/**
* virNetDevMacVLanReserveID:
*
* @id: id 0 - MACVLAN_MAX_ID+1 to reserve (or -1 for "first free")
* @flags: set VIR_NETDEV_MACVLAN_CREATE_WITH_TAP for macvtapN else macvlanN
* @quietFail: don't log an error if this name is already in-use
* @nextFree: reserve the next free ID *after* @id rather than @id itself
*
* Reserve the indicated ID in the appropriate bitmap, or find the
* first free ID if @id is -1.
*
* Returns newly reserved ID# on success, or -1 to indicate failure.
*/
static int
virNetDevMacVLanReserveID(int id, unsigned int flags,
bool quietFail, bool nextFree)
{
virBitmapPtr bitmap;
if (virNetDevMacVLanInitialize() < 0)
return -1;
bitmap = (flags & VIR_NETDEV_MACVLAN_CREATE_WITH_TAP) ?
macvtapIDs : macvlanIDs;
if (id > MACVLAN_MAX_ID) {
virReportError(VIR_ERR_INTERNAL_ERROR,
_("can't use name %s%d - out of range 0-%d"),
(flags & VIR_NETDEV_MACVLAN_CREATE_WITH_TAP) ?
MACVTAP_NAME_PREFIX : MACVLAN_NAME_PREFIX,
id, MACVLAN_MAX_ID);
return -1;
}
if ((id < 0 || nextFree) &&
(id = virBitmapNextClearBit(bitmap, id)) < 0) {
virReportError(VIR_ERR_INTERNAL_ERROR,
_("no unused %s names available"),
(flags & VIR_NETDEV_MACVLAN_CREATE_WITH_TAP) ?
MACVTAP_NAME_PREFIX : MACVLAN_NAME_PREFIX);
return -1;
}
if (virBitmapIsBitSet(bitmap, id)) {
if (quietFail) {
VIR_INFO("couldn't reserve name %s%d - already in use",
(flags & VIR_NETDEV_MACVLAN_CREATE_WITH_TAP) ?
MACVTAP_NAME_PREFIX : MACVLAN_NAME_PREFIX, id);
} else {
virReportError(VIR_ERR_INTERNAL_ERROR,
_("couldn't reserve name %s%d - already in use"),
(flags & VIR_NETDEV_MACVLAN_CREATE_WITH_TAP) ?
MACVTAP_NAME_PREFIX : MACVLAN_NAME_PREFIX, id);
}
return -1;
}
if (virBitmapSetBit(bitmap, id) < 0) {
virReportError(VIR_ERR_INTERNAL_ERROR,
_("couldn't mark %s%d as used"),
(flags & VIR_NETDEV_MACVLAN_CREATE_WITH_TAP) ?
MACVTAP_NAME_PREFIX : MACVLAN_NAME_PREFIX, id);
return -1;
}
VIR_INFO("reserving device %s%d",
(flags & VIR_NETDEV_MACVLAN_CREATE_WITH_TAP) ?
