forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
cpuset.c
2500 lines (2201 loc) · 71.6 KB
/
cpuset.c
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
/*
* kernel/cpuset.c
*
* Processor and Memory placement constraints for sets of tasks.
*
* Copyright (C) 2003 BULL SA.
* Copyright (C) 2004-2006 Silicon Graphics, Inc.
*
* Portions derived from Patrick Mochel's sysfs code.
* sysfs is Copyright (c) 2001-3 Patrick Mochel
*
* 2003-10-10 Written by Simon Derr.
* 2003-10-22 Updates by Stephen Hemminger.
* 2004 May-July Rework by Paul Jackson.
*
* This file is subject to the terms and conditions of the GNU General Public
* License. See the file COPYING in the main directory of the Linux
* distribution for more details.
*/
#include <linux/cpu.h>
#include <linux/cpumask.h>
#include <linux/cpuset.h>
#include <linux/err.h>
#include <linux/errno.h>
#include <linux/file.h>
#include <linux/fs.h>
#include <linux/init.h>
#include <linux/interrupt.h>
#include <linux/kernel.h>
#include <linux/kmod.h>
#include <linux/list.h>
#include <linux/mempolicy.h>
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/mount.h>
#include <linux/namei.h>
#include <linux/pagemap.h>
#include <linux/proc_fs.h>
#include <linux/rcupdate.h>
#include <linux/sched.h>
#include <linux/seq_file.h>
#include <linux/security.h>
#include <linux/slab.h>
#include <linux/smp_lock.h>
#include <linux/spinlock.h>
#include <linux/stat.h>
#include <linux/string.h>
#include <linux/time.h>
#include <linux/backing-dev.h>
#include <linux/sort.h>
#include <asm/uaccess.h>
#include <asm/atomic.h>
#include <linux/mutex.h>
#define CPUSET_SUPER_MAGIC 0x27e0eb
/*
* Tracks how many cpusets are currently defined in system.
* When there is only one cpuset (the root cpuset) we can
* short circuit some hooks.
*/
int number_of_cpusets __read_mostly;
/* See "Frequency meter" comments, below. */
struct fmeter {
int cnt; /* unprocessed events count */
int val; /* most recent output value */
time_t time; /* clock (secs) when val computed */
spinlock_t lock; /* guards read or write of above */
};
struct cpuset {
unsigned long flags; /* "unsigned long" so bitops work */
cpumask_t cpus_allowed; /* CPUs allowed to tasks in cpuset */
nodemask_t mems_allowed; /* Memory Nodes allowed to tasks */
/*
* Count is atomic so can incr (fork) or decr (exit) without a lock.
*/
atomic_t count; /* count tasks using this cpuset */
/*
* We link our 'sibling' struct into our parents 'children'.
* Our children link their 'sibling' into our 'children'.
*/
struct list_head sibling; /* my parents children */
struct list_head children; /* my children */
struct cpuset *parent; /* my parent */
struct dentry *dentry; /* cpuset fs entry */
/*
* Copy of global cpuset_mems_generation as of the most
* recent time this cpuset changed its mems_allowed.
*/
int mems_generation;
struct fmeter fmeter; /* memory_pressure filter */
};
/* bits in struct cpuset flags field */
typedef enum {
CS_CPU_EXCLUSIVE,
CS_MEM_EXCLUSIVE,
CS_MEMORY_MIGRATE,
CS_REMOVED,
CS_NOTIFY_ON_RELEASE,
CS_SPREAD_PAGE,
CS_SPREAD_SLAB,
} cpuset_flagbits_t;
/* convenient tests for these bits */
static inline int is_cpu_exclusive(const struct cpuset *cs)
{
return test_bit(CS_CPU_EXCLUSIVE, &cs->flags);
}
static inline int is_mem_exclusive(const struct cpuset *cs)
{
return test_bit(CS_MEM_EXCLUSIVE, &cs->flags);
}
static inline int is_removed(const struct cpuset *cs)
{
return test_bit(CS_REMOVED, &cs->flags);
}
static inline int notify_on_release(const struct cpuset *cs)
{
return test_bit(CS_NOTIFY_ON_RELEASE, &cs->flags);
}
static inline int is_memory_migrate(const struct cpuset *cs)
{
return test_bit(CS_MEMORY_MIGRATE, &cs->flags);
}
static inline int is_spread_page(const struct cpuset *cs)
{
return test_bit(CS_SPREAD_PAGE, &cs->flags);
}
static inline int is_spread_slab(const struct cpuset *cs)
{
return test_bit(CS_SPREAD_SLAB, &cs->flags);
}
/*
* Increment this integer everytime any cpuset changes its
* mems_allowed value. Users of cpusets can track this generation
* number, and avoid having to lock and reload mems_allowed unless
* the cpuset they're using changes generation.
