[PATCH 3/3] spapr_numa.c: fix ibm, max-associativity-domains calculation

[Daniel Henrique Barboza]

The current logic for calculating 'maxdomain' making it a sum of
numa_state->num_nodes with spapr->gpu_numa_id. spapr->gpu_numa_id is
used as a index to determine the next available NUMA id that a
given NVGPU can use.

The problem is that the initial value of gpu_numa_id, for any topology
that has more than one NUMA node, is equal to numa_state->num_nodes.
This means that our maxdomain will always be, at least, twice the
amount of existing NUMA nodes. This means that a guest with 4 NUMA
nodes will end up with the following max-associativity-domains:

rtas/ibm,max-associativity-domains
                 00000004 00000008 00000008 00000008 00000008

This overtuning of maxdomains doesn't go unnoticed in the guest, being
detected in SLUB during boot:

 dmesg | grep SLUB
[    0.000000] SLUB: HWalign=128, Order=0-3, MinObjects=0, CPUs=4, Nodes=8

SLUB is detecting 8 total nodes, with 4 nodes being online.

This patch fixes ibm,max-associativity-domains by considering the amount
of NVGPUs NUMA nodes presented in the guest, instead of
spapr->gpu_numa_id.

Reported-by: Cédric Le Goater <clg@kaod.org>
Signed-off-by: Daniel Henrique Barboza <danielhb413@gmail.com>
---
 hw/ppc/spapr_numa.c | 16 +++++++++++++++-
 1 file changed, 15 insertions(+), 1 deletion(-)

diff --git a/hw/ppc/spapr_numa.c b/hw/ppc/spapr_numa.c
index f71105c783..f4d6abce87 100644
--- a/hw/ppc/spapr_numa.c
+++ b/hw/ppc/spapr_numa.c
@@ -60,6 +60,19 @@ unsigned int spapr_numa_initial_nvgpu_NUMA_id(MachineState 
*machine)
     return MAX(1, machine->numa_state->num_nodes);
 }
 
+/*
+ * Note: if called before spapr_phb_pci_collect_nvgpu() finishes collecting
+ * all NVGPUs, this function will not give the right number of NVGPUs NUMA
+ * nodes.
+ */
+static
+unsigned int spapr_numa_get_number_nvgpus_nodes(SpaprMachineState *spapr)
+{
+    MachineState *ms = MACHINE(spapr);
+
+    return spapr->gpu_numa_id - spapr_numa_initial_nvgpu_NUMA_id(ms);
+}
+
 /*
  * This function will translate the user distances into
  * what the kernel understand as possible values: 10
@@ -311,6 +324,7 @@ void spapr_numa_write_rtas_dt(SpaprMachineState *spapr, 
void *fdt, int rtas)
 {
     MachineState *ms = MACHINE(spapr);
     SpaprMachineClass *smc = SPAPR_MACHINE_GET_CLASS(spapr);
+    uint32_t number_nvgpus_nodes = spapr_numa_get_number_nvgpus_nodes(spapr);
     uint32_t refpoints[] = {
         cpu_to_be32(0x4),
         cpu_to_be32(0x3),
@@ -318,7 +332,7 @@ void spapr_numa_write_rtas_dt(SpaprMachineState *spapr, 
void *fdt, int rtas)
         cpu_to_be32(0x1),
     };
     uint32_t nr_refpoints = ARRAY_SIZE(refpoints);
-    uint32_t maxdomain = ms->numa_state->num_nodes + spapr->gpu_numa_id;
+    uint32_t maxdomain = ms->numa_state->num_nodes + number_nvgpus_nodes;
     uint32_t maxdomains[] = {
         cpu_to_be32(4),
         cpu_to_be32(maxdomain),
-- 
2.26.2