Linux kernel guest reports warning when two CPUs in one socket have
been associated with different NUMA nodes, using the following command
lines.
-smp 6,maxcpus=6,sockets=2,clusters=1,cores=3,threads=1 \
-numa node,nodeid=0,cpus=0-1,memdev=ram0 \
-numa node,nodeid=1,cpus=2-3,memdev=ram1 \
-numa node,nodeid=2,cpus=4-5,memdev=ram2 \
------------[ cut here ]------------
WARNING: CPU: 0 PID: 1 at kernel/sched/topology.c:2271
build_sched_domains+0x284/0x910
Modules linked in:
CPU: 0 PID: 1 Comm: swapper/0 Not tainted 5.14.0-268.el9.aarch64 #1
pstate: 00400005 (nzcv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
pc : build_sched_domains+0x284/0x910
lr : build_sched_domains+0x184/0x910
sp : ffff80000804bd50
x29: ffff80000804bd50 x28: 0000000000000002 x27: 0000000000000000
x26: ffff800009cf9a80 x25: 0000000000000000 x24: ffff800009cbf840
x23: ffff000080325000 x22: ffff0000005df800 x21: ffff80000a4ce508
x20: 0000000000000000 x19: ffff000080324440 x18: 0000000000000014
x17: 00000000388925c0 x16: 000000005386a066 x15: 000000009c10cc2e
x14: 00000000000001c0 x13: 0000000000000001 x12: ffff00007fffb1a0
x11: ffff00007fffb180 x10: ffff80000a4ce508 x9 : 0000000000000041
x8 : ffff80000a4ce500 x7 : ffff80000a4cf920 x6 : 0000000000000001
x5 : 0000000000000001 x4 : 0000000000000007 x3 : 0000000000000002
x2 : 0000000000001000 x1 : ffff80000a4cf928 x0 : 0000000000000001
Call trace:
build_sched_domains+0x284/0x910
sched_init_domains+0xac/0xe0
sched_init_smp+0x48/0xc8
kernel_init_freeable+0x140/0x1ac
kernel_init+0x28/0x140
ret_from_fork+0x10/0x20
Fix it by preventing mutiple CPUs in one socket to be associated with
different NUMA nodes.
Reported-by: Yihuang Yu <yi...@redhat.com>
Signed-off-by: Gavin Shan <gs...@redhat.com>
---
hw/arm/virt.c | 37 +++++++++++++++++++++++++++++++++++++
1 file changed, 37 insertions(+)
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index ac626b3bef..e0af267c77 100644
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -230,6 +230,39 @@ static bool cpu_type_valid(const char *cpu)
return false;
}
+static bool numa_state_valid(MachineState *ms)
+{
+ MachineClass *mc = MACHINE_GET_CLASS(ms);
+ NumaState *state = ms->numa_state;
+ const CPUArchIdList *possible_cpus = mc->possible_cpu_arch_ids(ms);
+ const CPUArchId *cpus = possible_cpus->cpus;
+ int len = possible_cpus->len, i, j;
+
+ if (!state || state->num_nodes <= 1 || len <= 1) {
+ return true;
+ }
+
+ for (i = 0; i < len; i++) {
+ for (j = i + 1; j < len; j++) {
+ if (cpus[i].props.has_socket_id &&
+ cpus[i].props.has_node_id &&
+ cpus[j].props.has_socket_id &&
+ cpus[j].props.has_node_id &&
+ cpus[i].props.socket_id == cpus[j].props.socket_id &&
+ cpus[i].props.node_id != cpus[j].props.node_id) {
+ error_report("CPU-%d and CPU-%d in socket-%ld have been "
+ "associated with node-%ld and node-%ld",
+ i, j, cpus[i].props.socket_id,
+ cpus[i].props.node_id,
+ cpus[j].props.node_id);
+ return false;
+ }
+ }
+ }
+
+ return true;
+}
+
static void create_randomness(MachineState *ms, const char *node)
{
struct {
@@ -2040,6 +2073,10 @@ static void machvirt_init(MachineState *machine)
exit(1);
}
+ if (!numa_state_valid(machine)) {
+ exit(1);
+ }
+
possible_cpus = mc->possible_cpu_arch_ids(machine);
/*
--
2.23.0
