blob: 97bae3c576c23668cc0fccfbc45ff97b8172840e [file] [log] [blame]
David Howellsc24b7202009-04-13 14:40:01 -07001 ==============================
2 UNEVICTABLE LRU INFRASTRUCTURE
3 ==============================
Lee Schermerhornfa07e782008-10-18 20:26:47 -07004
David Howellsc24b7202009-04-13 14:40:01 -07005========
6CONTENTS
7========
Lee Schermerhornfa07e782008-10-18 20:26:47 -07008
David Howellsc24b7202009-04-13 14:40:01 -07009 (*) The Unevictable LRU
Lee Schermerhornfa07e782008-10-18 20:26:47 -070010
David Howellsc24b7202009-04-13 14:40:01 -070011 - The unevictable page list.
12 - Memory control group interaction.
13 - Marking address spaces unevictable.
14 - Detecting Unevictable Pages.
15 - vmscan's handling of unevictable pages.
16
17 (*) mlock()'d pages.
18
19 - History.
20 - Basic management.
21 - mlock()/mlockall() system call handling.
22 - Filtering special vmas.
23 - munlock()/munlockall() system call handling.
24 - Migrating mlocked pages.
25 - mmap(MAP_LOCKED) system call handling.
26 - munmap()/exit()/exec() system call handling.
27 - try_to_unmap().
28 - try_to_munlock() reverse map scan.
29 - Page reclaim in shrink_*_list().
30
31
32============
33INTRODUCTION
34============
35
36This document describes the Linux memory manager's "Unevictable LRU"
37infrastructure and the use of this to manage several types of "unevictable"
38pages.
39
40The document attempts to provide the overall rationale behind this mechanism
41and the rationale for some of the design decisions that drove the
42implementation. The latter design rationale is discussed in the context of an
43implementation description. Admittedly, one can obtain the implementation
44details - the "what does it do?" - by reading the code. One hopes that the
45descriptions below add value by provide the answer to "why does it do that?".
46
47
48===================
49THE UNEVICTABLE LRU
50===================
51
52The Unevictable LRU facility adds an additional LRU list to track unevictable
53pages and to hide these pages from vmscan. This mechanism is based on a patch
54by Larry Woodman of Red Hat to address several scalability problems with page
Lee Schermerhornfa07e782008-10-18 20:26:47 -070055reclaim in Linux. The problems have been observed at customer sites on large
David Howellsc24b7202009-04-13 14:40:01 -070056memory x86_64 systems.
Lee Schermerhornfa07e782008-10-18 20:26:47 -070057
David Howellsc24b7202009-04-13 14:40:01 -070058To illustrate this with an example, a non-NUMA x86_64 platform with 128GB of
59main memory will have over 32 million 4k pages in a single zone. When a large
60fraction of these pages are not evictable for any reason [see below], vmscan
61will spend a lot of time scanning the LRU lists looking for the small fraction
62of pages that are evictable. This can result in a situation where all CPUs are
63spending 100% of their time in vmscan for hours or days on end, with the system
64completely unresponsive.
Lee Schermerhornfa07e782008-10-18 20:26:47 -070065
David Howellsc24b7202009-04-13 14:40:01 -070066The unevictable list addresses the following classes of unevictable pages:
Lee Schermerhornfa07e782008-10-18 20:26:47 -070067
David Howellsc24b7202009-04-13 14:40:01 -070068 (*) Those owned by ramfs.
69
70 (*) Those mapped into SHM_LOCK'd shared memory regions.
71
72 (*) Those mapped into VM_LOCKED [mlock()ed] VMAs.
73
74The infrastructure may also be able to handle other conditions that make pages
Lee Schermerhornfa07e782008-10-18 20:26:47 -070075unevictable, either by definition or by circumstance, in the future.
76
77
David Howellsc24b7202009-04-13 14:40:01 -070078THE UNEVICTABLE PAGE LIST
79-------------------------
Lee Schermerhornfa07e782008-10-18 20:26:47 -070080
81The Unevictable LRU infrastructure consists of an additional, per-zone, LRU list
82called the "unevictable" list and an associated page flag, PG_unevictable, to
David Howellsc24b7202009-04-13 14:40:01 -070083indicate that the page is being managed on the unevictable list.
84
85The PG_unevictable flag is analogous to, and mutually exclusive with, the
86PG_active flag in that it indicates on which LRU list a page resides when
Michal Hockoe6e8dd52011-03-16 15:01:37 +010087PG_lru is set.
Lee Schermerhornfa07e782008-10-18 20:26:47 -070088
89The Unevictable LRU infrastructure maintains unevictable pages on an additional
90LRU list for a few reasons:
91
David Howellsc24b7202009-04-13 14:40:01 -070092 (1) We get to "treat unevictable pages just like we treat other pages in the
93 system - which means we get to use the same code to manipulate them, the
94 same code to isolate them (for migrate, etc.), the same code to keep track
95 of the statistics, etc..." [Rik van Riel]
Lee Schermerhornfa07e782008-10-18 20:26:47 -070096
David Howellsc24b7202009-04-13 14:40:01 -070097 (2) We want to be able to migrate unevictable pages between nodes for memory
98 defragmentation, workload management and memory hotplug. The linux kernel
99 can only migrate pages that it can successfully isolate from the LRU
100 lists. If we were to maintain pages elsewhere than on an LRU-like list,
101 where they can be found by isolate_lru_page(), we would prevent their
102 migration, unless we reworked migration code to find the unevictable pages
103 itself.