MACVTAP_NAME_PREFIX : MACVLAN_NAME_PREFIX, id);
return id;
}
bool
virNumaNodeIsAvailable(int node)
{
bool ret = false;
virBitmapPtr map = NULL;
if (virFileReadValueBitmap(&map, "%s/node/online", SYSFS_SYSTEM_PATH) < 0)
return false;
ret = virBitmapIsBitSet(map, node);
virBitmapFree(map);
return ret;
}
int
virPortAllocatorAcquire(const virPortAllocatorRange *range,
unsigned short *port)
{
int ret = -1;
size_t i;
virPortAllocatorPtr pa = virPortAllocatorGet();
*port = 0;
if (!pa)
return -1;
virObjectLock(pa);
for (i = range->start; i <= range->end && !*port; i++) {
bool used = false, v6used = false;
if (virBitmapIsBitSet(pa->bitmap, i))
continue;
if (virPortAllocatorBindToPort(&v6used, i, AF_INET6) < 0 ||
virPortAllocatorBindToPort(&used, i, AF_INET) < 0)
goto cleanup;
if (!used && !v6used) {
/* Add port to bitmap of reserved ports */
if (virBitmapSetBit(pa->bitmap, i) < 0) {
virReportError(VIR_ERR_INTERNAL_ERROR,
_("Failed to reserve port %zu"), i);
goto cleanup;
}
*port = i;
ret = 0;
}
}
if (*port == 0) {
virReportError(VIR_ERR_INTERNAL_ERROR,
_("Unable to find an unused port in range '%s' (%d-%d)"),
range->name, range->start, range->end);
}
cleanup:
virObjectUnlock(pa);
return ret;
}
int virProcessSetAffinity(pid_t pid,
virBitmapPtr map)
{
size_t i;
cpuset_t mask;
CPU_ZERO(&mask);
for (i = 0; i < virBitmapSize(map); i++) {
if (virBitmapIsBitSet(map, i))
CPU_SET(i, &mask);
}
if (cpuset_setaffinity(CPU_LEVEL_WHICH, CPU_WHICH_PID, pid,
sizeof(mask), &mask) != 0) {
virReportSystemError(errno,
_("cannot set CPU affinity on process %d"), pid);
return -1;
}
return 0;
}
int
virPortAllocatorSetUsed(unsigned short port)
{
int ret = -1;
virPortAllocatorPtr pa = virPortAllocatorGet();
if (!pa)
return -1;
virObjectLock(pa);
if (virBitmapIsBitSet(pa->bitmap, port) ||
virBitmapSetBit(pa->bitmap, port) < 0) {
virReportError(VIR_ERR_INTERNAL_ERROR,
_("Failed to reserve port %d"), port);
goto cleanup;
}
ret = 0;
cleanup:
virObjectUnlock(pa);
return ret;
}
/**
* virNetDevMacVLanReleaseID:
* @id: id 0 - MACVLAN_MAX_ID+1 to release
*
* Returns 0 for success or -1 for failure.
*/
static int
virNetDevMacVLanReleaseID(int id, unsigned int flags)
{
virBitmapPtr bitmap;
if (virNetDevMacVLanInitialize() < 0)
return 0;
bitmap = (flags & VIR_NETDEV_MACVLAN_CREATE_WITH_TAP) ?
macvtapIDs : macvlanIDs;
if (id > MACVLAN_MAX_ID) {
virReportError(VIR_ERR_INTERNAL_ERROR,
_("can't free name %s%d - out of range 0-%d"),
(flags & VIR_NETDEV_MACVLAN_CREATE_WITH_TAP) ?
MACVTAP_NAME_PREFIX : MACVLAN_NAME_PREFIX,
id, MACVLAN_MAX_ID);
return -1;
}
if (id < 0)
return 0;
VIR_INFO("releasing %sdevice %s%d",
virBitmapIsBitSet(bitmap, id) ? "" : "unreserved",
(flags & VIR_NETDEV_MACVLAN_CREATE_WITH_TAP) ?
MACVTAP_NAME_PREFIX : MACVLAN_NAME_PREFIX, id);
if (virBitmapClearBit(bitmap, id) < 0) {
virReportError(VIR_ERR_INTERNAL_ERROR,
_("couldn't mark %s%d as unused"),
(flags & VIR_NETDEV_MACVLAN_CREATE_WITH_TAP) ?
MACVTAP_NAME_PREFIX : MACVLAN_NAME_PREFIX, id);
return -1;
}
return 0;
}
int virProcessSetAffinity(pid_t pid, virBitmapPtr map)
{
size_t i;
VIR_DEBUG("Set process affinity on %lld\n", (long long)pid);
# ifdef CPU_ALLOC
/* New method dynamically allocates cpu mask, allowing unlimted cpus */
int numcpus = 1024;
size_t masklen;
cpu_set_t *mask;
/* Not only may the statically allocated cpu_set_t be too small,
* but there is no way to ask the kernel what size is large enough.
* So you have no option but to pick a size, try, catch EINVAL,
* enlarge, and re-try.
