[Qemu-devel] [PATCH v19 09/11] hostmem backend: implement memory policy

[Hu Tao]

Signed-off-by: Hu Tao <address@hidden>
---
 backends/hostmem.c       | 97 ++++++++++++++++++++++++++++++++++++++++++++++--
 include/sysemu/hostmem.h |  4 ++
 qapi-schema.json         | 20 ++++++++++
 3 files changed, 118 insertions(+), 3 deletions(-)

diff --git a/backends/hostmem.c b/backends/hostmem.c
index 0bd3900..077e8cc 100644
--- a/backends/hostmem.c
+++ b/backends/hostmem.c
@@ -10,11 +10,14 @@
  * See the COPYING file in the top-level directory.
  */
 #include "sysemu/hostmem.h"
-#include "sysemu/sysemu.h"
 #include "qapi/visitor.h"
+#include "qapi-visit.h"
 #include "qapi/qmp/qerror.h"
 #include "qemu/config-file.h"
 #include "qom/object_interfaces.h"
+#ifdef CONFIG_NUMA
+#include <numaif.h>
+#endif
 
 static void
 hostmemory_backend_get_size(Object *obj, Visitor *v, void *opaque,
@@ -50,11 +53,85 @@ hostmemory_backend_set_size(Object *obj, Visitor *v, void 
*opaque,
     backend->size = value;
 }
 
+static void
+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, &host_nodes, name, errp);
+}
+
+static void
+set_host_nodes(Object *obj, Visitor *v, void *opaque, const char *name,
+               Error **errp)
+{
+    HostMemoryBackend *backend = MEMORY_BACKEND(obj);
+    uint16List *l = NULL;
+
+    visit_type_uint16List(v, &l, name, errp);
+
+    while (l) {
+        bitmap_set(backend->host_nodes, l->value, 1);
+        l = l->next;
+    }
+}
+
+static void
+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
+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;
+}
+
 static void hostmemory_backend_initfn(Object *obj)
 {
     object_property_add(obj, "size", "int",
                         hostmemory_backend_get_size,
                         hostmemory_backend_set_size, NULL, NULL, NULL);
+    object_property_add(obj, "host-nodes", "int",
+                        get_host_nodes,
+                        set_host_nodes, NULL, NULL, NULL);
+    object_property_add(obj, "policy", "str",
+                        get_policy,
+                        set_policy, NULL, NULL, NULL);
 }
 
 static void hostmemory_backend_finalize(Object *obj)
@@ -69,8 +146,22 @@ static void hostmemory_backend_finalize(Object *obj)
 static void
 hostmemory_backend_memory_init(UserCreatable *uc, Error **errp)
 {
-    error_setg(errp, "memory_init is not implemented for type [%s]",
-               object_get_typename(OBJECT(uc)));
+#ifdef CONFIG_NUMA
+    HostMemoryBackend *backend = MEMORY_BACKEND(uc);
+    void *p = memory_region_get_ram_ptr(&backend->mr);
+    unsigned long maxnode = find_last_bit(backend->host_nodes, MAX_NODES);
+
+    /* This is a workaround for a long standing bug in Linux'
+     * mbind implementation, which cuts off the last specified
+     * node.
+     */
+    if (mbind(p, backend->size, backend->policy, backend->host_nodes,
+              maxnode + 2, 0)) {
+        error_setg_errno(errp, errno,
+                         "cannot bind memory to host NUMA nodes\n");
+        return;
+    }
+#endif
 }
 
 MemoryRegion *
diff --git a/include/sysemu/hostmem.h b/include/sysemu/hostmem.h
index bc3ffb3..a2b0702 100644
--- a/include/sysemu/hostmem.h
+++ b/include/sysemu/hostmem.h
@@ -12,10 +12,12 @@
 #ifndef QEMU_RAM_H
 #define QEMU_RAM_H
 
+#include "sysemu/sysemu.h" /* for MAX_NODES */
 #include "qom/object.h"
 #include "qapi/error.h"
 #include "exec/memory.h"
 #include "qemu/option.h"
+#include "qemu/bitmap.h"
 
 #define TYPE_MEMORY_BACKEND "memory"
 #define MEMORY_BACKEND(obj) \
@@ -50,6 +52,8 @@ struct HostMemoryBackend {
 
     /* protected */
     uint64_t size;
+    DECLARE_BITMAP(host_nodes, MAX_NODES);
+    HostMemPolicy policy;
 
     MemoryRegion mr;
 };
diff --git a/qapi-schema.json b/qapi-schema.json
index 62e0b83..86b78a5 100644
--- a/qapi-schema.json
+++ b/qapi-schema.json
@@ -4554,3 +4554,23 @@
    '*cpus':   ['uint16'],
    '*mem':    'size',
    '*memdev': 'str' }}
+
+##
+# @HostMemPolicy
+#
+# Host memory policy types
+#
+# @default: restore default policy, remove any nondefault policy
+#
+# @preferred: set the preferred host nodes for allocation
+#
+# @membind: a strict policy that restricts memory allocation to the
+#           host nodes specified
+#
+# @interleave: memory allocations are interleaved across the set
+#              of host nodes specified
+#
+# Since 2.1
+##
+{ 'enum': 'HostMemPolicy',
+  'data': [ 'default', 'preferred', 'membind', 'interleave' ] }
-- 
1.8.5.2.229.g4448466