*
* A single, global generation is needed because attach_task() could
* reattach a task to a different cpuset, which must not have its
* generation numbers aliased with those of that tasks previous cpuset.
*
* Generations are needed for mems_allowed because one task cannot
* modify anothers memory placement. So we must enable every task,
* on every visit to __alloc_pages(), to efficiently check whether
* its current->cpuset->mems_allowed has changed, requiring an update
* of its current->mems_allowed.
*
* Since cpuset_mems_generation is guarded by manage_mutex,
* there is no need to mark it atomic.
*/
static int cpuset_mems_generation;
static struct cpuset top_cpuset = {
.flags = ((1 << CS_CPU_EXCLUSIVE) | (1 << CS_MEM_EXCLUSIVE)),
.cpus_allowed = CPU_MASK_ALL,
.mems_allowed = NODE_MASK_ALL,
.count = ATOMIC_INIT(0),
.sibling = LIST_HEAD_INIT(top_cpuset.sibling),
.children = LIST_HEAD_INIT(top_cpuset.children),
};
static struct vfsmount *cpuset_mount;
static struct super_block *cpuset_sb;
/*
* We have two global cpuset mutexes below. They can nest.
* It is ok to first take manage_mutex, then nest callback_mutex. We also
* require taking task_lock() when dereferencing a tasks cpuset pointer.
* See "The task_lock() exception", at the end of this comment.
*
* A task must hold both mutexes to modify cpusets. If a task
* holds manage_mutex, then it blocks others wanting that mutex,
* ensuring that it is the only task able to also acquire callback_mutex
* and be able to modify cpusets. It can perform various checks on
* the cpuset structure first, knowing nothing will change. It can
* also allocate memory while just holding manage_mutex. While it is
* performing these checks, various callback routines can briefly
* acquire callback_mutex to query cpusets. Once it is ready to make
* the changes, it takes callback_mutex, blocking everyone else.
*
* Calls to the kernel memory allocator can not be made while holding
* callback_mutex, as that would risk double tripping on callback_mutex
* from one of the callbacks into the cpuset code from within
* __alloc_pages().
*
* If a task is only holding callback_mutex, then it has read-only
* access to cpusets.
*
* The task_struct fields mems_allowed and mems_generation may only
* be accessed in the context of that task, so require no locks.
*
* Any task can increment and decrement the count field without lock.
* So in general, code holding manage_mutex or callback_mutex can't rely
* on the count field not changing. However, if the count goes to
* zero, then only attach_task(), which holds both mutexes, can
* increment it again. Because a count of zero means that no tasks
* are currently attached, therefore there is no way a task attached
* to that cpuset can fork (the other way to increment the count).
* So code holding manage_mutex or callback_mutex can safely assume that
* if the count is zero, it will stay zero. Similarly, if a task
* holds manage_mutex or callback_mutex on a cpuset with zero count, it
* knows that the cpuset won't be removed, as cpuset_rmdir() needs
* both of those mutexes.
*
* The cpuset_common_file_write handler for operations that modify
* the cpuset hierarchy holds manage_mutex across the entire operation,
* single threading all such cpuset modifications across the system.
*
* The cpuset_common_file_read() handlers only hold callback_mutex across
* small pieces of code, such as when reading out possibly multi-word
* cpumasks and nodemasks.
*
* The fork and exit callbacks cpuset_fork() and cpuset_exit(), don't
* (usually) take either mutex. These are the two most performance
* critical pieces of code here. The exception occurs on cpuset_exit(),
* when a task in a notify_on_release cpuset exits. Then manage_mutex
* is taken, and if the cpuset count is zero, a usermode call made
* to /sbin/cpuset_release_agent with the name of the cpuset (path
* relative to the root of cpuset file system) as the argument.