*
* http://lkml.org/lkml/2009/7/28/620
*/
realloc:
masklen = CPU_ALLOC_SIZE(numcpus);
mask = CPU_ALLOC(numcpus);
if (!mask) {
virReportOOMError();
return -1;
}
CPU_ZERO_S(masklen, mask);
for (i = 0; i < virBitmapSize(map); i++) {
if (virBitmapIsBitSet(map, i))
CPU_SET_S(i, masklen, mask);
}
if (sched_setaffinity(pid, masklen, mask) < 0) {
CPU_FREE(mask);
if (errno == EINVAL &&
numcpus < (1024 << 8)) { /* 262144 cpus ought to be enough for anyone */
numcpus = numcpus << 2;
goto realloc;
}
virReportSystemError(errno,
_("cannot set CPU affinity on process %d"), pid);
return -1;
}
CPU_FREE(mask);
# else
/* Legacy method uses a fixed size cpu mask, only allows up to 1024 cpus */
cpu_set_t mask;
CPU_ZERO(&mask);
for (i = 0; i < virBitmapSize(map); i++) {
if (virBitmapIsBitSet(map, i))
CPU_SET(i, &mask);
}
if (sched_setaffinity(pid, sizeof(mask), &mask) < 0) {
virReportSystemError(errno,
_("cannot set CPU affinity on process %d"), pid);
return -1;
}
# endif
return 0;
}
bool
dnsmasqCapsGet(dnsmasqCapsPtr caps, dnsmasqCapsFlags flag)
{
return caps && virBitmapIsBitSet(caps->flags, flag);
}
virHostCPUParseNode(const char *node,
virArch arch,
virBitmapPtr present_cpus_map,
virBitmapPtr online_cpus_map,
int threads_per_subcore,
int *sockets,
int *cores,
int *threads,
int *offline)
{
/* Biggest value we can expect to be used as either socket id
* or core id. Bitmaps will need to be sized accordingly */
const int ID_MAX = 4095;
int ret = -1;
int processors = 0;
DIR *cpudir = NULL;
struct dirent *cpudirent = NULL;
virBitmapPtr node_cpus_map = NULL;
virBitmapPtr sockets_map = NULL;
virBitmapPtr *cores_maps = NULL;
int npresent_cpus = virBitmapSize(present_cpus_map);
int sock_max = 0;
int sock;
int core;
size_t i;
int siblings;
unsigned int cpu;
int direrr;
*threads = 0;
*cores = 0;
*sockets = 0;
if (!(cpudir = opendir(node))) {
virReportSystemError(errno, _("cannot opendir %s"), node);
goto cleanup;
}
/* Keep track of the CPUs that belong to the current node */
if (!(node_cpus_map = virBitmapNew(npresent_cpus)))
goto cleanup;
/* enumerate sockets in the node */
if (!(sockets_map = virBitmapNew(ID_MAX + 1)))
goto cleanup;
while ((direrr = virDirRead(cpudir, &cpudirent, node)) > 0) {
if (sscanf(cpudirent->d_name, "cpu%u", &cpu) != 1)
continue;
if (!virBitmapIsBitSet(present_cpus_map, cpu))
continue;
/* Mark this CPU as part of the current node */
if (virBitmapSetBit(node_cpus_map, cpu) < 0)
goto cleanup;
if (!virBitmapIsBitSet(online_cpus_map, cpu))
continue;
/* Parse socket */
if ((sock = virHostCPUParseSocket(node, arch, cpu)) < 0)
goto cleanup;
if (sock > ID_MAX) {
virReportError(VIR_ERR_INTERNAL_ERROR,
_("Socket %d can't be handled (max socket is %d)"),
sock, ID_MAX);
goto cleanup;
}
if (virBitmapSetBit(sockets_map, sock) < 0)
goto cleanup;
if (sock > sock_max)
sock_max = sock;
}
if (direrr < 0)
goto cleanup;
sock_max++;
/* allocate cores maps for each socket */
if (VIR_ALLOC_N(cores_maps, sock_max) < 0)
goto cleanup;
for (i = 0; i < sock_max; i++)
if (!(cores_maps[i] = virBitmapNew(ID_MAX + 1)))
goto cleanup;
/* Iterate over all CPUs in the node, in ascending order */
