blob: ea03abfc97e95dc660b8028559d940357bc1c8f7 [file] [log] [blame]
Yasunori Goto6867c932007-08-10 13:00:59 -07001==============
2Memory Hotplug
3==============
4
Yasunori Goto10020ca2007-10-21 16:41:36 -07005Created: Jul 28 2007
6Add description of notifier of memory hotplug Oct 11 2007
Yasunori Goto6867c932007-08-10 13:00:59 -07007
8This document is about memory hotplug including how-to-use and current status.
9Because Memory Hotplug is still under development, contents of this text will
10be changed often.
11
121. Introduction
13 1.1 purpose of memory hotplug
14 1.2. Phases of memory hotplug
15 1.3. Unit of Memory online/offline operation
162. Kernel Configuration
173. sysfs files for memory hotplug
184. Physical memory hot-add phase
19 4.1 Hardware(Firmware) Support
20 4.2 Notify memory hot-add event by hand
215. Logical Memory hot-add phase
22 5.1. State of memory
23 5.2. How to online memory
246. Logical memory remove
25 6.1 Memory offline and ZONE_MOVABLE
26 6.2. How to offline memory
277. Physical memory remove
Yasunori Goto10020ca2007-10-21 16:41:36 -0700288. Memory hotplug event notifier
299. Future Work List
Yasunori Goto6867c932007-08-10 13:00:59 -070030
31Note(1): x86_64's has special implementation for memory hotplug.
32 This text does not describe it.
33Note(2): This text assumes that sysfs is mounted at /sys.
34
35
36---------------
371. Introduction
38---------------
39
401.1 purpose of memory hotplug
41------------
42Memory Hotplug allows users to increase/decrease the amount of memory.
43Generally, there are two purposes.
44
45(A) For changing the amount of memory.
46 This is to allow a feature like capacity on demand.
47(B) For installing/removing DIMMs or NUMA-nodes physically.
48 This is to exchange DIMMs/NUMA-nodes, reduce power consumption, etc.
49
50(A) is required by highly virtualized environments and (B) is required by
51hardware which supports memory power management.
52
53Linux memory hotplug is designed for both purpose.
54
55
561.2. Phases of memory hotplug
57---------------
58There are 2 phases in Memory Hotplug.
59 1) Physical Memory Hotplug phase
60 2) Logical Memory Hotplug phase.
61
62The First phase is to communicate hardware/firmware and make/erase
63environment for hotplugged memory. Basically, this phase is necessary
64for the purpose (B), but this is good phase for communication between
65highly virtualized environments too.
66
67When memory is hotplugged, the kernel recognizes new memory, makes new memory
68management tables, and makes sysfs files for new memory's operation.
69
70If firmware supports notification of connection of new memory to OS,
71this phase is triggered automatically. ACPI can notify this event. If not,
72"probe" operation by system administration is used instead.
73(see Section 4.).
74
75Logical Memory Hotplug phase is to change memory state into
Matt LaPlante19f59462009-04-27 15:06:31 +020076available/unavailable for users. Amount of memory from user's view is
Yasunori Goto6867c932007-08-10 13:00:59 -070077changed by this phase. The kernel makes all memory in it as free pages
78when a memory range is available.
79
80In this document, this phase is described as online/offline.
81
Matt LaPlante19f59462009-04-27 15:06:31 +020082Logical Memory Hotplug phase is triggered by write of sysfs file by system
Yasunori Goto6867c932007-08-10 13:00:59 -070083administrator. For the hot-add case, it must be executed after Physical Hotplug
84phase by hand.
85(However, if you writes udev's hotplug scripts for memory hotplug, these
86 phases can be execute in seamless way.)
87
88
891.3. Unit of Memory online/offline operation
90------------
Li Zhong56a3c652014-06-04 16:07:03 -070091Memory hotplug uses SPARSEMEM memory model which allows memory to be divided
92into chunks of the same size. These chunks are called "sections". The size of
93a memory section is architecture dependent. For example, power uses 16MiB, ia64
94uses 1GiB.