*
* A cpuset can only be deleted if both its 'count' of using tasks
* is zero, and its list of 'children' cpusets is empty. Since all
* tasks in the system use _some_ cpuset, and since there is always at
* least one task in the system (init, pid == 1), therefore, top_cpuset
* always has either children cpusets and/or using tasks. So we don't
* need a special hack to ensure that top_cpuset cannot be deleted.
*
* The above "Tale of Two Semaphores" would be complete, but for:
*
* The task_lock() exception
*
* The need for this exception arises from the action of attach_task(),
* which overwrites one tasks cpuset pointer with another. It does
* so using both mutexes, however there are several performance
* critical places that need to reference task->cpuset without the
* expense of grabbing a system global mutex. Therefore except as
* noted below, when dereferencing or, as in attach_task(), modifying
* a tasks cpuset pointer we use task_lock(), which acts on a spinlock
* (task->alloc_lock) already in the task_struct routinely used for
* such matters.
*
* P.S. One more locking exception. RCU is used to guard the
* update of a tasks cpuset pointer by attach_task() and the
* access of task->cpuset->mems_generation via that pointer in
* the routine cpuset_update_task_memory_state().
*/
static DEFINE_MUTEX(manage_mutex);
static DEFINE_MUTEX(callback_mutex);
/*
* A couple of forward declarations required, due to cyclic reference loop:
* cpuset_mkdir -> cpuset_create -> cpuset_populate_dir -> cpuset_add_file
* -> cpuset_create_file -> cpuset_dir_inode_operations -> cpuset_mkdir.
*/
static int cpuset_mkdir(struct inode *dir, struct dentry *dentry, int mode);
static int cpuset_rmdir(struct inode *unused_dir, struct dentry *dentry);
static struct backing_dev_info cpuset_backing_dev_info = {
.ra_pages = 0, /* No readahead */
.capabilities = BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_WRITEBACK,
};
static struct inode *cpuset_new_inode(mode_t mode)
{
struct inode *inode = new_inode(cpuset_sb);
if (inode) {
inode->i_mode = mode;
inode->i_uid = current->fsuid;
inode->i_gid = current->fsgid;
inode->i_blksize = PAGE_CACHE_SIZE;
inode->i_blocks = 0;
inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
inode->i_mapping->backing_dev_info = &cpuset_backing_dev_info;
}
return inode;
}
static void cpuset_diput(struct dentry *dentry, struct inode *inode)
{
/* is dentry a directory ? if so, kfree() associated cpuset */
if (S_ISDIR(inode->i_mode)) {
struct cpuset *cs = dentry->d_fsdata;
BUG_ON(!(is_removed(cs)));
kfree(cs);
}
iput(inode);
}
static struct dentry_operations cpuset_dops = {
.d_iput = cpuset_diput,
};
static struct dentry *cpuset_get_dentry(struct dentry *parent, const char *name)
{
struct dentry *d = lookup_one_len(name, parent, strlen(name));
if (!IS_ERR(d))
d->d_op = &cpuset_dops;
return d;
}
static void remove_dir(struct dentry *d)
{
struct dentry *parent = dget(d->d_parent);
d_delete(d);
simple_rmdir(parent->d_inode, d);
dput(parent);
}
/*
* NOTE : the dentry must have been dget()'ed
*/
static void cpuset_d_remove_dir(struct dentry *dentry)
{
struct list_head *node;
spin_lock(&dcache_lock);
node = dentry->d_subdirs.next;
while (node != &dentry->d_subdirs) {
struct dentry *d = list_entry(node, struct dentry, d_u.d_child);
list_del_init(node);
if (d->d_inode) {
d = dget_locked(d);
spin_unlock(&dcache_lock);
d_delete(d);
simple_unlink(dentry->d_inode, d);
dput(d);
spin_lock(&dcache_lock);
}
node = dentry->d_subdirs.next;
}
list_del_init(&dentry->d_u.d_child);
spin_unlock(&dcache_lock);
remove_dir(dentry);
}
static struct super_operations cpuset_ops = {
.statfs = simple_statfs,
.drop_inode = generic_delete_inode,
};
static int cpuset_fill_super(struct super_block *sb, void *unused_data,
int unused_silent)
{
struct inode *inode;
struct dentry *root;
sb->s_blocksize = PAGE_CACHE_SIZE;
sb->s_blocksize_bits = PAGE_CACHE_SHIFT;
sb->s_magic = CPUSET_SUPER_MAGIC;
sb->s_op = &cpuset_ops;
cpuset_sb = sb;
inode = cpuset_new_inode(S_IFDIR | S_IRUGO | S_IXUGO | S_IWUSR);
if (inode) {
inode->i_op = &simple_dir_inode_operations;
inode->i_fop = &simple_dir_operations;
/* directories start off with i_nlink == 2 (for "." entry) */
inode->i_nlink++;
} else {
return -ENOMEM;
}
root = d_alloc_root(inode);
if (!root) {
iput(inode);
return -ENOMEM;
}
sb->s_root = root;
return 0;
}
static int cpuset_get_sb(struct file_system_type *fs_type,
int flags, const char *unused_dev_name,
void *data, struct vfsmount *mnt)
{
return get_sb_single(fs_type, flags, data, cpuset_fill_super, mnt);
}
static struct file_system_type cpuset_fs_type = {
.name = "cpuset",
.get_sb = cpuset_get_sb,
.kill_sb = kill_litter_super,
};
/* struct cftype:
*
* The files in the cpuset filesystem mostly have a very simple read/write
* handling, some common function will take care of it. Nevertheless some cases
* (read tasks) are special and therefore I define this structure for every
* kind of file.
