-
Notifications
You must be signed in to change notification settings - Fork 61.4k
Expand file tree
/
Copy pathfork.c
More file actions
3310 lines (2831 loc) · 80.9 KB
/
fork.c
File metadata and controls
3310 lines (2831 loc) · 80.9 KB
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
// SPDX-License-Identifier: GPL-2.0-only
/*
* linux/kernel/fork.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
*/
/*
* 'fork.c' contains the help-routines for the 'fork' system call
* (see also entry.S and others).
* Fork is rather simple, once you get the hang of it, but the memory
* management can be a bitch. See 'mm/memory.c': 'copy_page_range()'
*/
#include <linux/anon_inodes.h>
#include <linux/slab.h>
#include <linux/sched/autogroup.h>
#include <linux/sched/mm.h>
#include <linux/sched/user.h>
#include <linux/sched/numa_balancing.h>
#include <linux/sched/stat.h>
#include <linux/sched/task.h>
#include <linux/sched/task_stack.h>
#include <linux/sched/cputime.h>
#include <linux/sched/ext.h>
#include <linux/seq_file.h>
#include <linux/rtmutex.h>
#include <linux/init.h>
#include <linux/unistd.h>
#include <linux/module.h>
#include <linux/vmalloc.h>
#include <linux/completion.h>
#include <linux/personality.h>
#include <linux/mempolicy.h>
#include <linux/sem.h>
#include <linux/file.h>
#include <linux/fdtable.h>
#include <linux/iocontext.h>
#include <linux/key.h>
#include <linux/kmsan.h>
#include <linux/binfmts.h>
#include <linux/mman.h>
#include <linux/mmu_notifier.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/mm_inline.h>
#include <linux/memblock.h>
#include <linux/nsproxy.h>
#include <linux/capability.h>
#include <linux/cpu.h>
#include <linux/cgroup.h>
#include <linux/security.h>
#include <linux/hugetlb.h>
#include <linux/seccomp.h>
#include <linux/swap.h>
#include <linux/syscalls.h>
#include <linux/syscall_user_dispatch.h>
#include <linux/jiffies.h>
#include <linux/futex.h>
#include <linux/compat.h>
#include <linux/kthread.h>
#include <linux/task_io_accounting_ops.h>
#include <linux/rcupdate.h>
#include <linux/ptrace.h>
#include <linux/mount.h>
#include <linux/audit.h>
#include <linux/memcontrol.h>
#include <linux/ftrace.h>
#include <linux/proc_fs.h>
#include <linux/profile.h>
#include <linux/rmap.h>
#include <linux/ksm.h>
#include <linux/acct.h>
#include <linux/userfaultfd_k.h>
#include <linux/tsacct_kern.h>
#include <linux/cn_proc.h>
#include <linux/freezer.h>
#include <linux/delayacct.h>
#include <linux/taskstats_kern.h>
#include <linux/tty.h>
#include <linux/fs_struct.h>
#include <linux/magic.h>
#include <linux/perf_event.h>
#include <linux/posix-timers.h>
#include <linux/user-return-notifier.h>
#include <linux/oom.h>
#include <linux/khugepaged.h>
#include <linux/signalfd.h>
#include <linux/uprobes.h>
#include <linux/aio.h>
#include <linux/compiler.h>
#include <linux/sysctl.h>
#include <linux/kcov.h>
#include <linux/livepatch.h>
#include <linux/thread_info.h>
#include <linux/kstack_erase.h>
#include <linux/kasan.h>
#include <linux/scs.h>
#include <linux/io_uring.h>
#include <linux/io_uring_types.h>
#include <linux/bpf.h>
#include <linux/stackprotector.h>
#include <linux/user_events.h>
#include <linux/iommu.h>
#include <linux/rseq.h>
#include <uapi/linux/pidfd.h>
#include <linux/pidfs.h>
#include <linux/tick.h>
#include <linux/unwind_deferred.h>
#include <linux/pgalloc.h>
#include <linux/uaccess.h>
#include <asm/mmu_context.h>
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>
/* For dup_mmap(). */
#include "../mm/internal.h"
#include <trace/events/sched.h>
#define CREATE_TRACE_POINTS
#include <trace/events/task.h>
#include <kunit/visibility.h>
/*
* Minimum number of threads to boot the kernel
*/
#define MIN_THREADS 20
/*
* Maximum number of threads
*/
#define MAX_THREADS FUTEX_TID_MASK
/*
* Protected counters by write_lock_irq(&tasklist_lock)
*/
unsigned long total_forks; /* Handle normal Linux uptimes. */
int nr_threads; /* The idle threads do not count.. */
static int max_threads; /* tunable limit on nr_threads */
#define NAMED_ARRAY_INDEX(x) [x] = __stringify(x)
static const char * const resident_page_types[] = {
NAMED_ARRAY_INDEX(MM_FILEPAGES),
NAMED_ARRAY_INDEX(MM_ANONPAGES),
NAMED_ARRAY_INDEX(MM_SWAPENTS),
NAMED_ARRAY_INDEX(MM_SHMEMPAGES),
};
DEFINE_PER_CPU(unsigned long, process_counts) = 0;
__cacheline_aligned DEFINE_RWLOCK(tasklist_lock); /* outer */
#ifdef CONFIG_PROVE_RCU
int lockdep_tasklist_lock_is_held(void)
{
return lockdep_is_held(&tasklist_lock);
}
EXPORT_SYMBOL_GPL(lockdep_tasklist_lock_is_held);
#endif /* #ifdef CONFIG_PROVE_RCU */
int nr_processes(void)
{
int cpu;
int total = 0;
for_each_possible_cpu(cpu)
total += per_cpu(process_counts, cpu);
return total;
}
void __weak arch_release_task_struct(struct task_struct *tsk)
{
}
static struct kmem_cache *task_struct_cachep;
static inline struct task_struct *alloc_task_struct_node(int node)
{
return kmem_cache_alloc_node(task_struct_cachep, GFP_KERNEL, node);
}
static inline void free_task_struct(struct task_struct *tsk)
{
kmem_cache_free(task_struct_cachep, tsk);
}
#ifdef CONFIG_VMAP_STACK
/*
* vmalloc() is a bit slow, and calling vfree() enough times will force a TLB
* flush. Try to minimize the number of calls by caching stacks.
