summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--drivers/base/memory.c36
-rw-r--r--include/linux/memory.h1
-rw-r--r--mm/memory_hotplug.c43
3 files changed, 64 insertions, 16 deletions
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index 55907c27075b..84c4e1f72cbd 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -872,3 +872,39 @@ int walk_memory_blocks(unsigned long start, unsigned long size,
}
return ret;
}
+
+struct for_each_memory_block_cb_data {
+ walk_memory_blocks_func_t func;
+ void *arg;
+};
+
+static int for_each_memory_block_cb(struct device *dev, void *data)
+{
+ struct memory_block *mem = to_memory_block(dev);
+ struct for_each_memory_block_cb_data *cb_data = data;
+
+ return cb_data->func(mem, cb_data->arg);
+}
+
+/**
+ * for_each_memory_block - walk through all present memory blocks
+ *
+ * @arg: argument passed to func
+ * @func: callback for each memory block walked
+ *
+ * This function walks through all present memory blocks, calling func on
+ * each memory block.
+ *
+ * In case func() returns an error, walking is aborted and the error is
+ * returned.
+ */
+int for_each_memory_block(void *arg, walk_memory_blocks_func_t func)
+{
+ struct for_each_memory_block_cb_data cb_data = {
+ .func = func,
+ .arg = arg,
+ };
+
+ return bus_for_each_dev(&memory_subsys, NULL, &cb_data,
+ for_each_memory_block_cb);
+}
diff --git a/include/linux/memory.h b/include/linux/memory.h
index 0ebb105eb261..4c75dae8dd29 100644
--- a/include/linux/memory.h
+++ b/include/linux/memory.h
@@ -119,6 +119,7 @@ extern struct memory_block *find_memory_block(struct mem_section *);
typedef int (*walk_memory_blocks_func_t)(struct memory_block *, void *);
extern int walk_memory_blocks(unsigned long start, unsigned long size,
void *arg, walk_memory_blocks_func_t func);
+extern int for_each_memory_block(void *arg, walk_memory_blocks_func_t func);
#define CONFIG_MEM_BLOCK_SIZE (PAGES_PER_SECTION<<PAGE_SHIFT)
#endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 07e5c67f48a8..3b62a9ff8ea0 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1646,6 +1646,18 @@ static int check_cpu_on_node(pg_data_t *pgdat)
return 0;
}
+static int check_no_memblock_for_node_cb(struct memory_block *mem, void *arg)
+{
+ int nid = *(int *)arg;
+
+ /*
+ * If a memory block belongs to multiple nodes, the stored nid is not
+ * reliable. However, such blocks are always online (e.g., cannot get
+ * offlined) and, therefore, are still spanned by the node.
+ */
+ return mem->nid == nid ? -EEXIST : 0;
+}
+
/**
* try_offline_node
* @nid: the node ID
@@ -1658,25 +1670,24 @@ static int check_cpu_on_node(pg_data_t *pgdat)
void try_offline_node(int nid)
{
pg_data_t *pgdat = NODE_DATA(nid);
- unsigned long start_pfn = pgdat->node_start_pfn;
- unsigned long end_pfn = start_pfn + pgdat->node_spanned_pages;
- unsigned long pfn;
-
- for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
- unsigned long section_nr = pfn_to_section_nr(pfn);
-
- if (!present_section_nr(section_nr))
- continue;
+ int rc;
- if (pfn_to_nid(pfn) != nid)
- continue;
+ /*
+ * If the node still spans pages (especially ZONE_DEVICE), don't
+ * offline it. A node spans memory after move_pfn_range_to_zone(),
+ * e.g., after the memory block was onlined.
+ */
+ if (pgdat->node_spanned_pages)
+ return;
- /*
- * some memory sections of this node are not removed, and we
- * can't offline node now.
- */
+ /*
+ * Especially offline memory blocks might not be spanned by the
+ * node. They will get spanned by the node once they get onlined.
+ * However, they link to the node in sysfs and can get onlined later.
+ */
+ rc = for_each_memory_block(&nid, check_no_memblock_for_node_cb);
+ if (rc)
return;
- }
if (check_cpu_on_node(pgdat))
return;