*
*
* When reading/writing to a file:
* - the cpuset to use in file->f_dentry->d_parent->d_fsdata
* - the 'cftype' of the file is file->f_dentry->d_fsdata
*/
struct cftype {
char *name;
int private;
int (*open) (struct inode *inode, struct file *file);
ssize_t (*read) (struct file *file, char __user *buf, size_t nbytes,
loff_t *ppos);
int (*write) (struct file *file, const char __user *buf, size_t nbytes,
loff_t *ppos);
int (*release) (struct inode *inode, struct file *file);
};
static inline struct cpuset *__d_cs(struct dentry *dentry)
{
return dentry->d_fsdata;
}
static inline struct cftype *__d_cft(struct dentry *dentry)
{
return dentry->d_fsdata;
}
/*
* Call with manage_mutex held. Writes path of cpuset into buf.
* Returns 0 on success, -errno on error.
*/
static int cpuset_path(const struct cpuset *cs, char *buf, int buflen)
{
char *start;
start = buf + buflen;
*--start = '\0';
for (;;) {
int len = cs->dentry->d_name.len;
if ((start -= len) < buf)
return -ENAMETOOLONG;
memcpy(start, cs->dentry->d_name.name, len);
cs = cs->parent;
if (!cs)
break;
if (!cs->parent)
continue;
if (--start < buf)
return -ENAMETOOLONG;
*start = '/';
}
memmove(buf, start, buf + buflen - start);
return 0;
}
/*
* Notify userspace when a cpuset is released, by running
* /sbin/cpuset_release_agent with the name of the cpuset (path
* relative to the root of cpuset file system) as the argument.
*
* Most likely, this user command will try to rmdir this cpuset.
*
* This races with the possibility that some other task will be
* attached to this cpuset before it is removed, or that some other
* user task will 'mkdir' a child cpuset of this cpuset. That's ok.
* The presumed 'rmdir' will fail quietly if this cpuset is no longer
* unused, and this cpuset will be reprieved from its death sentence,
* to continue to serve a useful existence. Next time it's released,
* we will get notified again, if it still has 'notify_on_release' set.
*
* The final arg to call_usermodehelper() is 0, which means don't
* wait. The separate /sbin/cpuset_release_agent task is forked by
* call_usermodehelper(), then control in this thread returns here,
* without waiting for the release agent task. We don't bother to
* wait because the caller of this routine has no use for the exit
* status of the /sbin/cpuset_release_agent task, so no sense holding
* our caller up for that.
*
* When we had only one cpuset mutex, we had to call this
* without holding it, to avoid deadlock when call_usermodehelper()
* allocated memory. With two locks, we could now call this while
* holding manage_mutex, but we still don't, so as to minimize
* the time manage_mutex is held.