Yasunori Goto6867c932007-08-10 13:00:59 -070095
Li Zhong56a3c652014-06-04 16:07:03 -070096Memory sections are combined into chunks referred to as "memory blocks". The
97size of a memory block is architecture dependent and represents the logical
98unit upon which memory online/offline operations are to be performed. The
99default size of a memory block is the same as memory section size unless an
100architecture specifies otherwise. (see Section 3.)
101
102To determine the size (in bytes) of a memory block please read this file:
Yasunori Goto6867c932007-08-10 13:00:59 -0700103
104/sys/devices/system/memory/block_size_bytes
105
Yasunori Goto6867c932007-08-10 13:00:59 -0700106
107-----------------------
1082. Kernel Configuration
109-----------------------
110To use memory hotplug feature, kernel must be compiled with following
111config options.
112
113- For all memory hotplug
114 Memory model -> Sparse Memory (CONFIG_SPARSEMEM)
115 Allow for memory hot-add (CONFIG_MEMORY_HOTPLUG)
116
117- To enable memory removal, the followings are also necessary
118 Allow for memory hot remove (CONFIG_MEMORY_HOTREMOVE)
119 Page Migration (CONFIG_MIGRATION)
120
121- For ACPI memory hotplug, the followings are also necessary
122 Memory hotplug (under ACPI Support menu) (CONFIG_ACPI_HOTPLUG_MEMORY)
123 This option can be kernel module.
124
125- As a related configuration, if your box has a feature of NUMA-node hotplug
126 via ACPI, then this option is necessary too.
127 ACPI0004,PNP0A05 and PNP0A06 Container Driver (under ACPI Support menu)
128 (CONFIG_ACPI_CONTAINER).
129 This option can be kernel module too.
130
Li Zhong56a3c652014-06-04 16:07:03 -0700131
Yasunori Goto6867c932007-08-10 13:00:59 -0700132--------------------------------
Li Zhong56a3c652014-06-04 16:07:03 -07001333 sysfs files for memory hotplug
Yasunori Goto6867c932007-08-10 13:00:59 -0700134--------------------------------
Li Zhong56a3c652014-06-04 16:07:03 -0700135All memory blocks have their device information in sysfs. Each memory block
136is described under /sys/devices/system/memory as
Yasunori Goto6867c932007-08-10 13:00:59 -0700137
138/sys/devices/system/memory/memoryXXX
Li Zhong56a3c652014-06-04 16:07:03 -0700139(XXX is the memory block id.)
Yasunori Goto6867c932007-08-10 13:00:59 -0700140
Li Zhong56a3c652014-06-04 16:07:03 -0700141For the memory block covered by the sysfs directory. It is expected that all
Nathan Fontenot0c2c99b2011-01-20 10:43:34 -0600142memory sections in this range are present and no memory holes exist in the
143range. Currently there is no way to determine if there is a memory hole, but
144the existence of one should not affect the hotplug capabilities of the memory
145block.
Yasunori Goto6867c932007-08-10 13:00:59 -0700146
Li Zhong56a3c652014-06-04 16:07:03 -0700147For example, assume 1GiB memory block size. A device for a memory starting at
Yasunori Goto6867c932007-08-10 13:00:59 -07001480x100000000 is /sys/device/system/memory/memory4
149(0x100000000 / 1Gib = 4)
150This device covers address range [0x100000000 ... 0x140000000)
151
Li Zhong56a3c652014-06-04 16:07:03 -0700152Under each memory block, you can see 4 files:
Yasunori Goto6867c932007-08-10 13:00:59 -0700153
Li Zhong56a3c652014-06-04 16:07:03 -0700154/sys/devices/system/memory/memoryXXX/phys_index
Yasunori Goto6867c932007-08-10 13:00:59 -0700155/sys/devices/system/memory/memoryXXX/phys_device
156/sys/devices/system/memory/memoryXXX/state
Gary Hadec04fc582009-01-06 14:39:14 -0800157/sys/devices/system/memory/memoryXXX/removable
Zhang Zhened2f2402014-10-09 15:26:31 -0700158/sys/devices/system/memory/memoryXXX/valid_zones
Yasunori Goto6867c932007-08-10 13:00:59 -0700159
Li Zhong56a3c652014-06-04 16:07:03 -0700160'phys_index' : read-only and contains memory block id, same as XXX.
