Merge remote-tracking branch 'remotes/ehabkost/tags/work/numa-verify-cpus-pull-request' into staging

NUMA queue 2015-03-19

# gpg: Signature made Thu Mar 19 19:25:53 2015 GMT using RSA key ID 984DC5A6
# gpg: Can't check signature: public key not found

* remotes/ehabkost/tags/work/numa-verify-cpus-pull-request:
  numa: Print warning if no node is assigned to a CPU
  pc: fix default VCPU to NUMA node mapping
  numa: introduce machine callback for VCPU to node mapping
  numa: Reject configuration if CPU appears on multiple nodes
  numa: Reject CPU indexes > max_cpus
  numa: Fix off-by-one error at MAX_CPUMASK_BITS check

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

5 files changed, 82 insertions, 10 deletions

diff --git a/hw/i386/pc.c b/hw/i386/pc.c
index 4b46c299c3..a52d2aff7c 100644
--- a/hw/i386/pc.c
+++ b/hw/i386/pc.c
@@ -1851,6 +1851,14 @@ static void pc_machine_initfn(Object *obj)
                              NULL, NULL);
 }
 
+static unsigned pc_cpu_index_to_socket_id(unsigned cpu_index)
+{
+    unsigned pkg_id, core_id, smt_id;
+    x86_topo_ids_from_idx(smp_cores, smp_threads, cpu_index,
+                          &pkg_id, &core_id, &smt_id);
+    return pkg_id;
+}
+
 static void pc_machine_class_init(ObjectClass *oc, void *data)
 {
     MachineClass *mc = MACHINE_CLASS(oc);
@@ -1859,6 +1867,7 @@ static void pc_machine_class_init(ObjectClass *oc, void *data)
 
     pcmc->get_hotplug_handler = mc->get_hotplug_handler;
     mc->get_hotplug_handler = pc_get_hotpug_handler;
+    mc->cpu_index_to_socket_id = pc_cpu_index_to_socket_id;
     hc->plug = pc_machine_device_plug_cb;
     hc->unplug_request = pc_machine_device_unplug_request_cb;
     hc->unplug = pc_machine_device_unplug_cb;
diff --git a/include/hw/boards.h b/include/hw/boards.h
index 1feea2b176..78838d13d4 100644
--- a/include/hw/boards.h
+++ b/include/hw/boards.h
@@ -82,6 +82,10 @@ bool machine_mem_merge(MachineState *machine);
  *    of HotplugHandler object, which handles hotplug operation
  *    for a given @dev. It may return NULL if @dev doesn't require
  *    any actions to be performed by hotplug handler.
+ * @cpu_index_to_socket_id:
+ *    used to provide @cpu_index to socket number mapping, allowing
+ *    a machine to group CPU threads belonging to the same socket/package
+ *    Returns: socket number given cpu_index belongs to.
  */
 struct MachineClass {
     /*< private >*/
@@ -118,6 +122,7 @@ struct MachineClass {
 
     HotplugHandler *(*get_hotplug_handler)(MachineState *machine,
                                            DeviceState *dev);
+    unsigned (*cpu_index_to_socket_id)(unsigned cpu_index);
 };
 
 /**
diff --git a/include/sysemu/numa.h b/include/sysemu/numa.h
index 5633b856a8..6523b4d7f9 100644
--- a/include/sysemu/numa.h
+++ b/include/sysemu/numa.h
@@ -6,6 +6,7 @@
 #include "qemu/option.h"
 #include "sysemu/sysemu.h"
 #include "sysemu/hostmem.h"
+#include "hw/boards.h"
 
 extern int nb_numa_nodes;   /* Number of NUMA nodes */
 
@@ -16,7 +17,7 @@ typedef struct node_info {
     bool present;
 } NodeInfo;
 extern NodeInfo numa_info[MAX_NODES];
-void parse_numa_opts(void);
+void parse_numa_opts(MachineClass *mc);
 void numa_post_machine_init(void);
 void query_numa_node_mem(uint64_t node_mem[]);
 extern QemuOptsList qemu_numa_opts;
diff --git a/numa.c b/numa.c
index ffbec68fd8..c975fb2682 100644
--- a/numa.c
+++ b/numa.c
@@ -76,9 +76,11 @@ static void numa_node_parse(NumaNodeOptions *node, QemuOpts *opts, Error **errp)
     }
 
