Memoryless nodes: Generic management of nodemasks for various purposes

Why do we need to support memoryless nodes?

KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> wrote:

> For fujitsu, problem is called "empty" node.
>
> When ACPI's SRAT table includes "possible nodes", ia64 bootstrap(acpi_numa_init)
> creates nodes, which includes no memory, no cpu.
>
> I tried to remove empty-node in past, but that was denied.
> It was because we can hot-add cpu to the empty node.
> (node-hotplug triggered by cpu is not implemented now. and it will be ugly.)
>
>
> For HP, (Lee can comment on this later), they have memory-less-node.
> As far as I hear, HP's machine can have following configration.
>
> (example)
> Node0: CPU0   memory AAA MB
> Node1: CPU1   memory AAA MB
> Node2: CPU2   memory AAA MB
> Node3: CPU3   memory AAA MB
> Node4: Memory XXX GB
>
> AAA is very small value (below 16MB)  and will be omitted by ia64 bootstrap.
> After boot, only Node 4 has valid memory (but have no cpu.)
>
> Maybe this is memory-interleave by firmware config.

Christoph Lameter <clameter@sgi.com> wrote:

> Future SGI platforms (actually also current one can have but nothing like
> that is deployed to my knowledge) have nodes with only cpus. Current SGI
> platforms have nodes with just I/O that we so far cannot manage in the
> core. So the arch code maps them to the nearest memory node.

Lee Schermerhorn <Lee.Schermerhorn@hp.com> wrote:

> For the HP platforms, we can configure each cell with from 0% to 100%
> "cell local memory".  When we configure with <100% CLM, the "missing
> percentages" are interleaved by hardware on a cache-line granularity to
> improve bandwidth at the expense of latency for numa-challenged
> applications [and OSes, but not our problem ;-)].  When we boot Linux on
> such a config, all of the real nodes have no memory--it all resides in a
> single interleaved pseudo-node.
>
> When we boot Linux on a 100% CLM configuration [== NUMA], we still have
> the interleaved pseudo-node.  It contains a few hundred MB stolen from
> the real nodes to contain the DMA zone.  [Interleaved memory resides at
> phys addr 0].  The memoryless-nodes patches, along with the zoneorder
> patches, support this config as well.
>
> Also, when we boot a NUMA config with the "mem=" command line,
> specifying less memory than actually exists, Linux takes the excluded
> memory "off the top" rather than distributing it across the nodes.  This
> can result in memoryless nodes, as well.
>

This patch:

Preparation for memoryless node patches.

Provide a generic way to keep nodemasks describing various characteristics of
NUMA nodes.

Remove the node_online_map and the node_possible map and realize the same
functionality using two nodes stats: N_POSSIBLE and N_ONLINE.

[Lee.Schermerhorn@hp.com: Initialize N_*_MEMORY and N_CPU masks for non-NUMA config]
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Tested-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Acked-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Acked-by: Bob Picco <bob.picco@hp.com>
Cc: Nishanth Aravamudan <nacc@us.ibm.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Mel Gorman <mel@skynet.ie>
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: "Serge E. Hallyn" <serge@hallyn.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

include/linux/nodemask.h

@@ -337,32 +337,82 @@ static inline void __nodes_remap(nodemask_t *dstp, const nodemask_t *srcp,
 		for ((node) = 0; (node) < 1; (node)++)
 #endif /* MAX_NUMNODES */
 
+/*
+ * Bitmasks that are kept for all the nodes.
+ */
+enum node_states {
+	N_POSSIBLE,	/* The node could become online at some point */
+	N_ONLINE,	/* The node is online */
+	NR_NODE_STATES
+};
+
 /*
  * The following particular system nodemasks and operations
  * on them manage all possible and online nodes.
  */
 
-extern nodemask_t node_online_map;
-extern nodemask_t node_possible_map;
+extern nodemask_t node_states[NR_NODE_STATES];
 