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700104
105
David Howellsc24b7202009-04-13 14:40:01 -0700106The unevictable list does not differentiate between file-backed and anonymous,
107swap-backed pages. This differentiation is only important while the pages are,
108in fact, evictable.
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700109
David Howellsc24b7202009-04-13 14:40:01 -0700110The unevictable list benefits from the "arrayification" of the per-zone LRU
111lists and statistics originally proposed and posted by Christoph Lameter.
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700112
David Howellsc24b7202009-04-13 14:40:01 -0700113The unevictable list does not use the LRU pagevec mechanism. Rather,
114unevictable pages are placed directly on the page's zone's unevictable list
115under the zone lru_lock. This allows us to prevent the stranding of pages on
116the unevictable list when one task has the page isolated from the LRU and other
117tasks are changing the "evictability" state of the page.
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700118
119
David Howellsc24b7202009-04-13 14:40:01 -0700120MEMORY CONTROL GROUP INTERACTION
121--------------------------------
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700122
David Howellsc24b7202009-04-13 14:40:01 -0700123The unevictable LRU facility interacts with the memory control group [aka
124memory controller; see Documentation/cgroups/memory.txt] by extending the
125lru_list enum.
126
127The memory controller data structure automatically gets a per-zone unevictable
128list as a result of the "arrayification" of the per-zone LRU lists (one per
129lru_list enum element). The memory controller tracks the movement of pages to
130and from the unevictable list.
131
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700132When a memory control group comes under memory pressure, the controller will
133not attempt to reclaim pages on the unevictable list. This has a couple of
David Howellsc24b7202009-04-13 14:40:01 -0700134effects:
135
136 (1) Because the pages are "hidden" from reclaim on the unevictable list, the
137 reclaim process can be more efficient, dealing only with pages that have a
138 chance of being reclaimed.
139
140 (2) On the other hand, if too many of the pages charged to the control group
141 are unevictable, the evictable portion of the working set of the tasks in
142 the control group may not fit into the available memory. This can cause
143 the control group to thrash or to OOM-kill tasks.
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700144
145
David Howellsc24b7202009-04-13 14:40:01 -0700146MARKING ADDRESS SPACES UNEVICTABLE
147----------------------------------
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700148
David Howellsc24b7202009-04-13 14:40:01 -0700149For facilities such as ramfs none of the pages attached to the address space
150may be evicted. To prevent eviction of any such pages, the AS_UNEVICTABLE
151address space flag is provided, and this can be manipulated by a filesystem
152using a number of wrapper functions:
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700153
David Howellsc24b7202009-04-13 14:40:01 -0700154 (*) void mapping_set_unevictable(struct address_space *mapping);
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700155
David Howellsc24b7202009-04-13 14:40:01 -0700156 Mark the address space as being completely unevictable.
157
158 (*) void mapping_clear_unevictable(struct address_space *mapping);
159
160 Mark the address space as being evictable.
161
162 (*) int mapping_unevictable(struct address_space *mapping);
163
164 Query the address space, and return true if it is completely
165 unevictable.
166
167These are currently used in two places in the kernel:
168
169 (1) By ramfs to mark the address spaces of its inodes when they are created,
170 and this mark remains for the life of the inode.
171
172 (2) By SYSV SHM to mark SHM_LOCK'd address spaces until SHM_UNLOCK is called.
173
174 Note that SHM_LOCK is not required to page in the locked pages if they're
175 swapped out; the application must touch the pages manually if it wants to
176 ensure they're in memory.
177
178
179DETECTING UNEVICTABLE PAGES
180---------------------------
181
182The function page_evictable() in vmscan.c determines whether a page is
183evictable or not using the query function outlined above [see section "Marking
184address spaces unevictable"] to check the AS_UNEVICTABLE flag.
185
186For address spaces that are so marked after being populated (as SHM regions
187might be), the lock action (eg: SHM_LOCK) can be lazy, and need not populate
188the page tables for the region as does, for example, mlock(), nor need it make
189any special effort to push any pages in the SHM_LOCK'd area to the unevictable
190list. Instead, vmscan will do this if and when it encounters the pages during
191a reclamation scan.
192
193On an unlock action (such as SHM_UNLOCK), the unlocker (eg: shmctl()) must scan
194the pages in the region and "rescue" them from the unevictable list if no other
195condition is keeping them unevictable. If an unevictable region is destroyed,
196the pages are also "rescued" from the unevictable list in the process of
197freeing them.
198
199page_evictable() also checks for mlocked pages by testing an additional page
200flag, PG_mlocked (as wrapped by PageMlocked()). If the page is NOT mlocked,
201and a non-NULL VMA is supplied, page_evictable() will check whether the VMA is
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700202VM_LOCKED via is_mlocked_vma(). is_mlocked_vma() will SetPageMlocked() and
203update the appropriate statistics if the vma is VM_LOCKED. This method allows
204efficient "culling" of pages in the fault path that are being faulted in to
David Howellsc24b7202009-04-13 14:40:01 -0700205VM_LOCKED VMAs.