*/
static void cpuset_release_agent(const char *pathbuf)
{
char *argv[3], *envp[3];
int i;
if (!pathbuf)
return;
i = 0;
argv[i++] = "/sbin/cpuset_release_agent";
argv[i++] = (char *)pathbuf;
argv[i] = NULL;
i = 0;
/* minimal command environment */
envp[i++] = "HOME=/";
envp[i++] = "PATH=/sbin:/bin:/usr/sbin:/usr/bin";
envp[i] = NULL;
call_usermodehelper(argv[0], argv, envp, 0);
kfree(pathbuf);
}
/*
* Either cs->count of using tasks transitioned to zero, or the
* cs->children list of child cpusets just became empty. If this
* cs is notify_on_release() and now both the user count is zero and
* the list of children is empty, prepare cpuset path in a kmalloc'd
* buffer, to be returned via ppathbuf, so that the caller can invoke
* cpuset_release_agent() with it later on, once manage_mutex is dropped.
* Call here with manage_mutex held.
*
* This check_for_release() routine is responsible for kmalloc'ing
* pathbuf. The above cpuset_release_agent() is responsible for
* kfree'ing pathbuf. The caller of these routines is responsible
* for providing a pathbuf pointer, initialized to NULL, then
* calling check_for_release() with manage_mutex held and the address
* of the pathbuf pointer, then dropping manage_mutex, then calling
* cpuset_release_agent() with pathbuf, as set by check_for_release().
*/
static void check_for_release(struct cpuset *cs, char **ppathbuf)
{
if (notify_on_release(cs) && atomic_read(&cs->count) == 0 &&
list_empty(&cs->children)) {
char *buf;
buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
if (!buf)
return;
if (cpuset_path(cs, buf, PAGE_SIZE) < 0)
kfree(buf);
else
*ppathbuf = buf;
}
}
/*
* Return in *pmask the portion of a cpusets's cpus_allowed that
* are online. If none are online, walk up the cpuset hierarchy
* until we find one that does have some online cpus. If we get
* all the way to the top and still haven't found any online cpus,
* return cpu_online_map. Or if passed a NULL cs from an exit'ing
* task, return cpu_online_map.
*
* One way or another, we guarantee to return some non-empty subset
* of cpu_online_map.
*
* Call with callback_mutex held.
*/
static void guarantee_online_cpus(const struct cpuset *cs, cpumask_t *pmask)
{
while (cs && !cpus_intersects(cs->cpus_allowed, cpu_online_map))
cs = cs->parent;
if (cs)
cpus_and(*pmask, cs->cpus_allowed, cpu_online_map);
else
*pmask = cpu_online_map;
BUG_ON(!cpus_intersects(*pmask, cpu_online_map));
}
/*
* Return in *pmask the portion of a cpusets's mems_allowed that
* are online. If none are online, walk up the cpuset hierarchy
* until we find one that does have some online mems. If we get
* all the way to the top and still haven't found any online mems,
* return node_online_map.
*
* One way or another, we guarantee to return some non-empty subset
* of node_online_map.
*
* Call with callback_mutex held.
*/
static void guarantee_online_mems(const struct cpuset *cs, nodemask_t *pmask)
{
while (cs && !nodes_intersects(cs->mems_allowed, node_online_map))
cs = cs->parent;
if (cs)
nodes_and(*pmask, cs->mems_allowed, node_online_map);
else
*pmask = node_online_map;
BUG_ON(!nodes_intersects(*pmask, node_online_map));
}
/**
* cpuset_update_task_memory_state - update task memory placement
*
* If the current tasks cpusets mems_allowed changed behind our
* backs, update current->mems_allowed, mems_generation and task NUMA
* mempolicy to the new value.
*
* Task mempolicy is updated by rebinding it relative to the
* current->cpuset if a task has its memory placement changed.
* Do not call this routine if in_interrupt().
*
* Call without callback_mutex or task_lock() held. May be
* called with or without manage_mutex held. Thanks in part to
* 'the_top_cpuset_hack', the tasks cpuset pointer will never
* be NULL. This routine also might acquire callback_mutex and
* current->mm->mmap_sem during call.
*
* Reading current->cpuset->mems_generation doesn't need task_lock
* to guard the current->cpuset derefence, because it is guarded
* from concurrent freeing of current->cpuset by attach_task(),
* using RCU.
*
* The rcu_dereference() is technically probably not needed,
* as I don't actually mind if I see a new cpuset pointer but
* an old value of mems_generation. However this really only
* matters on alpha systems using cpusets heavily. If I dropped
* that rcu_dereference(), it would save them a memory barrier.
