4 files changed, 131 insertions, 36 deletions

diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 8726779e1409..d9196c9f93d9 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -223,9 +223,6 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address,
 	is_write = error_code & ESR_DST;
 #endif /* CONFIG_4xx || CONFIG_BOOKE */
 
-	if (is_write)
-		flags |= FAULT_FLAG_WRITE;
-
 #ifdef CONFIG_PPC_ICSWX
 	/*
 	 * we need to do this early because this "data storage
@@ -280,6 +277,9 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address,
 
 	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
 
+	if (user_mode(regs))
+		flags |= FAULT_FLAG_USER;
+
 	/* When running in the kernel we expect faults to occur only to
 	 * addresses in user space.  All other faults represent errors in the
 	 * kernel and should generate an OOPS.  Unfortunately, in the case of an
@@ -408,6 +408,7 @@ good_area:
 	} else if (is_write) {
 		if (!(vma->vm_flags & VM_WRITE))
 			goto bad_area;
+		flags |= FAULT_FLAG_WRITE;
 	/* a read */
 	} else {
 		/* protection fault */
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index e303a6d74e3a..929e3e675868 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -250,9 +250,9 @@ static int __init htab_dt_scan_seg_sizes(unsigned long node,
 					 const char *uname, int depth,
 					 void *data)
 {
-	char *type = of_get_flat_dt_prop(node, "device_type", NULL);
-	u32 *prop;
-	unsigned long size = 0;
+	const char *type = of_get_flat_dt_prop(node, "device_type", NULL);
+	const __be32 *prop;
+	int size = 0;
 
 	/* We are scanning "cpu" nodes only */
 	if (type == NULL || strcmp(type, "cpu") != 0)
@@ -306,9 +306,9 @@ static int __init htab_dt_scan_page_sizes(unsigned long node,
 					  const char *uname, int depth,
 					  void *data)
 {
-	char *type = of_get_flat_dt_prop(node, "device_type", NULL);
-	u32 *prop;
-	unsigned long size = 0;
+	const char *type = of_get_flat_dt_prop(node, "device_type", NULL);
+	const __be32 *prop;
+	int size = 0;
 
 	/* We are scanning "cpu" nodes only */
 	if (type == NULL || strcmp(type, "cpu") != 0)
@@ -389,9 +389,9 @@ static int __init htab_dt_scan_page_sizes(unsigned long node,
 static int __init htab_dt_scan_hugepage_blocks(unsigned long node,
 					const char *uname, int depth,
 					void *data) {
-	char *type = of_get_flat_dt_prop(node, "device_type", NULL);
-	unsigned long *addr_prop;
-	u32 *page_count_prop;
+	const char *type = of_get_flat_dt_prop(node, "device_type", NULL);
+	const __be64 *addr_prop;
+	const __be32 *page_count_prop;
 	unsigned int expected_pages;
 	long unsigned int phys_addr;
 	long unsigned int block_size;
@@ -533,8 +533,8 @@ static int __init htab_dt_scan_pftsize(unsigned long node,
 				       const char *uname, int depth,
 				       void *data)
 {
-	char *type = of_get_flat_dt_prop(node, "device_type", NULL);
-	u32 *prop;
+	const char *type = of_get_flat_dt_prop(node, "device_type", NULL);
+	const __be32 *prop;
 
 	/* We are scanning "cpu" nodes only */
 	if (type == NULL || strcmp(type, "cpu") != 0)
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 92c456ce1f87..51663518ea40 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -27,9 +27,12 @@
 #include <linux/seq_file.h>
 #include <linux/uaccess.h>
 #include <linux/slab.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>
@@ -151,9 +154,22 @@ static void __init get_node_active_region(unsigned long pfn,
 	}
 }
 
-static void map_cpu_to_node(int cpu, int node)
+static void reset_numa_cpu_lookup_table(void)
+{
+	unsigned int cpu;
+
+	for_each_possible_cpu(cpu)
+		numa_cpu_lookup_table[cpu] = -1;
+}
+
+static 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)
+{
+	update_numa_cpu_lookup_table(cpu, node);
 
 	dbg("adding cpu %d to node %d\n", cpu, node);
 
