1 files changed, 76 insertions, 21 deletions

diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 3c7dec70cda0..9fcf2d195830 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -461,25 +461,69 @@ static int of_drconf_to_nid_single(struct drmem_lmb *lmb)
 	return nid;
 }
 
+#ifdef CONFIG_PPC_SPLPAR
+static int vphn_get_nid(long lcpu)
+{
+	__be32 associativity[VPHN_ASSOC_BUFSIZE] = {0};
+	long rc, hwid;
+
+	/*
+	 * On a shared lpar, device tree will not have node associativity.
+	 * At this time lppaca, or its __old_status field may not be
+	 * updated. Hence kernel cannot detect if its on a shared lpar. So
+	 * request an explicit associativity irrespective of whether the
+	 * lpar is shared or dedicated. Use the device tree property as a
+	 * fallback. cpu_to_phys_id is only valid between
+	 * smp_setup_cpu_maps() and smp_setup_pacas().
+	 */
+	if (firmware_has_feature(FW_FEATURE_VPHN)) {
+		if (cpu_to_phys_id)
+			hwid = cpu_to_phys_id[lcpu];
+		else
+			hwid = get_hard_smp_processor_id(lcpu);
+
+		rc = hcall_vphn(hwid, VPHN_FLAG_VCPU, associativity);
+		if (rc == H_SUCCESS)
+			return associativity_to_nid(associativity);
+	}
+
+	return NUMA_NO_NODE;
+}
+#else
+static int vphn_get_nid(long unused)
+{
+	return NUMA_NO_NODE;
+}
+#endif  /* CONFIG_PPC_SPLPAR */
+
 /*
  * Figure out to which domain a cpu belongs and stick it there.
  * Return the id of the domain used.
  */
 static int numa_setup_cpu(unsigned long lcpu)
 {
-	int nid = NUMA_NO_NODE;
 	struct device_node *cpu;
+	int fcpu = cpu_first_thread_sibling(lcpu);
+	int nid = NUMA_NO_NODE;
 
 	/*
 	 * 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).
+	 * Since cpu_to_node binding remains the same for all threads in the
+	 * core. If a valid cpu-to-node mapping is already available, for
+	 * the first thread in the core, use it.
 	 */
-	if ((nid = numa_cpu_lookup_table[lcpu]) >= 0) {
+	nid = numa_cpu_lookup_table[fcpu];
+	if (nid >= 0) {
 		map_cpu_to_node(lcpu, nid);
 		return nid;
 	}
 
+	nid = vphn_get_nid(lcpu);
+	if (nid != NUMA_NO_NODE)
+		goto out_present;
+
 	cpu = of_get_cpu_node(lcpu, NULL);
 
 	if (!cpu) {
@@ -491,13 +535,26 @@ static int numa_setup_cpu(unsigned long lcpu)
 	}
 
 	nid = of_node_to_nid_single(cpu);
+	of_node_put(cpu);
 
 out_present:
 	if (nid < 0 || !node_possible(nid))
 		nid = first_online_node;
 
+	/*
+	 * Update for the first thread of the core. All threads of a core
+	 * have to be part of the same node. This not only avoids querying
+	 * for every other thread in the core, but always avoids a case
+	 * where virtual node associativity change causes subsequent threads
+	 * of a core to be associated with different nid. However if first
+	 * thread is already online, expect it to have a valid mapping.
+	 */
+	if (fcpu != lcpu) {
+		WARN_ON(cpu_online(fcpu));
+		map_cpu_to_node(fcpu, nid);
+	}
+
 	map_cpu_to_node(lcpu, nid);
-	of_node_put(cpu);
 out:
 	return nid;
 }
@@ -1191,23 +1248,30 @@ static long vphn_get_associativity(unsigned long cpu,
 				VPHN_FLAG_VCPU, associativity);
 
 	switch (rc) {
+	case H_SUCCESS:
+		dbg("VPHN hcall succeeded. Reset polling...\n");
+		timed_topology_update(0);
+		goto out;
+
 	case H_FUNCTION:
-		printk_once(KERN_INFO
-			"VPHN is not supported. Disabling polling...\n");
-		stop_topology_update();
+		pr_err_ratelimited("VPHN unsupported. Disabling polling...\n");
 		break;
 	case H_HARDWARE:
-		printk(KERN_ERR
-			"hcall_vphn() experienced a hardware fault "
+		pr_err_ratelimited("hcall_vphn() experienced a hardware fault "
 			"preventing VPHN. Disabling polling...\n");
-		stop_topology_update();
 		break;
-	case H_SUCCESS:
-		dbg("VPHN hcall succeeded. Reset polling...\n");
-		timed_topology_update(0);
+	case H_PARAMETER:
+		pr_err_ratelimited("hcall_vphn() was passed an invalid parameter. "
+			"Disabling polling...\n");
+		break;
+	default:
+		pr_err_ratelimited("hcall_vphn() returned %ld. Disabling polling...\n"
+			, rc);
 		break;
 	}
 
+	stop_topology_update();
+out:
 	return rc;
 }
 
@@ -1568,15 +1632,6 @@ int prrn_is_enabled(void)
 	return prrn_enabled;
 }
 
-void __init shared_proc_topology_init(void)
-{
-	if (lppaca_shared_proc(get_lppaca())) {
-		bitmap_fill(cpumask_bits(&cpu_associativity_changes_mask),
-			    nr_cpumask_bits);
-		numa_update_cpu_topology(false);
-	}
-}
-
 static int topology_read(struct seq_file *file, void *v)
 {
 	if (vphn_enabled || prrn_enabled)