static void host_memory_backend_init(Object *obj)
{
HostMemoryBackend *backend = MEMORY_BACKEND(obj);
backend->merge = qemu_opt_get_bool(qemu_get_machine_opts(),
"mem-merge", true);
backend->dump = qemu_opt_get_bool(qemu_get_machine_opts(),
"dump-guest-core", true);
backend->prealloc = mem_prealloc;
object_property_add_bool(obj, "merge",
host_memory_backend_get_merge,
host_memory_backend_set_merge, NULL);
object_property_add_bool(obj, "dump",
host_memory_backend_get_dump,
host_memory_backend_set_dump, NULL);
object_property_add_bool(obj, "prealloc",
host_memory_backend_get_prealloc,
host_memory_backend_set_prealloc, NULL);
object_property_add(obj, "size", "int",
host_memory_backend_get_size,
host_memory_backend_set_size, NULL, NULL, NULL);
object_property_add(obj, "host-nodes", "int",
host_memory_backend_get_host_nodes,
host_memory_backend_set_host_nodes, NULL, NULL, NULL);
object_property_add(obj, "policy", "str",
host_memory_backend_get_policy,
host_memory_backend_set_policy, NULL, NULL, NULL);
}
static void
host_memory_backend_set_size(Object *obj, Visitor *v, const char *name,
void *opaque, Error **errp)
{
HostMemoryBackend *backend = MEMORY_BACKEND(obj);
Error *local_err = NULL;
uint64_t value;
if (host_memory_backend_mr_inited(backend)) {
error_setg(&local_err, "cannot change property value");
goto out;
}
visit_type_size(v, name, &value, &local_err);
if (local_err) {
goto out;
}
if (!value) {
error_setg(&local_err, "Property '%s.%s' doesn't take value '%"
PRIu64 "'", object_get_typename(obj), name, value);
goto out;
}
backend->size = value;
out:
error_propagate(errp, local_err);
}
static void
host_memory_backend_get_host_nodes(Object *obj, Visitor *v, const char *name,
void *opaque, Error **errp)
{
HostMemoryBackend *backend = MEMORY_BACKEND(obj);
uint16List *host_nodes = NULL;
uint16List **node = &host_nodes;
unsigned long value;
value = find_first_bit(backend->host_nodes, MAX_NODES);
if (value == MAX_NODES) {
return;
}
*node = g_malloc0(sizeof(**node));
(*node)->value = value;
node = &(*node)->next;
do {
value = find_next_bit(backend->host_nodes, MAX_NODES, value + 1);
if (value == MAX_NODES) {
break;
}
*node = g_malloc0(sizeof(**node));
(*node)->value = value;
node = &(*node)->next;
} while (true);
visit_type_uint16List(v, name, &host_nodes, errp);
}
static void host_memory_backend_set_prealloc(Object *obj, bool value,
Error **errp)
{
HostMemoryBackend *backend = MEMORY_BACKEND(obj);
if (backend->force_prealloc) {
if (value) {
error_setg(errp,
"remove -mem-prealloc to use the prealloc property");
return;
}
}
if (!memory_region_size(&backend->mr)) {
backend->prealloc = value;
return;
}
if (value && !backend->prealloc) {
int fd = memory_region_get_fd(&backend->mr);
void *ptr = memory_region_get_ram_ptr(&backend->mr);
uint64_t sz = memory_region_size(&backend->mr);
os_mem_prealloc(fd, ptr, sz);
backend->prealloc = true;
}
}
static void
host_memory_backend_get_host_nodes(Object *obj, Visitor *v, const char *name,
void *opaque, Error **errp)
{
HostMemoryBackend *backend = MEMORY_BACKEND(obj);
uint16List *host_nodes = NULL;
uint16List **node = &host_nodes;
unsigned long value;
value = find_first_bit(backend->host_nodes, MAX_NODES);
node = host_memory_append_node(node, value);
if (value == MAX_NODES) {
goto out;
}
do {
value = find_next_bit(backend->host_nodes, MAX_NODES, value + 1);