* For all other arch's, rcu_dereference is a no-op anyway, and for
* alpha systems not using cpusets, another planned optimization,
* avoiding the rcu critical section for tasks in the root cpuset
* which is statically allocated, so can't vanish, will make this
* irrelevant. Better to use RCU as intended, than to engage in
* some cute trick to save a memory barrier that is impossible to
* test, for alpha systems using cpusets heavily, which might not
* even exist.
*
* This routine is needed to update the per-task mems_allowed data,
* within the tasks context, when it is trying to allocate memory
* (in various mm/mempolicy.c routines) and notices that some other
* task has been modifying its cpuset.
*/
void cpuset_update_task_memory_state(void)
{
int my_cpusets_mem_gen;
struct task_struct *tsk = current;
struct cpuset *cs;
if (tsk->cpuset == &top_cpuset) {
/* Don't need rcu for top_cpuset. It's never freed. */
my_cpusets_mem_gen = top_cpuset.mems_generation;
} else {
rcu_read_lock();
cs = rcu_dereference(tsk->cpuset);
my_cpusets_mem_gen = cs->mems_generation;
rcu_read_unlock();
}
if (my_cpusets_mem_gen != tsk->cpuset_mems_generation) {
mutex_lock(&callback_mutex);
task_lock(tsk);
cs = tsk->cpuset; /* Maybe changed when task not locked */
guarantee_online_mems(cs, &tsk->mems_allowed);
tsk->cpuset_mems_generation = cs->mems_generation;
if (is_spread_page(cs))
tsk->flags |= PF_SPREAD_PAGE;
else
tsk->flags &= ~PF_SPREAD_PAGE;
if (is_spread_slab(cs))
tsk->flags |= PF_SPREAD_SLAB;
else
tsk->flags &= ~PF_SPREAD_SLAB;
task_unlock(tsk);
mutex_unlock(&callback_mutex);
mpol_rebind_task(tsk, &tsk->mems_allowed);
}
}
/*
* is_cpuset_subset(p, q) - Is cpuset p a subset of cpuset q?
*
* One cpuset is a subset of another if all its allowed CPUs and
* Memory Nodes are a subset of the other, and its exclusive flags
* are only set if the other's are set. Call holding manage_mutex.
*/
static int is_cpuset_subset(const struct cpuset *p, const struct cpuset *q)
{
return cpus_subset(p->cpus_allowed, q->cpus_allowed) &&
nodes_subset(p->mems_allowed, q->mems_allowed) &&
is_cpu_exclusive(p) <= is_cpu_exclusive(q) &&
is_mem_exclusive(p) <= is_mem_exclusive(q);
}
/*
* validate_change() - Used to validate that any proposed cpuset change
* follows the structural rules for cpusets.
*
* If we replaced the flag and mask values of the current cpuset
* (cur) with those values in the trial cpuset (trial), would
* our various subset and exclusive rules still be valid? Presumes
* manage_mutex held.
*
* 'cur' is the address of an actual, in-use cpuset. Operations
* such as list traversal that depend on the actual address of the
* cpuset in the list must use cur below, not trial.
*
* 'trial' is the address of bulk structure copy of cur, with
* perhaps one or more of the fields cpus_allowed, mems_allowed,
* or flags changed to new, trial values.
*
* Return 0 if valid, -errno if not.
*/
static int validate_change(const struct cpuset *cur, const struct cpuset *trial)
{
struct cpuset *c, *par;
/* Each of our child cpusets must be a subset of us */
list_for_each_entry(c, &cur->children, sibling) {
if (!is_cpuset_subset(c, trial))
return -EBUSY;
}
/* Remaining checks don't apply to root cpuset */
if ((par = cur->parent) == NULL)
return 0;
/* We must be a subset of our parent cpuset */
if (!is_cpuset_subset(trial, par))
return -EACCES;
/* If either I or some sibling (!= me) is exclusive, we can't overlap */
list_for_each_entry(c, &par->children, sibling) {
if ((is_cpu_exclusive(trial) || is_cpu_exclusive(c)) &&
c != cur &&
cpus_intersects(trial->cpus_allowed, c->cpus_allowed))
return -EINVAL;
if ((is_mem_exclusive(trial) || is_mem_exclusive(c)) &&
c != cur &&
nodes_intersects(trial->mems_allowed, c->mems_allowed))
return -EINVAL;
}
return 0;
}
/*
* For a given cpuset cur, partition the system as follows
* a. All cpus in the parent cpuset's cpus_allowed that are not part of any
* exclusive child cpusets
* b. All cpus in the current cpuset's cpus_allowed that are not part of any
* exclusive child cpusets
* Build these two partitions by calling partition_sched_domains
*
* Call with manage_mutex held. May nest a call to the
* lock_cpu_hotplug()/unlock_cpu_hotplug() pair.