Nathan Fontenot0c2c99b2011-01-20 10:43:34 -0600161'state' : read-write
162 at read: contains online/offline state of memory.
Lai Jiangshan511c2ab2012-12-11 16:03:16 -0800163 at write: user can specify "online_kernel",
164 "online_movable", "online", "offline" command
Xishi Qiu59e68a12013-08-22 17:42:44 +0800165 which will be performed on all sections in the block.
Nathan Fontenot0c2c99b2011-01-20 10:43:34 -0600166'phys_device' : read-only: designed to show the name of physical memory
167 device. This is not well implemented now.
168'removable' : read-only: contains an integer value indicating
169 whether the memory block is removable or not
170 removable. A value of 1 indicates that the memory
171 block is removable and a value of 0 indicates that
172 it is not removable. A memory block is removable only if
173 every section in the block is removable.
Zhang Zhened2f2402014-10-09 15:26:31 -0700174'valid_zones' : read-only: designed to show which zones this memory block
175 can be onlined to.
176 The first column shows it's default zone.
177 "memory6/valid_zones: Normal Movable" shows this memoryblock
178 can be onlined to ZONE_NORMAL by default and to ZONE_MOVABLE
179 by online_movable.
180 "memory7/valid_zones: Movable Normal" shows this memoryblock
181 can be onlined to ZONE_MOVABLE by default and to ZONE_NORMAL
182 by online_kernel.
Yasunori Goto6867c932007-08-10 13:00:59 -0700183
184NOTE:
185 These directories/files appear after physical memory hotplug phase.
186
Alex Chiangdee5d0d2009-12-14 17:59:05 -0800187If CONFIG_NUMA is enabled the memoryXXX/ directories can also be accessed
188via symbolic links located in the /sys/devices/system/node/node* directories.
189
190For example:
Gary Hadec04fc582009-01-06 14:39:14 -0800191/sys/devices/system/node/node0/memory9 -> ../../memory/memory9
Yasunori Goto6867c932007-08-10 13:00:59 -0700192
Alex Chiangdee5d0d2009-12-14 17:59:05 -0800193A backlink will also be created:
194/sys/devices/system/memory/memory9/node0 -> ../../node/node0
195
Li Zhong56a3c652014-06-04 16:07:03 -0700196
Yasunori Goto6867c932007-08-10 13:00:59 -0700197--------------------------------
1984. Physical memory hot-add phase
199--------------------------------
200
2014.1 Hardware(Firmware) Support
202------------
203On x86_64/ia64 platform, memory hotplug by ACPI is supported.
204
205In general, the firmware (ACPI) which supports memory hotplug defines
206memory class object of _HID "PNP0C80". When a notify is asserted to PNP0C80,
207Linux's ACPI handler does hot-add memory to the system and calls a hotplug udev
208script. This will be done automatically.
209
210But scripts for memory hotplug are not contained in generic udev package(now).
211You may have to write it by yourself or online/offline memory by hand.
212Please see "How to online memory", "How to offline memory" in this text.
213
214If firmware supports NUMA-node hotplug, and defines an object _HID "ACPI0004",
215"PNP0A05", or "PNP0A06", notification is asserted to it, and ACPI handler
216calls hotplug code for all of objects which are defined in it.
217If memory device is found, memory hotplug code will be called.
218
219
2204.2 Notify memory hot-add event by hand
221------------
David Rientjes7cdb0d22014-06-23 13:22:03 -0700222On some architectures, the firmware may not notify the kernel of a memory
223hotplug event. Therefore, the memory "probe" interface is supported to
224explicitly notify the kernel. This interface depends on
225CONFIG_ARCH_MEMORY_PROBE and can be configured on powerpc, sh, and x86
226if hotplug is supported, although for x86 this should be handled by ACPI
227notification.
