[PATCH V10 0/2] powerpc/dlpar: Correct display of hot-add/hot-remove CPUs and memory

[PATCH V10 0/2] powerpc/dlpar: Correct display of hot-add/hot-remove CPUs and memory

[Michael Bringmann]

From: mwb@linux.vnet.ibm.com
To: linuxppc-dev@lists.ozlabs.org, linux-kernel@vger.kernel.org
Cc: nfont@linux.vnet.ibm.com
Cc: mwb@linux.vnet.ibm.com
Subject: [PATCH V10 0/2] powerpc/dlpar: Correct display of hot-add/hot-remove CPUs and memory

On Power systems with shared configurations of CPUs and memory, there
are some issues with association of additional CPUs and memory to nodes
when hot-adding resources.  These patches address some of those problems.

powerpc/numa: Correct the currently broken capability to set the
topology for shared CPUs in LPARs.  At boot time for shared CPU
lpars, the topology for each shared CPU is set to node zero, however,
this is now updated correctly using the Virtual Processor Home Node
(VPHN) capabilities information provided by the pHyp. The VPHN handling
in Linux is disabled, if PRRN handling is present.

Also, update initialization checks for device-tree attributes to
independently recognize PRRN or VPHN usage.

Finally, try to distinguish the VPHN code from the NUMA code better,
and move relevant functions to another file.

powerpc/nodes: On systems like PowerPC which allow 'hot-add' of CPU
or memory resources, it may occur that the new resources are to be
inserted into nodes that were not used for these resources at bootup.
In the kernel, any node that is used must be defined and initialized
at boot.

This patch extracts the value of the 'min_common_depth' element from
the "rtas" device tree property "ibm,max-associativity-domains" to use
as the maximum number of nodes to setup as possibly available in the
system.  [The 'min_common_depth' element is calculated from memory
associations found while loading all of the configured memory into
the system data structures at boot.]  This new setting will override
the instruction,

    nodes_and(node_possible_map, node_possible_map, node_online_map);

presently seen in the function arch/powerpc/mm/numa.c:initmem_init().

If the property is not present at boot, no operation will be performed
to define or enable additional nodes.

Signed-off-by: Michael Bringmann <mwb@linux.vnet.ibm.com>

Michael Bringmann (2):
  powerpc/numa: Update CPU topology when VPHN enabled
  powerpc/nodes: Ensure enough nodes avail for operations
---
Changes in V10:
  -- Reorganize VPHN code
  -- Revise index used with property "ibm,max-associativity-domains"

[PATCH V10 1/2] powerpc/numa: Update CPU topology when VPHN enabled

[Michael Bringmann]

powerpc/numa: Correct the currently broken capability to set the
topology for shared CPUs in LPARs.  At boot time for shared CPU
lpars, the topology for each shared CPU is set to node zero, however,
this is now updated correctly using the Virtual Processor Home Node
(VPHN) capabilities information provided by the pHyp.

Also, update initialization checks for device-tree attributes to
independently recognize PRRN or VPHN usage.

Finally, try to distinguish the VPHN code from the NUMA code better,
and move relevant functions to another file.

Signed-off-by: Michael Bringmann <mwb@linux.vnet.ibm.com>
---
Changes in V10:
  -- Reorganize VPHN code to distinguish it from NUMA processing
---
 arch/powerpc/include/asm/topology.h          |    8 
 arch/powerpc/mm/numa.c                       |  503 ----------------------
 arch/powerpc/mm/vphn.c                       |  586 ++++++++++++++++++++++++++
 arch/powerpc/mm/vphn.h                       |    4 
 arch/powerpc/platforms/pseries/hotplug-cpu.c |    2 
 5 files changed, 609 insertions(+), 494 deletions(-)

diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
index dc4e159..600e1c6 100644
--- a/arch/powerpc/include/asm/topology.h
+++ b/arch/powerpc/include/asm/topology.h
@@ -98,6 +98,14 @@ static inline int prrn_is_enabled(void)
 }
 #endif /* CONFIG_NUMA && CONFIG_PPC_SPLPAR */
 
+#if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_NEED_MULTIPLE_NODES)
+#if defined(CONFIG_PPC_SPLPAR)
+extern int timed_topology_update(int nsecs);
+#else
+#define	timed_topology_update(nsecs)	0
+#endif /* CONFIG_PPC_SPLPAR */
+#endif /* CONFIG_HOTPLUG_CPU || CONFIG_NEED_MULTIPLE_NODES */
+
 #include <asm-generic/topology.h>
 
 #ifdef CONFIG_SMP
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index b95c584..73427e290 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -29,6 +29,7 @@
 #include <linux/seq_file.h>
 #include <linux/uaccess.h>
 #include <linux/slab.h>
+#include <linux/sched.h>
 #include <asm/cputhreads.h>
 #include <asm/sparsemem.h>
 #include <asm/prom.h>
@@ -41,8 +42,12 @@
 #include <asm/setup.h>
 #include <asm/vdso.h>
 
+#include "vphn.h"
+
 static int numa_enabled = 1;
 
+bool topology_updates_enabled = true;
+
 static char *cmdline __initdata;
 
 static int numa_debug;
@@ -60,8 +65,7 @@
 static int n_mem_addr_cells, n_mem_size_cells;
 static int form1_affinity;
 
-#define MAX_DISTANCE_REF_POINTS 4
-static int distance_ref_points_depth;
+int distance_ref_points_depth;
 static const __be32 *distance_ref_points;
 static int distance_lookup_table[MAX_NUMNODES][MAX_DISTANCE_REF_POINTS];
 
@@ -142,12 +146,12 @@ static void reset_numa_cpu_lookup_table(void)
 		numa_cpu_lookup_table[cpu] = -1;
 }
 
-static void update_numa_cpu_lookup_table(unsigned int cpu, int node)
+void update_numa_cpu_lookup_table(unsigned int cpu, int node)
 {
 	numa_cpu_lookup_table[cpu] = node;
 }
 
-static void map_cpu_to_node(int cpu, int node)
+void map_cpu_to_node(int cpu, int node)
 {
 	update_numa_cpu_lookup_table(cpu, node);
 
@@ -158,7 +162,7 @@ static void map_cpu_to_node(int cpu, int node)
 }
 
 #if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_PPC_SPLPAR)
-static void unmap_cpu_from_node(unsigned long cpu)
+void unmap_cpu_from_node(unsigned long cpu)
 {
 	int node = numa_cpu_lookup_table[cpu];
 
@@ -233,7 +237,7 @@ static void initialize_distance_lookup_table(int nid,
 /* Returns nid in the range [0..MAX_NUMNODES-1], or -1 if no useful numa
  * info is found.
  */
-static int associativity_to_nid(const __be32 *associativity)
+int associativity_to_nid(const __be32 *associativity)
 {
 	int nid = -1;
 
@@ -957,8 +961,6 @@ static int __init early_numa(char *p)
 }
 early_param("numa", early_numa);
 
