virDomainObjIsActive(vm)) {
+            qemuReportError(VIR_ERR_INTERNAL_ERROR, "%s",
+                            _("guest unexpectedly quit during hotplug"));
+            goto error;
+        }
 
-        if (!(devstr = qemuBuildPCIHostdevDevStr(hostdev)))
+        if (!(devstr = qemuBuildPCIHostdevDevStr(hostdev, configfd_name)))
             goto error;
 
         qemuDomainObjEnterMonitorWithDriver(driver, vm);
@@ -7713,6 +7739,9 @@ static int qemudDomainAttachHostPciDevice(struct qemud_driver *driver,
     vm->def->hostdevs[vm->def->nhostdevs++] = hostdev;
 
     VIR_FREE(devstr);
+    VIR_FREE(configfd_name);
+    if (configfd >= 0)
+        close(configfd);
 
     return 0;
 
@@ -7724,6 +7753,9 @@ error:
 
     VIR_FREE(devstr);
     pciDeviceListDel(driver->activePciHostdevs, pci);
+    VIR_FREE(configfd_name);
+    if (configfd >= 0)
+        close(configfd);
 
     return -1;
 }