memory-hotplug: remove sysfs file of node

Introduce a new function try_offline_node() to remove sysfs file of node
when all memory sections of this node are removed.  If some memory
sections of this node are not removed, this function does nothing.

Signed-off-by: Wen Congyang <wency@cn.fujitsu.com>
Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Jiang Liu <jiang.liu@huawei.com>
Cc: Jianguo Wu <wujianguo@huawei.com>
Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Lai Jiangshan <laijs@cn.fujitsu.com>
Cc: Wu Jianguo <wujianguo@huawei.com>
Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 63 insertions, 5 deletions

diff --git a/drivers/acpi/acpi_memhotplug.c b/drivers/acpi/acpi_memhotplug.c
index 034d3e72aa92..da1f82b445e0 100644
--- a/drivers/acpi/acpi_memhotplug.c
+++ b/drivers/acpi/acpi_memhotplug.c
@@ -280,9 +280,11 @@ static int acpi_memory_enable_device(struct acpi_memory_device *mem_device)
 
 static int acpi_memory_remove_memory(struct acpi_memory_device *mem_device)
 {
-        int result = 0;
+        int result = 0, nid;
         struct acpi_memory_info *info, *n;
 
+        nid = acpi_get_node(mem_device->device->handle);
+
         list_for_each_entry_safe(info, n, &mem_device->res_list, list) {
                 if (info->failed)
                         /* The kernel does not use this memory block */
@@ -295,7 +297,9 @@ static int acpi_memory_remove_memory(struct acpi_memory_device *mem_device)
                          */
                         return -EBUSY;
 
-                result = remove_memory(info->start_addr, info->length);
+                if (nid < 0)
+                        nid = memory_add_physaddr_to_nid(info->start_addr);
+                result = remove_memory(nid, info->start_addr, info->length);
                 if (result)
                         return result;
 
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 4d523fe75ba1..69903ccf549e 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -248,7 +248,7 @@ extern int arch_add_memory(int nid, u64 start, u64 size);
 extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages);
 extern int offline_memory_block(struct memory_block *mem);
 extern bool is_memblock_offlined(struct memory_block *mem);
-extern int remove_memory(u64 start, u64 size);
+extern int remove_memory(int nid, u64 start, u64 size);
 extern int sparse_add_one_section(struct zone *zone, unsigned long start_pfn,
                                                                 int nr_pages);
 extern void sparse_remove_one_section(struct zone *zone, struct mem_section *ms);
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 3f792375f326..aea6374f435a 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -29,6 +29,7 @@
 #include <linux/suspend.h>
 #include <linux/mm_inline.h>
 #include <linux/firmware-map.h>
+#include <linux/stop_machine.h>
 
 #include <asm/tlbflush.h>
 
@@ -1679,7 +1680,58 @@ static int is_memblock_offlined_cb(struct memory_block *mem, void *arg)
         return ret;
 }
 
-int __ref remove_memory(u64 start, u64 size)
+static int check_cpu_on_node(void *data)
+{
+        struct pglist_data *pgdat = data;
+        int cpu;
+
+        for_each_present_cpu(cpu) {
+                if (cpu_to_node(cpu) == pgdat->node_id)
+                        /*
+                         * the cpu on this node isn't removed, and we can't
+                         * offline this node.
+                         */
+                        return -EBUSY;
+        }
+
+        return 0;
+}
+
+/* offline the node if all memory sections of this node are removed */
+static void try_offline_node(int nid)
+{
+        unsigned long start_pfn = NODE_DATA(nid)->node_start_pfn;
+        unsigned long end_pfn = start_pfn + NODE_DATA(nid)->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;
+
+                if (pfn_to_nid(pfn) != nid)
+                        continue;
+
+                /*
+                 * some memory sections of this node are not removed, and we
+                 * can't offline node now.
+                 */
+                return;
+        }
+
+        if (stop_machine(check_cpu_on_node, NODE_DATA(nid), NULL))
+                return;
+
+        /*
+         * all memory/cpu of this node are removed, we can offline this
+         * node now.
+         */
+        node_set_offline(nid);
+        unregister_one_node(nid);
+}
+
+int __ref remove_memory(int nid, u64 start, u64 size)
 {
         unsigned long start_pfn, end_pfn;
         int ret = 0;
@@ -1734,6 +1786,8 @@ repeat:
 
         arch_remove_memory(start, size);
 
+        try_offline_node(nid);
+
         unlock_memory_hotplug();
 
         return 0;
@@ -1743,7 +1797,7 @@ int offline_pages(unsigned long start_pfn, unsigned long nr_pages)
 {
         return -EINVAL;
 }
-int remove_memory(u64 start, u64 size)
+int remove_memory(int nid, u64 start, u64 size)
 {
         return -EINVAL;
 }