if (value == MAX_NODES) {
break;
}
node = host_memory_append_node(node, value);
} while (true);
out:
visit_type_uint16List(v, name, &host_nodes, errp);
}
static void
host_memory_backend_get_size(Object *obj, Visitor *v, const char *name,
void *opaque, Error **errp)
{
HostMemoryBackend *backend = MEMORY_BACKEND(obj);
uint64_t value = backend->size;
visit_type_size(v, name, &value, errp);
}
static void
host_memory_backend_get_policy(Object *obj, Visitor *v, void *opaque,
const char *name, Error **errp)
{
HostMemoryBackend *backend = MEMORY_BACKEND(obj);
int policy = backend->policy;
visit_type_enum(v, &policy, HostMemPolicy_lookup, NULL, name, errp);
}
static void
memfd_backend_instance_init(Object *obj)
{
HostMemoryBackendMemfd *m = MEMORY_BACKEND_MEMFD(obj);
/* default to sealed file */
m->seal = true;
MEMORY_BACKEND(m)->share = true;
}
static void ivshmem_check_memdev_is_busy(Object *obj, const char *name,
Object *val, Error **errp)
{
if (host_memory_backend_is_mapped(MEMORY_BACKEND(val))) {
char *path = object_get_canonical_path_component(val);
error_setg(errp, "can't use already busy memdev: %s", path);
g_free(path);
} else {
qdev_prop_allow_set_link_before_realize(obj, name, val, errp);
}
}
static void file_memory_backend_set_share(Object *o, bool value, Error **errp)
{
HostMemoryBackend *backend = MEMORY_BACKEND(o);
HostMemoryBackendFile *fb = MEMORY_BACKEND_FILE(o);
if (host_memory_backend_mr_inited(backend)) {
error_setg(errp, "cannot change property value");
return;
}
fb->share = value;
}
static void set_mem_path(Object *o, const char *str, Error **errp)
{
HostMemoryBackend *backend = MEMORY_BACKEND(o);
HostMemoryBackendFile *fb = MEMORY_BACKEND_FILE(o);
if (host_memory_backend_mr_inited(backend)) {
error_setg(errp, "cannot change property value");
return;
}
g_free(fb->mem_path);
fb->mem_path = g_strdup(str);
}
static void file_backend_unparent(Object *obj)
{
HostMemoryBackend *backend = MEMORY_BACKEND(obj);
HostMemoryBackendFile *fb = MEMORY_BACKEND_FILE(obj);
if (host_memory_backend_mr_inited(backend) && fb->discard_data) {
void *ptr = memory_region_get_ram_ptr(&backend->mr);
uint64_t sz = memory_region_size(&backend->mr);
qemu_madvise(ptr, sz, QEMU_MADV_REMOVE);
}
}
static void
host_memory_backend_set_policy(Object *obj, Visitor *v, void *opaque,
const char *name, Error **errp)
{
HostMemoryBackend *backend = MEMORY_BACKEND(obj);
int policy;
visit_type_enum(v, &policy, HostMemPolicy_lookup, NULL, name, errp);
backend->policy = policy;
#ifndef CONFIG_NUMA
if (policy != HOST_MEM_POLICY_DEFAULT) {
error_setg(errp, "NUMA policies are not supported by this QEMU");
}
#endif
}
static void desugar_shm(IVShmemState *s)
{
Object *obj;
char *path;
obj = object_new("memory-backend-file");
path = g_strdup_printf("/dev/shm/%s", s->shmobj);
object_property_set_str(obj, path, "mem-path", &error_abort);
g_free(path);
object_property_set_int(obj, s->legacy_size, "size", &error_abort);
object_property_set_bool(obj, true, "share", &error_abort);
object_property_add_child(OBJECT(s), "internal-shm-backend", obj,
&error_abort);
user_creatable_complete(obj, &error_abort);
s->hostmem = MEMORY_BACKEND(obj);
}
static void
host_memory_backend_set_host_nodes(Object *obj, Visitor *v, const char *name,
void *opaque, Error **errp)
{
#ifdef CONFIG_NUMA
HostMemoryBackend *backend = MEMORY_BACKEND(obj);
