[PATCH] spapr: Add a new level of NUMA for GPUs

[Reza Arbab]

NUMA nodes corresponding to GPU memory currently have the same
affinity/distance as normal memory nodes. Add a third NUMA associativity
reference point enabling us to give GPU nodes more distance.

Before, `numactl -H` output in a guest with 4 GPUs (nodes 2-5):

node distances:
node   0   1   2   3   4   5
  0:  10  40  40  40  40  40
  1:  40  10  40  40  40  40
  2:  40  40  10  40  40  40
  3:  40  40  40  10  40  40
  4:  40  40  40  40  10  40
  5:  40  40  40  40  40  10

After:

node distances:
node   0   1   2   3   4   5
  0:  10  40  80  80  80  80
  1:  40  10  80  80  80  80
  2:  80  80  10  80  80  80
  3:  80  80  80  10  80  80
  4:  80  80  80  80  10  80
  5:  80  80  80  80  80  10

These are the same distances as on the host, mirroring the change made
to host firmware in skiboot commit f845a648b8cb ("numa/associativity:
Add a new level of NUMA for GPU's").

Signed-off-by: Reza Arbab <ar...@linux.ibm.com>
---
 hw/ppc/spapr.c             | 6 +++++-
 hw/ppc/spapr_pci_nvlink2.c | 8 +++-----
 2 files changed, 8 insertions(+), 6 deletions(-)

diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c
index c18eab0a2305..53567f98f0c6 100644
--- a/hw/ppc/spapr.c
+++ b/hw/ppc/spapr.c
@@ -892,7 +892,11 @@ static void spapr_dt_rtas(SpaprMachineState *spapr, void 
*fdt)
     int rtas;
     GString *hypertas = g_string_sized_new(256);
     GString *qemu_hypertas = g_string_sized_new(256);
-    uint32_t refpoints[] = { cpu_to_be32(0x4), cpu_to_be32(0x4) };
+    uint32_t refpoints[] = {
+        cpu_to_be32(0x4),
+        cpu_to_be32(0x4),
+        cpu_to_be32(0x2),
+    };
     uint64_t max_device_addr = MACHINE(spapr)->device_memory->base +
         memory_region_size(&MACHINE(spapr)->device_memory->mr);
     uint32_t lrdr_capacity[] = {
diff --git a/hw/ppc/spapr_pci_nvlink2.c b/hw/ppc/spapr_pci_nvlink2.c
index 8332d5694e46..f2cb26019e88 100644
--- a/hw/ppc/spapr_pci_nvlink2.c
+++ b/hw/ppc/spapr_pci_nvlink2.c
@@ -37,8 +37,6 @@
 #define PHANDLE_NVLINK(phb, gn, nn)  (0x00130000 | (((phb)->index) << 8) | \
                                      ((gn) << 4) | (nn))
 
-#define SPAPR_GPU_NUMA_ID           (cpu_to_be32(1))
-
 typedef struct SpaprPhbPciNvGpuSlot {
         uint64_t tgt;
         uint64_t gpa;
@@ -361,9 +359,9 @@ void spapr_phb_nvgpu_ram_populate_dt(SpaprPhbState *sphb, 
void *fdt)
                                                     "nvlink2-mr[0]", NULL);
         uint32_t associativity[] = {
             cpu_to_be32(0x4),
-            SPAPR_GPU_NUMA_ID,
-            SPAPR_GPU_NUMA_ID,
-            SPAPR_GPU_NUMA_ID,
+            cpu_to_be32(nvslot->numa_id),
+            cpu_to_be32(nvslot->numa_id),
+            cpu_to_be32(nvslot->numa_id),
             cpu_to_be32(nvslot->numa_id)
         };
         uint64_t size = object_property_get_uint(nv_mrobj, "size", NULL);
-- 
2.18.1