[Qemu-devel] [PATCH V8 04/11] NUMA: Add numa_info structure to contain numa nodes info

[Wanlong Gao <gaowanlong@cn.fujitsu.com>]

Add the numa_info structure to contain the numa nodes memory,
VCPUs information and the future added numa nodes host memory
policies.

Reviewed-by: Eduardo Habkost <ehabkost@redhat.com>
Signed-off-by: Andre Przywara <andre.przywara@amd.com>
Signed-off-by: Wanlong Gao <gaowanlong@cn.fujitsu.com>
---
 hw/i386/pc.c            |  4 ++--
 include/sysemu/sysemu.h |  8 ++++++--
 monitor.c               |  2 +-
 numa.c                  | 21 +++++++++++----------
 vl.c                    |  7 +++----
 5 files changed, 23 insertions(+), 19 deletions(-)

diff --git a/hw/i386/pc.c b/hw/i386/pc.c
index e8bc8ce..1a534b2 100644
--- a/hw/i386/pc.c
+++ b/hw/i386/pc.c
@@ -653,14 +653,14 @@ static FWCfgState *bochs_bios_init(void)
         unsigned int apic_id = x86_cpu_apic_id_from_index(i);
         assert(apic_id < apic_id_limit);
         for (j = 0; j < nb_numa_nodes; j++) {
-            if (test_bit(i, node_cpumask[j])) {
+            if (test_bit(i, numa_info[j].node_cpu)) {
                 numa_fw_cfg[apic_id + 1] = cpu_to_le64(j);
                 break;
             }
         }
     }
     for (i = 0; i < nb_numa_nodes; i++) {
-        numa_fw_cfg[apic_id_limit + 1 + i] = cpu_to_le64(node_mem[i]);
+        numa_fw_cfg[apic_id_limit + 1 + i] = cpu_to_le64(numa_info[i].node_mem);
     }
     fw_cfg_add_bytes(fw_cfg, FW_CFG_NUMA, numa_fw_cfg,
                      (1 + apic_id_limit + nb_numa_nodes) *
diff --git a/include/sysemu/sysemu.h b/include/sysemu/sysemu.h
index b42f4a1..b683d08 100644
--- a/include/sysemu/sysemu.h
+++ b/include/sysemu/sysemu.h
@@ -9,6 +9,7 @@
 #include "qapi-types.h"
 #include "qemu/notify.h"
 #include "qemu/main-loop.h"
+#include "qemu/bitmap.h"
 
 /* vl.c */
 
@@ -130,8 +131,11 @@ extern QEMUClock *rtc_clock;
 #define MAX_CPUMASK_BITS 255
 extern int nb_numa_nodes;
 extern int nb_numa_mem_nodes;
-extern uint64_t node_mem[MAX_NODES];
-extern unsigned long *node_cpumask[MAX_NODES];
+typedef struct node_info {
+    uint64_t node_mem;
+    DECLARE_BITMAP(node_cpu, MAX_CPUMASK_BITS);
+} NodeInfo;
+extern NodeInfo numa_info[MAX_NODES];
 extern QemuOptsList qemu_numa_opts;
 int numa_init_func(QemuOpts *opts, void *opaque);
 void set_numa_nodes(void);
diff --git a/monitor.c b/monitor.c
index 5dc0aa9..513af25 100644
--- a/monitor.c
+++ b/monitor.c
@@ -1826,7 +1826,7 @@ static void do_info_numa(Monitor *mon, const QDict *qdict)
         }
         monitor_printf(mon, "\n");
         monitor_printf(mon, "node %d size: %" PRId64 " MB\n", i,
-            node_mem[i] >> 20);
+            numa_info[i].node_mem >> 20);
     }
 }
 
diff --git a/numa.c b/numa.c
index 7b37a3b..fa2e4ea 100644
--- a/numa.c
+++ b/numa.c
@@ -53,7 +53,7 @@ static int numa_node_parse(NumaNodeOptions *opts)
     }
 