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700206
207
David Howellsc24b7202009-04-13 14:40:01 -0700208VMSCAN'S HANDLING OF UNEVICTABLE PAGES
209--------------------------------------
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700210
211If unevictable pages are culled in the fault path, or moved to the unevictable
David Howellsc24b7202009-04-13 14:40:01 -0700212list at mlock() or mmap() time, vmscan will not encounter the pages until they
213have become evictable again (via munlock() for example) and have been "rescued"
214from the unevictable list. However, there may be situations where we decide,
215for the sake of expediency, to leave a unevictable page on one of the regular
216active/inactive LRU lists for vmscan to deal with. vmscan checks for such
217pages in all of the shrink_{active|inactive|page}_list() functions and will
218"cull" such pages that it encounters: that is, it diverts those pages to the
219unevictable list for the zone being scanned.
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700220
David Howellsc24b7202009-04-13 14:40:01 -0700221There may be situations where a page is mapped into a VM_LOCKED VMA, but the
222page is not marked as PG_mlocked. Such pages will make it all the way to
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700223shrink_page_list() where they will be detected when vmscan walks the reverse
David Howellsc24b7202009-04-13 14:40:01 -0700224map in try_to_unmap(). If try_to_unmap() returns SWAP_MLOCK,
225shrink_page_list() will cull the page at that point.
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700226
David Howellsc24b7202009-04-13 14:40:01 -0700227To "cull" an unevictable page, vmscan simply puts the page back on the LRU list
228using putback_lru_page() - the inverse operation to isolate_lru_page() - after
229dropping the page lock. Because the condition which makes the page unevictable
230may change once the page is unlocked, putback_lru_page() will recheck the
231unevictable state of a page that it places on the unevictable list. If the
232page has become unevictable, putback_lru_page() removes it from the list and
233retries, including the page_unevictable() test. Because such a race is a rare
234event and movement of pages onto the unevictable list should be rare, these
235extra evictabilty checks should not occur in the majority of calls to
236putback_lru_page().
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700237
238
David Howellsc24b7202009-04-13 14:40:01 -0700239=============
240MLOCKED PAGES
241=============
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700242
David Howellsc24b7202009-04-13 14:40:01 -0700243The unevictable page list is also useful for mlock(), in addition to ramfs and
244SYSV SHM. Note that mlock() is only available in CONFIG_MMU=y situations; in
245NOMMU situations, all mappings are effectively mlocked.
246
247
248HISTORY
249-------
250
251The "Unevictable mlocked Pages" infrastructure is based on work originally
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700252posted by Nick Piggin in an RFC patch entitled "mm: mlocked pages off LRU".
David Howellsc24b7202009-04-13 14:40:01 -0700253Nick posted his patch as an alternative to a patch posted by Christoph Lameter
254to achieve the same objective: hiding mlocked pages from vmscan.
255
256In Nick's patch, he used one of the struct page LRU list link fields as a count
257of VM_LOCKED VMAs that map the page. This use of the link field for a count
258prevented the management of the pages on an LRU list, and thus mlocked pages
259were not migratable as isolate_lru_page() could not find them, and the LRU list
260link field was not available to the migration subsystem.
261
262Nick resolved this by putting mlocked pages back on the lru list before
263attempting to isolate them, thus abandoning the count of VM_LOCKED VMAs. When
264Nick's patch was integrated with the Unevictable LRU work, the count was
265replaced by walking the reverse map to determine whether any VM_LOCKED VMAs
266mapped the page. More on this below.
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700267
268
David Howellsc24b7202009-04-13 14:40:01 -0700269BASIC MANAGEMENT
270----------------
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700271
David Howellsc24b7202009-04-13 14:40:01 -0700272mlocked pages - pages mapped into a VM_LOCKED VMA - are a class of unevictable
273pages. When such a page has been "noticed" by the memory management subsystem,
274the page is marked with the PG_mlocked flag. This can be manipulated using the
275PageMlocked() functions.
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700276
David Howellsc24b7202009-04-13 14:40:01 -0700277A PG_mlocked page will be placed on the unevictable list when it is added to
278the LRU. Such pages can be "noticed" by memory management in several places:
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700279
David Howellsc24b7202009-04-13 14:40:01 -0700280 (1) in the mlock()/mlockall() system call handlers;
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700281
David Howellsc24b7202009-04-13 14:40:01 -0700282 (2) in the mmap() system call handler when mmapping a region with the
283 MAP_LOCKED flag;
284
285 (3) mmapping a region in a task that has called mlockall() with the MCL_FUTURE
286 flag
287
288 (4) in the fault path, if mlocked pages are "culled" in the fault path,
289 and when a VM_LOCKED stack segment is expanded; or
290
291 (5) as mentioned above, in vmscan:shrink_page_list() when attempting to
292 reclaim a page in a VM_LOCKED VMA via try_to_unmap()
293
294all of which result in the VM_LOCKED flag being set for the VMA if it doesn't
295already have it set.
