Merge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc

Pull powerpc update from Benjamin Herrenschmidt:
 "The main highlights this time around are:

   - A pile of addition POWER8 bits and nits, such as updated
     performance counter support (Michael Ellerman), new branch history
     buffer support (Anshuman Khandual), base support for the new PCI
     host bridge when not using the hypervisor (Gavin Shan) and other
     random related bits and fixes from various contributors.

   - Some rework of our page table format by Aneesh Kumar which fixes a
     thing or two and paves the way for THP support.  THP itself will
     not make it this time around however.

   - More Freescale updates, including Altivec support on the new e6500
     cores, new PCI controller support, and a pile of new boards support
     and updates.

   - The usual batch of trivial cleanups & fixes"

* 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc: (156 commits)
  powerpc: Fix build error for book3e
  powerpc: Context switch the new EBB SPRs
  powerpc: Turn on the EBB H/FSCR bits
  powerpc: Replace CPU_FTR_BCTAR with CPU_FTR_ARCH_207S
  powerpc: Setup BHRB instructions facility in HFSCR for POWER8
  powerpc: Fix interrupt range check on debug exception
  powerpc: Update tlbie/tlbiel as per ISA doc
  powerpc: Print page size info during boot
  powerpc: print both base and actual page size on hash failure
  powerpc: Fix hpte_decode to use the correct decoding for page sizes
  powerpc: Decode the pte-lp-encoding bits correctly.
  powerpc: Use encode avpn where we need only avpn values
  powerpc: Reduce PTE table memory wastage
  powerpc: Move the pte free routines from common header
  powerpc: Reduce the PTE_INDEX_SIZE
  powerpc: Switch 16GB and 16MB explicit hugepages to a different page table format
  powerpc: New hugepage directory format
  powerpc: Don't truncate pgd_index wrongly
  powerpc: Don't hard code the size of pte page
  powerpc: Save DAR and DSISR in pt_regs on MCE
  ...

1 files changed, 216 insertions, 62 deletions

diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index fa33c546e77..88c0425dc0a 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -22,6 +22,10 @@
 #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 <asm/sparsemem.h>
 #include <asm/prom.h>
@@ -30,6 +34,7 @@
 #include <asm/paca.h>
 #include <asm/hvcall.h>
 #include <asm/setup.h>
+#include <asm/vdso.h>
 
 static int numa_enabled = 1;
 
@@ -77,7 +82,7 @@ static void __init setup_node_to_cpumask_map(void)
 	dbg("Node to cpumask map for %d nodes\n", nr_node_ids);
 }
 
-static int __cpuinit fake_numa_create_new_node(unsigned long end_pfn,
+static int __init fake_numa_create_new_node(unsigned long end_pfn,
 						unsigned int *nid)
 {
 	unsigned long long mem;
@@ -199,7 +204,7 @@ int __node_distance(int a, int b)
 	int distance = LOCAL_DISTANCE;
 
 	if (!form1_affinity)
-		return distance;
+		return ((a == b) ? LOCAL_DISTANCE : REMOTE_DISTANCE);
 
 	for (i = 0; i < distance_ref_points_depth; i++) {
 		if (distance_lookup_table[a][i] == distance_lookup_table[b][i])
@@ -289,9 +294,7 @@ EXPORT_SYMBOL_GPL(of_node_to_nid);
 static int __init find_min_common_depth(void)
 {
 	int depth;
-	struct device_node *chosen;
 	struct device_node *root;
-	const char *vec5;
 
 	if (firmware_has_feature(FW_FEATURE_OPAL))
 		root = of_find_node_by_path("/ibm,opal");
@@ -323,24 +326,10 @@ static int __init find_min_common_depth(void)
 
 	distance_ref_points_depth /= sizeof(int);
 
-#define VEC5_AFFINITY_BYTE	5
-#define VEC5_AFFINITY		0x80
-
-	if (firmware_has_feature(FW_FEATURE_OPAL))
+	if (firmware_has_feature(FW_FEATURE_OPAL) ||
+	    firmware_has_feature(FW_FEATURE_TYPE1_AFFINITY)) {
+		dbg("Using form 1 affinity\n");
 		form1_affinity = 1;
-	else {
-		chosen = of_find_node_by_path("/chosen");
-		if (chosen) {
-			vec5 = of_get_property(chosen,
-					       "ibm,architecture-vec-5", NULL);
-			if (vec5 && (vec5[VEC5_AFFINITY_BYTE] &
-							VEC5_AFFINITY)) {
-				dbg("Using form 1 affinity\n");
-				form1_affinity = 1;
-			}
-
-			of_node_put(chosen);
-		}
 	}
 
 	if (form1_affinity) {
@@ -1268,10 +1257,18 @@ u64 memory_hotplug_max(void)
 