for (cpu = 0; cpu < npresent_cpus; cpu++) {
/* Skip CPUs that are not part of the current node */
if (!virBitmapIsBitSet(node_cpus_map, cpu))
continue;
if (!virBitmapIsBitSet(online_cpus_map, cpu)) {
if (threads_per_subcore > 0 &&
cpu % threads_per_subcore != 0 &&
virBitmapIsBitSet(online_cpus_map,
cpu - (cpu % threads_per_subcore))) {
/* Secondary offline threads are counted as online when
* subcores are in use and the corresponding primary
* thread is online */
processors++;
} else {
/* But they are counted as offline otherwise */
(*offline)++;
}
continue;
}
processors++;
/* Parse socket */
if ((sock = virHostCPUParseSocket(node, arch, cpu)) < 0)
goto cleanup;
if (!virBitmapIsBitSet(sockets_map, sock)) {
virReportError(VIR_ERR_INTERNAL_ERROR, "%s",
_("CPU socket topology has changed"));
goto cleanup;
}
/* Parse core */
if (ARCH_IS_S390(arch)) {
/* logical cpu is equivalent to a core on s390 */
core = cpu;
} else {
if ((core = virHostCPUGetValue(node, cpu,
"topology/core_id", 0)) < 0)
goto cleanup;
}
if (core > ID_MAX) {
virReportError(VIR_ERR_INTERNAL_ERROR,
_("Core %d can't be handled (max core is %d)"),
core, ID_MAX);
goto cleanup;
}
if (virBitmapSetBit(cores_maps[sock], core) < 0)
goto cleanup;
if (!(siblings = virHostCPUCountThreadSiblings(node, cpu)))
goto cleanup;
if (siblings > *threads)
*threads = siblings;
}
/* finalize the returned data */
*sockets = virBitmapCountBits(sockets_map);
for (i = 0; i < sock_max; i++) {
if (!virBitmapIsBitSet(sockets_map, i))
continue;
core = virBitmapCountBits(cores_maps[i]);
if (core > *cores)
*cores = core;
}
if (threads_per_subcore > 0) {
/* The thread count ignores offline threads, which means that only
* only primary threads have been considered so far. If subcores
* are in use, we need to also account for secondary threads */
*threads *= threads_per_subcore;
}
ret = processors;
cleanup:
/* don't shadow a more serious error */
if (cpudir && closedir(cpudir) < 0 && ret >= 0) {
virReportSystemError(errno, _("problem closing %s"), node);
ret = -1;
}
if (cores_maps)
for (i = 0; i < sock_max; i++)
virBitmapFree(cores_maps[i]);
VIR_FREE(cores_maps);
virBitmapFree(sockets_map);
virBitmapFree(node_cpus_map);
return ret;
}
/* Align def->disks to def->domain. Sort the list of def->disks,
* filling in any missing disks or snapshot state defaults given by
* the domain, with a fallback to a passed in default. Convert paths
* to disk targets for uniformity. Issue an error and return -1 if
* any def->disks[n]->name appears more than once or does not map to
* dom->disks. If require_match, also ensure that there is no
* conflicting requests for both internal and external snapshots. */
int
virDomainSnapshotAlignDisks(virDomainSnapshotDefPtr def,
int default_snapshot,
bool require_match)
{
int ret = -1;
virBitmapPtr map = NULL;
size_t i;
int ndisks;
if (!def->dom) {
virReportError(VIR_ERR_INTERNAL_ERROR, "%s",
_("missing domain in snapshot"));
goto cleanup;
}
if (def->ndisks > def->dom->ndisks) {
virReportError(VIR_ERR_CONFIG_UNSUPPORTED, "%s",
_("too many disk snapshot requests for domain"));