296
297mlocked pages become unlocked and rescued from the unevictable list when:
298
299 (1) mapped in a range unlocked via the munlock()/munlockall() system calls;
300
301 (2) munmap()'d out of the last VM_LOCKED VMA that maps the page, including
302 unmapping at task exit;
303
304 (3) when the page is truncated from the last VM_LOCKED VMA of an mmapped file;
305 or
306
307 (4) before a page is COW'd in a VM_LOCKED VMA.
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700308
309
David Howellsc24b7202009-04-13 14:40:01 -0700310mlock()/mlockall() SYSTEM CALL HANDLING
311---------------------------------------
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700312
313Both [do_]mlock() and [do_]mlockall() system call handlers call mlock_fixup()
David Howellsc24b7202009-04-13 14:40:01 -0700314for each VMA in the range specified by the call. In the case of mlockall(),
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700315this is the entire active address space of the task. Note that mlock_fixup()
David Howellsc24b7202009-04-13 14:40:01 -0700316is used for both mlocking and munlocking a range of memory. A call to mlock()
317an already VM_LOCKED VMA, or to munlock() a VMA that is not VM_LOCKED is
318treated as a no-op, and mlock_fixup() simply returns.
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700319
David Howellsc24b7202009-04-13 14:40:01 -0700320If the VMA passes some filtering as described in "Filtering Special Vmas"
321below, mlock_fixup() will attempt to merge the VMA with its neighbors or split
322off a subset of the VMA if the range does not cover the entire VMA. Once the
323VMA has been merged or split or neither, mlock_fixup() will call
324__mlock_vma_pages_range() to fault in the pages via get_user_pages() and to
325mark the pages as mlocked via mlock_vma_page().
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700326
David Howellsc24b7202009-04-13 14:40:01 -0700327Note that the VMA being mlocked might be mapped with PROT_NONE. In this case,
328get_user_pages() will be unable to fault in the pages. That's okay. If pages
329do end up getting faulted into this VM_LOCKED VMA, we'll handle them in the
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700330fault path or in vmscan.
331
332Also note that a page returned by get_user_pages() could be truncated or
David Howellsc24b7202009-04-13 14:40:01 -0700333migrated out from under us, while we're trying to mlock it. To detect this,
334__mlock_vma_pages_range() checks page_mapping() after acquiring the page lock.
335If the page is still associated with its mapping, we'll go ahead and call
336mlock_vma_page(). If the mapping is gone, we just unlock the page and move on.
337In the worst case, this will result in a page mapped in a VM_LOCKED VMA
338remaining on a normal LRU list without being PageMlocked(). Again, vmscan will
339detect and cull such pages.
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700340
David Howellsc24b7202009-04-13 14:40:01 -0700341mlock_vma_page() will call TestSetPageMlocked() for each page returned by
342get_user_pages(). We use TestSetPageMlocked() because the page might already
343be mlocked by another task/VMA and we don't want to do extra work. We
344especially do not want to count an mlocked page more than once in the
345statistics. If the page was already mlocked, mlock_vma_page() need do nothing
346more.
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700347
348If the page was NOT already mlocked, mlock_vma_page() attempts to isolate the
349page from the LRU, as it is likely on the appropriate active or inactive list
David Howellsc24b7202009-04-13 14:40:01 -0700350at that time. If the isolate_lru_page() succeeds, mlock_vma_page() will put
351back the page - by calling putback_lru_page() - which will notice that the page
352is now mlocked and divert the page to the zone's unevictable list. If
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700353mlock_vma_page() is unable to isolate the page from the LRU, vmscan will handle
David Howellsc24b7202009-04-13 14:40:01 -0700354it later if and when it attempts to reclaim the page.
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700355
356
David Howellsc24b7202009-04-13 14:40:01 -0700357FILTERING SPECIAL VMAS
358----------------------
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700359
David Howellsc24b7202009-04-13 14:40:01 -0700360mlock_fixup() filters several classes of "special" VMAs:
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700361
David Howellsc24b7202009-04-13 14:40:01 -07003621) VMAs with VM_IO or VM_PFNMAP set are skipped entirely. The pages behind
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700363 these mappings are inherently pinned, so we don't need to mark them as
David Howellsc24b7202009-04-13 14:40:01 -0700364 mlocked. In any case, most of the pages have no struct page in which to so
365 mark the page. Because of this, get_user_pages() will fail for these VMAs,
366 so there is no sense in attempting to visit them.
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700367
David Howellsc24b7202009-04-13 14:40:01 -07003682) VMAs mapping hugetlbfs page are already effectively pinned into memory. We
369 neither need nor want to mlock() these pages. However, to preserve the
370 prior behavior of mlock() - before the unevictable/mlock changes -
371 mlock_fixup() will call make_pages_present() in the hugetlbfs VMA range to
372 allocate the huge pages and populate the ptes.
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700373
David Howellsc24b7202009-04-13 14:40:01 -07003743) VMAs with VM_DONTEXPAND or VM_RESERVED are generally userspace mappings of
375 kernel pages, such as the VDSO page, relay channel pages, etc. These pages
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700376 are inherently unevictable and are not managed on the LRU lists.