-static bool topology_updates_enabled = true;
-
 static int __init early_topology_updates(char *p)
 {
 	if (!p)
@@ -1135,488 +1137,3 @@ u64 memory_hotplug_max(void)
         return max(hot_add_drconf_memory_max(), memblock_end_of_DRAM());
 }
 #endif /* CONFIG_MEMORY_HOTPLUG */
-
-/* Virtual Processor Home Node (VPHN) support */
-#ifdef CONFIG_PPC_SPLPAR
-
-#include "vphn.h"
-
-struct topology_update_data {
-	struct topology_update_data *next;
-	unsigned int cpu;
-	int old_nid;
-	int new_nid;
-};
-
-static u8 vphn_cpu_change_counts[NR_CPUS][MAX_DISTANCE_REF_POINTS];
-static cpumask_t cpu_associativity_changes_mask;
-static int vphn_enabled;
-static int prrn_enabled;
-static void reset_topology_timer(void);
-
-/*
- * Store the current values of the associativity change counters in the
- * hypervisor.
- */
-static void setup_cpu_associativity_change_counters(void)
-{
-	int cpu;
-
-	/* The VPHN feature supports a maximum of 8 reference points */
-	BUILD_BUG_ON(MAX_DISTANCE_REF_POINTS > 8);
-
-	for_each_possible_cpu(cpu) {
-		int i;
-		u8 *counts = vphn_cpu_change_counts[cpu];
-		volatile u8 *hypervisor_counts = lppaca[cpu].vphn_assoc_counts;
-
-		for (i = 0; i < distance_ref_points_depth; i++)
-			counts[i] = hypervisor_counts[i];
-	}
-}
-
-/*
- * The hypervisor maintains a set of 8 associativity change counters in
- * the VPA of each cpu that correspond to the associativity levels in the
- * ibm,associativity-reference-points property. When an associativity
- * level changes, the corresponding counter is incremented.
- *
- * Set a bit in cpu_associativity_changes_mask for each cpu whose home
- * node associativity levels have changed.
- *
- * Returns the number of cpus with unhandled associativity changes.
- */
-static int update_cpu_associativity_changes_mask(void)
-{
-	int cpu;
-	cpumask_t *changes = &cpu_associativity_changes_mask;
-
-	for_each_possible_cpu(cpu) {
-		int i, changed = 0;
-		u8 *counts = vphn_cpu_change_counts[cpu];
-		volatile u8 *hypervisor_counts = lppaca[cpu].vphn_assoc_counts;
-
-		for (i = 0; i < distance_ref_points_depth; i++) {
-			if (hypervisor_counts[i] != counts[i]) {
-				counts[i] = hypervisor_counts[i];
-				changed = 1;
-			}
-		}
-		if (changed) {
-			cpumask_or(changes, changes, cpu_sibling_mask(cpu));
-			cpu = cpu_last_thread_sibling(cpu);
-		}
-	}
-
-	return cpumask_weight(changes);
-}
-
-/*
- * Retrieve the new associativity information for a virtual processor's
- * home node.
- */
-static long hcall_vphn(unsigned long cpu, __be32 *associativity)
-{
-	long rc;
-	long retbuf[PLPAR_HCALL9_BUFSIZE] = {0};
-	u64 flags = 1;
-	int hwcpu = get_hard_smp_processor_id(cpu);
-
-	rc = plpar_hcall9(H_HOME_NODE_ASSOCIATIVITY, retbuf, flags, hwcpu);
-	vphn_unpack_associativity(retbuf, associativity);
-
-	return rc;
-}
-
-static long vphn_get_associativity(unsigned long cpu,
-					__be32 *associativity)
-{
-	long rc;
-
-	rc = hcall_vphn(cpu, associativity);
-
-	switch (rc) {
-	case H_FUNCTION:
-		printk(KERN_INFO
-			"VPHN is not supported. Disabling polling...\n");
-		stop_topology_update();
-		break;
-	case H_HARDWARE:
-		printk(KERN_ERR
-			"hcall_vphn() experienced a hardware fault "
-			"preventing VPHN. Disabling polling...\n");
-		stop_topology_update();
-	}
-
-	return rc;
-}
-
-/*
- * Update the CPU maps and sysfs entries for a single CPU when its NUMA
- * characteristics change. This function doesn't perform any locking and is
- * only safe to call from stop_machine().
- */
-static int update_cpu_topology(void *data)
-{
-	struct topology_update_data *update;
-	unsigned long cpu;
-
-	if (!data)
-		return -EINVAL;
-
-	cpu = smp_processor_id();
-
-	for (update = data; update; update = update->next) {
-		int new_nid = update->new_nid;
-		if (cpu != update->cpu)
-			continue;
-
-		unmap_cpu_from_node(cpu);
-		map_cpu_to_node(cpu, new_nid);
-		set_cpu_numa_node(cpu, new_nid);
-		set_cpu_numa_mem(cpu, local_memory_node(new_nid));
-		vdso_getcpu_init();
-	}
-
-	return 0;
-}
-
-static int update_lookup_table(void *data)
-{
-	struct topology_update_data *update;
-
-	if (!data)
-		return -EINVAL;
-
-	/*
-	 * Upon topology update, the numa-cpu lookup table needs to be updated
-	 * for all threads in the core, including offline CPUs, to ensure that
-	 * future hotplug operations respect the cpu-to-node associativity
-	 * properly.
-	 */
-	for (update = data; update; update = update->next) {
-		int nid, base, j;
-
-		nid = update->new_nid;
-		base = cpu_first_thread_sibling(update->cpu);
-
-		for (j = 0; j < threads_per_core; j++) {
-			update_numa_cpu_lookup_table(base + j, nid);
-		}
-	}
-
-	return 0;
-}
-
-/*
- * Update the node maps and sysfs entries for each cpu whose home node
- * has changed. Returns 1 when the topology has changed, and 0 otherwise.
- *
- * cpus_locked says whether we already hold cpu_hotplug_lock.
- */
-int numa_update_cpu_topology(bool cpus_locked)
-{
-	unsigned int cpu, sibling, changed = 0;
-	struct topology_update_data *updates, *ud;
-	__be32 associativity[VPHN_ASSOC_BUFSIZE] = {0};
-	cpumask_t updated_cpus;
-	struct device *dev;
-	int weight, new_nid, i = 0;
-
-	if (!prrn_enabled && !vphn_enabled)
-		return 0;
-
-	weight = cpumask_weight(&cpu_associativity_changes_mask);
-	if (!weight)
-		return 0;
-
-	updates = kzalloc(weight * (sizeof(*updates)), GFP_KERNEL);
-	if (!updates)
-		return 0;
-
-	cpumask_clear(&updated_cpus);
-
-	for_each_cpu(cpu, &cpu_associativity_changes_mask) {
-		/*
-		 * If siblings aren't flagged for changes, updates list
-		 * will be too short. Skip on this update and set for next
-		 * update.
-		 */
-		if (!cpumask_subset(cpu_sibling_mask(cpu),
-					&cpu_associativity_changes_mask)) {
-			pr_info("Sibling bits not set for associativity "
-					"change, cpu%d\n", cpu);
-			cpumask_or(&cpu_associativity_changes_mask,
-					&cpu_associativity_changes_mask,
-					cpu_sibling_mask(cpu));
-			cpu = cpu_last_thread_sibling(cpu);
-			continue;
-		}
-
-		/* Use associativity from first thread for all siblings */
-		vphn_get_associativity(cpu, associativity);
-		new_nid = associativity_to_nid(associativity);
-		if (new_nid < 0 || !node_online(new_nid))
-			new_nid = first_online_node;
-
-		if (new_nid == numa_cpu_lookup_table[cpu]) {
-			cpumask_andnot(&cpu_associativity_changes_mask,
-					&cpu_associativity_changes_mask,
-					cpu_sibling_mask(cpu));
-			cpu = cpu_last_thread_sibling(cpu);
-			continue;
-		}
-
-		for_each_cpu(sibling, cpu_sibling_mask(cpu)) {
-			ud = &updates[i++];
-			ud->cpu = sibling;
-			ud->new_nid = new_nid;
-			ud->old_nid = numa_cpu_lookup_table[sibling];
-			cpumask_set_cpu(sibling, &updated_cpus);
-			if (i < weight)
-				ud->next = &updates[i];
-		}
-		cpu = cpu_last_thread_sibling(cpu);
-	}
-
-	pr_debug("Topology update for the following CPUs:\n");
-	if (cpumask_weight(&updated_cpus)) {
-		for (ud = &updates[0]; ud; ud = ud->next) {
-			pr_debug("cpu %d moving from node %d "
-					  "to %d\n", ud->cpu,
-					  ud->old_nid, ud->new_nid);
-		}
-	}
-
-	/*
-	 * In cases where we have nothing to update (because the updates list
-	 * is too short or because the new topology is same as the old one),
-	 * skip invoking update_cpu_topology() via stop-machine(). This is
-	 * necessary (and not just a fast-path optimization) since stop-machine
-	 * can end up electing a random CPU to run update_cpu_topology(), and
-	 * thus trick us into setting up incorrect cpu-node mappings (since
-	 * 'updates' is kzalloc()'ed).
-	 *
-	 * And for the similar reason, we will skip all the following updating.
-	 */
-	if (!cpumask_weight(&updated_cpus))
-		goto out;
-
-	if (cpus_locked)
-		stop_machine_cpuslocked(update_cpu_topology, &updates[0],
-					&updated_cpus);
-	else
-		stop_machine(update_cpu_topology, &updates[0], &updated_cpus);
-
-	/*
-	 * Update the numa-cpu lookup table with the new mappings, even for
-	 * offline CPUs. It is best to perform this update from the stop-
-	 * machine context.
-	 */
-	if (cpus_locked)
-		stop_machine_cpuslocked(update_lookup_table, &updates[0],
-					cpumask_of(raw_smp_processor_id()));
-	else
-		stop_machine(update_lookup_table, &updates[0],
-			     cpumask_of(raw_smp_processor_id()));
-
-	for (ud = &updates[0]; ud; ud = ud->next) {
-		unregister_cpu_under_node(ud->cpu, ud->old_nid);
-		register_cpu_under_node(ud->cpu, ud->new_nid);
-
-		dev = get_cpu_device(ud->cpu);
-		if (dev)
-			kobject_uevent(&dev->kobj, KOBJ_CHANGE);
-		cpumask_clear_cpu(ud->cpu, &cpu_associativity_changes_mask);
-		changed = 1;
-	}
-
-out:
-	kfree(updates);
-	return changed;
-}
-
-int arch_update_cpu_topology(void)
-{
-	lockdep_assert_cpus_held();
-	return numa_update_cpu_topology(true);
-}
-
-static void topology_work_fn(struct work_struct *work)
-{
-	rebuild_sched_domains();
-}
-static DECLARE_WORK(topology_work, topology_work_fn);
-
-static void topology_schedule_update(void)
-{
-	schedule_work(&topology_work);
-}
-
-static void topology_timer_fn(unsigned long ignored)
-{
-	if (prrn_enabled && cpumask_weight(&cpu_associativity_changes_mask))
-		topology_schedule_update();
-	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 reset_topology_timer(void)
-{
-	topology_timer.data = 0;
-	topology_timer.expires = jiffies + 60 * HZ;
-	mod_timer(&topology_timer, topology_timer.expires);
-}
-
-#ifdef CONFIG_SMP
-
-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_reconfig_data *update = data;
-	int rc = NOTIFY_DONE;
-
-	switch (action) {
-	case OF_RECONFIG_UPDATE_PROPERTY:
-		if (!of_prop_cmp(update->dn->type, "cpu") &&
-		    !of_prop_cmp(update->prop->name, "ibm,associativity")) {
-			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,
-};
-
-#endif
-
-/*
- * Start polling for associativity changes.
- */
-int start_topology_update(void)
-{
-	int rc = 0;
-
-	if (firmware_has_feature(FW_FEATURE_PRRN)) {
-		if (!prrn_enabled) {
-			prrn_enabled = 1;
-			vphn_enabled = 0;
-#ifdef CONFIG_SMP
-			rc = of_reconfig_notifier_register(&dt_update_nb);
-#endif
-		}
-	} else if (firmware_has_feature(FW_FEATURE_VPHN) &&
-		   lppaca_shared_proc(get_lppaca())) {
-		if (!vphn_enabled) {
-			prrn_enabled = 0;
-			vphn_enabled = 1;
-			setup_cpu_associativity_change_counters();
-			init_timer_deferrable(&topology_timer);
-			reset_topology_timer();
-		}
-	}
-
-	return rc;
-}
-
-/*
- * Disable polling for VPHN associativity changes.
- */
-int stop_topology_update(void)
-{
-	int rc = 0;
-
-	if (prrn_enabled) {
-		prrn_enabled = 0;
-#ifdef CONFIG_SMP
-		rc = of_reconfig_notifier_unregister(&dt_update_nb);
-#endif
-	} else if (vphn_enabled) {
-		vphn_enabled = 0;
-		rc = del_timer_sync(&topology_timer);
-	}
-
-	return rc;
-}
-
-int prrn_is_enabled(void)
-{
-	return prrn_enabled;
-}
-
-static int topology_read(struct seq_file *file, void *v)
-{
-	if (vphn_enabled || prrn_enabled)
-		seq_puts(file, "on\n");
-	else
-		seq_puts(file, "off\n");
-
-	return 0;
-}
-
-static int topology_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, topology_read, NULL);
-}
-
-static ssize_t topology_write(struct file *file, const char __user *buf,
-			      size_t count, loff_t *off)
-{
-	char kbuf[4]; /* "on" or "off" plus null. */
-	int read_len;
-
-	read_len = count < 3 ? count : 3;
-	if (copy_from_user(kbuf, buf, read_len))
-		return -EINVAL;
-
-	kbuf[read_len] = '\0';
-
-	if (!strncmp(kbuf, "on", 2))
-		start_topology_update();
-	else if (!strncmp(kbuf, "off", 3))
-		stop_topology_update();
-	else
-		return -EINVAL;
-
-	return count;
-}
-
-static const struct file_operations topology_ops = {
-	.read = seq_read,
-	.write = topology_write,
-	.open = topology_open,
-	.release = single_release
-};
-
-static int topology_update_init(void)
-{
-	/* Do not poll for changes if disabled at boot */
-	if (topology_updates_enabled)
-		start_topology_update();
-
-	if (!proc_create("powerpc/topology_updates", 0644, NULL, &topology_ops))
-		return -ENOMEM;
-
-	return 0;
-}
-device_initcall(topology_update_init);
-#endif /* CONFIG_PPC_SPLPAR */
diff --git a/arch/powerpc/mm/vphn.c b/arch/powerpc/mm/vphn.c
index 5f8ef50..006bcc2 100644
--- a/arch/powerpc/mm/vphn.c
+++ b/arch/powerpc/mm/vphn.c
@@ -1,4 +1,46 @@
-#include <asm/byteorder.h>
+/*
+ * pSeries VPHN support
+ *
+ * Copyright (C) 2016 Greg Kurz <gkurz@linux.vnet.ibm.com>, IBM
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/threads.h>
+#include <linux/bootmem.h>
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <linux/mmzone.h>
+#include <linux/export.h>
+#include <linux/nodemask.h>
+#include <linux/cpu.h>
+#include <linux/notifier.h>
+#include <linux/memblock.h>
+#include <linux/of.h>
+#include <linux/pfn.h>
+#include <linux/cpuset.h>
+#include <linux/node.h>
+#include <linux/stop_machine.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <linux/uaccess.h>
+#include <linux/slab.h>
+#include <linux/sched.h>
+#include <asm/cputhreads.h>
+#include <asm/sparsemem.h>
+#include <asm/prom.h>
+#include <asm/smp.h>
+#include <asm/cputhreads.h>
+#include <asm/topology.h>
+#include <asm/firmware.h>
+#include <asm/paca.h>
+#include <asm/hvcall.h>
+#include <asm/setup.h>
+#include <asm/vdso.h>
+
 #include "vphn.h"
 
