powerpc/pseries: Update CPU maps when device tree is updated

Platform events such as partition migration or the new PRRN firmware
feature can cause the NUMA characteristics of a CPU to change, and these
changes will be reflected in the device tree nodes for the affected
CPUs.

This patch registers a handler for Open Firmware device tree updates
and reconfigures the CPU and node maps whenever the associativity
changes. Currently, this is accomplished by marking the affected CPUs in
the cpu_associativity_changes_mask and allowing
arch_update_cpu_topology() to retrieve the new associativity information
using hcall_vphn().

Protecting the NUMA cpu maps from concurrent access during an update
operation will be addressed in a subsequent patch in this series.

Signed-off-by: Nathan Fontenot <nfont@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

4 files changed, 79 insertions, 25 deletions

diff --git a/arch/powerpc/include/asm/firmware.h b/arch/powerpc/include/asm/firmware.h
index 6e336e0978b1..0df54646f968 100644
--- a/arch/powerpc/include/asm/firmware.h
+++ b/arch/powerpc/include/asm/firmware.h
@@ -51,6 +51,7 @@
 #define FW_FEATURE_SET_MODE     ASM_CONST(0x0000000040000000)
 #define FW_FEATURE_BEST_ENERGY  ASM_CONST(0x0000000080000000)
 #define FW_FEATURE_TYPE1_AFFINITY ASM_CONST(0x0000000100000000)
+#define FW_FEATURE_PRRN         ASM_CONST(0x0000000200000000)
 
 #ifndef __ASSEMBLY__
 
@@ -66,7 +67,7 @@ enum {
                 FW_FEATURE_MULTITCE | FW_FEATURE_SPLPAR | FW_FEATURE_LPAR |
                 FW_FEATURE_CMO | FW_FEATURE_VPHN | FW_FEATURE_XCMO |
                 FW_FEATURE_SET_MODE | FW_FEATURE_BEST_ENERGY |
-                FW_FEATURE_TYPE1_AFFINITY,
+                FW_FEATURE_TYPE1_AFFINITY | FW_FEATURE_PRRN,
         FW_FEATURE_PSERIES_ALWAYS = 0,
         FW_FEATURE_POWERNV_POSSIBLE = FW_FEATURE_OPAL | FW_FEATURE_OPALv2,
         FW_FEATURE_POWERNV_ALWAYS = 0,
diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h
index 2ea8b856d605..bc2da154f68b 100644
--- a/arch/powerpc/include/asm/prom.h
+++ b/arch/powerpc/include/asm/prom.h
@@ -128,6 +128,7 @@ struct of_drconf_cell {
 #define OV5_CMO                 0x0480  /* Cooperative Memory Overcommitment */
 #define OV5_XCMO                0x0440  /* Page Coalescing */
 #define OV5_TYPE1_AFFINITY      0x0580  /* Type 1 NUMA affinity */
+#define OV5_PRRN                0x0540  /* Platform Resource Reassignment */
 #define OV5_PFO_HW_RNG          0x0E80  /* PFO Random Number Generator */
 #define OV5_PFO_HW_842          0x0E40  /* PFO Compression Accelerator */
 #define OV5_PFO_HW_ENCR         0x0E20  /* PFO Encryption Accelerator */
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 4cee83592b0c..42f50c352242 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -1257,7 +1257,8 @@ u64 memory_hotplug_max(void)
 static u8 vphn_cpu_change_counts[NR_CPUS][MAX_DISTANCE_REF_POINTS];
 static cpumask_t cpu_associativity_changes_mask;
 static int vphn_enabled;
-static void set_topology_timer(void);
+static int prrn_enabled;
+static void reset_topology_timer(void);
 
 /*
  * Store the current values of the associativity change counters in the
@@ -1293,11 +1294,9 @@ static void setup_cpu_associativity_change_counters(void)
  */
 static int update_cpu_associativity_changes_mask(void)
 {
-        int cpu, nr_cpus = 0;
+        int cpu;
         cpumask_t *changes = &cpu_associativity_changes_mask;
 
-        cpumask_clear(changes);
-
         for_each_possible_cpu(cpu) {
                 int i, changed = 0;
                 u8 *counts = vphn_cpu_change_counts[cpu];
@@ -1311,11 +1310,10 @@ static int update_cpu_associativity_changes_mask(void)
                 }
                 if (changed) {
                         cpumask_set_cpu(cpu, changes);
-                        nr_cpus++;
                 }
         }
 
-        return nr_cpus;
+        return cpumask_weight(changes);
 }
 
 /*
@@ -1416,7 +1414,7 @@ int arch_update_cpu_topology(void)
         unsigned int associativity[VPHN_ASSOC_BUFSIZE] = {0};
         struct device *dev;
 
-        for_each_cpu(cpu,&cpu_associativity_changes_mask) {
+        for_each_cpu(cpu, &cpu_associativity_changes_mask) {
                 vphn_get_associativity(cpu, associativity);
                 nid = associativity_to_nid(associativity);
 