David Howellsc24b7202009-04-13 14:40:01 -0700377 mlock_fixup() treats these VMAs the same as hugetlbfs VMAs. It calls
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700378 make_pages_present() to populate the ptes.
379
David Howellsc24b7202009-04-13 14:40:01 -0700380Note that for all of these special VMAs, mlock_fixup() does not set the
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700381VM_LOCKED flag. Therefore, we won't have to deal with them later during
David Howellsc24b7202009-04-13 14:40:01 -0700382munlock(), munmap() or task exit. Neither does mlock_fixup() account these
383VMAs against the task's "locked_vm".
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700384
385
David Howellsc24b7202009-04-13 14:40:01 -0700386munlock()/munlockall() SYSTEM CALL HANDLING
387-------------------------------------------
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700388
David Howellsc24b7202009-04-13 14:40:01 -0700389The munlock() and munlockall() system calls are handled by the same functions -
390do_mlock[all]() - as the mlock() and mlockall() system calls with the unlock vs
391lock operation indicated by an argument. So, these system calls are also
392handled by mlock_fixup(). Again, if called for an already munlocked VMA,
393mlock_fixup() simply returns. Because of the VMA filtering discussed above,
394VM_LOCKED will not be set in any "special" VMAs. So, these VMAs will be
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700395ignored for munlock.
396
David Howellsc24b7202009-04-13 14:40:01 -0700397If the VMA is VM_LOCKED, mlock_fixup() again attempts to merge or split off the
398specified range. The range is then munlocked via the function
399__mlock_vma_pages_range() - the same function used to mlock a VMA range -
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700400passing a flag to indicate that munlock() is being performed.
401
David Howellsc24b7202009-04-13 14:40:01 -0700402Because the VMA access protections could have been changed to PROT_NONE after
Hugh Dickins63d6c5a2009-01-06 14:39:38 -0800403faulting in and mlocking pages, get_user_pages() was unreliable for visiting
David Howellsc24b7202009-04-13 14:40:01 -0700404these pages for munlocking. Because we don't want to leave pages mlocked,
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700405get_user_pages() was enhanced to accept a flag to ignore the permissions when
David Howellsc24b7202009-04-13 14:40:01 -0700406fetching the pages - all of which should be resident as a result of previous
407mlocking.
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700408
409For munlock(), __mlock_vma_pages_range() unlocks individual pages by calling
410munlock_vma_page(). munlock_vma_page() unconditionally clears the PG_mlocked
David Howellsc24b7202009-04-13 14:40:01 -0700411flag using TestClearPageMlocked(). As with mlock_vma_page(),
412munlock_vma_page() use the Test*PageMlocked() function to handle the case where
413the page might have already been unlocked by another task. If the page was
414mlocked, munlock_vma_page() updates that zone statistics for the number of
415mlocked pages. Note, however, that at this point we haven't checked whether
416the page is mapped by other VM_LOCKED VMAs.
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700417
David Howellsc24b7202009-04-13 14:40:01 -0700418We can't call try_to_munlock(), the function that walks the reverse map to
419check for other VM_LOCKED VMAs, without first isolating the page from the LRU.
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700420try_to_munlock() is a variant of try_to_unmap() and thus requires that the page
David Howellsc24b7202009-04-13 14:40:01 -0700421not be on an LRU list [more on these below]. However, the call to
422isolate_lru_page() could fail, in which case we couldn't try_to_munlock(). So,
423we go ahead and clear PG_mlocked up front, as this might be the only chance we
424have. If we can successfully isolate the page, we go ahead and
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700425try_to_munlock(), which will restore the PG_mlocked flag and update the zone
David Howellsc24b7202009-04-13 14:40:01 -0700426page statistics if it finds another VMA holding the page mlocked. If we fail
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700427to isolate the page, we'll have left a potentially mlocked page on the LRU.
David Howellsc24b7202009-04-13 14:40:01 -0700428This is fine, because we'll catch it later if and if vmscan tries to reclaim
429the page. This should be relatively rare.
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700430
431
David Howellsc24b7202009-04-13 14:40:01 -0700432MIGRATING MLOCKED PAGES
433-----------------------
434
435A page that is being migrated has been isolated from the LRU lists and is held
436locked across unmapping of the page, updating the page's address space entry
437and copying the contents and state, until the page table entry has been
438replaced with an entry that refers to the new page. Linux supports migration
439of mlocked pages and other unevictable pages. This involves simply moving the
440PG_mlocked and PG_unevictable states from the old page to the new page.
441
442Note that page migration can race with mlocking or munlocking of the same page.
443This has been discussed from the mlock/munlock perspective in the respective
444sections above. Both processes (migration and m[un]locking) hold the page
445locked. This provides the first level of synchronization. Page migration
446zeros out the page_mapping of the old page before unlocking it, so m[un]lock
447can skip these pages by testing the page mapping under page lock.
448
449To complete page migration, we place the new and old pages back onto the LRU
450after dropping the page lock. The "unneeded" page - old page on success, new
451page on failure - will be freed when the reference count held by the migration
452process is released. To ensure that we don't strand pages on the unevictable
453list because of a race between munlock and migration, page migration uses the
454putback_lru_page() function to add migrated pages back to the LRU.
