51e72bc1dd
JSON uses "name":value, but many of our visitor interfaces were called with visit_type_FOO(v, &value, name, errp). This can be a bit confusing to have to mentally swap the parameter order to match JSON order. It's particularly bad for visit_start_struct(), where the 'name' parameter is smack in the middle of the otherwise-related group of 'obj, kind, size' parameters! It's time to do a global swap of the parameter ordering, so that the 'name' parameter is always immediately after the Visitor argument. Additional reason in favor of the swap: the existing include/qjson.h prefers listing 'name' first in json_prop_*(), and I have plans to unify that file with the qapi visitors; listing 'name' first in qapi will minimize churn to the (admittedly few) qjson.h clients. Later patches will then fix docs, object.h, visitor-impl.h, and those clients to match. Done by first patching scripts/qapi*.py by hand to make generated files do what I want, then by running the following Coccinelle script to affect the rest of the code base: $ spatch --sp-file script `git grep -l '\bvisit_' -- '**/*.[ch]'` I then had to apply some touchups (Coccinelle insisted on TAB indentation in visitor.h, and botched the signature of visit_type_enum() by rewriting 'const char *const strings[]' to the syntactically invalid 'const char*const[] strings'). The movement of parameters is sufficient to provoke compiler errors if any callers were missed. // Part 1: Swap declaration order @@ type TV, TErr, TObj, T1, T2; identifier OBJ, ARG1, ARG2; @@ void visit_start_struct -(TV v, TObj OBJ, T1 ARG1, const char *name, T2 ARG2, TErr errp) +(TV v, const char *name, TObj OBJ, T1 ARG1, T2 ARG2, TErr errp) { ... } @@ type bool, TV, T1; identifier ARG1; @@ bool visit_optional -(TV v, T1 ARG1, const char *name) +(TV v, const char *name, T1 ARG1) { ... } @@ type TV, TErr, TObj, T1; identifier OBJ, ARG1; @@ void visit_get_next_type -(TV v, TObj OBJ, T1 ARG1, const char *name, TErr errp) +(TV v, const char *name, TObj OBJ, T1 ARG1, TErr errp) { ... } @@ type TV, TErr, TObj, T1, T2; identifier OBJ, ARG1, ARG2; @@ void visit_type_enum -(TV v, TObj OBJ, T1 ARG1, T2 ARG2, const char *name, TErr errp) +(TV v, const char *name, TObj OBJ, T1 ARG1, T2 ARG2, TErr errp) { ... } @@ type TV, TErr, TObj; identifier OBJ; identifier VISIT_TYPE =~ "^visit_type_"; @@ void VISIT_TYPE -(TV v, TObj OBJ, const char *name, TErr errp) +(TV v, const char *name, TObj OBJ, TErr errp) { ... } // Part 2: swap caller order @@ expression V, NAME, OBJ, ARG1, ARG2, ERR; identifier VISIT_TYPE =~ "^visit_type_"; @@ ( -visit_start_struct(V, OBJ, ARG1, NAME, ARG2, ERR) +visit_start_struct(V, NAME, OBJ, ARG1, ARG2, ERR) | -visit_optional(V, ARG1, NAME) +visit_optional(V, NAME, ARG1) | -visit_get_next_type(V, OBJ, ARG1, NAME, ERR) +visit_get_next_type(V, NAME, OBJ, ARG1, ERR) | -visit_type_enum(V, OBJ, ARG1, ARG2, NAME, ERR) +visit_type_enum(V, NAME, OBJ, ARG1, ARG2, ERR) | -VISIT_TYPE(V, OBJ, NAME, ERR) +VISIT_TYPE(V, NAME, OBJ, ERR) ) Signed-off-by: Eric Blake <eblake@redhat.com> Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com> Message-Id: <1454075341-13658-19-git-send-email-eblake@redhat.com> Signed-off-by: Markus Armbruster <armbru@redhat.com>
376 lines
11 KiB
C
376 lines
11 KiB
C
/*
|
|
* QEMU Host Memory Backend
|
|
*
|
|
* Copyright (C) 2013-2014 Red Hat Inc
|
|
*
|
|
* Authors:
|
|
* Igor Mammedov <imammedo@redhat.com>
|
|
*
|
|
* This work is licensed under the terms of the GNU GPL, version 2 or later.
|
|
* See the COPYING file in the top-level directory.