goto cleanup;
}
/* Unlikely to have a guest without disks but technically possible. */
if (!def->dom->ndisks) {
ret = 0;
goto cleanup;
}
if (!(map = virBitmapNew(def->dom->ndisks)))
goto cleanup;
/* Double check requested disks. */
for (i = 0; i < def->ndisks; i++) {
virDomainSnapshotDiskDefPtr disk = &def->disks[i];
int idx = virDomainDiskIndexByName(def->dom, disk->name, false);
int disk_snapshot;
if (idx < 0) {
virReportError(VIR_ERR_CONFIG_UNSUPPORTED,
_("no disk named '%s'"), disk->name);
goto cleanup;
}
if (virBitmapIsBitSet(map, idx)) {
virReportError(VIR_ERR_CONFIG_UNSUPPORTED,
_("disk '%s' specified twice"),
disk->name);
goto cleanup;
}
ignore_value(virBitmapSetBit(map, idx));
disk->index = idx;
disk_snapshot = def->dom->disks[idx]->snapshot;
if (!disk->snapshot) {
if (disk_snapshot &&
(!require_match ||
disk_snapshot == VIR_DOMAIN_SNAPSHOT_LOCATION_NONE))
disk->snapshot = disk_snapshot;
else
disk->snapshot = default_snapshot;
} else if (require_match &&
disk->snapshot != default_snapshot &&
!(disk->snapshot == VIR_DOMAIN_SNAPSHOT_LOCATION_NONE &&
disk_snapshot == VIR_DOMAIN_SNAPSHOT_LOCATION_NONE)) {
const char *tmp;
tmp = virDomainSnapshotLocationTypeToString(default_snapshot);
virReportError(VIR_ERR_CONFIG_UNSUPPORTED,
_("disk '%s' must use snapshot mode '%s'"),
disk->name, tmp);
goto cleanup;
}
if (disk->src->path &&
disk->snapshot != VIR_DOMAIN_SNAPSHOT_LOCATION_EXTERNAL) {
virReportError(VIR_ERR_CONFIG_UNSUPPORTED,
_("file '%s' for disk '%s' requires "
"use of external snapshot mode"),
disk->src->path, disk->name);
goto cleanup;
}
if (STRNEQ(disk->name, def->dom->disks[idx]->dst)) {
VIR_FREE(disk->name);
if (VIR_STRDUP(disk->name, def->dom->disks[idx]->dst) < 0)
goto cleanup;
}
}
/* Provide defaults for all remaining disks. */
ndisks = def->ndisks;
if (VIR_EXPAND_N(def->disks, def->ndisks,
def->dom->ndisks - def->ndisks) < 0)
goto cleanup;
for (i = 0; i < def->dom->ndisks; i++) {
virDomainSnapshotDiskDefPtr disk;
if (virBitmapIsBitSet(map, i))
continue;
disk = &def->disks[ndisks++];
if (VIR_ALLOC(disk->src) < 0)
goto cleanup;
if (VIR_STRDUP(disk->name, def->dom->disks[i]->dst) < 0)
goto cleanup;
disk->index = i;
/* Don't snapshot empty drives */
if (virStorageSourceIsEmpty(def->dom->disks[i]->src))
disk->snapshot = VIR_DOMAIN_SNAPSHOT_LOCATION_NONE;
else
disk->snapshot = def->dom->disks[i]->snapshot;
disk->src->type = VIR_STORAGE_TYPE_FILE;
if (!disk->snapshot)
disk->snapshot = default_snapshot;
}
qsort(&def->disks[0], def->ndisks, sizeof(def->disks[0]), disksorter);
/* Generate any default external file names, but only if the
* backing file is a regular file. */
for (i = 0; i < def->ndisks; i++) {
virDomainSnapshotDiskDefPtr disk = &def->disks[i];
if (disk->snapshot == VIR_DOMAIN_SNAPSHOT_LOCATION_EXTERNAL &&
!disk->src->path) {
const char *original = virDomainDiskGetSource(def->dom->disks[i]);
const char *tmp;
struct stat sb;
if (disk->src->type != VIR_STORAGE_TYPE_FILE) {
virReportError(VIR_ERR_CONFIG_UNSUPPORTED,
_("cannot generate external snapshot name "
"for disk '%s' on a '%s' device"),
disk->name,
virStorageTypeToString(disk->src->type));