*/
#define NR_CACHED_STACKS 2
static DEFINE_PER_CPU(struct vm_struct *, cached_stacks[NR_CACHED_STACKS]);
/*
* Allocated stacks are cached and later reused by new threads, so memcg
* accounting is performed by the code assigning/releasing stacks to tasks.
* We need a zeroed memory without __GFP_ACCOUNT.
*/
#define GFP_VMAP_STACK (GFP_KERNEL | __GFP_ZERO)
struct vm_stack {
struct rcu_head rcu;
struct vm_struct *stack_vm_area;
};
static struct vm_struct *alloc_thread_stack_node_from_cache(struct task_struct *tsk, int node)
{
struct vm_struct *vm_area;
unsigned int i;
/*
* If the node has memory, we are guaranteed the stacks are backed by local pages.
* Otherwise the pages are arbitrary.
*
* Note that depending on cpuset it is possible we will get migrated to a different
* node immediately after allocating here, so this does *not* guarantee locality for
* arbitrary callers.
*/
scoped_guard(preempt) {
if (node != NUMA_NO_NODE && numa_node_id() != node)
return NULL;
for (i = 0; i < NR_CACHED_STACKS; i++) {
vm_area = this_cpu_xchg(cached_stacks[i], NULL);
if (vm_area)
return vm_area;
}
}
return NULL;
}
static bool try_release_thread_stack_to_cache(struct vm_struct *vm_area)
{
unsigned int i;
int nid;
/*
* Don't cache stacks if any of the pages don't match the local domain, unless
* there is no local memory to begin with.
*
* Note that lack of local memory does not automatically mean it makes no difference
* performance-wise which other domain backs the stack. In this case we are merely
* trying to avoid constantly going to vmalloc.
*/
scoped_guard(preempt) {
nid = numa_node_id();
if (node_state(nid, N_MEMORY)) {
for (i = 0; i < vm_area->nr_pages; i++) {
struct page *page = vm_area->pages[i];
if (page_to_nid(page) != nid)
return false;
}
}
for (i = 0; i < NR_CACHED_STACKS; i++) {
struct vm_struct *tmp = NULL;
if (this_cpu_try_cmpxchg(cached_stacks[i], &tmp, vm_area))
return true;
}
}
return false;
}
static void thread_stack_free_rcu(struct rcu_head *rh)
{
struct vm_stack *vm_stack = container_of(rh, struct vm_stack, rcu);
struct vm_struct *vm_area = vm_stack->stack_vm_area;
if (try_release_thread_stack_to_cache(vm_stack->stack_vm_area))
return;
vfree(vm_area->addr);
}
static void thread_stack_delayed_free(struct task_struct *tsk)
{
struct vm_stack *vm_stack = tsk->stack;
vm_stack->stack_vm_area = tsk->stack_vm_area;
call_rcu(&vm_stack->rcu, thread_stack_free_rcu);
}
static int free_vm_stack_cache(unsigned int cpu)
{
struct vm_struct **cached_vm_stack_areas = per_cpu_ptr(cached_stacks, cpu);
int i;
for (i = 0; i < NR_CACHED_STACKS; i++) {
struct vm_struct *vm_area = cached_vm_stack_areas[i];
if (!vm_area)
continue;
vfree(vm_area->addr);
cached_vm_stack_areas[i] = NULL;
}
return 0;
}
static int memcg_charge_kernel_stack(struct vm_struct *vm_area)
{
int i;
int ret;
int nr_charged = 0;
BUG_ON(vm_area->nr_pages != THREAD_SIZE / PAGE_SIZE);
for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) {
ret = memcg_kmem_charge_page(vm_area->pages[i], GFP_KERNEL, 0);
if (ret)
goto err;
nr_charged++;
}
return 0;
err:
for (i = 0; i < nr_charged; i++)
memcg_kmem_uncharge_page(vm_area->pages[i], 0);
return ret;
}
static int alloc_thread_stack_node(struct task_struct *tsk, int node)
{
struct vm_struct *vm_area;
void *stack;
vm_area = alloc_thread_stack_node_from_cache(tsk, node);
if (vm_area) {
if (memcg_charge_kernel_stack(vm_area)) {
vfree(vm_area->addr);
return -ENOMEM;
}
/* Reset stack metadata. */
kasan_unpoison_range(vm_area->addr, THREAD_SIZE);
stack = kasan_reset_tag(vm_area->addr);
/* Clear stale pointers from reused stack. */
memset(stack, 0, THREAD_SIZE);
tsk->stack_vm_area = vm_area;
tsk->stack = stack;
return 0;
}
stack = __vmalloc_node(THREAD_SIZE, THREAD_ALIGN,
GFP_VMAP_STACK,
node, __builtin_return_address(0));
if (!stack)
return -ENOMEM;
vm_area = find_vm_area(stack);
if (memcg_charge_kernel_stack(vm_area)) {
vfree(stack);
return -ENOMEM;
}
/*
* We can't call find_vm_area() in interrupt context, and
* free_thread_stack() can be called in interrupt context,
* so cache the vm_struct.