@@ -518,11 +534,24 @@ static int of_drconf_to_nid_single(struct of_drconf_cell *drmem,
  */
 static int __cpuinit numa_setup_cpu(unsigned long lcpu)
 {
-	int nid = 0;
-	struct device_node *cpu = of_get_cpu_node(lcpu, NULL);
+	int nid;
+	struct device_node *cpu;
+
+	/*
+	 * If a valid cpu-to-node mapping is already available, use it
+	 * directly instead of querying the firmware, since it represents
+	 * the most recent mapping notified to us by the platform (eg: VPHN).
+	 */
+	if ((nid = numa_cpu_lookup_table[lcpu]) >= 0) {
+		map_cpu_to_node(lcpu, nid);
+		return nid;
+	}
+
+	cpu = of_get_cpu_node(lcpu, NULL);
 
 	if (!cpu) {
 		WARN_ON(1);
+		nid = 0;
 		goto out;
 	}
 
@@ -557,8 +586,8 @@ static int __cpuinit cpu_numa_callback(struct notifier_block *nfb,
 	case CPU_UP_CANCELED:
 	case CPU_UP_CANCELED_FROZEN:
 		unmap_cpu_from_node(lcpu);
-		break;
 		ret = NOTIFY_OK;
+		break;
 #endif
 	}
 	return ret;
@@ -1065,6 +1094,7 @@ void __init do_init_bootmem(void)
 	 */
 	setup_node_to_cpumask_map();
 
+	reset_numa_cpu_lookup_table();
 	register_cpu_notifier(&ppc64_numa_nb);
 	cpu_numa_callback(&ppc64_numa_nb, CPU_UP_PREPARE,
 			  (void *)(unsigned long)boot_cpuid);
@@ -1319,7 +1349,8 @@ static int update_cpu_associativity_changes_mask(void)
 			}
 		}
 		if (changed) {
-			cpumask_set_cpu(cpu, changes);
+			cpumask_or(changes, changes, cpu_sibling_mask(cpu));
+			cpu = cpu_last_thread_sibling(cpu);
 		}
 	}
 
@@ -1427,17 +1458,42 @@ static int update_cpu_topology(void *data)
 	if (!data)
 		return -EINVAL;
 
-	cpu = get_cpu();
+	cpu = smp_processor_id();
 
 	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;
+}
+
+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;
@@ -1449,12 +1505,12 @@ static int update_cpu_topology(void *data)
  */
 int arch_update_cpu_topology(void)
 {
-	unsigned int cpu, changed = 0;
+	unsigned int cpu, sibling, 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;
+	int weight, new_nid, i = 0;
 
 	weight = cpumask_weight(&cpu_associativity_changes_mask);
 	if (!weight)
@@ -1467,24 +1523,62 @@ int arch_update_cpu_topology(void)
 	cpumask_clear(&updated_cpus);
 
 	for_each_cpu(cpu, &cpu_associativity_changes_mask) {
-		ud = &updates[i++];
-		ud->cpu = cpu;
-		vphn_get_associativity(cpu, associativity);
-		ud->new_nid = associativity_to_nid(associativity);
-
-		if (ud->new_nid < 0 || !node_online(ud->new_nid))
-			ud->new_nid = first_online_node;
+		/*
+		 * 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;
+		}
 
-		ud->old_nid = numa_cpu_lookup_table[cpu];
-		cpumask_set_cpu(cpu, &updated_cpus);
+		/* 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;
+		}
 
-		if (i < weight)
-			ud->next = &updates[i];
+		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);
 	}
 
 	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.
+	 */
+	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);
diff --git a/arch/powerpc/mm/slice.c b/arch/powerpc/mm/slice.c
index 3e99c149271a..7ce9cf3b6988 100644
--- a/arch/powerpc/mm/slice.c
+++ b/arch/powerpc/mm/slice.c
@@ -258,7 +258,7 @@ static bool slice_scan_available(unsigned long addr,
 		slice = GET_HIGH_SLICE_INDEX(addr);
 		*boundary_addr = (slice + end) ?
 			((slice + end) << SLICE_HIGH_SHIFT) : SLICE_LOW_TOP;
-		return !!(available.high_slices & (1u << slice));
+		return !!(available.high_slices & (1ul << slice));
 	}
 }