 /*
@@ -68,3 +110,545 @@ int vphn_unpack_associativity(const long *packed, __be32 *unpacked)
 
 	return nr_assoc_doms;
 }
+
+
+/* Virtual Processor Home Node (VPHN) support */
+#ifdef CONFIG_PPC_SPLPAR
+
+extern bool topology_updates_enabled;
+extern int distance_ref_points_depth;
+
+extern int associativity_to_nid(const __be32 *associativity);
+extern void unmap_cpu_from_node(unsigned long cpu);
+extern void map_cpu_to_node(int cpu, int node);
+extern void update_numa_cpu_lookup_table(unsigned int cpu, int node);
+
+
+struct topology_update_data {
+	struct topology_update_data *next;
+	unsigned int cpu;
+	int old_nid;
+	int new_nid;
+};
+
+#define	TOPOLOGY_DEF_TIMER_SECS		60
+
+static u8 vphn_cpu_change_counts[NR_CPUS][MAX_DISTANCE_REF_POINTS];
+static cpumask_t cpu_associativity_changes_mask;
+static int topology_timer_secs = TOPOLOGY_DEF_TIMER_SECS;
+static int vphn_enabled;
+static int prrn_enabled;
+static int topology_inited;
+static int topology_update_needed;
+
+static void reset_topology_timer(void);
+
+/*
+ * Change polling interval for associativity changes.
+ */
+int timed_topology_update(int nsecs)
+{
+	if (nsecs > 0)
+		topology_timer_secs = nsecs;
+	else
+		topology_timer_secs = TOPOLOGY_DEF_TIMER_SECS;
+
+	if (vphn_enabled)
+		reset_topology_timer();
+
+	return 0;
+}
+
+/*
+ * Store the current values of the associativity change counters in the
+ * hypervisor.
+ */
+static void setup_cpu_associativity_change_counters(void)
+{
+	int cpu;
+
+	/* The VPHN feature supports a maximum of 8 reference points */
+	BUILD_BUG_ON(MAX_DISTANCE_REF_POINTS > 8);
+
+	for_each_possible_cpu(cpu) {
+		int i;
+		u8 *counts = vphn_cpu_change_counts[cpu];
+		volatile u8 *hypervisor_counts = lppaca[cpu].vphn_assoc_counts;
+
+		for (i = 0; i < distance_ref_points_depth; i++)
+			counts[i] = hypervisor_counts[i];
+	}
+}
+
+/*
+ * The hypervisor maintains a set of 8 associativity change counters in
+ * the VPA of each cpu that correspond to the associativity levels in the
+ * ibm,associativity-reference-points property. When an associativity
+ * level changes, the corresponding counter is incremented.
+ *
+ * Set a bit in cpu_associativity_changes_mask for each cpu whose home
+ * node associativity levels have changed.
+ *
+ * Returns the number of cpus with unhandled associativity changes.
+ */
+static int update_cpu_associativity_changes_mask(void)
+{
+	int cpu;
+	cpumask_t *changes = &cpu_associativity_changes_mask;
+
+	for_each_possible_cpu(cpu) {
+		int i, changed = 0;
+		u8 *counts = vphn_cpu_change_counts[cpu];
+		volatile u8 *hypervisor_counts = lppaca[cpu].vphn_assoc_counts;
+
+		for (i = 0; i < distance_ref_points_depth; i++) {
+			if (hypervisor_counts[i] != counts[i]) {
+				counts[i] = hypervisor_counts[i];
+				changed = 1;
+			}
+		}
+		if (changed) {
+			cpumask_or(changes, changes, cpu_sibling_mask(cpu));
+			cpu = cpu_last_thread_sibling(cpu);
+		}
+	}
+
+	return cpumask_weight(changes);
+}
+
+/*
+ * Retrieve the new associativity information for a virtual processor's
+ * home node.
+ */
+static long hcall_vphn(unsigned long cpu, __be32 *associativity)
+{
+	long rc;
+	long retbuf[PLPAR_HCALL9_BUFSIZE] = {0};
+	u64 flags = 1;
+	int hwcpu = get_hard_smp_processor_id(cpu);
+
+	rc = plpar_hcall9(H_HOME_NODE_ASSOCIATIVITY, retbuf, flags, hwcpu);
+	vphn_unpack_associativity(retbuf, associativity);
+
+	return rc;
+}
+
+static long vphn_get_associativity(unsigned long cpu,
+								__be32 *associativity)
+{
+	long rc;
+
+	rc = hcall_vphn(cpu, associativity);
+
+	switch (rc) {
+	case H_FUNCTION:
+		pr_debug("VPHN is not supported. Disabling polling...\n");
+		stop_topology_update();
+		break;
+	case H_HARDWARE:
+		printk(KERN_ERR
+			"hcall_vphn() experienced a hardware fault "
+			"preventing VPHN. Disabling polling...\n");
+		stop_topology_update();
+		break;
+	case H_SUCCESS:
+		printk(KERN_INFO
+			"VPHN hcall succeeded. Reset polling...\n");
+		timed_topology_update(0);
+		break;
+	}
+
+	return rc;
+}
+
+/*
+ * Update the CPU maps and sysfs entries for a single CPU when its NUMA
+ * characteristics change. This function doesn't perform any locking and is
+ * only safe to call from stop_machine().
+ */
+static int update_cpu_topology(void *data)
+{
+	struct topology_update_data *update;
+	unsigned long cpu;
+
+	if (!data)
+		return -EINVAL;
+
+	cpu = smp_processor_id();
+
+	for (update = data; update; update = update->next) {
+		int new_nid = update->new_nid;
+		if (cpu != update->cpu)
+			continue;
+
+		unmap_cpu_from_node(cpu);
+		map_cpu_to_node(cpu, new_nid);
+		set_cpu_numa_node(cpu, new_nid);
+		set_cpu_numa_mem(cpu, local_memory_node(new_nid));
+		vdso_getcpu_init();
+	}
+
+	return 0;
+}
+
+static int update_lookup_table(void *data)
+{
+	struct topology_update_data *update;
+
+	if (!data)
+		return -EINVAL;
+
+	/*
+	 * Upon topology update, the numa-cpu lookup table needs to be updated
+	 * for all threads in the core, including offline CPUs, to ensure that
+	 * future hotplug operations respect the cpu-to-node associativity
+	 * properly.
+	 */
+	for (update = data; update; update = update->next) {
+		int nid, base, j;
+
+		nid = update->new_nid;
+		base = cpu_first_thread_sibling(update->cpu);
+
+		for (j = 0; j < threads_per_core; j++) {
+			update_numa_cpu_lookup_table(base + j, nid);
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * Update the node maps and sysfs entries for each cpu whose home node
+ * has changed. Returns 1 when the topology has changed, and 0 otherwise.
+ *
+ * cpus_locked says whether we already hold cpu_hotplug_lock.
+ */
+int numa_update_cpu_topology(bool cpus_locked)
+{
+	unsigned int cpu, sibling, changed = 0;
+	struct topology_update_data *updates, *ud;
+	__be32 associativity[VPHN_ASSOC_BUFSIZE] = {0};
+	cpumask_t updated_cpus;
+	struct device *dev;
+	int weight, new_nid, i = 0;
+
+	if (!prrn_enabled && !vphn_enabled) {
+		if (!topology_inited)
+			topology_update_needed = 1;
+		return 0;
+	}
+
+	weight = cpumask_weight(&cpu_associativity_changes_mask);
+	if (!weight)
+		return 0;
+
+	updates = kzalloc(weight * (sizeof(*updates)), GFP_KERNEL);
+	if (!updates)
+		return 0;
+
+	cpumask_clear(&updated_cpus);
+
+	for_each_cpu(cpu, &cpu_associativity_changes_mask) {
+		/*
+		 * If siblings aren't flagged for changes, updates list
+		 * will be too short. Skip on this update and set for next
+		 * update.
+		 */
+		if (!cpumask_subset(cpu_sibling_mask(cpu),
+					&cpu_associativity_changes_mask)) {
+			pr_info("Sibling bits not set for associativity "
+					"change, cpu%d\n", cpu);
+			cpumask_or(&cpu_associativity_changes_mask,
+					&cpu_associativity_changes_mask,
+					cpu_sibling_mask(cpu));
+			cpu = cpu_last_thread_sibling(cpu);
+			continue;
+		}
+
+		/* Use associativity from first thread for all siblings */
+		vphn_get_associativity(cpu, associativity);
+		new_nid = associativity_to_nid(associativity);
+		if (new_nid < 0 || !node_online(new_nid))
+			new_nid = first_online_node;
+
+		if (new_nid == numa_cpu_lookup_table[cpu]) {
+			cpumask_andnot(&cpu_associativity_changes_mask,
+					&cpu_associativity_changes_mask,
+					cpu_sibling_mask(cpu));
+			cpu = cpu_last_thread_sibling(cpu);
+			continue;
+		}
+
+		for_each_cpu(sibling, cpu_sibling_mask(cpu)) {
+			ud = &updates[i++];
+			ud->cpu = sibling;
+			ud->new_nid = new_nid;
+			ud->old_nid = numa_cpu_lookup_table[sibling];
+			cpumask_set_cpu(sibling, &updated_cpus);
+			if (i < weight)
+				ud->next = &updates[i];
+			else
+				ud->next = NULL;	/* Don't overrun and use data
+									 * from previous hotplug ops */
+		}
+		cpu = cpu_last_thread_sibling(cpu);
+	}
+
+	pr_debug("Topology update for the following CPUs:\n");
+	if (cpumask_weight(&updated_cpus)) {
+		for (ud = &updates[0]; ud; ud = ud->next) {
+			pr_debug("cpu %d moving from node %d "
+					  "to %d\n", ud->cpu,
+					  ud->old_nid, ud->new_nid);
+		}
+	}
+
+	/*
+	 * In cases where we have nothing to update (because the updates list
+	 * is too short or because the new topology is same as the old one),
+	 * skip invoking update_cpu_topology() via stop-machine(). This is
+	 * necessary (and not just a fast-path optimization) since stop-machine
+	 * can end up electing a random CPU to run update_cpu_topology(), and
+	 * thus trick us into setting up incorrect cpu-node mappings (since
+	 * 'updates' is kzalloc()'ed).
+	 *
+	 * And for the similar reason, we will skip all the following updating.
+	 */
+	if (!cpumask_weight(&updated_cpus))
+		goto out;
+
+	if (cpus_locked)
+		stop_machine_cpuslocked(update_cpu_topology, &updates[0],
+					&updated_cpus);
+	else
+		stop_machine(update_cpu_topology, &updates[0], &updated_cpus);
+
+	/*
+	 * Update the numa-cpu lookup table with the new mappings, even for
+	 * offline CPUs. It is best to perform this update from the stop-
+	 * machine context.
+	 */
+	if (cpus_locked)
+		stop_machine_cpuslocked(update_lookup_table, &updates[0],
+					cpumask_of(raw_smp_processor_id()));
+	else
+		stop_machine(update_lookup_table, &updates[0],
+			     cpumask_of(raw_smp_processor_id()));
+
+	for (ud = &updates[0]; ud; ud = ud->next) {
+		unregister_cpu_under_node(ud->cpu, ud->old_nid);
+		register_cpu_under_node(ud->cpu, ud->new_nid);
+
+		dev = get_cpu_device(ud->cpu);
+		if (dev)
+			kobject_uevent(&dev->kobj, KOBJ_CHANGE);
+		cpumask_clear_cpu(ud->cpu, &cpu_associativity_changes_mask);
+		changed = 1;
+	}
+
+out:
+	kfree(updates);
+	topology_update_needed = 0;
+	return changed;
+}
+
+int arch_update_cpu_topology(void)
+{
+	lockdep_assert_cpus_held();
+	return numa_update_cpu_topology(true);
+}
+
+static void topology_work_fn(struct work_struct *work)
+{
+	rebuild_sched_domains();
+}
+static DECLARE_WORK(topology_work, topology_work_fn);
+
+static void topology_schedule_update(void)
+{
+	schedule_work(&topology_work);
+}
+
+static int shared_topology_update(void)
+{
+	if (firmware_has_feature(FW_FEATURE_VPHN) &&
+		   lppaca_shared_proc(get_lppaca()))
+		topology_schedule_update();
+
+	return 0;
+}
+device_initcall(shared_topology_update);
+
+static void topology_timer_fn(unsigned long ignored)
+{
+	if (prrn_enabled && cpumask_weight(&cpu_associativity_changes_mask))
+		topology_schedule_update();
+	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 reset_topology_timer(void)
+{
+	topology_timer.data = 0;
+	topology_timer.expires = jiffies + topology_timer_secs * HZ;
+	mod_timer(&topology_timer, topology_timer.expires);
+}
+
+#ifdef CONFIG_SMP
+
+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_reconfig_data *update = data;
+	int rc = NOTIFY_DONE;
+
+	switch (action) {
+	case OF_RECONFIG_UPDATE_PROPERTY:
+		if (!of_prop_cmp(update->dn->type, "cpu") &&
+		    !of_prop_cmp(update->prop->name, "ibm,associativity")) {
+			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,
+};
+
+#endif
+
+/*
+ * Start polling for associativity changes.
+ */
+int start_topology_update(void)
+{
+	int rc = 0;
+
+	if (firmware_has_feature(FW_FEATURE_PRRN)) {
+		if (!prrn_enabled) {
+			prrn_enabled = 1;
+#ifdef CONFIG_SMP
+			rc = of_reconfig_notifier_register(&dt_update_nb);
+#endif
+		}
+	}
+	if (firmware_has_feature(FW_FEATURE_VPHN) &&
+		   lppaca_shared_proc(get_lppaca())) {
+		if (!vphn_enabled) {
+			vphn_enabled = 1;
+			setup_cpu_associativity_change_counters();
+			init_timer_deferrable(&topology_timer);
+			reset_topology_timer();
+		}
+	}
+
+	return rc;
+}
+
+/*
+ * Disable polling for VPHN associativity changes.
+ */
+int stop_topology_update(void)
+{
+	int rc = 0;
+
+	if (prrn_enabled) {
+		prrn_enabled = 0;
+#ifdef CONFIG_SMP
+		rc = of_reconfig_notifier_unregister(&dt_update_nb);
+#endif
+	}
+	if (vphn_enabled) {
+		vphn_enabled = 0;
+		rc = del_timer_sync(&topology_timer);
+	}
+
+	return rc;
+}
+
+int prrn_is_enabled(void)
+{
+	return prrn_enabled;
+}
+
+static int topology_read(struct seq_file *file, void *v)
+{
+	if (vphn_enabled || prrn_enabled)
+		seq_puts(file, "on\n");
+	else
+		seq_puts(file, "off\n");
+
+	return 0;
+}
+
+static int topology_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, topology_read, NULL);
+}
+
+static ssize_t topology_write(struct file *file, const char __user *buf,
+			      size_t count, loff_t *off)
+{
+	char kbuf[4]; /* "on" or "off" plus null. */
+	int read_len;
+
+	read_len = count < 3 ? count : 3;
+	if (copy_from_user(kbuf, buf, read_len))
+		return -EINVAL;
+
+	kbuf[read_len] = '\0';
+
+	if (!strncmp(kbuf, "on", 2))
+		start_topology_update();
+	else if (!strncmp(kbuf, "off", 3))
+		stop_topology_update();
+	else
+		return -EINVAL;
+
+	return count;
+}
+
+static const struct file_operations topology_ops = {
+	.read = seq_read,
+	.write = topology_write,
+	.open = topology_open,
+	.release = single_release
+};
+
+static int topology_update_init(void)
+{
+	/* Do not poll for changes if disabled at boot */
+	if (topology_updates_enabled)
+		start_topology_update();
+
+	if (!proc_create("powerpc/topology_updates", 0644, NULL, &topology_ops))
+		return -ENOMEM;
+
+	topology_inited = 1;
+	if (topology_update_needed)
+		bitmap_fill(cpumask_bits(&cpu_associativity_changes_mask),
+					nr_cpumask_bits);
+
+	return 0;
+}
+device_initcall(topology_update_init);
+#endif /* CONFIG_PPC_SPLPAR */
diff --git a/arch/powerpc/mm/vphn.h b/arch/powerpc/mm/vphn.h
index fe8b780..a8ec93b 100644
--- a/arch/powerpc/mm/vphn.h
+++ b/arch/powerpc/mm/vphn.h
@@ -5,6 +5,10 @@
  */
 #define VPHN_REGISTER_COUNT 6
 
