powerpc/numa: Detect support for coregroup

Add support for grouping cores based on the device-tree classification.
- The last domain in the associativity domains always refers to the
core.
- If primary reference domain happens to be the penultimate domain in
the associativity domains device-tree property, then there are no
coregroups. However if its not a penultimate domain, then there are
coregroups. There can be more than one coregroup. For now we would be
interested in the last or the smallest coregroups, i.e one sub-group
per DIE.

Currently there are no firmwares that are exposing this grouping. Hence
allow the basis for grouping to be abstract.  Once the firmware starts
using this grouping, code would be added to detect the type of grouping
and adjust the sd domain flags accordingly.

Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Reviewed-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200810071834.92514-8-srikar@linux.vnet.ibm.com

diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h
index b727f5f..041f0b9 100644 (file)
--- a/arch/powerpc/include/asm/smp.h
+++ b/arch/powerpc/include/asm/smp.h
@@ -28,6 +28,7 @@
 extern int boot_cpuid;
 extern int spinning_secondaries;
 extern u32 *cpu_to_phys_id;
+extern bool coregroup_enabled;
 
 extern void cpu_die(void);
 extern int cpu_to_chip_id(int cpu);

diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 016a822..a44b935 100644 (file)
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -75,6 +75,7 @@ static DEFINE_PER_CPU(int, cpu_state) = { 0 };
 
 struct task_struct *secondary_current;
 bool has_big_cores;
+bool coregroup_enabled;
 
 DEFINE_PER_CPU(cpumask_var_t, cpu_sibling_map);
 DEFINE_PER_CPU(cpumask_var_t, cpu_smallcore_map);

diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 481951a..b2c44c5 100644 (file)
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -897,7 +897,9 @@ static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn)
 static void __init find_possible_nodes(void)
 {
        struct device_node *rtas;
-       u32 numnodes, i;
+       const __be32 *domains;
+       int prop_length, max_nodes;
+       u32 i;
 
        if (!numa_enabled)
                return;
@@ -906,25 +908,31 @@ static void __init find_possible_nodes(void)
        if (!rtas)
                return;
 
-       if (of_property_read_u32_index(rtas, "ibm,current-associativity-domains",
-                               min_common_depth, &numnodes)) {
-               /*
-                * ibm,current-associativity-domains is a fairly recent
-                * property. If it doesn't exist, then fallback on
-                * ibm,max-associativity-domains. Current denotes what the
-                * platform can support compared to max which denotes what the
-                * Hypervisor can support.
-                */
-               if (of_property_read_u32_index(rtas, "ibm,max-associativity-domains",
-                               min_common_depth, &numnodes))
+       /*
+        * ibm,current-associativity-domains is a fairly recent property. If
+        * it doesn't exist, then fallback on ibm,max-associativity-domains.
+        * Current denotes what the platform can support compared to max
+        * which denotes what the Hypervisor can support.
+        */
+       domains = of_get_property(rtas, "ibm,current-associativity-domains",
+                                       &prop_length);
+       if (!domains) {
+               domains = of_get_property(rtas, "ibm,max-associativity-domains",
+                                       &prop_length);
+               if (!domains)
                        goto out;
        }
 
-       for (i = 0; i < numnodes; i++) {
+       max_nodes = of_read_number(&domains[min_common_depth], 1);
+       for (i = 0; i < max_nodes; i++) {
                if (!node_possible(i))
                        node_set(i, node_possible_map);
        }
 
+       prop_length /= sizeof(int);
+       if (prop_length > min_common_depth + 2)
+               coregroup_enabled = 1;
+
 out:
        of_node_put(rtas);
 }