summaryrefslogtreecommitdiffstats
path: root/mm
diff options
context:
space:
mode:
authorLee Schermerhorn <lee.schermerhorn@hp.com>2010-05-26 14:45:00 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2010-05-27 09:12:57 -0700
commit7aac789885512388a66d47280d7e7777ffba1e59 (patch)
treeaf4ac98260268889a422dd264102d2f15d5c1983 /mm
parent3bccd996276b108c138e8176793a26ecef54d573 (diff)
downloadlinux-stable-7aac789885512388a66d47280d7e7777ffba1e59.tar.gz
linux-stable-7aac789885512388a66d47280d7e7777ffba1e59.tar.bz2
linux-stable-7aac789885512388a66d47280d7e7777ffba1e59.zip
numa: introduce numa_mem_id()- effective local memory node id
Introduce numa_mem_id(), based on generic percpu variable infrastructure to track "nearest node with memory" for archs that support memoryless nodes. Define API in <linux/topology.h> when CONFIG_HAVE_MEMORYLESS_NODES defined, else stubs. Architectures will define HAVE_MEMORYLESS_NODES if/when they support them. Archs can override definitions of: numa_mem_id() - returns node number of "local memory" node set_numa_mem() - initialize [this cpus'] per cpu variable 'numa_mem' cpu_to_mem() - return numa_mem for specified cpu; may be used as lvalue Generic initialization of 'numa_mem' occurs in __build_all_zonelists(). This will initialize the boot cpu at boot time, and all cpus on change of numa_zonelist_order, or when node or memory hot-plug requires zonelist rebuild. Archs that support memoryless nodes will need to initialize 'numa_mem' for secondary cpus as they're brought on-line. [akpm@linux-foundation.org: fix build] Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Christoph Lameter <cl@linux-foundation.org> Cc: Tejun Heo <tj@kernel.org> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Christoph Lameter <cl@linux-foundation.org> Cc: Nick Piggin <npiggin@suse.de> Cc: David Rientjes <rientjes@google.com> Cc: Eric Whitney <eric.whitney@hp.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: Pekka Enberg <penberg@cs.helsinki.fi> Cc: <linux-arch@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm')
-rw-r--r--mm/page_alloc.c45
1 files changed, 44 insertions, 1 deletions
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 6fe1b65ee1a8..431214b941ac 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -62,6 +62,17 @@ DEFINE_PER_CPU(int, numa_node);
EXPORT_PER_CPU_SYMBOL(numa_node);
#endif
+#ifdef CONFIG_HAVE_MEMORYLESS_NODES
+/*
+ * N.B., Do NOT reference the '_numa_mem_' per cpu variable directly.
+ * It will not be defined when CONFIG_HAVE_MEMORYLESS_NODES is not defined.
+ * Use the accessor functions set_numa_mem(), numa_mem_id() and cpu_to_mem()
+ * defined in <linux/topology.h>.
+ */
+DEFINE_PER_CPU(int, _numa_mem_); /* Kernel "local memory" node */
+EXPORT_PER_CPU_SYMBOL(_numa_mem_);
+#endif
+
/*
* Array of node states.
*/
@@ -2861,6 +2872,24 @@ static void build_zonelist_cache(pg_data_t *pgdat)
zlc->z_to_n[z - zonelist->_zonerefs] = zonelist_node_idx(z);
}
+#ifdef CONFIG_HAVE_MEMORYLESS_NODES
+/*
+ * Return node id of node used for "local" allocations.
+ * I.e., first node id of first zone in arg node's generic zonelist.
+ * Used for initializing percpu 'numa_mem', which is used primarily
+ * for kernel allocations, so use GFP_KERNEL flags to locate zonelist.
+ */
+int local_memory_node(int node)
+{
+ struct zone *zone;
+
+ (void)first_zones_zonelist(node_zonelist(node, GFP_KERNEL),
+ gfp_zone(GFP_KERNEL),
+ NULL,
+ &zone);
+ return zone->node;
+}
+#endif
#else /* CONFIG_NUMA */
@@ -2975,9 +3004,23 @@ static __init_refok int __build_all_zonelists(void *data)
* needs the percpu allocator in order to allocate its pagesets
* (a chicken-egg dilemma).
*/
- for_each_possible_cpu(cpu)
+ for_each_possible_cpu(cpu) {
setup_pageset(&per_cpu(boot_pageset, cpu), 0);
+#ifdef CONFIG_HAVE_MEMORYLESS_NODES
+ /*
+ * We now know the "local memory node" for each node--
+ * i.e., the node of the first zone in the generic zonelist.
+ * Set up numa_mem percpu variable for on-line cpus. During
+ * boot, only the boot cpu should be on-line; we'll init the
+ * secondary cpus' numa_mem as they come on-line. During
+ * node/memory hotplug, we'll fixup all on-line cpus.
+ */
+ if (cpu_online(cpu))
+ set_cpu_numa_mem(cpu, local_memory_node(cpu_to_node(cpu)));
+#endif
+ }
+
return 0;
}