+/* Maximum number of affinity reference points supported by NUMA/VPHN.
+ */
+#define MAX_DISTANCE_REF_POINTS 4
+
 /*
  * 6 64-bit registers unpacked into up to 24 be32 associativity values. To
  * form the complete property we have to add the length in the first cell.
diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
index 6afd1ef..5a7fb1e 100644
--- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
+++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
@@ -356,6 +356,7 @@ static int dlpar_online_cpu(struct device_node *dn)
 			BUG_ON(get_cpu_current_state(cpu)
 					!= CPU_STATE_OFFLINE);
 			cpu_maps_update_done();
+			timed_topology_update(1);
 			rc = device_online(get_cpu_device(cpu));
 			if (rc)
 				goto out;
@@ -522,6 +523,7 @@ static int dlpar_offline_cpu(struct device_node *dn)
 				set_preferred_offline_state(cpu,
 							    CPU_STATE_OFFLINE);
 				cpu_maps_update_done();
+				timed_topology_update(1);
 				rc = device_offline(get_cpu_device(cpu));
 				if (rc)
 					goto out;

Re: [PATCH V10 1/2] powerpc/numa: Update CPU topology when VPHN enabled

[Nathan Fontenot]

On 08/24/2017 05:07 PM, Michael Bringmann wrote:
> 
> powerpc/numa: Correct the currently broken capability to set the
> topology for shared CPUs in LPARs.  At boot time for shared CPU
> lpars, the topology for each shared CPU is set to node zero, however,
> this is now updated correctly using the Virtual Processor Home Node
> (VPHN) capabilities information provided by the pHyp.
> 
> Also, update initialization checks for device-tree attributes to
> independently recognize PRRN or VPHN usage.
> 
> Finally, try to distinguish the VPHN code from the NUMA code better,
> and move relevant functions to another file.

You need to split the move of the vphn code to a different file into
a separate patch. With thia all in one patch it is really difficult
to distinguish what pieces are code changes and what is just moving
code around.

