[PULL 30/30] spapr_numa: move NVLink2 associativity handling to spapr_numa.c

[David Gibson <david@gibson.dropbear.id.au>]

From: Daniel Henrique Barboza <danielhb413@gmail.com>

The NVLink2 GPUs works like a regular NUMA node with its
own associativity values, regardless of user input.

This can be handled inside spapr_numa_associativity_init(),
initializing NVGPU_MAX_NUM associativity arrays that can
be used by the GPUs.

Signed-off-by: Daniel Henrique Barboza <danielhb413@gmail.com>
Message-Id: <20200903220639.563090-5-danielhb413@gmail.com>
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
---
 hw/ppc/spapr_numa.c        | 28 +++++++++++++++++++++++++++-
 hw/ppc/spapr_pci_nvlink2.c | 20 +++-----------------
 2 files changed, 30 insertions(+), 18 deletions(-)

diff --git a/hw/ppc/spapr_numa.c b/hw/ppc/spapr_numa.c
index 5a82a84438..93a000b729 100644
--- a/hw/ppc/spapr_numa.c
+++ b/hw/ppc/spapr_numa.c
@@ -13,14 +13,18 @@
 #include "qemu/osdep.h"
 #include "qemu-common.h"
 #include "hw/ppc/spapr_numa.h"
+#include "hw/pci-host/spapr.h"
 #include "hw/ppc/fdt.h"
 
+/* Moved from hw/ppc/spapr_pci_nvlink2.c */
+#define SPAPR_GPU_NUMA_ID           (cpu_to_be32(1))
 
 void spapr_numa_associativity_init(SpaprMachineState *spapr,
                                    MachineState *machine)
 {
+    SpaprMachineClass *smc = SPAPR_MACHINE_GET_CLASS(spapr);
     int nb_numa_nodes = machine->numa_state->num_nodes;
-    int i;
+    int i, j, max_nodes_with_gpus;
 
     /*
      * For all associativity arrays: first position is the size,
@@ -35,6 +39,28 @@ void spapr_numa_associativity_init(SpaprMachineState *spapr,
         spapr->numa_assoc_array[i][0] = cpu_to_be32(MAX_DISTANCE_REF_POINTS);
         spapr->numa_assoc_array[i][MAX_DISTANCE_REF_POINTS] = cpu_to_be32(i);
     }
+
+    /*
+     * Initialize NVLink GPU associativity arrays. We know that
+     * the first GPU will take the first available NUMA id, and
+     * we'll have a maximum of NVGPU_MAX_NUM GPUs in the machine.
+     * At this point we're not sure if there are GPUs or not, but
+     * let's initialize the associativity arrays and allow NVLink
+     * GPUs to be handled like regular NUMA nodes later on.
+     */
+    max_nodes_with_gpus = nb_numa_nodes + NVGPU_MAX_NUM;
+
+    for (i = nb_numa_nodes; i < max_nodes_with_gpus; i++) {
+        spapr->numa_assoc_array[i][0] = cpu_to_be32(MAX_DISTANCE_REF_POINTS);
+
+        for (j = 1; j < MAX_DISTANCE_REF_POINTS; j++) {
+            uint32_t gpu_assoc = smc->pre_5_1_assoc_refpoints ?
+                                 SPAPR_GPU_NUMA_ID : cpu_to_be32(i);
+            spapr->numa_assoc_array[i][j] = gpu_assoc;
+        }
+
+        spapr->numa_assoc_array[i][MAX_DISTANCE_REF_POINTS] = cpu_to_be32(i);
+    }
 }
 
 void spapr_numa_write_associativity_dt(SpaprMachineState *spapr, void *fdt,
diff --git a/hw/ppc/spapr_pci_nvlink2.c b/hw/ppc/spapr_pci_nvlink2.c
index 76ae77ebc8..8ef9b40a18 100644
--- a/hw/ppc/spapr_pci_nvlink2.c
+++ b/hw/ppc/spapr_pci_nvlink2.c
@@ -26,6 +26,7 @@
 #include "qemu-common.h"
 #include "hw/pci/pci.h"
 #include "hw/pci-host/spapr.h"
+#include "hw/ppc/spapr_numa.h"
 #include "qemu/error-report.h"
 #include "hw/ppc/fdt.h"
 #include "hw/pci/pci_bridge.h"
@@ -37,8 +38,6 @@
 #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;
@@ -360,13 +359,6 @@ void spapr_phb_nvgpu_ram_populate_dt(SpaprPhbState *sphb, void *fdt)
         Object *nv_mrobj = object_property_get_link(OBJECT(nvslot->gpdev),
                                                     "nvlink2-mr[0]",
                                                     &error_abort);
-        uint32_t associativity[] = {
-            cpu_to_be32(0x4),
-            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);
         uint64_t mem_reg[2] = { cpu_to_be64(nvslot->gpa), cpu_to_be64(size) };
         char *mem_name = g_strdup_printf("memory@%"PRIx64, nvslot->gpa);
@@ -376,14 +368,8 @@ void spapr_phb_nvgpu_ram_populate_dt(SpaprPhbState *sphb, void *fdt)
         _FDT((fdt_setprop_string(fdt, off, "device_type", "memory")));
         _FDT((fdt_setprop(fdt, off, "reg", mem_reg, sizeof(mem_reg))));
 
-        if (sphb->pre_5_1_assoc) {
-            associativity[1] = SPAPR_GPU_NUMA_ID;
-            associativity[2] = SPAPR_GPU_NUMA_ID;
-            associativity[3] = SPAPR_GPU_NUMA_ID;
-        }
-
-        _FDT((fdt_setprop(fdt, off, "ibm,associativity", associativity,
-                          sizeof(associativity))));
+        spapr_numa_write_associativity_dt(SPAPR_MACHINE(qdev_get_machine()),
+                                          fdt, off, nvslot->numa_id);
 
         _FDT((fdt_setprop_string(fdt, off, "compatible",
                                  "ibm,coherent-device-memory")));
-- 
2.26.2