|
|
*/
|
|
#include "qemu/osdep.h"
|
|
#include "sysemu/hostmem.h"
|
|
#include "hw/boards.h"
|
|
#include "qapi/visitor.h"
|
|
#include "qapi-types.h"
|
|
#include "qapi-visit.h"
|
|
#include "qemu/config-file.h"
|
|
#include "qom/object_interfaces.h"
|
|
|
|
#ifdef CONFIG_NUMA
|
|
#include <numaif.h>
|
|
QEMU_BUILD_BUG_ON(HOST_MEM_POLICY_DEFAULT != MPOL_DEFAULT);
|
|
QEMU_BUILD_BUG_ON(HOST_MEM_POLICY_PREFERRED != MPOL_PREFERRED);
|
|
QEMU_BUILD_BUG_ON(HOST_MEM_POLICY_BIND != MPOL_BIND);
|
|
QEMU_BUILD_BUG_ON(HOST_MEM_POLICY_INTERLEAVE != MPOL_INTERLEAVE);
|
|
#endif
|
|
|
|
static void
|
|
host_memory_backend_get_size(Object *obj, Visitor *v, void *opaque,
|
|
const char *name, Error **errp)
|
|
{
|
|
HostMemoryBackend *backend = MEMORY_BACKEND(obj);
|
|
uint64_t value = backend->size;
|
|
|
|
visit_type_size(v, name, &value, errp);
|
|
}
|
|
|
|
static void
|
|
host_memory_backend_set_size(Object *obj, Visitor *v, void *opaque,
|
|
const char *name, Error **errp)
|
|
{
|
|
HostMemoryBackend *backend = MEMORY_BACKEND(obj);
|
|
Error *local_err = NULL;
|
|
uint64_t value;
|
|
|
|
if (memory_region_size(&backend->mr)) {
|
|
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, void *opaque,
|
|
const char *name, 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_host_nodes(Object *obj, Visitor *v, void *opaque,
|
|
const char *name, 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 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_merge(Object *obj, Error **errp)
|
|
{
|
|
HostMemoryBackend *backend = MEMORY_BACKEND(obj);
|
|
|
|
return backend->merge;
|
|
}
|
|
|
|
static void host_memory_backend_set_merge(Object *obj, bool value, Error **errp)
|
|
{
|
|
HostMemoryBackend *backend = MEMORY_BACKEND(obj);
|
|
|
|
if (!memory_region_size(&backend->mr)) {
|
|
backend->merge = value;
|
|
return;
|
|
}
|
|
|
|
if (value != backend->merge) {
|
|
void *ptr = memory_region_get_ram_ptr(&backend->mr);
|
|
uint64_t sz = memory_region_size(&backend->mr);
|
|
|
|
qemu_madvise(ptr, sz,
|
|
value ? QEMU_MADV_MERGEABLE : QEMU_MADV_UNMERGEABLE);
|
|
backend->merge = value;
|
|
}
|
|
}
|
|
|
|
static bool host_memory_backend_get_dump(Object *obj, Error **errp)
|
|
{
|
|
HostMemoryBackend *backend = MEMORY_BACKEND(obj);
|
|
|
|
return backend->dump;
|
|
}
|
|
|
|
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 bool host_memory_backend_get_prealloc(Object *obj, Error **errp)
|
|
{
|
|
HostMemoryBackend *backend = MEMORY_BACKEND(obj);
|
|
|
|
return backend->prealloc || backend->force_prealloc;
|
|
}
|
|
|
|
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_init(Object *obj)
|
|
{
|
|
HostMemoryBackend *backend = MEMORY_BACKEND(obj);
|
|
MachineState *machine = MACHINE(qdev_get_machine());
|
|
|
|
backend->merge = machine_mem_merge(machine);
|
|
backend->dump = machine_dump_guest_core(machine);
|
|
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_enum(obj, "policy", "HostMemPolicy",
|
|
HostMemPolicy_lookup,
|
|
host_memory_backend_get_policy,
|
|
host_memory_backend_set_policy, NULL);
|
|
}
|
|
|
|
MemoryRegion *
|
|
host_memory_backend_get_memory(HostMemoryBackend *backend, Error **errp)
|
|
{
|
|
return memory_region_size(&backend->mr) ? &backend->mr : NULL;
|
|
}
|
|
|
|
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)) {
|
|
if (backend->policy != MPOL_DEFAULT || errno != ENOSYS) {
|
|
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_can_be_deleted(UserCreatable *uc, Error **errp)
|
|
{
|
|
MemoryRegion *mr;
|
|
|
|
mr = host_memory_backend_get_memory(MEMORY_BACKEND(uc), errp);
|
|
if (memory_region_is_mapped(mr)) {
|
|
return false;
|
|
} else {
|
|
return true;
|
|
}
|
|
}
|
|
|
|
static void
|
|
host_memory_backend_class_init(ObjectClass *oc, void *data)
|
|
{
|
|
UserCreatableClass *ucc = USER_CREATABLE_CLASS(oc);
|
|
|
|
ucc->complete = host_memory_backend_memory_complete;
|
|
ucc->can_be_deleted = host_memory_backend_can_be_deleted;
|
|
}
|
|
|
|
static const TypeInfo host_memory_backend_info = {
|
|
.name = TYPE_MEMORY_BACKEND,
|
|
.parent = TYPE_OBJECT,
|
|
.abstract = true,
|
|
.class_size = sizeof(HostMemoryBackendClass),
|
|
.class_init = host_memory_backend_class_init,
|
|
.instance_size = sizeof(HostMemoryBackend),
|
|
.instance_init = host_memory_backend_init,
|
|
.interfaces = (InterfaceInfo[]) {
|
|
{ TYPE_USER_CREATABLE },
|
|
{ }
|
|
}
|
|
};
|
|
|
|
static void register_types(void)
|
|
{
|
|
type_register_static(&host_memory_backend_info);
|
|
}
|
|
|
|
type_init(register_types);
|