-Nathan

> 
> Signed-off-by: Michael Bringmann <mwb@linux.vnet.ibm.com>
> ---
> Changes in V10:
>   -- Reorganize VPHN code to distinguish it from NUMA processing
> ---
>  arch/powerpc/include/asm/topology.h          |    8 
>  arch/powerpc/mm/numa.c                       |  503 ----------------------
>  arch/powerpc/mm/vphn.c                       |  586 ++++++++++++++++++++++++++
>  arch/powerpc/mm/vphn.h                       |    4 
>  arch/powerpc/platforms/pseries/hotplug-cpu.c |    2 
>  5 files changed, 609 insertions(+), 494 deletions(-)
> 
> diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
> index dc4e159..600e1c6 100644
> --- a/arch/powerpc/include/asm/topology.h
> +++ b/arch/powerpc/include/asm/topology.h
> @@ -98,6 +98,14 @@ static inline int prrn_is_enabled(void)
>  }
>  #endif /* CONFIG_NUMA && CONFIG_PPC_SPLPAR */
> 
> +#if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_NEED_MULTIPLE_NODES)
> +#if defined(CONFIG_PPC_SPLPAR)
> +extern int timed_topology_update(int nsecs);
> +#else
> +#define	timed_topology_update(nsecs)	0
> +#endif /* CONFIG_PPC_SPLPAR */
> +#endif /* CONFIG_HOTPLUG_CPU || CONFIG_NEED_MULTIPLE_NODES */
> +
>  #include <asm-generic/topology.h>
> 
>  #ifdef CONFIG_SMP
> diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
> index b95c584..73427e290 100644
> --- a/arch/powerpc/mm/numa.c
> +++ b/arch/powerpc/mm/numa.c
> @@ -29,6 +29,7 @@
>  #include <linux/seq_file.h>
>  #include <linux/uaccess.h>
>  #include <linux/slab.h>
> +#include <linux/sched.h>
>  #include <asm/cputhreads.h>
>  #include <asm/sparsemem.h>
>  #include <asm/prom.h>
> @@ -41,8 +42,12 @@
>  #include <asm/setup.h>
>  #include <asm/vdso.h>
> 
> +#include "vphn.h"
> +
>  static int numa_enabled = 1;
> 
> +bool topology_updates_enabled = true;
> +
>  static char *cmdline __initdata;
> 
>  static int numa_debug;
> @@ -60,8 +65,7 @@
>  static int n_mem_addr_cells, n_mem_size_cells;
>  static int form1_affinity;
> 
> -#define MAX_DISTANCE_REF_POINTS 4
> -static int distance_ref_points_depth;
> +int distance_ref_points_depth;
>  static const __be32 *distance_ref_points;
>  static int distance_lookup_table[MAX_NUMNODES][MAX_DISTANCE_REF_POINTS];
> 
> @@ -142,12 +146,12 @@ static void reset_numa_cpu_lookup_table(void)
>  		numa_cpu_lookup_table[cpu] = -1;
>  }
> 
> -static void update_numa_cpu_lookup_table(unsigned int cpu, int node)
> +void update_numa_cpu_lookup_table(unsigned int cpu, int node)
>  {
>  	numa_cpu_lookup_table[cpu] = node;
>  }
> 
> -static void map_cpu_to_node(int cpu, int node)
> +void map_cpu_to_node(int cpu, int node)
>  {
>  	update_numa_cpu_lookup_table(cpu, node);
> 
> @@ -158,7 +162,7 @@ static void map_cpu_to_node(int cpu, int node)
>  }
> 
>  #if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_PPC_SPLPAR)
> -static void unmap_cpu_from_node(unsigned long cpu)
> +void unmap_cpu_from_node(unsigned long cpu)
>  {
>  	int node = numa_cpu_lookup_table[cpu];
> 
> @@ -233,7 +237,7 @@ static void initialize_distance_lookup_table(int nid,
>  /* Returns nid in the range [0..MAX_NUMNODES-1], or -1 if no useful numa
>   * info is found.
>   */
> -static int associativity_to_nid(const __be32 *associativity)
> +int associativity_to_nid(const __be32 *associativity)
>  {
>  	int nid = -1;
> 
> @@ -957,8 +961,6 @@ static int __init early_numa(char *p)
>  }
>  early_param("numa", early_numa);
> 
> -static bool topology_updates_enabled = true;
> -
>  static int __init early_topology_updates(char *p)
>  {
>  	if (!p)
> @@ -1135,488 +1137,3 @@ u64 memory_hotplug_max(void)
>          return max(hot_add_drconf_memory_max(), memblock_end_of_DRAM());
>  }
>  #endif /* CONFIG_MEMORY_HOTPLUG */
> -
> -/* Virtual Processor Home Node (VPHN) support */
> -#ifdef CONFIG_PPC_SPLPAR
> -
> -#include "vphn.h"
> -
> -struct topology_update_data {
> -	struct topology_update_data *next;
> -	unsigned int cpu;
> -	int old_nid;
> -	int new_nid;
> -};
> -
> -static u8 vphn_cpu_change_counts[NR_CPUS][MAX_DISTANCE_REF_POINTS];
> -static cpumask_t cpu_associativity_changes_mask;
> -static int vphn_enabled;
> -static int prrn_enabled;
> -static void reset_topology_timer(void);
> -
> -/*
> - * Store the current values of the associativity change counters in the
> - * hypervisor.
> - */
> -static void setup_cpu_associativity_change_counters(void)
> -{
> -	int cpu;
> -
> -	/* The VPHN feature supports a maximum of 8 reference points */
> -	BUILD_BUG_ON(MAX_DISTANCE_REF_POINTS > 8);
> -
> -	for_each_possible_cpu(cpu) {
> -		int i;
> -		u8 *counts = vphn_cpu_change_counts[cpu];
> -		volatile u8 *hypervisor_counts = lppaca[cpu].vphn_assoc_counts;
> -
> -		for (i = 0; i < distance_ref_points_depth; i++)
> -			counts[i] = hypervisor_counts[i];
> -	}
> -}
> -
> -/*
> - * The hypervisor maintains a set of 8 associativity change counters in
> - * the VPA of each cpu that correspond to the associativity levels in the
> - * ibm,associativity-reference-points property. When an associativity
> - * level changes, the corresponding counter is incremented.
> - *
> - * Set a bit in cpu_associativity_changes_mask for each cpu whose home
> - * node associativity levels have changed.
> - *
> - * Returns the number of cpus with unhandled associativity changes.
> - */
> -static int update_cpu_associativity_changes_mask(void)
> -{
> -	int cpu;
> -	cpumask_t *changes = &cpu_associativity_changes_mask;
> -
> -	for_each_possible_cpu(cpu) {
> -		int i, changed = 0;
> -		u8 *counts = vphn_cpu_change_counts[cpu];
> -		volatile u8 *hypervisor_counts = lppaca[cpu].vphn_assoc_counts;
> -
> -		for (i = 0; i < distance_ref_points_depth; i++) {
> -			if (hypervisor_counts[i] != counts[i]) {
> -				counts[i] = hypervisor_counts[i];
> -				changed = 1;
> -			}
> -		}
> -		if (changed) {
> -			cpumask_or(changes, changes, cpu_sibling_mask(cpu));
> -			cpu = cpu_last_thread_sibling(cpu);
> -		}
> -	}
> -
> -	return cpumask_weight(changes);
> -}
> -
> -/*
> - * Retrieve the new associativity information for a virtual processor's
> - * home node.
> - */
> -static long hcall_vphn(unsigned long cpu, __be32 *associativity)
> -{
> -	long rc;
> -	long retbuf[PLPAR_HCALL9_BUFSIZE] = {0};
> -	u64 flags = 1;
> -	int hwcpu = get_hard_smp_processor_id(cpu);
> -
> -	rc = plpar_hcall9(H_HOME_NODE_ASSOCIATIVITY, retbuf, flags, hwcpu);
> -	vphn_unpack_associativity(retbuf, associativity);
> -
> -	return rc;
> -}
> -
> -static long vphn_get_associativity(unsigned long cpu,
> -					__be32 *associativity)
> -{
> -	long rc;
> -
> -	rc = hcall_vphn(cpu, associativity);
> -
> -	switch (rc) {
> -	case H_FUNCTION:
> -		printk(KERN_INFO
> -			"VPHN is not supported. Disabling polling...\n");
> -		stop_topology_update();
> -		break;
> -	case H_HARDWARE:
> -		printk(KERN_ERR
> -			"hcall_vphn() experienced a hardware fault "
> -			"preventing VPHN. Disabling polling...\n");
> -		stop_topology_update();
> -	}
> -
> -	return rc;
> -}
> -
> -/*
> - * Update the CPU maps and sysfs entries for a single CPU when its NUMA
> - * characteristics change. This function doesn't perform any locking and is
> - * only safe to call from stop_machine().
> - */
> -static int update_cpu_topology(void *data)
> -{
> -	struct topology_update_data *update;
> -	unsigned long cpu;
> -
> -	if (!data)
> -		return -EINVAL;
> -
> -	cpu = smp_processor_id();
> -
> -	for (update = data; update; update = update->next) {
> -		int new_nid = update->new_nid;
> -		if (cpu != update->cpu)
> -			continue;
> -
> -		unmap_cpu_from_node(cpu);
> -		map_cpu_to_node(cpu, new_nid);
> -		set_cpu_numa_node(cpu, new_nid);
> -		set_cpu_numa_mem(cpu, local_memory_node(new_nid));
> -		vdso_getcpu_init();
> -	}
> -
> -	return 0;
> -}
> -
> -static int update_lookup_table(void *data)
> -{
> -	struct topology_update_data *update;
> -
> -	if (!data)
> -		return -EINVAL;
> -
> -	/*
> -	 * Upon topology update, the numa-cpu lookup table needs to be updated
> -	 * for all threads in the core, including offline CPUs, to ensure that
> -	 * future hotplug operations respect the cpu-to-node associativity
> -	 * properly.
> -	 */
> -	for (update = data; update; update = update->next) {
> -		int nid, base, j;
> -
> -		nid = update->new_nid;
> -		base = cpu_first_thread_sibling(update->cpu);
> -
> -		for (j = 0; j < threads_per_core; j++) {
> -			update_numa_cpu_lookup_table(base + j, nid);
> -		}
> -	}
> -
> -	return 0;
> -}
> -
> -/*
> - * Update the node maps and sysfs entries for each cpu whose home node
> - * has changed. Returns 1 when the topology has changed, and 0 otherwise.
> - *
> - * cpus_locked says whether we already hold cpu_hotplug_lock.
> - */
> -int numa_update_cpu_topology(bool cpus_locked)
> -{
> -	unsigned int cpu, sibling, changed = 0;
> -	struct topology_update_data *updates, *ud;
> -	__be32 associativity[VPHN_ASSOC_BUFSIZE] = {0};
> -	cpumask_t updated_cpus;
> -	struct device *dev;
> -	int weight, new_nid, i = 0;
> -
> -	if (!prrn_enabled && !vphn_enabled)
> -		return 0;
> -
> -	weight = cpumask_weight(&cpu_associativity_changes_mask);
> -	if (!weight)
> -		return 0;
> -
> -	updates = kzalloc(weight * (sizeof(*updates)), GFP_KERNEL);
> -	if (!updates)
> -		return 0;
> -
> -	cpumask_clear(&updated_cpus);
> -
> -	for_each_cpu(cpu, &cpu_associativity_changes_mask) {
> -		/*
> -		 * If siblings aren't flagged for changes, updates list
> -		 * will be too short. Skip on this update and set for next
> -		 * update.
> -		 */
> -		if (!cpumask_subset(cpu_sibling_mask(cpu),
> -					&cpu_associativity_changes_mask)) {
> -			pr_info("Sibling bits not set for associativity "
> -					"change, cpu%d\n", cpu);
> -			cpumask_or(&cpu_associativity_changes_mask,
> -					&cpu_associativity_changes_mask,
> -					cpu_sibling_mask(cpu));
> -			cpu = cpu_last_thread_sibling(cpu);
> -			continue;
> -		}
> -
> -		/* Use associativity from first thread for all siblings */
> -		vphn_get_associativity(cpu, associativity);
> -		new_nid = associativity_to_nid(associativity);
> -		if (new_nid < 0 || !node_online(new_nid))
> -			new_nid = first_online_node;
> -
> -		if (new_nid == numa_cpu_lookup_table[cpu]) {
> -			cpumask_andnot(&cpu_associativity_changes_mask,
> -					&cpu_associativity_changes_mask,
> -					cpu_sibling_mask(cpu));
> -			cpu = cpu_last_thread_sibling(cpu);
> -			continue;
> -		}
> -
> -		for_each_cpu(sibling, cpu_sibling_mask(cpu)) {
> -			ud = &updates[i++];
> -			ud->cpu = sibling;
> -			ud->new_nid = new_nid;
> -			ud->old_nid = numa_cpu_lookup_table[sibling];
> -			cpumask_set_cpu(sibling, &updated_cpus);
> -			if (i < weight)
> -				ud->next = &updates[i];
> -		}
> -		cpu = cpu_last_thread_sibling(cpu);
> -	}
> -
> -	pr_debug("Topology update for the following CPUs:\n");
> -	if (cpumask_weight(&updated_cpus)) {
> -		for (ud = &updates[0]; ud; ud = ud->next) {
> -			pr_debug("cpu %d moving from node %d "
> -					  "to %d\n", ud->cpu,
> -					  ud->old_nid, ud->new_nid);
> -		}
> -	}
> -
> -	/*
> -	 * In cases where we have nothing to update (because the updates list
> -	 * is too short or because the new topology is same as the old one),
> -	 * skip invoking update_cpu_topology() via stop-machine(). This is