*/
static void update_cpu_domains(struct cpuset *cur)
{
struct cpuset *c, *par = cur->parent;
cpumask_t pspan, cspan;
if (par == NULL || cpus_empty(cur->cpus_allowed))
return;
/*
* Get all cpus from parent's cpus_allowed not part of exclusive
* children
*/
pspan = par->cpus_allowed;
list_for_each_entry(c, &par->children, sibling) {
if (is_cpu_exclusive(c))
cpus_andnot(pspan, pspan, c->cpus_allowed);
}
if (is_removed(cur) || !is_cpu_exclusive(cur)) {
cpus_or(pspan, pspan, cur->cpus_allowed);
if (cpus_equal(pspan, cur->cpus_allowed))
return;
cspan = CPU_MASK_NONE;
} else {
if (cpus_empty(pspan))
return;
cspan = cur->cpus_allowed;
/*
* Get all cpus from current cpuset's cpus_allowed not part
* of exclusive children
*/
list_for_each_entry(c, &cur->children, sibling) {
if (is_cpu_exclusive(c))
cpus_andnot(cspan, cspan, c->cpus_allowed);
}
}
lock_cpu_hotplug();
partition_sched_domains(&pspan, &cspan);
unlock_cpu_hotplug();
}
/*
* Call with manage_mutex held. May take callback_mutex during call.
*/
static int update_cpumask(struct cpuset *cs, char *buf)
{
struct cpuset trialcs;
int retval, cpus_unchanged;
trialcs = *cs;
retval = cpulist_parse(buf, trialcs.cpus_allowed);
if (retval < 0)
return retval;
cpus_and(trialcs.cpus_allowed, trialcs.cpus_allowed, cpu_online_map);
if (cpus_empty(trialcs.cpus_allowed))
return -ENOSPC;
retval = validate_change(cs, &trialcs);
if (retval < 0)
return retval;
cpus_unchanged = cpus_equal(cs->cpus_allowed, trialcs.cpus_allowed);
mutex_lock(&callback_mutex);
cs->cpus_allowed = trialcs.cpus_allowed;
mutex_unlock(&callback_mutex);
if (is_cpu_exclusive(cs) && !cpus_unchanged)
update_cpu_domains(cs);
return 0;
}
/*
* cpuset_migrate_mm
*
* Migrate memory region from one set of nodes to another.
*
* Temporarilly set tasks mems_allowed to target nodes of migration,
* so that the migration code can allocate pages on these nodes.
*
* Call holding manage_mutex, so our current->cpuset won't change
* during this call, as manage_mutex holds off any attach_task()
* calls. Therefore we don't need to take task_lock around the
* call to guarantee_online_mems(), as we know no one is changing
* our tasks cpuset.
*
* Hold callback_mutex around the two modifications of our tasks
* mems_allowed to synchronize with cpuset_mems_allowed().
*
* While the mm_struct we are migrating is typically from some
* other task, the task_struct mems_allowed that we are hacking
* is for our current task, which must allocate new pages for that
* migrating memory region.
*
* We call cpuset_update_task_memory_state() before hacking
* our tasks mems_allowed, so that we are assured of being in
* sync with our tasks cpuset, and in particular, callbacks to
* cpuset_update_task_memory_state() from nested page allocations
* won't see any mismatch of our cpuset and task mems_generation
* values, so won't overwrite our hacked tasks mems_allowed
* nodemask.
