mm, memory-hotplug: dynamic configure movable memory and portion memory

Add online_movable and online_kernel for logic memory hotplug.  This is
the dynamic version of "movablecore" & "kernelcore".

We have the same reason to introduce it as to introduce "movablecore" &
"kernelcore".  It has the same motive as "movablecore" & "kernelcore", but
it is dynamic/running-time:

o We can configure memory as kernelcore or movablecore after boot.

  Userspace workload is increased, we need more hugepage, we can't use
  "online_movable" to add memory and allow the system use more
  THP(transparent-huge-page), vice-verse when kernel workload is increase.

  Also help for virtualization to dynamic configure host/guest's memory,
  to save/(reduce waste) memory.

  Memory capacity on Demand

o When a new node is physically online after boot, we need to use
  "online_movable" or "online_kernel" to configure/portion it as we
  expected when we logic-online it.

  This configuration also helps for physically-memory-migrate.

o all benefit as the same as existed "movablecore" & "kernelcore".

o Preparing for movable-node, which is very important for power-saving,
  hardware partitioning and high-available-system(hardware fault
  management).

(Note, we don't introduce movable-node here.)

Action behavior:
When a memoryblock/memorysection is onlined by "online_movable", the kernel
will not have directly reference to the page of the memoryblock,
thus we can remove that memory any time when needed.

When it is online by "online_kernel", the kernel can use it.
When it is online by "online", the zone type doesn't changed.

Current constraints:
Only the memoryblock which is adjacent to the ZONE_MOVABLE
can be online from ZONE_NORMAL to ZONE_MOVABLE.

Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: Wen Congyang <wency@cn.fujitsu.com>
Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: Lai Jiangshan <laijs@cn.fujitsu.com>
Cc: Jiang Liu <jiang.liu@huawei.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: David Rientjes <rientjes@google.com>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Greg KH <greg@kroah.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/Documentation/memory-hotplug.txt b/Documentation/memory-hotplug.txt
index 6e6cbc78f329493def769e5509896772f2fcd496..c6f993d491b51982bbd4e8029dc8ff55a229d2af 100644 (file)
--- a/Documentation/memory-hotplug.txt
+++ b/Documentation/memory-hotplug.txt
@@ -161,7 +161,8 @@ a recent addition and not present on older kernels.
                    in the memory block.
 'state'           : read-write
                     at read:  contains online/offline state of memory.
-                    at write: user can specify "online", "offline" command
+                    at write: user can specify "online_kernel",
+                    "online_movable", "online", "offline" command
                     which will be performed on al sections in the block.
 'phys_device'     : read-only: designed to show the name of physical memory
                     device.  This is not well implemented now.
@@ -255,6 +256,17 @@ For onlining, you have to write "online" to the section's state file as:
 
 % echo online > /sys/devices/system/memory/memoryXXX/state
 
+This onlining will not change the ZONE type of the target memory section,
+If the memory section is in ZONE_NORMAL, you can change it to ZONE_MOVABLE:
+
+% echo online_movable > /sys/devices/system/memory/memoryXXX/state
+(NOTE: current limit: this memory section must be adjacent to ZONE_MOVABLE)
+
+And if the memory section is in ZONE_MOVABLE, you can change it to ZONE_NORMAL:
+
+% echo online_kernel > /sys/devices/system/memory/memoryXXX/state
+(NOTE: current limit: this memory section must be adjacent to ZONE_NORMAL)
+
 After this, section memoryXXX's state will be 'online' and the amount of
 available memory will be increased.
 

diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index 7eb1211ab6881f0117f35f5e46b28f4dde86b2d3..97774a904551b29e0b38a028ecee3b4fe864bc56 100644 (file)
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -254,7 +254,7 @@ static bool pages_correctly_reserved(unsigned long start_pfn,
  * OK to have direct references to sparsemem variables in here.
  */
 static int
-memory_block_action(unsigned long phys_index, unsigned long action)
+memory_block_action(unsigned long phys_index, unsigned long action, int online_type)
 {
        unsigned long start_pfn;
        unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block;
@@ -269,7 +269,7 @@ memory_block_action(unsigned long phys_index, unsigned long action)
                        if (!pages_correctly_reserved(start_pfn, nr_pages))
                                return -EBUSY;
 
-                       ret = online_pages(start_pfn, nr_pages);
+                       ret = online_pages(start_pfn, nr_pages, online_type);
                        break;
                case MEM_OFFLINE:
                        ret = offline_pages(start_pfn, nr_pages);
@@ -284,7 +284,8 @@ memory_block_action(unsigned long phys_index, unsigned long action)
 }
 
 static int __memory_block_change_state(struct memory_block *mem,
-               unsigned long to_state, unsigned long from_state_req)
+               unsigned long to_state, unsigned long from_state_req,
+               int online_type)
 {
        int ret = 0;
 