     for (cpus = opts->cpus; cpus; cpus = cpus->next) {
-        bitmap_set(node_cpumask[nodenr], cpus->value, 1);
+        bitmap_set(numa_info[nodenr].node_cpu, cpus->value, 1);
     }
 
     if (opts->has_mem) {
@@ -64,7 +64,7 @@ static int numa_node_parse(NumaNodeOptions *opts)
             fprintf(stderr, "qemu: invalid numa mem size: %s\n", opts->mem);
             return -1;
         }
-        node_mem[nodenr] = mem_size;
+        numa_info[nodenr].node_mem = mem_size;
     }
 
     return 0;
@@ -88,7 +88,7 @@ static int numa_mem_parse(NumaMemOptions *opts)
 
     if (opts->has_size) {
         mem_size = opts->size;
-        node_mem[nodenr] = mem_size;
+        numa_info[nodenr].node_mem = mem_size;
     }
 
     return 0;
@@ -160,7 +160,7 @@ void set_numa_nodes(void)
          * and distribute the available memory equally across all nodes
          */
         for (i = 0; i < nb_numa_nodes; i++) {
-            if (node_mem[i] != 0) {
+            if (numa_info[i].node_mem != 0) {
                 break;
             }
         }
@@ -172,14 +172,15 @@ void set_numa_nodes(void)
              * the final node gets the rest.
              */
             for (i = 0; i < nb_numa_nodes - 1; i++) {
-                node_mem[i] = (ram_size / nb_numa_nodes) & ~((1 << 23UL) - 1);
-                usedmem += node_mem[i];
+                numa_info[i].node_mem = (ram_size / nb_numa_nodes) &
+                                        ~((1 << 23UL) - 1);
+                usedmem += numa_info[i].node_mem;
             }
-            node_mem[i] = ram_size - usedmem;
+            numa_info[i].node_mem = ram_size - usedmem;
         }
 
         for (i = 0; i < nb_numa_nodes; i++) {
-            if (!bitmap_empty(node_cpumask[i], MAX_CPUMASK_BITS)) {
+            if (!bitmap_empty(numa_info[i].node_cpu, MAX_CPUMASK_BITS)) {
                 break;
             }
         }
@@ -189,7 +190,7 @@ void set_numa_nodes(void)
          */
         if (i == nb_numa_nodes) {
             for (i = 0; i < max_cpus; i++) {
-                set_bit(i, node_cpumask[i % nb_numa_nodes]);
+                set_bit(i, numa_info[i % nb_numa_nodes].node_cpu);
             }
         }
     }
@@ -202,7 +203,7 @@ void set_numa_modes(void)
 
     for (cpu = first_cpu; cpu != NULL; cpu = cpu->next_cpu) {
         for (i = 0; i < nb_numa_nodes; i++) {
-            if (test_bit(cpu->cpu_index, node_cpumask[i])) {
+            if (test_bit(cpu->cpu_index, numa_info[i].node_cpu)) {
                 cpu->numa_node = i;
             }
         }
diff --git a/vl.c b/vl.c
index 5f0a5e4..89bbccb 100644
--- a/vl.c
+++ b/vl.c
@@ -251,8 +251,7 @@ static QTAILQ_HEAD(, FWBootEntry) fw_boot_order =
 
 int nb_numa_nodes;
 int nb_numa_mem_nodes;
-uint64_t node_mem[MAX_NODES];
-unsigned long *node_cpumask[MAX_NODES];
+NodeInfo numa_info[MAX_NODES];
 
 uint8_t qemu_uuid[16];
 
@@ -2887,8 +2886,8 @@ int main(int argc, char **argv, char **envp)
     translation = BIOS_ATA_TRANSLATION_AUTO;
 
     for (i = 0; i < MAX_NODES; i++) {
-        node_mem[i] = 0;
-        node_cpumask[i] = bitmap_new(MAX_CPUMASK_BITS);
+        numa_info[i].node_mem = 0;
+        bitmap_zero(numa_info[i].node_cpu, MAX_CPUMASK_BITS);
     }
 
     nb_numa_nodes = 0;
-- 
1.8.4.rc1.21.gfb56570