uint16List *l = NULL;
visit_type_uint16List(v, name, &l, errp);
while (l) {
bitmap_set(backend->host_nodes, l->value, 1);
l = l->next;
}
#else
error_setg(errp, "NUMA node binding are not supported by this QEMU");
#endif
}
static void host_memory_backend_set_dump(Object *obj, bool value, Error **errp)
{
HostMemoryBackend *backend = MEMORY_BACKEND(obj);
if (!memory_region_size(&backend->mr)) {
backend->dump = value;
return;
}
if (value != backend->dump) {
void *ptr = memory_region_get_ram_ptr(&backend->mr);
uint64_t sz = memory_region_size(&backend->mr);
qemu_madvise(ptr, sz,
value ? QEMU_MADV_DODUMP : QEMU_MADV_DONTDUMP);
backend->dump = value;
}
}
static void pc_dimm_check_memdev_is_busy(Object *obj, const char *name,
Object *val, Error **errp)
{
MemoryRegion *mr;
Error *local_err = NULL;
mr = host_memory_backend_get_memory(MEMORY_BACKEND(val), &local_err);
if (local_err) {
goto out;
}
if (memory_region_is_mapped(mr)) {
char *path = object_get_canonical_path_component(val);
error_setg(&local_err, "can't use already busy memdev: %s", path);
g_free(path);
} else {
qdev_prop_allow_set_link_before_realize(obj, name, val, &local_err);
}
out:
error_propagate(errp, local_err);
}
static void
host_memory_backend_memory_complete(UserCreatable *uc, Error **errp)
{
HostMemoryBackend *backend = MEMORY_BACKEND(uc);
HostMemoryBackendClass *bc = MEMORY_BACKEND_GET_CLASS(uc);
Error *local_err = NULL;
void *ptr;
uint64_t sz;
if (bc->alloc) {
bc->alloc(backend, &local_err);
if (local_err) {
error_propagate(errp, local_err);
return;
}
ptr = memory_region_get_ram_ptr(&backend->mr);
sz = memory_region_size(&backend->mr);
if (backend->merge) {
qemu_madvise(ptr, sz, QEMU_MADV_MERGEABLE);
}
if (!backend->dump) {
qemu_madvise(ptr, sz, QEMU_MADV_DONTDUMP);
}
#ifdef CONFIG_NUMA
unsigned long lastbit = find_last_bit(backend->host_nodes, MAX_NODES);
/* lastbit == MAX_NODES means maxnode = 0 */
unsigned long maxnode = (lastbit + 1) % (MAX_NODES + 1);
/* ensure policy won't be ignored in case memory is preallocated
* before mbind(). note: MPOL_MF_STRICT is ignored on hugepages so
* this doesn't catch hugepage case. */
unsigned flags = MPOL_MF_STRICT | MPOL_MF_MOVE;
/* check for invalid host-nodes and policies and give more verbose
* error messages than mbind(). */
if (maxnode && backend->policy == MPOL_DEFAULT) {
error_setg(errp, "host-nodes must be empty for policy default,"
" or you should explicitly specify a policy other"
" than default");
return;
} else if (maxnode == 0 && backend->policy != MPOL_DEFAULT) {
error_setg(errp, "host-nodes must be set for policy %s",
HostMemPolicy_lookup[backend->policy]);
return;
}
/* We can have up to MAX_NODES nodes, but we need to pass maxnode+1
* as argument to mbind() due to an old Linux bug (feature?) which
* cuts off the last specified node. This means backend->host_nodes
* must have MAX_NODES+1 bits available.
*/
assert(sizeof(backend->host_nodes) >=
BITS_TO_LONGS(MAX_NODES + 1) * sizeof(unsigned long));
assert(maxnode <= MAX_NODES);
if (mbind(ptr, sz, backend->policy,
maxnode ? backend->host_nodes : NULL, maxnode + 1, flags)) {
error_setg_errno(errp, errno,
"cannot bind memory to host NUMA nodes");
return;
}
#endif
/* Preallocate memory after the NUMA policy has been instantiated.
* This is necessary to guarantee memory is allocated with
* specified NUMA policy in place.
