[PATCH v1 4/7] util: Add write-only "node-affinity" property for ThreadContext

[David Hildenbrand]

Let's make it easier to pin threads created via a ThreadContext to
all current CPUs belonging to given NUMA nodes.

As "node-affinity" is simply a shortcut for setting "cpu-affinity", that
property cannot be read and if the CPUs for a node change due do CPU
hotplug, the CPU affinity will not get updated.

Reviewed-by: Michal Privoznik <mprivozn@redhat.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
---
 qapi/qom.json         |  7 +++-
 util/meson.build      |  2 +-
 util/thread-context.c | 84 +++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 91 insertions(+), 2 deletions(-)

diff --git a/qapi/qom.json b/qapi/qom.json
index 4775a333ed..d36bf3355f 100644
--- a/qapi/qom.json
+++ b/qapi/qom.json
@@ -838,10 +838,15 @@
 # @cpu-affinity: the CPU affinity for all threads created in the thread
 #                context (default: QEMU main thread affinity)
 #
+# @node-affinity: shortcut for looking up the current CPUs for the given nodes
+#                 and setting @cpu-affinity (default: QEMU main thread
+#                 affinity)
+#
 # Since: 7.2
 ##
 { 'struct': 'ThreadContextProperties',
-  'data': { '*cpu-affinity': ['uint16'] } }
+  'data': { '*cpu-affinity': ['uint16'],
+            '*node-affinity': ['uint16'] } }
 
 
 ##
diff --git a/util/meson.build b/util/meson.build
index e97cd2d779..c0a7bc54d4 100644
--- a/util/meson.build
+++ b/util/meson.build
@@ -1,5 +1,5 @@
 util_ss.add(files('osdep.c', 'cutils.c', 'unicode.c', 'qemu-timer-common.c'))
-util_ss.add(files('thread-context.c'))
+util_ss.add(files('thread-context.c'), numa)
 if not config_host_data.get('CONFIG_ATOMIC64')
   util_ss.add(files('atomic64.c'))
 endif
diff --git a/util/thread-context.c b/util/thread-context.c
index dcd607c532..880f0441be 100644
--- a/util/thread-context.c
+++ b/util/thread-context.c
@@ -22,6 +22,10 @@
 #include "qemu/module.h"
 #include "qemu/bitmap.h"
 
+#ifdef CONFIG_NUMA
+#include <numa.h>
+#endif
+
 enum {
     TC_CMD_NONE = 0,
     TC_CMD_STOP,
@@ -89,6 +93,11 @@ static void thread_context_set_cpu_affinity(Object *obj, 
Visitor *v,
     int nbits = 0, ret;
     Error *err = NULL;
 
+    if (tc->init_cpu_bitmap) {
+        error_setg(errp, "Mixing CPU and node affinity not supported");
+        return;
+    }
+
     visit_type_uint16List(v, name, &host_cpus, &err);
     if (err) {
         error_propagate(errp, err);
@@ -160,6 +169,79 @@ static void thread_context_get_cpu_affinity(Object *obj, 
Visitor *v,
     qapi_free_uint16List(host_cpus);
 }
 
+static void thread_context_set_node_affinity(Object *obj, Visitor *v,
+                                             const char *name, void *opaque,
+                                             Error **errp)
+{
+#ifdef CONFIG_NUMA
+    const int nbits = numa_num_possible_cpus();
+    ThreadContext *tc = THREAD_CONTEXT(obj);
+    uint16List *l, *host_nodes = NULL;
+    unsigned long *bitmap = NULL;
+    struct bitmask *tmp_cpus;
+    Error *err = NULL;
+    int ret, i;
+
+    if (tc->init_cpu_bitmap) {
+        error_setg(errp, "Mixing CPU and node affinity not supported");
+        return;
+    }
+
+    visit_type_uint16List(v, name, &host_nodes, &err);
+    if (err) {
+        error_propagate(errp, err);
+        return;
+    }
+
+    if (!host_nodes) {
+        error_setg(errp, "Node list is empty");
+        goto out;
+    }
+
+    bitmap = bitmap_new(nbits);
+    tmp_cpus = numa_allocate_cpumask();
+    for (l = host_nodes; l; l = l->next) {
+        numa_bitmask_clearall(tmp_cpus);
+        ret = numa_node_to_cpus(l->value, tmp_cpus);
+        if (ret) {
+            /* We ignore any errors, such as impossible nodes. */
+            continue;
+        }
+        for (i = 0; i < nbits; i++) {
+            if (numa_bitmask_isbitset(tmp_cpus, i)) {
+                set_bit(i, bitmap);
+            }
+        }
+    }
+    numa_free_cpumask(tmp_cpus);
+
+    if (bitmap_empty(bitmap, nbits)) {
+        error_setg(errp, "The nodes select no CPUs");
+        goto out;
+    }
+
+    if (tc->thread_id != -1) {
+        /*
+         * Note: we won't be adjusting the affinity of any thread that is still
+         * around for now, but only the affinity of the context thread.
+         */
+        ret = qemu_thread_set_affinity(&tc->thread, bitmap, nbits);
+        if (ret) {
+            error_setg(errp, "Setting CPU affinity failed: %s", strerror(ret));
+        }
+    } else {
+        tc->init_cpu_bitmap = bitmap;
+        bitmap = NULL;
+        tc->init_cpu_nbits = nbits;
+    }
+out:
+    g_free(bitmap);
+    qapi_free_uint16List(host_nodes);
+#else
+    error_setg(errp, "NUMA node affinity is not supported by this QEMU");
+#endif
+}
+
 static void thread_context_get_thread_id(Object *obj, Visitor *v,
                                          const char *name, void *opaque,
                                          Error **errp)
@@ -209,6 +291,8 @@ static void thread_context_class_init(ObjectClass *oc, void 
*data)
     object_class_property_add(oc, "cpu-affinity", "int",
                               thread_context_get_cpu_affinity,
                               thread_context_set_cpu_affinity, NULL, NULL);
+    object_class_property_add(oc, "node-affinity", "int", NULL,
+                              thread_context_set_node_affinity, NULL, NULL);
 }
 
 static void thread_context_instance_init(Object *obj)
-- 
2.37.3