goto cleanup;
}
if (!original) {
virReportError(VIR_ERR_CONFIG_UNSUPPORTED,
_("cannot generate external snapshot name "
"for disk '%s' without source"),
disk->name);
goto cleanup;
}
if (stat(original, &sb) < 0 || !S_ISREG(sb.st_mode)) {
virReportError(VIR_ERR_CONFIG_UNSUPPORTED,
_("source for disk '%s' is not a regular "
"file; refusing to generate external "
"snapshot name"),
disk->name);
goto cleanup;
}
tmp = strrchr(original, '.');
if (!tmp || strchr(tmp, '/')) {
if (virAsprintf(&disk->src->path, "%s.%s", original,
def->name) < 0)
goto cleanup;
} else {
if ((tmp - original) > INT_MAX) {
virReportError(VIR_ERR_INTERNAL_ERROR, "%s",
_("integer overflow"));
goto cleanup;
}
if (virAsprintf(&disk->src->path, "%.*s.%s",
(int) (tmp - original), original,
def->name) < 0)
goto cleanup;
}
}
}
ret = 0;
cleanup:
virBitmapFree(map);
return ret;
}
int virHostValidateQEMU(void)
{
virBitmapPtr flags;
int ret = 0;
bool hasHwVirt = false;
virHostMsgCheck("QEMU", "%s", _("for hardware virtualization"));
if (!(flags = virHostValidateGetCPUFlags()))
return -1;
switch (virArchFromHost()) {
case VIR_ARCH_I686:
case VIR_ARCH_X86_64:
if (virBitmapIsBitSet(flags, VIR_HOST_VALIDATE_CPU_FLAG_SVM) ||
virBitmapIsBitSet(flags, VIR_HOST_VALIDATE_CPU_FLAG_VMX))
hasHwVirt = true;
break;
case VIR_ARCH_S390:
case VIR_ARCH_S390X:
if (virBitmapIsBitSet(flags, VIR_HOST_VALIDATE_CPU_FLAG_SIE))
hasHwVirt = true;
break;
default:
hasHwVirt = false;
}
if (hasHwVirt) {
virHostMsgPass();
if (virHostValidateDeviceExists("QEMU", "/dev/kvm",
VIR_HOST_VALIDATE_FAIL,
_("Check that the 'kvm-intel' or 'kvm-amd' modules are "
"loaded & the BIOS has enabled virtualization")) < 0)
ret = -1;
else if (virHostValidateDeviceAccessible("QEMU", "/dev/kvm",
VIR_HOST_VALIDATE_FAIL,
_("Check /dev/kvm is world writable or you are in "
"a group that is allowed to access it")) < 0)
ret = -1;
} else {
virHostMsgFail(VIR_HOST_VALIDATE_WARN,
_("Only emulated CPUs are available, performance will be significantly limited"));
}
virBitmapFree(flags);
if (virHostValidateDeviceExists("QEMU", "/dev/vhost-net",
VIR_HOST_VALIDATE_WARN,
_("Load the 'vhost_net' module to improve performance "
"of virtio networking")) < 0)
ret = -1;
if (virHostValidateDeviceExists("QEMU", "/dev/net/tun",
VIR_HOST_VALIDATE_FAIL,
_("Load the 'tun' module to enable networking for QEMU guests")) < 0)
ret = -1;
if (virHostValidateCGroupController("QEMU", "memory",
VIR_HOST_VALIDATE_WARN,
"MEMCG") < 0)
ret = -1;
if (virHostValidateCGroupController("QEMU", "cpu",
VIR_HOST_VALIDATE_WARN,
"CGROUP_CPU") < 0)
ret = -1;
if (virHostValidateCGroupController("QEMU", "cpuacct",
VIR_HOST_VALIDATE_WARN,
"CGROUP_CPUACCT") < 0)
ret = -1;
if (virHostValidateCGroupController("QEMU", "cpuset",
VIR_HOST_VALIDATE_WARN,
"CPUSETS") < 0)
ret = -1;
if (virHostValidateCGroupController("QEMU", "devices",
VIR_HOST_VALIDATE_WARN,
"CGROUP_DEVICES") < 0)
ret = -1;
if (virHostValidateCGroupController("QEMU", "blkio",
VIR_HOST_VALIDATE_WARN,
"BLK_CGROUP") < 0)
ret = -1;
if (virHostValidateIOMMU("QEMU",
VIR_HOST_VALIDATE_WARN) < 0)
ret = -1;
return ret;
}
