#include "qom/object_interfaces.h"
#include "qemu/mmap-alloc.h"
#include "qemu/madvise.h"
+#include "hw/qdev-core.h"
#ifdef CONFIG_NUMA
#include <numaif.h>
+#include <numa.h>
QEMU_BUILD_BUG_ON(HOST_MEM_POLICY_DEFAULT != MPOL_DEFAULT);
+/*
+ * HOST_MEM_POLICY_PREFERRED may either translate to MPOL_PREFERRED or
+ * MPOL_PREFERRED_MANY, see comments further below.
+ */
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);
static void host_memory_backend_set_prealloc(Object *obj, bool value,
Error **errp)
{
- Error *local_err = NULL;
HostMemoryBackend *backend = MEMORY_BACKEND(obj);
if (!backend->reserve && value) {
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_threads, &local_err);
- if (local_err) {
- error_propagate(errp, local_err);
+ if (!qemu_prealloc_mem(fd, ptr, sz, backend->prealloc_threads,
+ backend->prealloc_context, false, errp)) {
return;
}
backend->prealloc = true;
/* TODO: convert access to globals to compat properties */
backend->merge = machine_mem_merge(machine);
backend->dump = machine_dump_guest_core(machine);
+ backend->guest_memfd = machine_require_guest_memfd(machine);
backend->reserve = true;
backend->prealloc_threads = machine->smp.cpus;
}
{
HostMemoryBackend *backend = MEMORY_BACKEND(uc);
HostMemoryBackendClass *bc = MEMORY_BACKEND_GET_CLASS(uc);
- Error *local_err = NULL;
void *ptr;
uint64_t sz;
+ bool async = !phase_check(PHASE_LATE_BACKENDS_CREATED);
- if (bc->alloc) {
- bc->alloc(backend, &local_err);
- if (local_err) {
- goto out;
- }
+ if (!bc->alloc) {
+ return;
+ }
+ if (!bc->alloc(backend, errp)) {
+ return;
+ }
- ptr = memory_region_get_ram_ptr(&backend->mr);
- sz = memory_region_size(&backend->mr);
+ 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);
- }
+ 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_str(backend->policy));
- return;
- }
+ 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;
+ int mode = backend->policy;
+
+ /* 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_str(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.
+ /*
+ * 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);
+
+#ifdef HAVE_NUMA_HAS_PREFERRED_MANY
+ if (mode == MPOL_PREFERRED && numa_has_preferred_many() > 0) {
+ /*
+ * Replace with MPOL_PREFERRED_MANY otherwise the mbind() below
+ * silently picks the first node.
*/
- assert(sizeof(backend->host_nodes) >=
- BITS_TO_LONGS(MAX_NODES + 1) * sizeof(unsigned long));
- assert(maxnode <= MAX_NODES);
-
- if (maxnode &&
- mbind(ptr, sz, backend->policy, backend->host_nodes, maxnode + 1,
- flags)) {
- if (backend->policy != MPOL_DEFAULT || errno != ENOSYS) {
- error_setg_errno(errp, errno,
- "cannot bind memory to host NUMA nodes");
- return;
- }
- }
+ mode = MPOL_PREFERRED_MANY;
+ }
#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,
- backend->prealloc_threads, &local_err);
- if (local_err) {
- goto out;
- }
+
+ if (maxnode &&
+ mbind(ptr, sz, mode, backend->host_nodes, maxnode + 1, flags)) {
+ if (backend->policy != MPOL_DEFAULT || errno != ENOSYS) {
+ error_setg_errno(errp, errno,
+ "cannot bind memory to host NUMA nodes");
+ return;
}
}
-out:
- error_propagate(errp, local_err);
+#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 && !qemu_prealloc_mem(memory_region_get_fd(&backend->mr),
+ ptr, sz,
+ backend->prealloc_threads,
+ backend->prealloc_context,
+ async, errp)) {
+ return;
+ }
}
static bool
NULL, NULL);
object_class_property_set_description(oc, "prealloc-threads",
"Number of CPU threads to use for prealloc");
+ object_class_property_add_link(oc, "prealloc-context",
+ TYPE_THREAD_CONTEXT, offsetof(HostMemoryBackend, prealloc_context),
+ object_property_allow_set_link, OBJ_PROP_LINK_STRONG);
+ object_class_property_set_description(oc, "prealloc-context",
+ "Context to use for creating CPU threads for preallocation");
object_class_property_add(oc, "size", "int",
host_memory_backend_get_size,
host_memory_backend_set_size,