 /* Virtual Processor Home Node (VPHN) support */
 #ifdef CONFIG_PPC_SPLPAR
+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 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
@@ -1307,11 +1304,9 @@ 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];
@@ -1325,11 +1320,10 @@ static int update_cpu_associativity_changes_mask(void)
 		}
 		if (changed) {
 			cpumask_set_cpu(cpu, changes);
-			nr_cpus++;
 		}
 	}
 
-	return nr_cpus;
+	return cpumask_weight(changes);
 }
 
 /*
@@ -1421,40 +1415,84 @@ static long vphn_get_associativity(unsigned long cpu,
 }
 
 /*
+ * 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 = get_cpu();
+
+	for (update = data; update; update = update->next) {
+		if (cpu != update->cpu)
+			continue;
+
+		unregister_cpu_under_node(update->cpu, update->old_nid);
+		unmap_cpu_from_node(update->cpu);
+		map_cpu_to_node(update->cpu, update->new_nid);
+		vdso_getcpu_init();
+		register_cpu_under_node(update->cpu, update->new_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.
  */
 int arch_update_cpu_topology(void)
 {
-	int cpu, nid, old_nid, changed = 0;
+	unsigned int cpu, changed = 0;
+	struct topology_update_data *updates, *ud;
 	unsigned int associativity[VPHN_ASSOC_BUFSIZE] = {0};
+	cpumask_t updated_cpus;
 	struct device *dev;
+	int weight, i = 0;
 
-	for_each_cpu(cpu,&cpu_associativity_changes_mask) {
+	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) {
+		ud = &updates[i++];
+		ud->cpu = cpu;
 		vphn_get_associativity(cpu, associativity);
-		nid = associativity_to_nid(associativity);
+		ud->new_nid = associativity_to_nid(associativity);
 
-		if (nid < 0 || !node_online(nid))
-			nid = first_online_node;
+		if (ud->new_nid < 0 || !node_online(ud->new_nid))
+			ud->new_nid = first_online_node;
 
-		old_nid = numa_cpu_lookup_table[cpu];
+		ud->old_nid = numa_cpu_lookup_table[cpu];
+		cpumask_set_cpu(cpu, &updated_cpus);
 
-		/* Disable hotplug while we update the cpu
-		 * masks and sysfs.
-		 */
-		get_online_cpus();
-		unregister_cpu_under_node(cpu, old_nid);
-		unmap_cpu_from_node(cpu);
-		map_cpu_to_node(cpu, nid);
-		register_cpu_under_node(cpu, nid);
-		put_online_cpus();
-
-		dev = get_cpu_device(cpu);
+		if (i < weight)
+			ud->next = &updates[i];
+	}
+
+	stop_machine(update_cpu_topology, &updates[0], &updated_cpus);
+
+	for (ud = &updates[0]; ud; ud = ud->next) {
+		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;
 	}
 
+	kfree(updates);
 	return changed;
 }
 
@@ -1471,49 +1509,165 @@ 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);
 }
 
+#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_prop_reconfig *update;
+	int rc = NOTIFY_DONE;
+
+	switch (action) {
+	case OF_RECONFIG_UPDATE_PROPERTY:
+		update = (struct of_prop_reconfig *)data;
+		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 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;
+#ifdef CONFIG_SMP
+			rc = of_reconfig_notifier_register(&dt_update_nb);
+#endif
+		}
+	} else if (firmware_has_feature(FW_FEATURE_VPHN) &&
+		   get_lppaca()->shared_proc) {
+		if (!vphn_enabled) {
+			prrn_enabled = 0;
+			vphn_enabled = 1;
+			setup_cpu_associativity_change_counters();
+			init_timer_deferrable(&topology_timer);
+			reset_topology_timer();
+		}
 	}
 
 	return rc;
 }
-__initcall(start_topology_update);
 
 /*
  * Disable polling for VPHN associativity changes.
  */
 int stop_topology_update(void)
 {
-	vphn_enabled = 0;
-	return del_timer_sync(&topology_timer);
+	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)
+{
+	start_topology_update();
+	proc_create("powerpc/topology_updates", 644, NULL, &topology_ops);
+
+	return 0;
 }
+device_initcall(topology_update_init);
 #endif /* CONFIG_PPC_SPLPAR */