455
456
457mmap(MAP_LOCKED) SYSTEM CALL HANDLING
458-------------------------------------
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700459
460In addition the the mlock()/mlockall() system calls, an application can request
David Howellsc24b7202009-04-13 14:40:01 -0700461that a region of memory be mlocked supplying the MAP_LOCKED flag to the mmap()
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700462call. Furthermore, any mmap() call or brk() call that expands the heap by a
463task that has previously called mlockall() with the MCL_FUTURE flag will result
David Howellsc24b7202009-04-13 14:40:01 -0700464in the newly mapped memory being mlocked. Before the unevictable/mlock
465changes, the kernel simply called make_pages_present() to allocate pages and
466populate the page table.
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700467
468To mlock a range of memory under the unevictable/mlock infrastructure, the
469mmap() handler and task address space expansion functions call
470mlock_vma_pages_range() specifying the vma and the address range to mlock.
David Howellsc24b7202009-04-13 14:40:01 -0700471mlock_vma_pages_range() filters VMAs like mlock_fixup(), as described above in
472"Filtering Special VMAs". It will clear the VM_LOCKED flag, which will have
473already been set by the caller, in filtered VMAs. Thus these VMA's need not be
474visited for munlock when the region is unmapped.
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700475
David Howellsc24b7202009-04-13 14:40:01 -0700476For "normal" VMAs, mlock_vma_pages_range() calls __mlock_vma_pages_range() to
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700477fault/allocate the pages and mlock them. Again, like mlock_fixup(),
478mlock_vma_pages_range() downgrades the mmap semaphore to read mode before
David Howellsc24b7202009-04-13 14:40:01 -0700479attempting to fault/allocate and mlock the pages and "upgrades" the semaphore
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700480back to write mode before returning.
481
David Howellsc24b7202009-04-13 14:40:01 -0700482The callers of mlock_vma_pages_range() will have already added the memory range
483to be mlocked to the task's "locked_vm". To account for filtered VMAs,
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700484mlock_vma_pages_range() returns the number of pages NOT mlocked. All of the
David Howellsc24b7202009-04-13 14:40:01 -0700485callers then subtract a non-negative return value from the task's locked_vm. A
486negative return value represent an error - for example, from get_user_pages()
487attempting to fault in a VMA with PROT_NONE access. In this case, we leave the
488memory range accounted as locked_vm, as the protections could be changed later
489and pages allocated into that region.
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700490
491
David Howellsc24b7202009-04-13 14:40:01 -0700492munmap()/exit()/exec() SYSTEM CALL HANDLING
493-------------------------------------------
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700494
495When unmapping an mlocked region of memory, whether by an explicit call to
496munmap() or via an internal unmap from exit() or exec() processing, we must
David Howellsc24b7202009-04-13 14:40:01 -0700497munlock the pages if we're removing the last VM_LOCKED VMA that maps the pages.
Hugh Dickins63d6c5a2009-01-06 14:39:38 -0800498Before the unevictable/mlock changes, mlocking did not mark the pages in any
499way, so unmapping them required no processing.
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700500
501To munlock a range of memory under the unevictable/mlock infrastructure, the
David Howellsc24b7202009-04-13 14:40:01 -0700502munmap() handler and task address space call tear down function
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700503munlock_vma_pages_all(). The name reflects the observation that one always
David Howellsc24b7202009-04-13 14:40:01 -0700504specifies the entire VMA range when munlock()ing during unmap of a region.
505Because of the VMA filtering when mlocking() regions, only "normal" VMAs that
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700506actually contain mlocked pages will be passed to munlock_vma_pages_all().
507
David Howellsc24b7202009-04-13 14:40:01 -0700508munlock_vma_pages_all() clears the VM_LOCKED VMA flag and, like mlock_fixup()
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700509for the munlock case, calls __munlock_vma_pages_range() to walk the page table
David Howellsc24b7202009-04-13 14:40:01 -0700510for the VMA's memory range and munlock_vma_page() each resident page mapped by
511the VMA. This effectively munlocks the page, only if this is the last
512VM_LOCKED VMA that maps the page.
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700513
514
David Howellsc24b7202009-04-13 14:40:01 -0700515try_to_unmap()
516--------------
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700517
David Howellsc24b7202009-04-13 14:40:01 -0700518Pages can, of course, be mapped into multiple VMAs. Some of these VMAs may
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700519have VM_LOCKED flag set. It is possible for a page mapped into one or more
David Howellsc24b7202009-04-13 14:40:01 -0700520VM_LOCKED VMAs not to have the PG_mlocked flag set and therefore reside on one
521of the active or inactive LRU lists. This could happen if, for example, a task
522in the process of munlocking the page could not isolate the page from the LRU.
523As a result, vmscan/shrink_page_list() might encounter such a page as described
524in section "vmscan's handling of unevictable pages". To handle this situation,
525try_to_unmap() checks for VM_LOCKED VMAs while it is walking a page's reverse
526map.
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700527
528try_to_unmap() is always called, by either vmscan for reclaim or for page
David Howellsc24b7202009-04-13 14:40:01 -0700529migration, with the argument page locked and isolated from the LRU. Separate
530functions handle anonymous and mapped file pages, as these types of pages have
531different reverse map mechanisms.