*/
if (backend->prealloc) {
os_mem_prealloc(memory_region_get_fd(&backend->mr), ptr, sz);
}
}
}
static bool host_memory_backend_get_dump(Object *obj, Error **errp)
{
HostMemoryBackend *backend = MEMORY_BACKEND(obj);
return backend->dump;
}
visit_type_uint16List(v, name, &l, errp);
while (l) {
bitmap_set(backend->host_nodes, l->value, 1);
l = l->next;
}
#else
error_setg(errp, "NUMA node binding are not supported by this QEMU");
#endif
}
static int
host_memory_backend_get_policy(Object *obj, Error **errp G_GNUC_UNUSED)
{
HostMemoryBackend *backend = MEMORY_BACKEND(obj);
return backend->policy;
}
static void
host_memory_backend_set_policy(Object *obj, int policy, Error **errp)
{
HostMemoryBackend *backend = MEMORY_BACKEND(obj);
backend->policy = policy;
#ifndef CONFIG_NUMA
if (policy != HOST_MEM_POLICY_DEFAULT) {
error_setg(errp, "NUMA policies are not supported by this QEMU");
}
#endif
}
static bool host_memory_backend_get_prealloc(Object *obj, Error **errp)
{
HostMemoryBackend *backend = MEMORY_BACKEND(obj);
return backend->prealloc || backend->force_prealloc;
}
static void numa_node_parse(NumaNodeOptions *node, QemuOpts *opts, Error **errp)
{
uint16_t nodenr;
uint16List *cpus = NULL;
if (node->has_nodeid) {
nodenr = node->nodeid;
} else {
nodenr = nb_numa_nodes;
}
if (nodenr >= MAX_NODES) {
error_setg(errp, "Max number of NUMA nodes reached: %"
PRIu16 "", nodenr);
return;
}
if (numa_info[nodenr].present) {
error_setg(errp, "Duplicate NUMA nodeid: %" PRIu16, nodenr);
return;
}
for (cpus = node->cpus; cpus; cpus = cpus->next) {
if (cpus->value > MAX_CPUMASK_BITS) {
error_setg(errp, "CPU number %" PRIu16 " is bigger than %d",
cpus->value, MAX_CPUMASK_BITS);
return;
}
bitmap_set(numa_info[nodenr].node_cpu, cpus->value, 1);
}
if (node->has_mem && node->has_memdev) {
error_setg(errp, "qemu: cannot specify both mem= and memdev=");
return;
}
if (have_memdevs == -1) {
have_memdevs = node->has_memdev;
}
if (node->has_memdev != have_memdevs) {
error_setg(errp, "qemu: memdev option must be specified for either "
"all or no nodes");
return;
}
if (node->has_mem) {
uint64_t mem_size = node->mem;
const char *mem_str = qemu_opt_get(opts, "mem");
/* Fix up legacy suffix-less format */
if (g_ascii_isdigit(mem_str[strlen(mem_str) - 1])) {
mem_size <<= 20;
}
numa_info[nodenr].node_mem = mem_size;
}
if (node->has_memdev) {
Object *o;
o = object_resolve_path_type(node->memdev, TYPE_MEMORY_BACKEND, NULL);
if (!o) {
error_setg(errp, "memdev=%s is ambiguous", node->memdev);
return;
}
object_ref(o);
numa_info[nodenr].node_mem = object_property_get_int(o, "size", NULL);
numa_info[nodenr].node_memdev = MEMORY_BACKEND(o);
}
numa_info[nodenr].present = true;
max_numa_nodeid = MAX(max_numa_nodeid, nodenr + 1);
}
static void pci_ivshmem_realize(PCIDevice *dev, Error **errp)
{
IVShmemState *s = IVSHMEM(dev);
uint8_t *pci_conf;
uint8_t attr = PCI_BASE_ADDRESS_SPACE_MEMORY |
PCI_BASE_ADDRESS_MEM_PREFETCH;
if (!!s->server_chr + !!s->shmobj + !!s->hostmem != 1) {
error_setg(errp,
"You must specify either 'shm', 'chardev' or 'x-memdev'");
return;
}
if (s->hostmem) {
MemoryRegion *mr;
if (s->sizearg) {
g_warning("size argument ignored with hostmem");
}
mr = host_memory_backend_get_memory(s->hostmem, errp);
s->ivshmem_size = memory_region_size(mr);
} else if (s->sizearg == NULL) {
