summaryrefslogtreecommitdiffstats
path: root/arch/x86/mm/srat.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2013-02-23 17:50:35 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2013-02-23 17:50:35 -0800
commit5ce1a70e2f00f0bce0cab57f798ca354b9496169 (patch)
tree6e80200536b7a3576fd71ff2c7135ffe87dc858e /arch/x86/mm/srat.c
parent9d3cae26acb471d5954cfdc25d1438b32060babe (diff)
parentef53d16cded7f89b3843b7a96970dab897843ea5 (diff)
downloadop-kernel-dev-5ce1a70e2f00f0bce0cab57f798ca354b9496169.zip
op-kernel-dev-5ce1a70e2f00f0bce0cab57f798ca354b9496169.tar.gz
Merge branch 'akpm' (more incoming from Andrew)
Merge second patch-bomb from Andrew Morton: - A little DM fix - the MM queue * emailed patches from Andrew Morton <akpm@linux-foundation.org>: (154 commits) ksm: allocate roots when needed mm: cleanup "swapcache" in do_swap_page mm,ksm: swapoff might need to copy mm,ksm: FOLL_MIGRATION do migration_entry_wait ksm: shrink 32-bit rmap_item back to 32 bytes ksm: treat unstable nid like in stable tree ksm: add some comments tmpfs: fix mempolicy object leaks tmpfs: fix use-after-free of mempolicy object mm/fadvise.c: drain all pagevecs if POSIX_FADV_DONTNEED fails to discard all pages mm: export mmu notifier invalidates mm: accelerate mm_populate() treatment of THP pages mm: use long type for page counts in mm_populate() and get_user_pages() mm: accurately document nr_free_*_pages functions with code comments HWPOISON: change order of error_states[]'s elements HWPOISON: fix misjudgement of page_action() for errors on mlocked pages memcg: stop warning on memcg_propagate_kmem net: change type of virtio_chan->p9_max_pages vmscan: change type of vm_total_pages to unsigned long fs/nfsd: change type of max_delegations, nfsd_drc_max_mem and nfsd_drc_mem_used ...
Diffstat (limited to 'arch/x86/mm/srat.c')
-rw-r--r--arch/x86/mm/srat.c125
1 files changed, 122 insertions, 3 deletions
diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c
index cdd0da9..79836d0 100644
--- a/arch/x86/mm/srat.c
+++ b/arch/x86/mm/srat.c
@@ -141,11 +141,126 @@ static inline int save_add_info(void) {return 1;}
static inline int save_add_info(void) {return 0;}
#endif
+#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
+static void __init
+handle_movablemem(int node, u64 start, u64 end, u32 hotpluggable)
+{
+ int overlap, i;
+ unsigned long start_pfn, end_pfn;
+
+ start_pfn = PFN_DOWN(start);
+ end_pfn = PFN_UP(end);
+
+ /*
+ * For movablemem_map=acpi:
+ *
+ * SRAT: |_____| |_____| |_________| |_________| ......
+ * node id: 0 1 1 2
+ * hotpluggable: n y y n
+ * movablemem_map: |_____| |_________|
+ *
+ * Using movablemem_map, we can prevent memblock from allocating memory
+ * on ZONE_MOVABLE at boot time.
+ *
+ * Before parsing SRAT, memblock has already reserve some memory ranges
+ * for other purposes, such as for kernel image. We cannot prevent
+ * kernel from using these memory, so we need to exclude these memory
+ * even if it is hotpluggable.
+ * Furthermore, to ensure the kernel has enough memory to boot, we make
+ * all the memory on the node which the kernel resides in
+ * un-hotpluggable.
+ */
+ if (hotpluggable && movablemem_map.acpi) {
+ /* Exclude ranges reserved by memblock. */
+ struct memblock_type *rgn = &memblock.reserved;
+
+ for (i = 0; i < rgn->cnt; i++) {
+ if (end <= rgn->regions[i].base ||
+ start >= rgn->regions[i].base +
+ rgn->regions[i].size)
+ continue;
+
+ /*
+ * If the memory range overlaps the memory reserved by
+ * memblock, then the kernel resides in this node.
+ */
+ node_set(node, movablemem_map.numa_nodes_kernel);
+
+ goto out;
+ }
+
+ /*
+ * If the kernel resides in this node, then the whole node
+ * should not be hotpluggable.
+ */
+ if (node_isset(node, movablemem_map.numa_nodes_kernel))
+ goto out;
+
+ insert_movablemem_map(start_pfn, end_pfn);
+
+ /*
+ * numa_nodes_hotplug nodemask represents which nodes are put
+ * into movablemem_map.map[].
+ */
+ node_set(node, movablemem_map.numa_nodes_hotplug);
+ goto out;
+ }
+
+ /*
+ * For movablemem_map=nn[KMG]@ss[KMG]:
+ *
+ * SRAT: |_____| |_____| |_________| |_________| ......
+ * node id: 0 1 1 2
+ * user specified: |__| |___|
+ * movablemem_map: |___| |_________| |______| ......
+ *
+ * Using movablemem_map, we can prevent memblock from allocating memory
+ * on ZONE_MOVABLE at boot time.
+ *
+ * NOTE: In this case, SRAT info will be ingored.
+ */
+ overlap = movablemem_map_overlap(start_pfn, end_pfn);
+ if (overlap >= 0) {
+ /*
+ * If part of this range is in movablemem_map, we need to
+ * add the range after it to extend the range to the end
+ * of the node, because from the min address specified to
+ * the end of the node will be ZONE_MOVABLE.
+ */
+ start_pfn = max(start_pfn,
+ movablemem_map.map[overlap].start_pfn);
+ insert_movablemem_map(start_pfn, end_pfn);
+
+ /*
+ * Set the nodemask, so that if the address range on one node
+ * is not continuse, we can add the subsequent ranges on the
+ * same node into movablemem_map.
+ */
+ node_set(node, movablemem_map.numa_nodes_hotplug);
+ } else {
+ if (node_isset(node, movablemem_map.numa_nodes_hotplug))
+ /*
+ * Insert the range if we already have movable ranges
+ * on the same node.
+ */
+ insert_movablemem_map(start_pfn, end_pfn);
+ }
+out:
+ return;
+}
+#else /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
+static inline void
+handle_movablemem(int node, u64 start, u64 end, u32 hotpluggable)
+{
+}
+#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
+
/* Callback for parsing of the Proximity Domain <-> Memory Area mappings */
int __init
acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
{
u64 start, end;
+ u32 hotpluggable;
int node, pxm;
if (srat_disabled())
@@ -154,7 +269,8 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
goto out_err_bad_srat;
if ((ma->flags & ACPI_SRAT_MEM_ENABLED) == 0)
goto out_err;
- if ((ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE) && !save_add_info())
+ hotpluggable = ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE;
+ if (hotpluggable && !save_add_info())
goto out_err;
start = ma->base_address;
@@ -174,9 +290,12 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
node_set(node, numa_nodes_parsed);
- printk(KERN_INFO "SRAT: Node %u PXM %u [mem %#010Lx-%#010Lx]\n",
+ printk(KERN_INFO "SRAT: Node %u PXM %u [mem %#010Lx-%#010Lx] %s\n",
node, pxm,
- (unsigned long long) start, (unsigned long long) end - 1);
+ (unsigned long long) start, (unsigned long long) end - 1,
+ hotpluggable ? "Hot Pluggable": "");
+
+ handle_movablemem(node, start, end, hotpluggable);
return 0;
out_err_bad_srat:
OpenPOWER on IntegriCloud