*/
static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from,
const nodemask_t *to)
{
struct task_struct *tsk = current;
cpuset_update_task_memory_state();
mutex_lock(&callback_mutex);
tsk->mems_allowed = *to;
mutex_unlock(&callback_mutex);
do_migrate_pages(mm, from, to, MPOL_MF_MOVE_ALL);
mutex_lock(&callback_mutex);
guarantee_online_mems(tsk->cpuset, &tsk->mems_allowed);
mutex_unlock(&callback_mutex);
}
/*
* Handle user request to change the 'mems' memory placement
* of a cpuset. Needs to validate the request, update the
* cpusets mems_allowed and mems_generation, and for each
* task in the cpuset, rebind any vma mempolicies and if
* the cpuset is marked 'memory_migrate', migrate the tasks
* pages to the new memory.
*
* Call with manage_mutex held. May take callback_mutex during call.
* Will take tasklist_lock, scan tasklist for tasks in cpuset cs,
* lock each such tasks mm->mmap_sem, scan its vma's and rebind
* their mempolicies to the cpusets new mems_allowed.
*/
static int update_nodemask(struct cpuset *cs, char *buf)
{
struct cpuset trialcs;
nodemask_t oldmem;
struct task_struct *g, *p;
struct mm_struct **mmarray;
int i, n, ntasks;
int migrate;
int fudge;
int retval;
trialcs = *cs;
retval = nodelist_parse(buf, trialcs.mems_allowed);
if (retval < 0)
goto done;
nodes_and(trialcs.mems_allowed, trialcs.mems_allowed, node_online_map);
oldmem = cs->mems_allowed;
if (nodes_equal(oldmem, trialcs.mems_allowed)) {
retval = 0; /* Too easy - nothing to do */
goto done;
}
if (nodes_empty(trialcs.mems_allowed)) {
retval = -ENOSPC;
goto done;
}
retval = validate_change(cs, &trialcs);
if (retval < 0)
goto done;
mutex_lock(&callback_mutex);
cs->mems_allowed = trialcs.mems_allowed;
cs->mems_generation = cpuset_mems_generation++;
mutex_unlock(&callback_mutex);
set_cpuset_being_rebound(cs); /* causes mpol_copy() rebind */
fudge = 10; /* spare mmarray[] slots */
fudge += cpus_weight(cs->cpus_allowed); /* imagine one fork-bomb/cpu */
retval = -ENOMEM;
/*
* Allocate mmarray[] to hold mm reference for each task
* in cpuset cs. Can't kmalloc GFP_KERNEL while holding
* tasklist_lock. We could use GFP_ATOMIC, but with a
* few more lines of code, we can retry until we get a big
* enough mmarray[] w/o using GFP_ATOMIC.
*/
while (1) {
ntasks = atomic_read(&cs->count); /* guess */
ntasks += fudge;
mmarray = kmalloc(ntasks * sizeof(*mmarray), GFP_KERNEL);
if (!mmarray)
goto done;
write_lock_irq(&tasklist_lock); /* block fork */
if (atomic_read(&cs->count) <= ntasks)
break; /* got enough */
write_unlock_irq(&tasklist_lock); /* try again */
kfree(mmarray);
}
n = 0;
/* Load up mmarray[] with mm reference for each task in cpuset. */
do_each_thread(g, p) {
struct mm_struct *mm;
if (n >= ntasks) {
printk(KERN_WARNING
"Cpuset mempolicy rebind incomplete.\n");
continue;
}
if (p->cpuset != cs)
continue;
mm = get_task_mm(p);
if (!mm)
continue;
mmarray[n++] = mm;
} while_each_thread(g, p);
write_unlock_irq(&tasklist_lock);
/*
* Now that we've dropped the tasklist spinlock, we can
* rebind the vma mempolicies of each mm in mmarray[] to their
* new cpuset, and release that mm. The mpol_rebind_mm()
* call takes mmap_sem, which we couldn't take while holding
* tasklist_lock. Forks can happen again now - the mpol_copy()
* cpuset_being_rebound check will catch such forks, and rebind
* their vma mempolicies too. Because we still hold the global
* cpuset manage_mutex, we know that no other rebind effort will
* be contending for the global variable cpuset_being_rebound.
* It's ok if we rebind the same mm twice; mpol_rebind_mm()
* is idempotent. Also migrate pages in each mm to new nodes.
*/
migrate = is_memory_migrate(cs);
for (i = 0; i < n; i++) {
struct mm_struct *mm = mmarray[i];
mpol_rebind_mm(mm, &cs->mems_allowed);
if (migrate)
cpuset_migrate_mm(mm, &oldmem, &cs->mems_allowed);
mmput(mm);
}