 #if MAX_NUMNODES > 1
-#define num_online_nodes()	nodes_weight(node_online_map)
-#define num_possible_nodes()	nodes_weight(node_possible_map)
-#define node_online(node)	node_isset((node), node_online_map)
-#define node_possible(node)	node_isset((node), node_possible_map)
-#define first_online_node	first_node(node_online_map)
-#define next_online_node(nid)	next_node((nid), node_online_map)
+static inline int node_state(int node, enum node_states state)
+{
+	return node_isset(node, node_states[state]);
+}
+
+static inline void node_set_state(int node, enum node_states state)
+{
+	__node_set(node, &node_states[state]);
+}
+
+static inline void node_clear_state(int node, enum node_states state)
+{
+	__node_clear(node, &node_states[state]);
+}
+
+static inline int num_node_state(enum node_states state)
+{
+	return nodes_weight(node_states[state]);
+}
+
+#define for_each_node_state(__node, __state) \
+	for_each_node_mask((__node), node_states[__state])
+
+#define first_online_node	first_node(node_states[N_ONLINE])
+#define next_online_node(nid)	next_node((nid), node_states[N_ONLINE])
+
 extern int nr_node_ids;
 #else
-#define num_online_nodes()	1
-#define num_possible_nodes()	1
-#define node_online(node)	((node) == 0)
-#define node_possible(node)	((node) == 0)
+
+static inline int node_state(int node, enum node_states state)
+{
+	return node == 0;
+}
+
+static inline void node_set_state(int node, enum node_states state)
+{
+}
+
+static inline void node_clear_state(int node, enum node_states state)
+{
+}
+
+static inline int num_node_state(enum node_states state)
+{
+	return 1;
+}
+
+#define for_each_node_state(node, __state) \
+	for ( (node) = 0; (node) == 0; (node) = 1)
+
 #define first_online_node	0
 #define next_online_node(nid)	(MAX_NUMNODES)
 #define nr_node_ids		1
+
 #endif
 
+#define node_online_map 	node_states[N_ONLINE]
+#define node_possible_map 	node_states[N_POSSIBLE]
+
 #define any_online_node(mask)			\
 ({						\
 	int node;				\
@@ -372,10 +422,15 @@ extern int nr_node_ids;
 	node;					\
 })
 
-#define node_set_online(node)	   set_bit((node), node_online_map.bits)
-#define node_set_offline(node)	   clear_bit((node), node_online_map.bits)
+#define num_online_nodes()	num_node_state(N_ONLINE)
+#define num_possible_nodes()	num_node_state(N_POSSIBLE)
+#define node_online(node)	node_state((node), N_ONLINE)
+#define node_possible(node)	node_state((node), N_POSSIBLE)
+
+#define node_set_online(node)	   node_set_state((node), N_ONLINE)
+#define node_set_offline(node)	   node_clear_state((node), N_ONLINE)
 
-#define for_each_node(node)	   for_each_node_mask((node), node_possible_map)
-#define for_each_online_node(node) for_each_node_mask((node), node_online_map)
+#define for_each_node(node)	   for_each_node_state(node, N_POSSIBLE)
+#define for_each_online_node(node) for_each_node_state(node, N_ONLINE)
 
 #endif /* __LINUX_NODEMASK_H */

mm/page_alloc.c

@@ -47,13 +47,21 @@
 #include "internal.h"
 
 /*
- * MCD - HACK: Find somewhere to initialize this EARLY, or make this
- * initializer cleaner
+ * Array of node states.
  */
-nodemask_t node_online_map __read_mostly = { { [0] = 1UL } };
-EXPORT_SYMBOL(node_online_map);
-nodemask_t node_possible_map __read_mostly = NODE_MASK_ALL;
-EXPORT_SYMBOL(node_possible_map);
+nodemask_t node_states[NR_NODE_STATES] __read_mostly = {
+	[N_POSSIBLE] = NODE_MASK_ALL,
+	[N_ONLINE] = { { [0] = 1UL } },
+#ifndef CONFIG_NUMA
+	[N_NORMAL_MEMORY] = { { [0] = 1UL } },
+#ifdef CONFIG_HIGHMEM
+	[N_HIGH_MEMORY] = { { [0] = 1UL } },
+#endif
+	[N_CPU] = { { [0] = 1UL } },
+#endif	/* NUMA */
+};
+EXPORT_SYMBOL(node_states);
+
 unsigned long totalram_pages __read_mostly;
 unsigned long totalreserve_pages __read_mostly;
 long nr_swap_pages;