We don't allow to offline memory block devices that belong to multiple
numa nodes. Therefore, such devices can never get removed. It is
sufficient to process a single node when removing the memory block. No
need to iterate over each and every PFN.
We already have the nid stored for each memory block. Make sure that
the nid always has a sane value.
Please note that checking for node_online(nid) is not required. If we
would have a memory block belonging to a node that is no longer offline,
then we would have a BUG in the node offlining code.
Cc: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
Cc: "Rafael J. Wysocki" <rafael@xxxxxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: David Hildenbrand <david@xxxxxxxxxx>
Cc: Stephen Rothwell <sfr@xxxxxxxxxxxxxxxx>
Cc: Pavel Tatashin <pasha.tatashin@xxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxx>
Cc: Oscar Salvador <osalvador@xxxxxxx>
Signed-off-by: David Hildenbrand <david@xxxxxxxxxx>
---
v1 -> v2:
- Remove the "mixed nid" part, add a comment instead. Drop the warning.
---
drivers/base/memory.c | 1 +
drivers/base/node.c | 39 +++++++++++++++------------------------
2 files changed, 16 insertions(+), 24 deletions(-)
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index 20c39d1bcef8..154d5d4a0779 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -674,6 +674,7 @@ static int init_memory_block(struct memory_block **memory,
mem->state = state;
start_pfn = section_nr_to_pfn(mem->start_section_nr);
mem->phys_device = arch_get_memory_phys_device(start_pfn);
+ mem->nid = NUMA_NO_NODE;
ret = register_memory(mem);
diff --git a/drivers/base/node.c b/drivers/base/node.c
index 75b7e6f6535b..840c95baa1d8 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -759,8 +759,6 @@ static int register_mem_sect_under_node(struct memory_block *mem_blk,
int ret, nid = *(int *)arg;
unsigned long pfn, sect_start_pfn, sect_end_pfn;
- mem_blk->nid = nid;
-
sect_start_pfn = section_nr_to_pfn(mem_blk->start_section_nr);
sect_end_pfn = section_nr_to_pfn(mem_blk->end_section_nr);
sect_end_pfn += PAGES_PER_SECTION - 1;
@@ -789,6 +787,13 @@ static int register_mem_sect_under_node(struct memory_block *mem_blk,
if (page_nid != nid)
continue;
}
+
+ /*
+ * If this memory block spans multiple nodes, we only indicate
+ * the last processed node.
+ */
+ mem_blk->nid = nid;
+
ret = sysfs_create_link_nowarn(&node_devices[nid]->dev.kobj,
&mem_blk->dev.kobj,
kobject_name(&mem_blk->dev.kobj));
@@ -804,32 +809,18 @@ static int register_mem_sect_under_node(struct memory_block *mem_blk,
}
/*
- * Unregister memory block device under all nodes that it spans.
- * Has to be called with mem_sysfs_mutex held (due to unlinked_nodes).
+ * Unregister a memory block device under the node it spans. Memory blocks
+ * with multiple nodes cannot be offlined and therefore also never be removed.
*/
void unregister_memory_block_under_nodes(struct memory_block *mem_blk)
{
- unsigned long pfn, sect_start_pfn, sect_end_pfn;
- static nodemask_t unlinked_nodes;
-
- nodes_clear(unlinked_nodes);
- sect_start_pfn = section_nr_to_pfn(mem_blk->start_section_nr);
- sect_end_pfn = section_nr_to_pfn(mem_blk->end_section_nr);
- for (pfn = sect_start_pfn; pfn <= sect_end_pfn; pfn++) {
- int nid;
+ if (mem_blk->nid == NUMA_NO_NODE)
+ return;
- nid = get_nid_for_pfn(pfn);
- if (nid < 0)
- continue;
- if (!node_online(nid))
- continue;
- if (node_test_and_set(nid, unlinked_nodes))
- continue;
- sysfs_remove_link(&node_devices[nid]->dev.kobj,
- kobject_name(&mem_blk->dev.kobj));
- sysfs_remove_link(&mem_blk->dev.kobj,
- kobject_name(&node_devices[nid]->dev.kobj));
- }
+ sysfs_remove_link(&node_devices[mem_blk->nid]->dev.kobj,
+ kobject_name(&mem_blk->dev.kobj));
+ sysfs_remove_link(&mem_blk->dev.kobj,
+ kobject_name(&node_devices[mem_blk->nid]->dev.kobj));
}
int link_mem_sections(int nid, unsigned long start_pfn, unsigned long end_pfn)
--
2.21.0
