[PATCH V6 0/2] pseries/nodes: Fix issues with memoryless nodes

[PATCH V6 0/2] pseries/nodes: Fix issues with memoryless nodes

[Michael Bringmann]

pseries/nodes: Ensure enough nodes avail for operations

pseries/initnodes: Ensure nodes initialized for hotplug

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

Michael Bringmann (2):
  pseries/nodes: Ensure enough nodes avail for operations
  pseries/initnodes: Ensure nodes initialized for hotplug
---
Changes in V6:
  -- Remove some node initialization/allocation from boot setup
  -- Add some needed node initialization to runtime code that maps
     CPUs based on VPHN associativity
  -- Add error checks and alternate recovery for compile flag
     CONFIG_MEMORY_HOTPLUG
  -- Add alternate node selection recovery for !CONFIG_MEMORY_HOTPLUG

[PATCH V6 1/2] pseries/nodes: Ensure enough nodes avail for operations

[Michael Bringmann]

pseries/nodes: On pseries systems 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.
This patch ensures that sufficient nodes are defined to support
configuration requirements after boot, as well as at boot.

This patch extracts the value of the lowest domain level (number
of allocable resources) from the device tree property
"ibm,max-associativity-domains" to use as the maximum number of nodes
to setup as possibly available in the system.  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 V6:
  -- Remove some node initialization/allocation from boot setup
---
 arch/powerpc/mm/numa.c |   40 +++++++++++++++++++++++++++++++++++++---
 1 file changed, 37 insertions(+), 3 deletions(-)

diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index eb604b3..334a1ff 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -892,6 +892,37 @@ 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 find_possible_nodes(void)
+{
+	struct device_node *rtas;
+	u32 numnodes, i;
+
+	if (min_common_depth <= 0)
+		return;
+
+	rtas = of_find_node_by_path("/rtas");
+	if (!rtas)
+		return;
+
+	if (of_property_read_u32_index(rtas,
+				"ibm,max-associativity-domains",
+				min_common_depth, &numnodes))
+		goto out;
+
+	pr_info("numa: Nodes = %d (mcd = %d)\n", numnodes,
+		min_common_depth);
+
+	for (i = 0; i < numnodes; i++) {
+		if (!node_possible(i)) {
+			setup_node_data(i, 0, 0);
+			node_set(i, node_possible_map);
+		}
+	}
+
+out:
+	of_node_put(rtas);
+}
+
 void __init initmem_init(void)
 {
 	int nid, cpu;
@@ -905,12 +936,15 @@ void __init initmem_init(void)
 	memblock_dump_all();
 
 	/*
-	 * Reduce the possible NUMA nodes to the online NUMA nodes,
-	 * since we do not support node hotplug. This ensures that  we
-	 * lower the maximum NUMA node ID to what is actually present.
+	 * Modify the set of possible NUMA nodes to reflect information
+	 * available about the set of online nodes, and the set of nodes
+	 * that we expect to make use of for this platform's affinity
+	 * calculations.
 	 */
 	nodes_and(node_possible_map, node_possible_map, node_online_map);
 
+	find_possible_nodes();
+
 	for_each_online_node(nid) {
 		unsigned long start_pfn, end_pfn;
 

[PATCH V6 2/2] pseries/initnodes: Ensure nodes initialized for hotplug

[Michael Bringmann]

pseries/nodes: On pseries systems which allow 'hot-add' of CPU,
it may occur that the new resources are to be inserted into nodes
that were not used for memory resources at bootup.  Many different
configurations of PowerPC resources may need to be supported depending
upon the environment.  This patch fixes some problems encountered at
runtime with configurations that support memory-less nodes, or that
hot-add CPUs into nodes that are memoryless during system execution
after boot.

Signed-off-by: Michael Bringmann <mwb@linux.vnet.ibm.com>
---
Changes in V6:
  -- Add some needed node initialization to runtime code that maps
     CPUs based on VPHN associativity
  -- Add error checks and alternate recovery for compile flag
     CONFIG_MEMORY_HOTPLUG
  -- Add alternate node selection recovery for !CONFIG_MEMORY_HOTPLUG
---
 arch/powerpc/mm/numa.c |   51 ++++++++++++++++++++++++++++++++++++++----------
 1 file changed, 40 insertions(+), 11 deletions(-)

diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 334a1ff..163f4cc 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -551,7 +551,7 @@ static int numa_setup_cpu(unsigned long lcpu)
 	nid = of_node_to_nid_single(cpu);
 
 out_present:
-	if (nid < 0 || !node_online(nid))
+	if (nid < 0 || !node_possible(nid))
 		nid = first_online_node;
 
 	map_cpu_to_node(lcpu, nid);
@@ -867,7 +867,7 @@ void __init dump_numa_cpu_topology(void)
 }
 
 /* Initialize NODE_DATA for a node on the local memory */
-static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn)
+static void setup_node_data(int nid, u64 start_pfn, u64 end_pfn)
 {
 	u64 spanned_pages = end_pfn - start_pfn;
 	const size_t nd_size = roundup(sizeof(pg_data_t), SMP_CACHE_BYTES);
@@ -913,10 +913,8 @@ static void __init find_possible_nodes(void)
 		min_common_depth);
 
 	for (i = 0; i < numnodes; i++) {
-		if (!node_possible(i)) {
-			setup_node_data(i, 0, 0);
+		if (!node_possible(i))
 			node_set(i, node_possible_map);
-		}
 	}
 
 out:
@@ -1312,6 +1310,42 @@ static long vphn_get_associativity(unsigned long cpu,
 	return rc;
 }
 
+static inline int find_cpu_nid(int cpu)
+{
+	__be32 associativity[VPHN_ASSOC_BUFSIZE] = {0};
+	int new_nid;
+
+	/* Use associativity from first thread for all siblings */
+	vphn_get_associativity(cpu, associativity);
+	new_nid = associativity_to_nid(associativity);
+	if (new_nid < 0 || !node_possible(new_nid))
+		new_nid = first_online_node;
+
+	if (NODE_DATA(new_nid) == NULL) {
+#ifdef CONFIG_MEMORY_HOTPLUG
+		/*
+		 * Need to ensure that NODE_DATA is initialized
+		 * for a node from available memory (see
+		 * memblock_alloc_try_nid).  If unable to init
+		 * the node, then default to nearest node that
+		 * has memory installed.
+		 */
+		if (try_online_node(new_nid))
+			new_nid = first_online_node;
+#else
+		/*
+		 * Default to using the nearest node that has
+		 * memory installed.  Otherwise, it would be 
+		 * necessary to patch the kernel MM code to deal
+		 * with more memoryless-node error conditions.
+		 */
+		new_nid = first_online_node;
+#endif
+	}
+
+	return new_nid;
+}
+
 /*
  * 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
@@ -1379,7 +1413,6 @@ 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;
@@ -1417,11 +1450,7 @@ int numa_update_cpu_topology(bool cpus_locked)
 			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;
+		new_nid = find_cpu_nid(cpu);
 
 		if (new_nid == numa_cpu_lookup_table[cpu]) {
 			cpumask_andnot(&cpu_associativity_changes_mask,