Yasunori Goto6867c932007-08-10 13:00:59 -0700228
229Probe interface is located at
230/sys/devices/system/memory/probe
231
232You can tell the physical address of new memory to the kernel by
233
234% echo start_address_of_new_memory > /sys/devices/system/memory/probe
235
Li Zhong56a3c652014-06-04 16:07:03 -0700236Then, [start_address_of_new_memory, start_address_of_new_memory +
237memory_block_size] memory range is hot-added. In this case, hotplug script is
238not called (in current implementation). You'll have to online memory by
239yourself. Please see "How to online memory" in this text.
Yasunori Goto6867c932007-08-10 13:00:59 -0700240
241
242------------------------------
2435. Logical Memory hot-add phase
244------------------------------
245
2465.1. State of memory
247------------
Li Zhong56a3c652014-06-04 16:07:03 -0700248To see (online/offline) state of a memory block, read 'state' file.
Yasunori Goto6867c932007-08-10 13:00:59 -0700249
250% cat /sys/device/system/memory/memoryXXX/state
251
252
Li Zhong56a3c652014-06-04 16:07:03 -0700253If the memory block is online, you'll read "online".
254If the memory block is offline, you'll read "offline".
Yasunori Goto6867c932007-08-10 13:00:59 -0700255
256
2575.2. How to online memory
258------------
259Even if the memory is hot-added, it is not at ready-to-use state.
Li Zhong56a3c652014-06-04 16:07:03 -0700260For using newly added memory, you have to "online" the memory block.
Yasunori Goto6867c932007-08-10 13:00:59 -0700261
Li Zhong56a3c652014-06-04 16:07:03 -0700262For onlining, you have to write "online" to the memory block's state file as:
Yasunori Goto6867c932007-08-10 13:00:59 -0700263
264% echo online > /sys/devices/system/memory/memoryXXX/state
265
Li Zhong56a3c652014-06-04 16:07:03 -0700266This onlining will not change the ZONE type of the target memory block,
267If the memory block is in ZONE_NORMAL, you can change it to ZONE_MOVABLE:
Lai Jiangshan511c2ab2012-12-11 16:03:16 -0800268
269% echo online_movable > /sys/devices/system/memory/memoryXXX/state
Li Zhong56a3c652014-06-04 16:07:03 -0700270(NOTE: current limit: this memory block must be adjacent to ZONE_MOVABLE)
Lai Jiangshan511c2ab2012-12-11 16:03:16 -0800271
Li Zhong56a3c652014-06-04 16:07:03 -0700272And if the memory block is in ZONE_MOVABLE, you can change it to ZONE_NORMAL:
Lai Jiangshan511c2ab2012-12-11 16:03:16 -0800273
274% echo online_kernel > /sys/devices/system/memory/memoryXXX/state
Li Zhong56a3c652014-06-04 16:07:03 -0700275(NOTE: current limit: this memory block must be adjacent to ZONE_NORMAL)
Lai Jiangshan511c2ab2012-12-11 16:03:16 -0800276
Li Zhong56a3c652014-06-04 16:07:03 -0700277After this, memory block XXX's state will be 'online' and the amount of
Yasunori Goto6867c932007-08-10 13:00:59 -0700278available memory will be increased.
279
280Currently, newly added memory is added as ZONE_NORMAL (for powerpc, ZONE_DMA).
281This may be changed in future.
282
283
284
285------------------------
2866. Logical memory remove
287------------------------
288
2896.1 Memory offline and ZONE_MOVABLE
290------------
291Memory offlining is more complicated than memory online. Because memory offline
Li Zhong56a3c652014-06-04 16:07:03 -0700292has to make the whole memory block be unused, memory offline can fail if
293the memory block includes memory which cannot be freed.
Yasunori Goto6867c932007-08-10 13:00:59 -0700294
295In general, memory offline can use 2 techniques.
