diff mbox

[4/5] Set numa topology for max_cpus

Message ID 991dfefdee8f4d1405f4b3cd799e7579f54b6c9f.1324584830.git.mtosatti@redhat.com
State New
Headers show

Commit Message

Marcelo Tosatti Dec. 22, 2011, 8:13 p.m. UTC
From: Vasilis Liaskovitis <vasilis.liaskovitis@profitbricks.com>

qemu-kvm passes numa/SRAT topology information for smp_cpus to SeaBIOS. However
SeaBIOS always expects to setup max_cpus number of SRAT cpu entries
(MaxCountCPUs variable in build_srat function of Seabios). When qemu-kvm runs
with smp_cpus != max_cpus (e.g. -smp 2,maxcpus=4), Seabios will mistakenly use
memory SRAT info for setting up CPU SRAT entries for the offline CPUs. Wrong
SRAT memory entries are also created. This breaks NUMA in a guest.
Fix by setting up SRAT info for max_cpus in qemu-kvm.

Signed-off-by: Vasilis Liaskovitis <vasilis.liaskovitis@profitbricks.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 hw/pc.c |    8 ++++----
 vl.c    |    2 +-
 2 files changed, 5 insertions(+), 5 deletions(-)
diff mbox

Patch

diff --git a/hw/pc.c b/hw/pc.c
index 3a71992..f51afa8 100644
--- a/hw/pc.c
+++ b/hw/pc.c
@@ -624,9 +624,9 @@  static void *bochs_bios_init(void)
      * of nodes, one word for each VCPU->node and one word for each node to
      * hold the amount of memory.
      */
-    numa_fw_cfg = g_malloc0((1 + smp_cpus + nb_numa_nodes) * 8);
+    numa_fw_cfg = g_malloc0((1 + max_cpus + nb_numa_nodes) * 8);
     numa_fw_cfg[0] = cpu_to_le64(nb_numa_nodes);
-    for (i = 0; i < smp_cpus; i++) {
+    for (i = 0; i < max_cpus; i++) {
         for (j = 0; j < nb_numa_nodes; j++) {
             if (node_cpumask[j] & (1 << i)) {
                 numa_fw_cfg[i + 1] = cpu_to_le64(j);
@@ -635,10 +635,10 @@  static void *bochs_bios_init(void)
         }
     }
     for (i = 0; i < nb_numa_nodes; i++) {
-        numa_fw_cfg[smp_cpus + 1 + i] = cpu_to_le64(node_mem[i]);
+        numa_fw_cfg[max_cpus + 1 + i] = cpu_to_le64(node_mem[i]);
     }
     fw_cfg_add_bytes(fw_cfg, FW_CFG_NUMA, (uint8_t *)numa_fw_cfg,
-                     (1 + smp_cpus + nb_numa_nodes) * 8);
+                     (1 + max_cpus + nb_numa_nodes) * 8);
 
     return fw_cfg;
 }
diff --git a/vl.c b/vl.c
index c03abb6..d925424 100644
--- a/vl.c
+++ b/vl.c
@@ -3305,7 +3305,7 @@  int main(int argc, char **argv, char **envp)
          * real machines which also use this scheme.
          */
         if (i == nb_numa_nodes) {
-            for (i = 0; i < smp_cpus; i++) {
+            for (i = 0; i < max_cpus; i++) {
                 node_cpumask[i % nb_numa_nodes] |= 1 << i;
             }
         }