@@ -314,14 +314,9 @@ static void add_str(GString *s, const gchar *s1)
g_string_append_len(s, s1, strlen(s1) + 1);
}
-static int spapr_dt_memory_node(void *fdt, int nodeid, hwaddr start,
- hwaddr size)
+static int spapr_dt_memory_node(SpaprMachineState *spapr, void *fdt, int nodeid,
+ hwaddr start, hwaddr size)
{
- uint32_t associativity[] = {
- cpu_to_be32(0x4), /* length */
- cpu_to_be32(0x0), cpu_to_be32(0x0),
- cpu_to_be32(0x0), cpu_to_be32(nodeid)
- };
char mem_name[32];
uint64_t mem_reg_property[2];
int off;
@@ -335,8 +330,7 @@ static int spapr_dt_memory_node(void *fdt, int nodeid, hwaddr start,
_FDT((fdt_setprop_string(fdt, off, "device_type", "memory")));
_FDT((fdt_setprop(fdt, off, "reg", mem_reg_property,
sizeof(mem_reg_property))));
- _FDT((fdt_setprop(fdt, off, "ibm,associativity", associativity,
- sizeof(associativity))));
+ spapr_numa_write_associativity_dt(spapr, fdt, off, nodeid);
return off;
}
@@ -649,7 +643,7 @@ static int spapr_dt_memory(SpaprMachineState *spapr, void *fdt)
if (!mem_start) {
/* spapr_machine_init() checks for rma_size <= node0_size
* already */
- spapr_dt_memory_node(fdt, i, 0, spapr->rma_size);
+ spapr_dt_memory_node(spapr, fdt, i, 0, spapr->rma_size);
mem_start += spapr->rma_size;
node_size -= spapr->rma_size;
}
@@ -661,7 +655,7 @@ static int spapr_dt_memory(SpaprMachineState *spapr, void *fdt)
sizetmp = 1ULL << ctzl(mem_start);
}
- spapr_dt_memory_node(fdt, i, mem_start, sizetmp);
+ spapr_dt_memory_node(spapr, fdt, i, mem_start, sizetmp);
node_size -= sizetmp;
mem_start += sizetmp;
}
@@ -1275,7 +1269,7 @@ void *spapr_build_fdt(SpaprMachineState *spapr, bool reset, size_t space)
/* NVDIMM devices */
if (mc->nvdimm_supported) {
- spapr_dt_persistent_memory(fdt);
+ spapr_dt_persistent_memory(spapr, fdt);
}
return fdt;
@@ -2810,6 +2804,9 @@ static void spapr_machine_init(MachineState *machine)
*/
spapr->gpu_numa_id = MAX(1, machine->numa_state->num_nodes);
+ /* Init numa_assoc_array */
+ spapr_numa_associativity_init(spapr, machine);
+
if ((!kvm_enabled() || kvmppc_has_cap_mmu_radix()) &&
ppc_type_check_compat(machine->cpu_type, CPU_POWERPC_LOGICAL_3_00, 0,
spapr->max_compat_pvr)) {
@@ -3394,7 +3391,7 @@ int spapr_lmb_dt_populate(SpaprDrc *drc, SpaprMachineState *spapr,
addr = spapr_drc_index(drc) * SPAPR_MEMORY_BLOCK_SIZE;
node = object_property_get_uint(OBJECT(drc->dev), PC_DIMM_NODE_PROP,
&error_abort);
- *fdt_start_offset = spapr_dt_memory_node(fdt, node, addr,
+ *fdt_start_offset = spapr_dt_memory_node(spapr, fdt, node, addr,
SPAPR_MEMORY_BLOCK_SIZE);
return 0;
}
@@ -15,6 +15,36 @@
#include "hw/ppc/spapr_numa.h"
#include "hw/ppc/fdt.h"
+
+void spapr_numa_associativity_init(SpaprMachineState *spapr,
+ MachineState *machine)
+{
+ int nb_numa_nodes = machine->numa_state->num_nodes;
+ int i;
+
+ /*
+ * For all associativity arrays: first position is the size,
+ * position MAX_DISTANCE_REF_POINTS is always the numa_id,
+ * represented by the index 'i'.