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700532
David Howellsc24b7202009-04-13 14:40:01 -0700533 (*) try_to_unmap_anon()
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700534
David Howellsc24b7202009-04-13 14:40:01 -0700535 To unmap anonymous pages, each VMA in the list anchored in the anon_vma
536 must be visited - at least until a VM_LOCKED VMA is encountered. If the
537 page is being unmapped for migration, VM_LOCKED VMAs do not stop the
538 process because mlocked pages are migratable. However, for reclaim, if
539 the page is mapped into a VM_LOCKED VMA, the scan stops.
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700540
David Howellsc24b7202009-04-13 14:40:01 -0700541 try_to_unmap_anon() attempts to acquire in read mode the mmap semphore of
542 the mm_struct to which the VMA belongs. If this is successful, it will
543 mlock the page via mlock_vma_page() - we wouldn't have gotten to
544 try_to_unmap_anon() if the page were already mlocked - and will return
545 SWAP_MLOCK, indicating that the page is unevictable.
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700546
David Howellsc24b7202009-04-13 14:40:01 -0700547 If the mmap semaphore cannot be acquired, we are not sure whether the page
548 is really unevictable or not. In this case, try_to_unmap_anon() will
549 return SWAP_AGAIN.
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700550
David Howellsc24b7202009-04-13 14:40:01 -0700551 (*) try_to_unmap_file() - linear mappings
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700552
David Howellsc24b7202009-04-13 14:40:01 -0700553 Unmapping of a mapped file page works the same as for anonymous mappings,
554 except that the scan visits all VMAs that map the page's index/page offset
555 in the page's mapping's reverse map priority search tree. It also visits
556 each VMA in the page's mapping's non-linear list, if the list is
557 non-empty.
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700558
David Howellsc24b7202009-04-13 14:40:01 -0700559 As for anonymous pages, on encountering a VM_LOCKED VMA for a mapped file
560 page, try_to_unmap_file() will attempt to acquire the associated
561 mm_struct's mmap semaphore to mlock the page, returning SWAP_MLOCK if this
562 is successful, and SWAP_AGAIN, if not.
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700563
David Howellsc24b7202009-04-13 14:40:01 -0700564 (*) try_to_unmap_file() - non-linear mappings
565
566 If a page's mapping contains a non-empty non-linear mapping VMA list, then
567 try_to_un{map|lock}() must also visit each VMA in that list to determine
568 whether the page is mapped in a VM_LOCKED VMA. Again, the scan must visit
569 all VMAs in the non-linear list to ensure that the pages is not/should not
570 be mlocked.
571
572 If a VM_LOCKED VMA is found in the list, the scan could terminate.
573 However, there is no easy way to determine whether the page is actually
574 mapped in a given VMA - either for unmapping or testing whether the
575 VM_LOCKED VMA actually pins the page.
576
577 try_to_unmap_file() handles non-linear mappings by scanning a certain
578 number of pages - a "cluster" - in each non-linear VMA associated with the
579 page's mapping, for each file mapped page that vmscan tries to unmap. If
580 this happens to unmap the page we're trying to unmap, try_to_unmap() will
581 notice this on return (page_mapcount(page) will be 0) and return
582 SWAP_SUCCESS. Otherwise, it will return SWAP_AGAIN, causing vmscan to
583 recirculate this page. We take advantage of the cluster scan in
584 try_to_unmap_cluster() as follows:
585
586 For each non-linear VMA, try_to_unmap_cluster() attempts to acquire the
587 mmap semaphore of the associated mm_struct for read without blocking.
588
589 If this attempt is successful and the VMA is VM_LOCKED,
590 try_to_unmap_cluster() will retain the mmap semaphore for the scan;
591 otherwise it drops it here.
592
593 Then, for each page in the cluster, if we're holding the mmap semaphore
594 for a locked VMA, try_to_unmap_cluster() calls mlock_vma_page() to
595 mlock the page. This call is a no-op if the page is already locked,
596 but will mlock any pages in the non-linear mapping that happen to be
597 unlocked.
598
599 If one of the pages so mlocked is the page passed in to try_to_unmap(),
600 try_to_unmap_cluster() will return SWAP_MLOCK, rather than the default
601 SWAP_AGAIN. This will allow vmscan to cull the page, rather than
602 recirculating it on the inactive list.
603
604 Again, if try_to_unmap_cluster() cannot acquire the VMA's mmap sem, it
605 returns SWAP_AGAIN, indicating that the page is mapped by a VM_LOCKED
606 VMA, but couldn't be mlocked.
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700607
608
David Howellsc24b7202009-04-13 14:40:01 -0700609try_to_munlock() REVERSE MAP SCAN
610---------------------------------
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700611
David Howellsc24b7202009-04-13 14:40:01 -0700612 [!] TODO/FIXME: a better name might be page_mlocked() - analogous to the
613 page_referenced() reverse map walker.