> -	 * necessary (and not just a fast-path optimization) since stop-machine
> -	 * can end up electing a random CPU to run update_cpu_topology(), and
> -	 * thus trick us into setting up incorrect cpu-node mappings (since
> -	 * 'updates' is kzalloc()'ed).
> -	 *
> -	 * And for the similar reason, we will skip all the following updating.
> -	 */
> -	if (!cpumask_weight(&updated_cpus))
> -		goto out;
> -
> -	if (cpus_locked)
> -		stop_machine_cpuslocked(update_cpu_topology, &updates[0],
> -					&updated_cpus);
> -	else
> -		stop_machine(update_cpu_topology, &updates[0], &updated_cpus);
> -
> -	/*
> -	 * Update the numa-cpu lookup table with the new mappings, even for
> -	 * offline CPUs. It is best to perform this update from the stop-
> -	 * machine context.
> -	 */
> -	if (cpus_locked)
> -		stop_machine_cpuslocked(update_lookup_table, &updates[0],
> -					cpumask_of(raw_smp_processor_id()));
> -	else
> -		stop_machine(update_lookup_table, &updates[0],
> -			     cpumask_of(raw_smp_processor_id()));
> -
> -	for (ud = &updates[0]; ud; ud = ud->next) {
> -		unregister_cpu_under_node(ud->cpu, ud->old_nid);
> -		register_cpu_under_node(ud->cpu, ud->new_nid);
> -
> -		dev = get_cpu_device(ud->cpu);
> -		if (dev)
> -			kobject_uevent(&dev->kobj, KOBJ_CHANGE);
> -		cpumask_clear_cpu(ud->cpu, &cpu_associativity_changes_mask);
> -		changed = 1;
> -	}
> -
> -out:
> -	kfree(updates);
> -	return changed;
> -}
> -
> -int arch_update_cpu_topology(void)
> -{
> -	lockdep_assert_cpus_held();
> -	return numa_update_cpu_topology(true);
> -}
> -
> -static void topology_work_fn(struct work_struct *work)
> -{
> -	rebuild_sched_domains();
> -}
> -static DECLARE_WORK(topology_work, topology_work_fn);
> -
> -static void topology_schedule_update(void)
> -{
> -	schedule_work(&topology_work);
> -}
> -
> -static void topology_timer_fn(unsigned long ignored)
> -{
> -	if (prrn_enabled && cpumask_weight(&cpu_associativity_changes_mask))
> -		topology_schedule_update();
> -	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 reset_topology_timer(void)
> -{
> -	topology_timer.data = 0;
> -	topology_timer.expires = jiffies + 60 * HZ;
> -	mod_timer(&topology_timer, topology_timer.expires);
> -}
> -
> -#ifdef CONFIG_SMP
> -
> -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_reconfig_data *update = data;
> -	int rc = NOTIFY_DONE;
> -
> -	switch (action) {
> -	case OF_RECONFIG_UPDATE_PROPERTY:
> -		if (!of_prop_cmp(update->dn->type, "cpu") &&
> -		    !of_prop_cmp(update->prop->name, "ibm,associativity")) {
> -			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,
> -};
> -
> -#endif
> -
> -/*
> - * Start polling for associativity changes.
> - */
> -int start_topology_update(void)
> -{
> -	int rc = 0;
> -
> -	if (firmware_has_feature(FW_FEATURE_PRRN)) {
> -		if (!prrn_enabled) {
> -			prrn_enabled = 1;
> -			vphn_enabled = 0;
> -#ifdef CONFIG_SMP
> -			rc = of_reconfig_notifier_register(&dt_update_nb);
> -#endif
> -		}
> -	} else if (firmware_has_feature(FW_FEATURE_VPHN) &&
> -		   lppaca_shared_proc(get_lppaca())) {
> -		if (!vphn_enabled) {
> -			prrn_enabled = 0;
> -			vphn_enabled = 1;
> -			setup_cpu_associativity_change_counters();
> -			init_timer_deferrable(&topology_timer);
> -			reset_topology_timer();
> -		}
> -	}
> -
> -	return rc;
> -}
> -
> -/*
> - * Disable polling for VPHN associativity changes.
> - */
> -int stop_topology_update(void)
> -{
> -	int rc = 0;
> -
> -	if (prrn_enabled) {
> -		prrn_enabled = 0;
> -#ifdef CONFIG_SMP
> -		rc = of_reconfig_notifier_unregister(&dt_update_nb);
> -#endif
> -	} else if (vphn_enabled) {
> -		vphn_enabled = 0;
> -		rc = del_timer_sync(&topology_timer);
> -	}
> -
> -	return rc;
> -}
> -
> -int prrn_is_enabled(void)
> -{
> -	return prrn_enabled;
> -}
> -
> -static int topology_read(struct seq_file *file, void *v)
> -{
> -	if (vphn_enabled || prrn_enabled)
> -		seq_puts(file, "on\n");
> -	else
> -		seq_puts(file, "off\n");
> -
> -	return 0;
> -}
> -
> -static int topology_open(struct inode *inode, struct file *file)
> -{
> -	return single_open(file, topology_read, NULL);
> -}
> -
> -static ssize_t topology_write(struct file *file, const char __user *buf,
> -			      size_t count, loff_t *off)
> -{
> -	char kbuf[4]; /* "on" or "off" plus null. */
> -	int read_len;
> -
> -	read_len = count < 3 ? count : 3;
> -	if (copy_from_user(kbuf, buf, read_len))
> -		return -EINVAL;
> -
> -	kbuf[read_len] = '\0';
> -
> -	if (!strncmp(kbuf, "on", 2))
> -		start_topology_update();
> -	else if (!strncmp(kbuf, "off", 3))
> -		stop_topology_update();
> -	else
> -		return -EINVAL;
> -
> -	return count;
> -}
> -
> -static const struct file_operations topology_ops = {
> -	.read = seq_read,
> -	.write = topology_write,
> -	.open = topology_open,
> -	.release = single_release
> -};
> -
> -static int topology_update_init(void)
> -{
> -	/* Do not poll for changes if disabled at boot */
> -	if (topology_updates_enabled)
> -		start_topology_update();
> -
> -	if (!proc_create("powerpc/topology_updates", 0644, NULL, &topology_ops))
> -		return -ENOMEM;
> -
> -	return 0;
> -}
> -device_initcall(topology_update_init);
> -#endif /* CONFIG_PPC_SPLPAR */
> diff --git a/arch/powerpc/mm/vphn.c b/arch/powerpc/mm/vphn.c
> index 5f8ef50..006bcc2 100644
> --- a/arch/powerpc/mm/vphn.c
> +++ b/arch/powerpc/mm/vphn.c
> @@ -1,4 +1,46 @@
> -#include <asm/byteorder.h>
> +/*
> + * pSeries VPHN support
> + *
> + * Copyright (C) 2016 Greg Kurz <gkurz@linux.vnet.ibm.com>, IBM
> + *
> + * This program is free software; you can redistribute it and/or
> + * modify it under the terms of the GNU General Public License
> + * as published by the Free Software Foundation; either version
> + * 2 of the License, or (at your option) any later version.
> + */
> +
> +#include <linux/threads.h>
> +#include <linux/bootmem.h>
> +#include <linux/init.h>
> +#include <linux/mm.h>
> +#include <linux/mmzone.h>
> +#include <linux/export.h>
> +#include <linux/nodemask.h>
> +#include <linux/cpu.h>
> +#include <linux/notifier.h>
> +#include <linux/memblock.h>
> +#include <linux/of.h>
> +#include <linux/pfn.h>
> +#include <linux/cpuset.h>
> +#include <linux/node.h>
> +#include <linux/stop_machine.h>
> +#include <linux/proc_fs.h>
> +#include <linux/seq_file.h>
> +#include <linux/uaccess.h>
> +#include <linux/slab.h>
> +#include <linux/sched.h>
> +#include <asm/cputhreads.h>
> +#include <asm/sparsemem.h>
> +#include <asm/prom.h>
> +#include <asm/smp.h>
> +#include <asm/cputhreads.h>
> +#include <asm/topology.h>
> +#include <asm/firmware.h>
> +#include <asm/paca.h>
> +#include <asm/hvcall.h>
> +#include <asm/setup.h>
> +#include <asm/vdso.h>
> +
>  #include "vphn.h"
> 
>  /*
> @@ -68,3 +110,545 @@ int vphn_unpack_associativity(const long *packed, __be32 *unpacked)
> 
>  	return nr_assoc_doms;
>  }
> +
> +
> +/* Virtual Processor Home Node (VPHN) support */
> +#ifdef CONFIG_PPC_SPLPAR
> +
> +extern bool topology_updates_enabled;
> +extern int distance_ref_points_depth;
> +
> +extern int associativity_to_nid(const __be32 *associativity);
> +extern void unmap_cpu_from_node(unsigned long cpu);
> +extern void map_cpu_to_node(int cpu, int node);
> +extern void update_numa_cpu_lookup_table(unsigned int cpu, int node);
> +
> +
> +struct topology_update_data {
> +	struct topology_update_data *next;
> +	unsigned int cpu;
> +	int old_nid;
> +	int new_nid;
> +};
> +
> +#define	TOPOLOGY_DEF_TIMER_SECS		60
> +
> +static u8 vphn_cpu_change_counts[NR_CPUS][MAX_DISTANCE_REF_POINTS];
> +static cpumask_t cpu_associativity_changes_mask;
> +static int topology_timer_secs = TOPOLOGY_DEF_TIMER_SECS;
> +static int vphn_enabled;
> +static int prrn_enabled;
> +static int topology_inited;
> +static int topology_update_needed;
> +
> +static void reset_topology_timer(void);
> +
> +/*
> + * Change polling interval for associativity changes.
> + */
> +int timed_topology_update(int nsecs)
> +{
> +	if (nsecs > 0)
> +		topology_timer_secs = nsecs;
> +	else
> +		topology_timer_secs = TOPOLOGY_DEF_TIMER_SECS;
> +
> +	if (vphn_enabled)
> +		reset_topology_timer();
> +
> +	return 0;
> +}
> +
> +/*
> + * Store the current values of the associativity change counters in the
> + * hypervisor.
> + */
> +static void setup_cpu_associativity_change_counters(void)
> +{
> +	int cpu;
> +
> +	/* The VPHN feature supports a maximum of 8 reference points */
> +	BUILD_BUG_ON(MAX_DISTANCE_REF_POINTS > 8);
> +
> +	for_each_possible_cpu(cpu) {
> +		int i;
> +		u8 *counts = vphn_cpu_change_counts[cpu];
> +		volatile u8 *hypervisor_counts = lppaca[cpu].vphn_assoc_counts;
> +
> +		for (i = 0; i < distance_ref_points_depth; i++)
> +			counts[i] = hypervisor_counts[i];
> +	}
> +}
> +
> +/*
> + * The hypervisor maintains a set of 8 associativity change counters in
> + * the VPA of each cpu that correspond to the associativity levels in the
> + * ibm,associativity-reference-points property. When an associativity
> + * level changes, the corresponding counter is incremented.
> + *
> + * Set a bit in cpu_associativity_changes_mask for each cpu whose home
> + * node associativity levels have changed.
> + *
> + * Returns the number of cpus with unhandled associativity changes.
> + */
> +static int update_cpu_associativity_changes_mask(void)
> +{
> +	int cpu;
> +	cpumask_t *changes = &cpu_associativity_changes_mask;
> +
> +	for_each_possible_cpu(cpu) {
> +		int i, changed = 0;
> +		u8 *counts = vphn_cpu_change_counts[cpu];
> +		volatile u8 *hypervisor_counts = lppaca[cpu].vphn_assoc_counts;
> +
> +		for (i = 0; i < distance_ref_points_depth; i++) {
> +			if (hypervisor_counts[i] != counts[i]) {
> +				counts[i] = hypervisor_counts[i];
> +				changed = 1;
> +			}
> +		}
> +		if (changed) {
> +			cpumask_or(changes, changes, cpu_sibling_mask(cpu));
> +			cpu = cpu_last_thread_sibling(cpu);
> +		}
> +	}
> +
> +	return cpumask_weight(changes);
> +}
> +
> +/*
> + * Retrieve the new associativity information for a virtual processor's
> + * home node.
> + */
> +static long hcall_vphn(unsigned long cpu, __be32 *associativity)
> +{
> +	long rc;
> +	long retbuf[PLPAR_HCALL9_BUFSIZE] = {0};
> +	u64 flags = 1;
> +	int hwcpu = get_hard_smp_processor_id(cpu);
> +
> +	rc = plpar_hcall9(H_HOME_NODE_ASSOCIATIVITY, retbuf, flags, hwcpu);
> +	vphn_unpack_associativity(retbuf, associativity);
> +
> +	return rc;
> +}
> +
> +static long vphn_get_associativity(unsigned long cpu,
> +								__be32 *associativity)
> +{
> +	long rc;
> +
> +	rc = hcall_vphn(cpu, associativity);
> +
> +	switch (rc) {
> +	case H_FUNCTION:
> +		pr_debug("VPHN is not supported. Disabling polling...\n");
> +		stop_topology_update();
> +		break;
> +	case H_HARDWARE:
> +		printk(KERN_ERR
> +			"hcall_vphn() experienced a hardware fault "
> +			"preventing VPHN. Disabling polling...\n");
> +		stop_topology_update();
> +		break;
> +	case H_SUCCESS:
> +		printk(KERN_INFO
> +			"VPHN hcall succeeded. Reset polling...\n");
> +		timed_topology_update(0);
> +		break;
> +	}
> +
> +	return rc;
> +}
> +
> +/*
> + * Update the CPU maps and sysfs entries for a single CPU when its NUMA
> + * characteristics change. This function doesn't perform any locking and is