+ *
+ * This will break on sparse NUMA setups, when/if QEMU starts
+ * to support it, because there will be no more guarantee that
+ * 'i' will be a valid node_id set by the user.
+ */
+ for (i = 0; i < nb_numa_nodes; i++) {
+ 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);
+ }
+}
+
+void spapr_numa_write_associativity_dt(SpaprMachineState *spapr, void *fdt,
+ int offset, int nodeid)
+{
+ _FDT((fdt_setprop(fdt, offset, "ibm,associativity",
+ spapr->numa_assoc_array[nodeid],
+ sizeof(spapr->numa_assoc_array[nodeid]))));
+}
+
/*
* Helper that writes ibm,associativity-reference-points and
* max-associativity-domains in the RTAS pointed by @rtas
@@ -31,6 +31,7 @@
#include "hw/ppc/fdt.h"
#include "qemu/range.h"
#include "sysemu/sysemu.h"
+#include "hw/ppc/spapr_numa.h"
void spapr_nvdimm_validate(HotplugHandler *hotplug_dev, NVDIMMDevice *nvdimm,
uint64_t size, Error **errp)
@@ -117,8 +118,8 @@ void spapr_create_nvdimm_dr_connectors(SpaprMachineState *spapr)
}
-static int spapr_dt_nvdimm(void *fdt, int parent_offset,
- NVDIMMDevice *nvdimm)
+static int spapr_dt_nvdimm(SpaprMachineState *spapr, void *fdt,
+ int parent_offset, NVDIMMDevice *nvdimm)
{
int child_offset;
char *buf;
@@ -128,11 +129,6 @@ static int spapr_dt_nvdimm(void *fdt, int parent_offset,
&error_abort);
uint64_t slot = object_property_get_uint(OBJECT(nvdimm), PC_DIMM_SLOT_PROP,
&error_abort);
- uint32_t associativity[] = {
- cpu_to_be32(0x4), /* length */
- cpu_to_be32(0x0), cpu_to_be32(0x0),
- cpu_to_be32(0x0), cpu_to_be32(node)
- };
uint64_t lsize = nvdimm->label_size;
uint64_t size = object_property_get_int(OBJECT(nvdimm), PC_DIMM_SIZE_PROP,
NULL);
@@ -152,8 +148,7 @@ static int spapr_dt_nvdimm(void *fdt, int parent_offset,
_FDT((fdt_setprop_string(fdt, child_offset, "compatible", "ibm,pmemory")));
_FDT((fdt_setprop_string(fdt, child_offset, "device_type", "ibm,pmemory")));
- _FDT((fdt_setprop(fdt, child_offset, "ibm,associativity", associativity,
- sizeof(associativity))));
+ spapr_numa_write_associativity_dt(spapr, fdt, child_offset, node);
buf = qemu_uuid_unparse_strdup(&nvdimm->uuid);
_FDT((fdt_setprop_string(fdt, child_offset, "ibm,unit-guid", buf)));
@@ -179,12 +174,12 @@ int spapr_pmem_dt_populate(SpaprDrc *drc, SpaprMachineState *spapr,
{
NVDIMMDevice *nvdimm = NVDIMM(drc->dev);
- *fdt_start_offset = spapr_dt_nvdimm(fdt, 0, nvdimm);
+ *fdt_start_offset = spapr_dt_nvdimm(spapr, fdt, 0, nvdimm);
return 0;
}
-void spapr_dt_persistent_memory(void *fdt)
+void spapr_dt_persistent_memory(SpaprMachineState *spapr, void *fdt)
{
int offset = fdt_subnode_offset(fdt, 0, "persistent-memory");
GSList *iter, *nvdimms = nvdimm_get_device_list();
@@ -202,7 +197,7 @@ void spapr_dt_persistent_memory(void *fdt)
for (iter = nvdimms; iter; iter = iter->next) {
NVDIMMDevice *nvdimm = iter->data;
- spapr_dt_nvdimm(fdt, offset, nvdimm);