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700614
David Howellsc24b7202009-04-13 14:40:01 -0700615When munlock_vma_page() [see section "munlock()/munlockall() System Call
616Handling" above] tries to munlock a page, it needs to determine whether or not
617the page is mapped by any VM_LOCKED VMA without actually attempting to unmap
618all PTEs from the page. For this purpose, the unevictable/mlock infrastructure
619introduced a variant of try_to_unmap() called try_to_munlock().
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700620
621try_to_munlock() calls the same functions as try_to_unmap() for anonymous and
622mapped file pages with an additional argument specifing unlock versus unmap
623processing. Again, these functions walk the respective reverse maps looking
David Howellsc24b7202009-04-13 14:40:01 -0700624for VM_LOCKED VMAs. When such a VMA is found for anonymous pages and file
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700625pages mapped in linear VMAs, as in the try_to_unmap() case, the functions
626attempt to acquire the associated mmap semphore, mlock the page via
627mlock_vma_page() and return SWAP_MLOCK. This effectively undoes the
Hugh Dickins63d6c5a2009-01-06 14:39:38 -0800628pre-clearing of the page's PG_mlocked done by munlock_vma_page.
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700629
David Howellsc24b7202009-04-13 14:40:01 -0700630If try_to_unmap() is unable to acquire a VM_LOCKED VMA's associated mmap
631semaphore, it will return SWAP_AGAIN. This will allow shrink_page_list() to
632recycle the page on the inactive list and hope that it has better luck with the
633page next time.
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700634
David Howellsc24b7202009-04-13 14:40:01 -0700635For file pages mapped into non-linear VMAs, the try_to_munlock() logic works
636slightly differently. On encountering a VM_LOCKED non-linear VMA that might
637map the page, try_to_munlock() returns SWAP_AGAIN without actually mlocking the
638page. munlock_vma_page() will just leave the page unlocked and let vmscan deal
639with it - the usual fallback position.
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700640
David Howellsc24b7202009-04-13 14:40:01 -0700641Note that try_to_munlock()'s reverse map walk must visit every VMA in a page's
642reverse map to determine that a page is NOT mapped into any VM_LOCKED VMA.
643However, the scan can terminate when it encounters a VM_LOCKED VMA and can
644successfully acquire the VMA's mmap semphore for read and mlock the page.
645Although try_to_munlock() might be called a great many times when munlocking a
646large region or tearing down a large address space that has been mlocked via
647mlockall(), overall this is a fairly rare event.
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700648
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700649
David Howellsc24b7202009-04-13 14:40:01 -0700650PAGE RECLAIM IN shrink_*_list()
651-------------------------------
652
653shrink_active_list() culls any obviously unevictable pages - i.e.
654!page_evictable(page, NULL) - diverting these to the unevictable list.
655However, shrink_active_list() only sees unevictable pages that made it onto the
656active/inactive lru lists. Note that these pages do not have PageUnevictable
657set - otherwise they would be on the unevictable list and shrink_active_list
658would never see them.
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700659
660Some examples of these unevictable pages on the LRU lists are:
661
David Howellsc24b7202009-04-13 14:40:01 -0700662 (1) ramfs pages that have been placed on the LRU lists when first allocated.
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700663
David Howellsc24b7202009-04-13 14:40:01 -0700664 (2) SHM_LOCK'd shared memory pages. shmctl(SHM_LOCK) does not attempt to
665 allocate or fault in the pages in the shared memory region. This happens
666 when an application accesses the page the first time after SHM_LOCK'ing
667 the segment.
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700668
David Howellsc24b7202009-04-13 14:40:01 -0700669 (3) mlocked pages that could not be isolated from the LRU and moved to the
670 unevictable list in mlock_vma_page().
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700671
David Howellsc24b7202009-04-13 14:40:01 -0700672 (4) Pages mapped into multiple VM_LOCKED VMAs, but try_to_munlock() couldn't
673 acquire the VMA's mmap semaphore to test the flags and set PageMlocked.
674 munlock_vma_page() was forced to let the page back on to the normal LRU
675 list for vmscan to handle.
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700676
David Howellsc24b7202009-04-13 14:40:01 -0700677shrink_inactive_list() also diverts any unevictable pages that it finds on the
678inactive lists to the appropriate zone's unevictable list.
679
680shrink_inactive_list() should only see SHM_LOCK'd pages that became SHM_LOCK'd
681after shrink_active_list() had moved them to the inactive list, or pages mapped
682into VM_LOCKED VMAs that munlock_vma_page() couldn't isolate from the LRU to
683recheck via try_to_munlock(). shrink_inactive_list() won't notice the latter,
684but will pass on to shrink_page_list().
Lee Schermerhornfa07e782008-10-18 20:26:47 -0700685
686shrink_page_list() again culls obviously unevictable pages that it could
Hugh Dickins63d6c5a2009-01-06 14:39:38 -0800687encounter for similar reason to shrink_inactive_list(). Pages mapped into
David Howellsc24b7202009-04-13 14:40:01 -0700688VM_LOCKED VMAs but without PG_mlocked set will make it all the way to
Hugh Dickins63d6c5a2009-01-06 14:39:38 -0800689try_to_unmap(). shrink_page_list() will divert them to the unevictable list
690when try_to_unmap() returns SWAP_MLOCK, as discussed above.