296
Li Zhong56a3c652014-06-04 16:07:03 -0700297(1) reclaim and free all memory in the memory block.
298(2) migrate all pages in the memory block.
Yasunori Goto6867c932007-08-10 13:00:59 -0700299
300In the current implementation, Linux's memory offline uses method (2), freeing
Li Zhong56a3c652014-06-04 16:07:03 -0700301all pages in the memory block by page migration. But not all pages are
Yasunori Goto6867c932007-08-10 13:00:59 -0700302migratable. Under current Linux, migratable pages are anonymous pages and
Li Zhong56a3c652014-06-04 16:07:03 -0700303page caches. For offlining a memory block by migration, the kernel has to
304guarantee that the memory block contains only migratable pages.
Yasunori Goto6867c932007-08-10 13:00:59 -0700305
Li Zhong56a3c652014-06-04 16:07:03 -0700306Now, a boot option for making a memory block which consists of migratable pages
307is supported. By specifying "kernelcore=" or "movablecore=" boot option, you can
Yasunori Goto6867c932007-08-10 13:00:59 -0700308create ZONE_MOVABLE...a zone which is just used for movable pages.
309(See also Documentation/kernel-parameters.txt)
310
311Assume the system has "TOTAL" amount of memory at boot time, this boot option
312creates ZONE_MOVABLE as following.
313
3141) When kernelcore=YYYY boot option is used,
315 Size of memory not for movable pages (not for offline) is YYYY.
316 Size of memory for movable pages (for offline) is TOTAL-YYYY.
317
3182) When movablecore=ZZZZ boot option is used,
319 Size of memory not for movable pages (not for offline) is TOTAL - ZZZZ.
320 Size of memory for movable pages (for offline) is ZZZZ.
321
322
Li Zhong56a3c652014-06-04 16:07:03 -0700323Note: Unfortunately, there is no information to show which memory block belongs
Yasunori Goto6867c932007-08-10 13:00:59 -0700324to ZONE_MOVABLE. This is TBD.
325
326
3276.2. How to offline memory
328------------
Li Zhong56a3c652014-06-04 16:07:03 -0700329You can offline a memory block by using the same sysfs interface that was used
330in memory onlining.
Yasunori Goto6867c932007-08-10 13:00:59 -0700331
332% echo offline > /sys/devices/system/memory/memoryXXX/state
333
Li Zhong56a3c652014-06-04 16:07:03 -0700334If offline succeeds, the state of the memory block is changed to be "offline".
Yasunori Goto6867c932007-08-10 13:00:59 -0700335If it fails, some error core (like -EBUSY) will be returned by the kernel.
Li Zhong56a3c652014-06-04 16:07:03 -0700336Even if a memory block does not belong to ZONE_MOVABLE, you can try to offline
337it. If it doesn't contain 'unmovable' memory, you'll get success.
Yasunori Goto6867c932007-08-10 13:00:59 -0700338
Li Zhong56a3c652014-06-04 16:07:03 -0700339A memory block under ZONE_MOVABLE is considered to be able to be offlined
340easily. But under some busy state, it may return -EBUSY. Even if a memory
341block cannot be offlined due to -EBUSY, you can retry offlining it and may be
342able to offline it (or not). (For example, a page is referred to by some kernel
343internal call and released soon.)
Yasunori Goto6867c932007-08-10 13:00:59 -0700344
345Consideration:
346Memory hotplug's design direction is to make the possibility of memory offlining
347higher and to guarantee unplugging memory under any situation. But it needs
348more work. Returning -EBUSY under some situation may be good because the user
349can decide to retry more or not by himself. Currently, memory offlining code
350does some amount of retry with 120 seconds timeout.
351
352-------------------------
3537. Physical memory remove
354-------------------------
355Need more implementation yet....
356 - Notification completion of remove works by OS to firmware.
357 - Guard from remove if not yet.
358
Yasunori Goto10020ca2007-10-21 16:41:36 -0700359--------------------------------
3608. Memory hotplug event notifier
361--------------------------------
Masanari Iidac94bed8e2012-04-10 00:22:13 +0900362Memory hotplug has event notifier. There are 6 types of notification.