     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);
+        if (cpus->value >= max_cpus) {
+            error_setg(errp,
+                       "CPU index (%" PRIu16 ")"
+                       " should be smaller than maxcpus (%d)",
+                       cpus->value, max_cpus);
             return;
         }
         bitmap_set(numa_info[nodenr].node_cpu, cpus->value, 1);
@@ -165,7 +167,52 @@ error:
     return -1;
 }
 
-void parse_numa_opts(void)
+static char *enumerate_cpus(unsigned long *cpus, int max_cpus)
+{
+    int cpu;
+    bool first = true;
+    GString *s = g_string_new(NULL);
+
+    for (cpu = find_first_bit(cpus, max_cpus);
+        cpu < max_cpus;
+        cpu = find_next_bit(cpus, max_cpus, cpu + 1)) {
+        g_string_append_printf(s, "%s%d", first ? "" : " ", cpu);
+        first = false;
+    }
+    return g_string_free(s, FALSE);
+}
+
+static void validate_numa_cpus(void)
+{
+    int i;
+    DECLARE_BITMAP(seen_cpus, MAX_CPUMASK_BITS);
+
+    bitmap_zero(seen_cpus, MAX_CPUMASK_BITS);
+    for (i = 0; i < nb_numa_nodes; i++) {
+        if (bitmap_intersects(seen_cpus, numa_info[i].node_cpu,
+                              MAX_CPUMASK_BITS)) {
+            bitmap_and(seen_cpus, seen_cpus,
+                       numa_info[i].node_cpu, MAX_CPUMASK_BITS);
+            error_report("CPU(s) present in multiple NUMA nodes: %s",
+                         enumerate_cpus(seen_cpus, max_cpus));;
+            exit(EXIT_FAILURE);
+        }
+        bitmap_or(seen_cpus, seen_cpus,
+                  numa_info[i].node_cpu, MAX_CPUMASK_BITS);
+    }
+
+    if (!bitmap_full(seen_cpus, max_cpus)) {
+        char *msg;
+        bitmap_complement(seen_cpus, seen_cpus, max_cpus);
+        msg = enumerate_cpus(seen_cpus, max_cpus);
+        error_report("warning: CPU(s) not present in any NUMA nodes: %s", msg);
+        error_report("warning: All CPU(s) up to maxcpus should be described "
+                     "in NUMA config");
+        g_free(msg);
+    }
+}
+
+void parse_numa_opts(MachineClass *mc)
 {
     int i;
 
@@ -233,15 +280,25 @@ void parse_numa_opts(void)
                 break;
             }
         }
-        /* assigning the VCPUs round-robin is easier to implement, guest OSes
-         * must cope with this anyway, because there are BIOSes out there in
-         * real machines which also use this scheme.
+        /* Historically VCPUs were assigned in round-robin order to NUMA
+         * nodes. However it causes issues with guest not handling it nice
+         * in case where cores/threads from a multicore CPU appear on
+         * different nodes. So allow boards to override default distribution
+         * rule grouping VCPUs by socket so that VCPUs from the same socket
+         * would be on the same node.
          */
         if (i == nb_numa_nodes) {
             for (i = 0; i < max_cpus; i++) {
-                set_bit(i, numa_info[i % nb_numa_nodes].node_cpu);
+                unsigned node_id = i % nb_numa_nodes;
+                if (mc->cpu_index_to_socket_id) {
+                    node_id = mc->cpu_index_to_socket_id(i) % nb_numa_nodes;
+                }
+
+                set_bit(i, numa_info[node_id].node_cpu);
             }
         }
+
+        validate_numa_cpus();
     }
 }
 
diff --git a/vl.c b/vl.c
index 69617d640a..75ec292216 100644
--- a/vl.c
+++ b/vl.c
@@ -4170,7 +4170,7 @@ int main(int argc, char **argv, char **envp)
     default_drive(default_floppy, snapshot, IF_FLOPPY, 0, FD_OPTS);
     default_drive(default_sdcard, snapshot, IF_SD, 0, SD_OPTS);
 
-    parse_numa_opts();
+    parse_numa_opts(machine_class);
 
     if (qemu_opts_foreach(qemu_find_opts("mon"), mon_init_func, NULL, 1) != 0) {
         exit(1);