+ spapr_dt_nvdimm(spapr, fdt, offset, nvdimm);
}
g_slist_free(nvdimms);
@@ -52,6 +52,7 @@
#include "sysemu/kvm.h"
#include "sysemu/hostmem.h"
#include "sysemu/numa.h"
+#include "hw/ppc/spapr_numa.h"
/* Copied from the kernel arch/powerpc/platforms/pseries/msi.c */
#define RTAS_QUERY_FN 0
@@ -2321,11 +2322,6 @@ int spapr_dt_phb(SpaprMachineState *spapr, SpaprPhbState *phb,
cpu_to_be32(1),
cpu_to_be32(RTAS_IBM_RESET_PE_DMA_WINDOW)
};
- uint32_t associativity[] = {cpu_to_be32(0x4),
- cpu_to_be32(0x0),
- cpu_to_be32(0x0),
- cpu_to_be32(0x0),
- cpu_to_be32(phb->numa_node)};
SpaprTceTable *tcet;
SpaprDrc *drc;
Error *err = NULL;
@@ -2358,8 +2354,7 @@ int spapr_dt_phb(SpaprMachineState *spapr, SpaprPhbState *phb,
/* Advertise NUMA via ibm,associativity */
if (phb->numa_node != -1) {
- _FDT(fdt_setprop(fdt, bus_off, "ibm,associativity", associativity,
- sizeof(associativity)));
+ spapr_numa_write_associativity_dt(spapr, fdt, bus_off, phb->numa_node);
}
/* Build the interrupt-map, this must matches what is done
@@ -105,6 +105,16 @@ typedef enum {
#define FDT_MAX_SIZE 0x100000
+/*
+ * NUMA related macros. MAX_DISTANCE_REF_POINTS was taken
+ * from Taken from Linux kernel arch/powerpc/mm/numa.h.
+ *
+ * NUMA_ASSOC_SIZE is the base array size of an ibm,associativity
+ * array for any non-CPU resource.
+ */
+#define MAX_DISTANCE_REF_POINTS 4
+#define NUMA_ASSOC_SIZE (MAX_DISTANCE_REF_POINTS + 1)
+
typedef struct SpaprCapabilities SpaprCapabilities;
struct SpaprCapabilities {
uint8_t caps[SPAPR_CAP_NUM];
@@ -231,6 +241,8 @@ struct SpaprMachineState {
unsigned gpu_numa_id;
SpaprTpmProxy *tpm_proxy;
+ uint32_t numa_assoc_array[MAX_NODES][NUMA_ASSOC_SIZE];
+
Error *fwnmi_migration_blocker;
};
@@ -13,8 +13,19 @@
#ifndef HW_SPAPR_NUMA_H
#define HW_SPAPR_NUMA_H
+#include "hw/boards.h"
#include "hw/ppc/spapr.h"
+/*
+ * Having both SpaprMachineState and MachineState as arguments
+ * feels odd, but it will spare a MACHINE() call inside the
+ * function. spapr_machine_init() is the only caller for it, and
+ * it has both pointers resolved already.
+ */
+void spapr_numa_associativity_init(SpaprMachineState *spapr,
+ MachineState *machine);
void spapr_numa_write_rtas_dt(SpaprMachineState *spapr, void *fdt, int rtas);
+void spapr_numa_write_associativity_dt(SpaprMachineState *spapr, void *fdt,
+ int offset, int nodeid);
#endif /* HW_SPAPR_NUMA_H */
@@ -27,7 +27,7 @@ QEMU_BUILD_BUG_ON(SPAPR_MINIMUM_SCM_BLOCK_SIZE % SPAPR_MEMORY_BLOCK_SIZE);
int spapr_pmem_dt_populate(SpaprDrc *drc, SpaprMachineState *spapr,
void *fdt, int *fdt_start_offset, Error **errp);
-void spapr_dt_persistent_memory(void *fdt);
+void spapr_dt_persistent_memory(SpaprMachineState *spapr, void *fdt);
void spapr_nvdimm_validate(HotplugHandler *hotplug_dev, NVDIMMDevice *nvdimm,
uint64_t size, Error **errp);
void spapr_add_nvdimm(DeviceState *dev, uint64_t slot, Error **errp);