s->ivshmem_size = 4 << 20; /* 4 MB default */
} else {
char *end;
int64_t size = qemu_strtosz(s->sizearg, &end);
if (size < 0 || *end != '\0' || !is_power_of_2(size)) {
error_setg(errp, "Invalid size %s", s->sizearg);
return;
}
s->ivshmem_size = size;
}
fifo8_create(&s->incoming_fifo, sizeof(int64_t));
/* IRQFD requires MSI */
if (ivshmem_has_feature(s, IVSHMEM_IOEVENTFD) &&
!ivshmem_has_feature(s, IVSHMEM_MSI)) {
error_setg(errp, "ioeventfd/irqfd requires MSI");
return;
}
/* check that role is reasonable */
if (s->role) {
if (strncmp(s->role, "peer", 5) == 0) {
s->role_val = IVSHMEM_PEER;
} else if (strncmp(s->role, "master", 7) == 0) {
s->role_val = IVSHMEM_MASTER;
} else {
error_setg(errp, "'role' must be 'peer' or 'master'");
return;
}
} else {
s->role_val = IVSHMEM_MASTER; /* default */
}
if (s->role_val == IVSHMEM_PEER) {
error_setg(&s->migration_blocker,
"Migration is disabled when using feature 'peer mode' in device 'ivshmem'");
migrate_add_blocker(s->migration_blocker);
}
pci_conf = dev->config;
pci_conf[PCI_COMMAND] = PCI_COMMAND_IO | PCI_COMMAND_MEMORY;
pci_config_set_interrupt_pin(pci_conf, 1);
memory_region_init_io(&s->ivshmem_mmio, OBJECT(s), &ivshmem_mmio_ops, s,
"ivshmem-mmio", IVSHMEM_REG_BAR_SIZE);
/* region for registers*/
pci_register_bar(dev, 0, PCI_BASE_ADDRESS_SPACE_MEMORY,
&s->ivshmem_mmio);
memory_region_init(&s->bar, OBJECT(s), "ivshmem-bar2-container", s->ivshmem_size);
if (s->ivshmem_64bit) {
attr |= PCI_BASE_ADDRESS_MEM_TYPE_64;
}
if (s->hostmem != NULL) {
MemoryRegion *mr;
IVSHMEM_DPRINTF("using hostmem\n");
mr = host_memory_backend_get_memory(MEMORY_BACKEND(s->hostmem), errp);
vmstate_register_ram(mr, DEVICE(s));
memory_region_add_subregion(&s->bar, 0, mr);
pci_register_bar(PCI_DEVICE(s), 2, attr, &s->bar);
} else if (s->server_chr != NULL) {
/* FIXME do not rely on what chr drivers put into filename */
if (strncmp(s->server_chr->filename, "unix:", 5)) {
error_setg(errp, "chardev is not a unix client socket");
return;
}
/* if we get a UNIX socket as the parameter we will talk
* to the ivshmem server to receive the memory region */
IVSHMEM_DPRINTF("using shared memory server (socket = %s)\n",
s->server_chr->filename);
if (ivshmem_has_feature(s, IVSHMEM_MSI) &&
ivshmem_setup_msi(s)) {
error_setg(errp, "msix initialization failed");
return;
}
/* we allocate enough space for 16 peers and grow as needed */
resize_peers(s, 16);
s->vm_id = -1;
pci_register_bar(dev, 2, attr, &s->bar);
s->eventfd_chr = g_malloc0(s->vectors * sizeof(CharDriverState *));
qemu_chr_add_handlers(s->server_chr, ivshmem_can_receive,
ivshmem_check_version, ivshmem_event, s);
} else {
/* just map the file immediately, we're not using a server */
int fd;
IVSHMEM_DPRINTF("using shm_open (shm object = %s)\n", s->shmobj);
/* try opening with O_EXCL and if it succeeds zero the memory
* by truncating to 0 */
if ((fd = shm_open(s->shmobj, O_CREAT|O_RDWR|O_EXCL,
S_IRWXU|S_IRWXG|S_IRWXO)) > 0) {
/* truncate file to length PCI device's memory */
if (ftruncate(fd, s->ivshmem_size) != 0) {
error_report("could not truncate shared file");
}
} else if ((fd = shm_open(s->shmobj, O_CREAT|O_RDWR,
S_IRWXU|S_IRWXG|S_IRWXO)) < 0) {
error_setg(errp, "could not open shared file");
return;
}
if (check_shm_size(s, fd, errp) == -1) {
return;
}
create_shared_memory_BAR(s, fd, attr, errp);
}
}