Yasunori Goto10020ca2007-10-21 16:41:36 -0700363
364MEMORY_GOING_ONLINE
365 Generated before new memory becomes available in order to be able to
366 prepare subsystems to handle memory. The page allocator is still unable
367 to allocate from the new memory.
368
369MEMORY_CANCEL_ONLINE
370 Generated if MEMORY_GOING_ONLINE fails.
371
372MEMORY_ONLINE
Matt LaPlante19f59462009-04-27 15:06:31 +0200373 Generated when memory has successfully brought online. The callback may
Yasunori Goto10020ca2007-10-21 16:41:36 -0700374 allocate pages from the new memory.
375
376MEMORY_GOING_OFFLINE
377 Generated to begin the process of offlining memory. Allocations are no
378 longer possible from the memory but some of the memory to be offlined
379 is still in use. The callback can be used to free memory known to a
Li Zhong56a3c652014-06-04 16:07:03 -0700380 subsystem from the indicated memory block.
Yasunori Goto10020ca2007-10-21 16:41:36 -0700381
382MEMORY_CANCEL_OFFLINE
383 Generated if MEMORY_GOING_OFFLINE fails. Memory is available again from
Li Zhong56a3c652014-06-04 16:07:03 -0700384 the memory block that we attempted to offline.
Yasunori Goto10020ca2007-10-21 16:41:36 -0700385
386MEMORY_OFFLINE
387 Generated after offlining memory is complete.
388
389A callback routine can be registered by
390 hotplug_memory_notifier(callback_func, priority)
391
392The second argument of callback function (action) is event types of above.
393The third argument is passed by pointer of struct memory_notify.
394
395struct memory_notify {
396 unsigned long start_pfn;
397 unsigned long nr_pages;
Lai Jiangshand9713672012-12-11 16:01:03 -0800398 int status_change_nid_normal;
Lai Jiangshan6715ddf2012-12-12 13:51:49 -0800399 int status_change_nid_high;
Matt LaPlante19f59462009-04-27 15:06:31 +0200400 int status_change_nid;
Yasunori Goto10020ca2007-10-21 16:41:36 -0700401}
402
403start_pfn is start_pfn of online/offline memory.
404nr_pages is # of pages of online/offline memory.
Lai Jiangshand9713672012-12-11 16:01:03 -0800405status_change_nid_normal is set node id when N_NORMAL_MEMORY of nodemask
406is (will be) set/clear, if this is -1, then nodemask status is not changed.
Lai Jiangshan6715ddf2012-12-12 13:51:49 -0800407status_change_nid_high is set node id when N_HIGH_MEMORY of nodemask
408is (will be) set/clear, if this is -1, then nodemask status is not changed.
409status_change_nid is set node id when N_MEMORY of nodemask is (will be)
Yasunori Goto10020ca2007-10-21 16:41:36 -0700410set/clear. It means a new(memoryless) node gets new memory by online and a
411node loses all memory. If this is -1, then nodemask status is not changed.
Lai Jiangshand9713672012-12-11 16:01:03 -0800412If status_changed_nid* >= 0, callback should create/discard structures for the
Yasunori Goto10020ca2007-10-21 16:41:36 -0700413node if necessary.
414
Yasunori Goto6867c932007-08-10 13:00:59 -0700415--------------
Yasunori Goto10020ca2007-10-21 16:41:36 -07004169. Future Work
Yasunori Goto6867c932007-08-10 13:00:59 -0700417--------------
418 - allowing memory hot-add to ZONE_MOVABLE. maybe we need some switch like
419 sysctl or new control file.
Li Zhong56a3c652014-06-04 16:07:03 -0700420 - showing memory block and physical device relationship.
Yasunori Goto6867c932007-08-10 13:00:59 -0700421 - test and make it better memory offlining.
422 - support HugeTLB page migration and offlining.
423 - memmap removing at memory offline.
424 - physical remove memory.
425