@@ -296,7 +297,7 @@ static int __memory_block_change_state(struct memory_block *mem,
        if (to_state == MEM_OFFLINE)
                mem->state = MEM_GOING_OFFLINE;
 
-       ret = memory_block_action(mem->start_section_nr, to_state);
+       ret = memory_block_action(mem->start_section_nr, to_state, online_type);
 
        if (ret) {
                mem->state = from_state_req;
@@ -319,12 +320,14 @@ out:
 }
 
 static int memory_block_change_state(struct memory_block *mem,
-               unsigned long to_state, unsigned long from_state_req)
+               unsigned long to_state, unsigned long from_state_req,
+               int online_type)
 {
        int ret;
 
        mutex_lock(&mem->state_mutex);
-       ret = __memory_block_change_state(mem, to_state, from_state_req);
+       ret = __memory_block_change_state(mem, to_state, from_state_req,
+                                         online_type);
        mutex_unlock(&mem->state_mutex);
 
        return ret;
@@ -338,10 +341,14 @@ store_mem_state(struct device *dev,
 
        mem = container_of(dev, struct memory_block, dev);
 
-       if (!strncmp(buf, "online", min((int)count, 6)))
-               ret = memory_block_change_state(mem, MEM_ONLINE, MEM_OFFLINE);
+       if (!strncmp(buf, "online_kernel", min((int)count, 13)))
+               ret = memory_block_change_state(mem, MEM_ONLINE, MEM_OFFLINE, ONLINE_KERNEL);
+       else if (!strncmp(buf, "online_movable", min((int)count, 14)))
+               ret = memory_block_change_state(mem, MEM_ONLINE, MEM_OFFLINE, ONLINE_MOVABLE);
+       else if (!strncmp(buf, "online", min((int)count, 6)))
+               ret = memory_block_change_state(mem, MEM_ONLINE, MEM_OFFLINE, ONLINE_KEEP);
        else if(!strncmp(buf, "offline", min((int)count, 7)))
-               ret = memory_block_change_state(mem, MEM_OFFLINE, MEM_ONLINE);
+               ret = memory_block_change_state(mem, MEM_OFFLINE, MEM_ONLINE, -1);
 
        if (ret)
                return ret;
@@ -676,7 +683,7 @@ int offline_memory_block(struct memory_block *mem)
 
        mutex_lock(&mem->state_mutex);
        if (mem->state != MEM_OFFLINE)
-               ret = __memory_block_change_state(mem, MEM_OFFLINE, MEM_ONLINE);
+               ret = __memory_block_change_state(mem, MEM_OFFLINE, MEM_ONLINE, -1);
        mutex_unlock(&mem->state_mutex);
 
        return ret;

diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 95573ec4ee6ce5cd0c2d343d8aab6021106f9c0c..4a45c4e500253a68c4b7f1dc59f0f31e9a26eeae 100644 (file)
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -26,6 +26,13 @@ enum {
        MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE = NODE_INFO,
 };
 
+/* Types for control the zone type of onlined memory */
+enum {
+       ONLINE_KEEP,
+       ONLINE_KERNEL,
+       ONLINE_MOVABLE,
+};
+
 /*
  * pgdat resizing functions
  */
@@ -46,6 +53,10 @@ void pgdat_resize_init(struct pglist_data *pgdat)
 }
 /*
  * Zone resizing functions
+ *
+ * Note: any attempt to resize a zone should has pgdat_resize_lock()
+ * zone_span_writelock() both held. This ensure the size of a zone
+ * can't be changed while pgdat_resize_lock() held.
  */
 static inline unsigned zone_span_seqbegin(struct zone *zone)
 {
@@ -71,7 +82,7 @@ extern int zone_grow_free_lists(struct zone *zone, unsigned long new_nr_pages);
 extern int zone_grow_waitqueues(struct zone *zone, unsigned long nr_pages);
 extern int add_one_highpage(struct page *page, int pfn, int bad_ppro);
 /* VM interface that may be used by firmware interface */
-extern int online_pages(unsigned long, unsigned long);
+extern int online_pages(unsigned long, unsigned long, int);
 extern void __offline_isolated_pages(unsigned long, unsigned long);
 
 typedef void (*online_page_callback_t)(struct page *page);

diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index d6c0d4c4b119d5fbcd0075282290fa0e924204c0..74b9355083080cba3f74b89e6dbbf3d42c60f31c 100644 (file)
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -214,6 +214,89 @@ static void grow_zone_span(struct zone *zone, unsigned long start_pfn,
        zone_span_writeunlock(zone);
 }
 