@@ -1438,6 +1436,7 @@ int arch_update_cpu_topology(void)
                 dev = get_cpu_device(cpu);
                 if (dev)
                         kobject_uevent(&dev->kobj, KOBJ_CHANGE);
+                cpumask_clear_cpu(cpu, &cpu_associativity_changes_mask);
                 changed = 1;
         }
 
@@ -1457,37 +1456,80 @@ void topology_schedule_update(void)
 
 static void topology_timer_fn(unsigned long ignored)
 {
-        if (!vphn_enabled)
-                return;
-        if (update_cpu_associativity_changes_mask() > 0)
+        if (prrn_enabled && cpumask_weight(&cpu_associativity_changes_mask))
                 topology_schedule_update();
-        set_topology_timer();
+        else if (vphn_enabled) {
+                if (update_cpu_associativity_changes_mask() > 0)
+                        topology_schedule_update();
+                reset_topology_timer();
+        }
 }
 static struct timer_list topology_timer =
         TIMER_INITIALIZER(topology_timer_fn, 0, 0);
 
-static void set_topology_timer(void)
+static void reset_topology_timer(void)
 {
         topology_timer.data = 0;
         topology_timer.expires = jiffies + 60 * HZ;
-        add_timer(&topology_timer);
+        mod_timer(&topology_timer, topology_timer.expires);
+}
+
+static void stage_topology_update(int core_id)
+{
+        cpumask_or(&cpu_associativity_changes_mask,
+                &cpu_associativity_changes_mask, cpu_sibling_mask(core_id));
+        reset_topology_timer();
+}
+
+static int dt_update_callback(struct notifier_block *nb,
+                                unsigned long action, void *data)
+{
+        struct of_prop_reconfig *update;
+        int rc = NOTIFY_DONE;
+
+        switch (action) {
+        case OF_RECONFIG_ADD_PROPERTY:
+        case OF_RECONFIG_UPDATE_PROPERTY:
+                update = (struct of_prop_reconfig *)data;
+                if (!of_prop_cmp(update->dn->type, "cpu")) {
+                        u32 core_id;
+                        of_property_read_u32(update->dn, "reg", &core_id);
+                        stage_topology_update(core_id);
+                        rc = NOTIFY_OK;
+                }
+                break;
+        }
+
+        return rc;
 }
 
+static struct notifier_block dt_update_nb = {
+        .notifier_call = dt_update_callback,
+};
+
 /*
- * Start polling for VPHN associativity changes.
+ * Start polling for associativity changes.
  */
 int start_topology_update(void)
 {
         int rc = 0;
 
-        /* Disabled until races with load balancing are fixed */
-        if (0 && firmware_has_feature(FW_FEATURE_VPHN) &&
-            get_lppaca()->shared_proc) {
-                vphn_enabled = 1;
-                setup_cpu_associativity_change_counters();
-                init_timer_deferrable(&topology_timer);
-                set_topology_timer();
-                rc = 1;
+        if (firmware_has_feature(FW_FEATURE_PRRN)) {
+                if (!prrn_enabled) {
+                        prrn_enabled = 1;
+                        vphn_enabled = 0;
+                        rc = of_reconfig_notifier_register(&dt_update_nb);
+                }
+        } else if (0 && firmware_has_feature(FW_FEATURE_VPHN) &&
+                   get_lppaca()->shared_proc) {
+                /* Disabled until races with load balancing are fixed */
+                if (!vphn_enabled) {
+                        prrn_enabled = 0;
+                        vphn_enabled = 1;
+                        setup_cpu_associativity_change_counters();
+                        init_timer_deferrable(&topology_timer);
+                        reset_topology_timer();
+                }
         }
 
         return rc;
@@ -1499,7 +1541,16 @@ __initcall(start_topology_update);
  */
 int stop_topology_update(void)
 {
-        vphn_enabled = 0;
-        return del_timer_sync(&topology_timer);
+        int rc = 0;
+
+        if (prrn_enabled) {
+                prrn_enabled = 0;
+                rc = of_reconfig_notifier_unregister(&dt_update_nb);
+        } else if (vphn_enabled) {
+                vphn_enabled = 0;
+                rc = del_timer_sync(&topology_timer);
+        }
+
+        return rc;
 }
 #endif /* CONFIG_PPC_SPLPAR */
diff --git a/arch/powerpc/platforms/pseries/firmware.c b/arch/powerpc/platforms/pseries/firmware.c
index 06639fa2d61d..8c80588abacc 100644
--- a/arch/powerpc/platforms/pseries/firmware.c
+++ b/arch/powerpc/platforms/pseries/firmware.c
@@ -110,6 +110,7 @@ struct vec5_fw_feature {
 static __initdata struct vec5_fw_feature
 vec5_fw_features_table[] = {
         {FW_FEATURE_TYPE1_AFFINITY,     OV5_TYPE1_AFFINITY},
+        {FW_FEATURE_PRRN,               OV5_PRRN},
 };
 
 void __init fw_vec5_feature_init(const char *vec5, unsigned long len)