> + * only safe to call from stop_machine().
> + */
> +static int update_cpu_topology(void *data)
> +{
> +	struct topology_update_data *update;
> +	unsigned long cpu;
> +
> +	if (!data)
> +		return -EINVAL;
> +
> +	cpu = smp_processor_id();
> +
> +	for (update = data; update; update = update->next) {
> +		int new_nid = update->new_nid;
> +		if (cpu != update->cpu)
> +			continue;
> +
> +		unmap_cpu_from_node(cpu);
> +		map_cpu_to_node(cpu, new_nid);
> +		set_cpu_numa_node(cpu, new_nid);
> +		set_cpu_numa_mem(cpu, local_memory_node(new_nid));
> +		vdso_getcpu_init();
> +	}
> +
> +	return 0;
> +}
> +
> +static int update_lookup_table(void *data)
> +{
> +	struct topology_update_data *update;
> +
> +	if (!data)
> +		return -EINVAL;
> +
> +	/*
> +	 * Upon topology update, the numa-cpu lookup table needs to be updated
> +	 * for all threads in the core, including offline CPUs, to ensure that
> +	 * future hotplug operations respect the cpu-to-node associativity
> +	 * properly.
> +	 */
> +	for (update = data; update; update = update->next) {
> +		int nid, base, j;
> +
> +		nid = update->new_nid;
> +		base = cpu_first_thread_sibling(update->cpu);
> +
> +		for (j = 0; j < threads_per_core; j++) {
> +			update_numa_cpu_lookup_table(base + j, nid);
> +		}
> +	}
> +
> +	return 0;
> +}
> +
> +/*
> + * Update the node maps and sysfs entries for each cpu whose home node
> + * has changed. Returns 1 when the topology has changed, and 0 otherwise.
> + *
> + * cpus_locked says whether we already hold cpu_hotplug_lock.
> + */
> +int numa_update_cpu_topology(bool cpus_locked)
> +{
> +	unsigned int cpu, sibling, changed = 0;
> +	struct topology_update_data *updates, *ud;
> +	__be32 associativity[VPHN_ASSOC_BUFSIZE] = {0};
> +	cpumask_t updated_cpus;
> +	struct device *dev;
> +	int weight, new_nid, i = 0;
> +
> +	if (!prrn_enabled && !vphn_enabled) {
> +		if (!topology_inited)
> +			topology_update_needed = 1;
> +		return 0;
> +	}
> +
> +	weight = cpumask_weight(&cpu_associativity_changes_mask);
> +	if (!weight)
> +		return 0;
> +
> +	updates = kzalloc(weight * (sizeof(*updates)), GFP_KERNEL);
> +	if (!updates)
> +		return 0;
> +
> +	cpumask_clear(&updated_cpus);
> +
> +	for_each_cpu(cpu, &cpu_associativity_changes_mask) {
> +		/*
> +		 * If siblings aren't flagged for changes, updates list
> +		 * will be too short. Skip on this update and set for next
> +		 * update.
> +		 */
> +		if (!cpumask_subset(cpu_sibling_mask(cpu),
> +					&cpu_associativity_changes_mask)) {
> +			pr_info("Sibling bits not set for associativity "
> +					"change, cpu%d\n", cpu);
> +			cpumask_or(&cpu_associativity_changes_mask,
> +					&cpu_associativity_changes_mask,
> +					cpu_sibling_mask(cpu));
> +			cpu = cpu_last_thread_sibling(cpu);
> +			continue;
> +		}
> +
> +		/* Use associativity from first thread for all siblings */
> +		vphn_get_associativity(cpu, associativity);
> +		new_nid = associativity_to_nid(associativity);
> +		if (new_nid < 0 || !node_online(new_nid))
> +			new_nid = first_online_node;
> +
> +		if (new_nid == numa_cpu_lookup_table[cpu]) {
> +			cpumask_andnot(&cpu_associativity_changes_mask,
> +					&cpu_associativity_changes_mask,
> +					cpu_sibling_mask(cpu));
> +			cpu = cpu_last_thread_sibling(cpu);
> +			continue;
> +		}
> +
> +		for_each_cpu(sibling, cpu_sibling_mask(cpu)) {
> +			ud = &updates[i++];
> +			ud->cpu = sibling;
> +			ud->new_nid = new_nid;
> +			ud->old_nid = numa_cpu_lookup_table[sibling];
> +			cpumask_set_cpu(sibling, &updated_cpus);
> +			if (i < weight)
> +				ud->next = &updates[i];
> +			else
> +				ud->next = NULL;	/* Don't overrun and use data
> +									 * from previous hotplug ops */
> +		}
> +		cpu = cpu_last_thread_sibling(cpu);
> +	}
> +
> +	pr_debug("Topology update for the following CPUs:\n");
> +	if (cpumask_weight(&updated_cpus)) {
> +		for (ud = &updates[0]; ud; ud = ud->next) {
> +			pr_debug("cpu %d moving from node %d "
> +					  "to %d\n", ud->cpu,
> +					  ud->old_nid, ud->new_nid);
> +		}
> +	}
> +
> +	/*
> +	 * In cases where we have nothing to update (because the updates list
> +	 * is too short or because the new topology is same as the old one),
> +	 * skip invoking update_cpu_topology() via stop-machine(). This is
> +	 * necessary (and not just a fast-path optimization) since stop-machine
> +	 * can end up electing a random CPU to run update_cpu_topology(), and
> +	 * thus trick us into setting up incorrect cpu-node mappings (since
> +	 * 'updates' is kzalloc()'ed).
> +	 *
> +	 * And for the similar reason, we will skip all the following updating.
> +	 */
> +	if (!cpumask_weight(&updated_cpus))
> +		goto out;
> +
> +	if (cpus_locked)
> +		stop_machine_cpuslocked(update_cpu_topology, &updates[0],
> +					&updated_cpus);
> +	else
> +		stop_machine(update_cpu_topology, &updates[0], &updated_cpus);
> +
> +	/*
> +	 * Update the numa-cpu lookup table with the new mappings, even for
> +	 * offline CPUs. It is best to perform this update from the stop-
> +	 * machine context.
> +	 */
> +	if (cpus_locked)
> +		stop_machine_cpuslocked(update_lookup_table, &updates[0],
> +					cpumask_of(raw_smp_processor_id()));
> +	else
> +		stop_machine(update_lookup_table, &updates[0],
> +			     cpumask_of(raw_smp_processor_id()));
> +
> +	for (ud = &updates[0]; ud; ud = ud->next) {
> +		unregister_cpu_under_node(ud->cpu, ud->old_nid);
> +		register_cpu_under_node(ud->cpu, ud->new_nid);
> +
> +		dev = get_cpu_device(ud->cpu);
> +		if (dev)
> +			kobject_uevent(&dev->kobj, KOBJ_CHANGE);
> +		cpumask_clear_cpu(ud->cpu, &cpu_associativity_changes_mask);
> +		changed = 1;
> +	}
> +
> +out:
> +	kfree(updates);
> +	topology_update_needed = 0;
> +	return changed;
> +}
> +
> +int arch_update_cpu_topology(void)
> +{
> +	lockdep_assert_cpus_held();
> +	return numa_update_cpu_topology(true);
> +}
> +
> +static void topology_work_fn(struct work_struct *work)
> +{
> +	rebuild_sched_domains();
> +}
> +static DECLARE_WORK(topology_work, topology_work_fn);
> +
> +static void topology_schedule_update(void)
> +{
> +	schedule_work(&topology_work);
> +}
> +
> +static int shared_topology_update(void)
> +{
> +	if (firmware_has_feature(FW_FEATURE_VPHN) &&
> +		   lppaca_shared_proc(get_lppaca()))
> +		topology_schedule_update();
> +
> +	return 0;
> +}
> +device_initcall(shared_topology_update);
> +
> +static void topology_timer_fn(unsigned long ignored)
> +{
> +	if (prrn_enabled && cpumask_weight(&cpu_associativity_changes_mask))
> +		topology_schedule_update();
> +	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 reset_topology_timer(void)
> +{
> +	topology_timer.data = 0;
> +	topology_timer.expires = jiffies + topology_timer_secs * HZ;
> +	mod_timer(&topology_timer, topology_timer.expires);
> +}
> +
> +#ifdef CONFIG_SMP
> +
> +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_reconfig_data *update = data;
> +	int rc = NOTIFY_DONE;
> +
> +	switch (action) {
> +	case OF_RECONFIG_UPDATE_PROPERTY:
> +		if (!of_prop_cmp(update->dn->type, "cpu") &&
> +		    !of_prop_cmp(update->prop->name, "ibm,associativity")) {
> +			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,
> +};
> +
> +#endif
> +
> +/*
> + * Start polling for associativity changes.
> + */
> +int start_topology_update(void)
> +{
> +	int rc = 0;
> +
> +	if (firmware_has_feature(FW_FEATURE_PRRN)) {
> +		if (!prrn_enabled) {
> +			prrn_enabled = 1;
> +#ifdef CONFIG_SMP
> +			rc = of_reconfig_notifier_register(&dt_update_nb);
> +#endif
> +		}
> +	}
> +	if (firmware_has_feature(FW_FEATURE_VPHN) &&
> +		   lppaca_shared_proc(get_lppaca())) {
> +		if (!vphn_enabled) {
> +			vphn_enabled = 1;
> +			setup_cpu_associativity_change_counters();
> +			init_timer_deferrable(&topology_timer);
> +			reset_topology_timer();
> +		}
> +	}
> +
> +	return rc;
> +}
> +
> +/*
> + * Disable polling for VPHN associativity changes.
> + */
> +int stop_topology_update(void)
> +{
> +	int rc = 0;
> +
> +	if (prrn_enabled) {
> +		prrn_enabled = 0;
> +#ifdef CONFIG_SMP
> +		rc = of_reconfig_notifier_unregister(&dt_update_nb);
> +#endif
> +	}
> +	if (vphn_enabled) {
> +		vphn_enabled = 0;
> +		rc = del_timer_sync(&topology_timer);
> +	}
> +
> +	return rc;
> +}
> +
> +int prrn_is_enabled(void)
> +{
> +	return prrn_enabled;
> +}
> +
> +static int topology_read(struct seq_file *file, void *v)
> +{
> +	if (vphn_enabled || prrn_enabled)
> +		seq_puts(file, "on\n");
> +	else
> +		seq_puts(file, "off\n");
> +
> +	return 0;
> +}
> +
> +static int topology_open(struct inode *inode, struct file *file)
> +{
> +	return single_open(file, topology_read, NULL);
> +}
> +
> +static ssize_t topology_write(struct file *file, const char __user *buf,
> +			      size_t count, loff_t *off)
> +{
> +	char kbuf[4]; /* "on" or "off" plus null. */
> +	int read_len;
> +
> +	read_len = count < 3 ? count : 3;
> +	if (copy_from_user(kbuf, buf, read_len))
> +		return -EINVAL;
> +
> +	kbuf[read_len] = '\0';
> +
> +	if (!strncmp(kbuf, "on", 2))
> +		start_topology_update();
> +	else if (!strncmp(kbuf, "off", 3))
> +		stop_topology_update();
> +	else
> +		return -EINVAL;
> +
> +	return count;
> +}
> +
> +static const struct file_operations topology_ops = {
> +	.read = seq_read,
> +	.write = topology_write,
> +	.open = topology_open,
> +	.release = single_release
> +};
> +
> +static int topology_update_init(void)
> +{
> +	/* Do not poll for changes if disabled at boot */
> +	if (topology_updates_enabled)
> +		start_topology_update();
> +
> +	if (!proc_create("powerpc/topology_updates", 0644, NULL, &topology_ops))
> +		return -ENOMEM;
> +
> +	topology_inited = 1;
> +	if (topology_update_needed)
> +		bitmap_fill(cpumask_bits(&cpu_associativity_changes_mask),
> +					nr_cpumask_bits);
> +
> +	return 0;
> +}
> +device_initcall(topology_update_init);
> +#endif /* CONFIG_PPC_SPLPAR */
> diff --git a/arch/powerpc/mm/vphn.h b/arch/powerpc/mm/vphn.h
> index fe8b780..a8ec93b 100644
> --- a/arch/powerpc/mm/vphn.h
> +++ b/arch/powerpc/mm/vphn.h
> @@ -5,6 +5,10 @@
>   */
>  #define VPHN_REGISTER_COUNT 6
> 
> +/* Maximum number of affinity reference points supported by NUMA/VPHN.
> + */
> +#define MAX_DISTANCE_REF_POINTS 4
> +
>  /*
>   * 6 64-bit registers unpacked into up to 24 be32 associativity values. To
>   * form the complete property we have to add the length in the first cell.
> diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
> index 6afd1ef..5a7fb1e 100644
> --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
> +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
> @@ -356,6 +356,7 @@ static int dlpar_online_cpu(struct device_node *dn)
>  			BUG_ON(get_cpu_current_state(cpu)
>  					!= CPU_STATE_OFFLINE);
>  			cpu_maps_update_done();
> +			timed_topology_update(1);
>  			rc = device_online(get_cpu_device(cpu));
>  			if (rc)
>  				goto out;
> @@ -522,6 +523,7 @@ static int dlpar_offline_cpu(struct device_node *dn)
>  				set_preferred_offline_state(cpu,
>  							    CPU_STATE_OFFLINE);
>  				cpu_maps_update_done();
> +				timed_topology_update(1);
>  				rc = device_offline(get_cpu_device(cpu));
>  				if (rc)
>  					goto out;
> 