+static void resize_zone(struct zone *zone, unsigned long start_pfn,
+               unsigned long end_pfn)
+{
+
+       zone_span_writelock(zone);
+
+       zone->zone_start_pfn = start_pfn;
+       zone->spanned_pages = end_pfn - start_pfn;
+
+       zone_span_writeunlock(zone);
+}
+
+static void fix_zone_id(struct zone *zone, unsigned long start_pfn,
+               unsigned long end_pfn)
+{
+       enum zone_type zid = zone_idx(zone);
+       int nid = zone->zone_pgdat->node_id;
+       unsigned long pfn;
+
+       for (pfn = start_pfn; pfn < end_pfn; pfn++)
+               set_page_links(pfn_to_page(pfn), zid, nid, pfn);
+}
+
+static int move_pfn_range_left(struct zone *z1, struct zone *z2,
+               unsigned long start_pfn, unsigned long end_pfn)
+{
+       unsigned long flags;
+
+       pgdat_resize_lock(z1->zone_pgdat, &flags);
+
+       /* can't move pfns which are higher than @z2 */
+       if (end_pfn > z2->zone_start_pfn + z2->spanned_pages)
+               goto out_fail;
+       /* the move out part mast at the left most of @z2 */
+       if (start_pfn > z2->zone_start_pfn)
+               goto out_fail;
+       /* must included/overlap */
+       if (end_pfn <= z2->zone_start_pfn)
+               goto out_fail;
+
+       resize_zone(z1, z1->zone_start_pfn, end_pfn);
+       resize_zone(z2, end_pfn, z2->zone_start_pfn + z2->spanned_pages);
+
+       pgdat_resize_unlock(z1->zone_pgdat, &flags);
+
+       fix_zone_id(z1, start_pfn, end_pfn);
+
+       return 0;
+out_fail:
+       pgdat_resize_unlock(z1->zone_pgdat, &flags);
+       return -1;
+}
+
+static int move_pfn_range_right(struct zone *z1, struct zone *z2,
+               unsigned long start_pfn, unsigned long end_pfn)
+{
+       unsigned long flags;
+
+       pgdat_resize_lock(z1->zone_pgdat, &flags);
+
+       /* can't move pfns which are lower than @z1 */
+       if (z1->zone_start_pfn > start_pfn)
+               goto out_fail;
+       /* the move out part mast at the right most of @z1 */
+       if (z1->zone_start_pfn + z1->spanned_pages >  end_pfn)
+               goto out_fail;
+       /* must included/overlap */
+       if (start_pfn >= z1->zone_start_pfn + z1->spanned_pages)
+               goto out_fail;
+
+       resize_zone(z1, z1->zone_start_pfn, start_pfn);
+       resize_zone(z2, start_pfn, z2->zone_start_pfn + z2->spanned_pages);
+
+       pgdat_resize_unlock(z1->zone_pgdat, &flags);
+
+       fix_zone_id(z2, start_pfn, end_pfn);
+
+       return 0;
+out_fail:
+       pgdat_resize_unlock(z1->zone_pgdat, &flags);
+       return -1;
+}
+
 static void grow_pgdat_span(struct pglist_data *pgdat, unsigned long start_pfn,
                            unsigned long end_pfn)
 {
@@ -508,7 +591,7 @@ static void node_states_set_node(int node, struct memory_notify *arg)
 }
 
 
-int __ref online_pages(unsigned long pfn, unsigned long nr_pages)
+int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_type)
 {
        unsigned long onlined_pages = 0;
        struct zone *zone;
@@ -525,6 +608,22 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages)
         */
        zone = page_zone(pfn_to_page(pfn));
 
+       if (online_type == ONLINE_KERNEL && zone_idx(zone) == ZONE_MOVABLE) {
+               if (move_pfn_range_left(zone - 1, zone, pfn, pfn + nr_pages)) {
+                       unlock_memory_hotplug();
+                       return -1;
+               }
+       }
+       if (online_type == ONLINE_MOVABLE && zone_idx(zone) == ZONE_MOVABLE - 1) {
+               if (move_pfn_range_right(zone, zone + 1, pfn, pfn + nr_pages)) {
+                       unlock_memory_hotplug();
+                       return -1;
+               }
+       }
+
+       /* Previous code may changed the zone of the pfn range */
+       zone = page_zone(pfn_to_page(pfn));
+
        arg.start_pfn = pfn;
        arg.nr_pages = nr_pages;
        node_states_check_changes_online(nr_pages, zone, &arg);