[PATCH V10 2/2] powerpc/nodes: Ensure enough nodes avail for operations

[Michael Bringmann]

From: Michael Bringmann <mwb@linux.vnet.ibm.com>
To: linuxppc-dev@lists.ozlabs.org
To: linux-kernel@vger.kernel.org
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Michael Bringmann <mwb@linux.vnet.ibm.com>
Cc: John Allen <jallen@linux.vnet.ibm.com>
Cc: Nathan Fontenot <nfont@linux.vnet.ibm.com>
Subject: [PATCH V10 2/2] powerpc/nodes: Ensure enough nodes avail for operations

powerpc/nodes: On systems like PowerPC which allow 'hot-add' of CPU
or memory resources, it may occur that the new resources are to be
inserted into nodes that were not used for these resources at bootup.
In the kernel, any node that is used must be defined and initialized
at boot.

This patch extracts the value of the 'min_common_depth' element from
the "rtas" device tree property "ibm,max-associativity-domains" to use
as the maximum number of nodes to setup as possibly available in the
system.  [The 'min_common_depth' element is calculated from memory
associations found while loading all of the configured memory into
the system data structures at boot.]  This new setting will override
the instruction,

    nodes_and(node_possible_map, node_possible_map, node_online_map);

presently seen in the function arch/powerpc/mm/numa.c:initmem_init().

If the property is not present at boot, no operation will be performed
to define or enable additional nodes.

Signed-off-by: Michael Bringmann <mwb@linux.vnet.ibm.com>
---
Changes in V10:
  -- Try to use 'min_common_depth' from NUMA initialization to select
     domain level to use for maximum nodes.
---
 arch/powerpc/mm/numa.c |   44 ++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 44 insertions(+)

diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 73427e290..841d3b6 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -896,6 +896,48 @@ static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn)
 	NODE_DATA(nid)->node_spanned_pages = spanned_pages;
 }
 
+static void __init node_associativity_setup(void)
+{
+	struct device_node *rtas;
+
+	rtas = of_find_node_by_path("/rtas");
+	if (rtas) {
+		const __be32 *prop;
+		u32 len, entries, numnodes, i;
+
+		prop = of_get_property(rtas, "ibm,max-associativity-domains", &len);
+		if (!prop || len < sizeof(unsigned int))
+			goto endit;
+
+		entries = of_read_number(prop++, 1);
+
+		if (len < (entries * sizeof(unsigned int)))
+			goto endit;
+
+		dbg("numa: Debug: Entries = %d MCD = %d\n", entries, min_common_depth);
+
+		if ((0 <= min_common_depth) && (min_common_depth <= (entries-1)))
+			entries = min_common_depth;
+		else
+			entries -= 1;
+
+		numnodes = of_read_number(&prop[entries], 1);
+
+		printk(KERN_INFO "numa: Nodes = %d\n", numnodes);
+
+		for (i = 0; i < numnodes; i++) {
+			if (!node_possible(i)) {
+				setup_node_data(i, 0, 0);
+				node_set(i, node_possible_map);
+			}
+		}
+	}
+
+endit:
+	if (rtas)
+		of_node_put(rtas);
+}
+
 void __init initmem_init(void)
 {
 	int nid, cpu;
@@ -915,6 +957,8 @@ void __init initmem_init(void)
 	 */
 	nodes_and(node_possible_map, node_possible_map, node_online_map);
 
+	node_associativity_setup();
+
 	for_each_online_node(nid) {
 		unsigned long start_pfn, end_pfn;