*/
tsk->stack_vm_area = vm_area;
stack = kasan_reset_tag(stack);
tsk->stack = stack;
return 0;
}
static void free_thread_stack(struct task_struct *tsk)
{
if (!try_release_thread_stack_to_cache(tsk->stack_vm_area))
thread_stack_delayed_free(tsk);
tsk->stack = NULL;
tsk->stack_vm_area = NULL;
}
#else /* !CONFIG_VMAP_STACK */
/*
* Allocate pages if THREAD_SIZE is >= PAGE_SIZE, otherwise use a
* kmemcache based allocator.
*/
#if THREAD_SIZE >= PAGE_SIZE
static void thread_stack_free_rcu(struct rcu_head *rh)
{
__free_pages(virt_to_page(rh), THREAD_SIZE_ORDER);
}
static void thread_stack_delayed_free(struct task_struct *tsk)
{
struct rcu_head *rh = tsk->stack;
call_rcu(rh, thread_stack_free_rcu);
}
static int alloc_thread_stack_node(struct task_struct *tsk, int node)
{
struct page *page = alloc_pages_node(node, THREADINFO_GFP,
THREAD_SIZE_ORDER);
if (likely(page)) {
tsk->stack = kasan_reset_tag(page_address(page));
return 0;
}
return -ENOMEM;
}
static void free_thread_stack(struct task_struct *tsk)
{
thread_stack_delayed_free(tsk);
tsk->stack = NULL;
}
#else /* !(THREAD_SIZE >= PAGE_SIZE) */
static struct kmem_cache *thread_stack_cache;
static void thread_stack_free_rcu(struct rcu_head *rh)
{
kmem_cache_free(thread_stack_cache, rh);
}
static void thread_stack_delayed_free(struct task_struct *tsk)
{
struct rcu_head *rh = tsk->stack;
call_rcu(rh, thread_stack_free_rcu);
}
static int alloc_thread_stack_node(struct task_struct *tsk, int node)
{
unsigned long *stack;
stack = kmem_cache_alloc_node(thread_stack_cache, THREADINFO_GFP, node);
stack = kasan_reset_tag(stack);
tsk->stack = stack;
return stack ? 0 : -ENOMEM;
}
static void free_thread_stack(struct task_struct *tsk)
{
thread_stack_delayed_free(tsk);
tsk->stack = NULL;
}
void thread_stack_cache_init(void)
{
thread_stack_cache = kmem_cache_create_usercopy("thread_stack",
THREAD_SIZE, THREAD_SIZE, 0, 0,
THREAD_SIZE, NULL);
BUG_ON(thread_stack_cache == NULL);
}
#endif /* THREAD_SIZE >= PAGE_SIZE */
#endif /* CONFIG_VMAP_STACK */
/* SLAB cache for signal_struct structures (tsk->signal) */
static struct kmem_cache *signal_cachep;
/* SLAB cache for sighand_struct structures (tsk->sighand) */
struct kmem_cache *sighand_cachep;
/* SLAB cache for files_struct structures (tsk->files) */
struct kmem_cache *files_cachep;
/* SLAB cache for fs_struct structures (tsk->fs) */
struct kmem_cache *fs_cachep;
/* SLAB cache for mm_struct structures (tsk->mm) */
static struct kmem_cache *mm_cachep;
static void account_kernel_stack(struct task_struct *tsk, int account)
{
if (IS_ENABLED(CONFIG_VMAP_STACK)) {
struct vm_struct *vm_area = task_stack_vm_area(tsk);
int i;
for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++)
mod_lruvec_page_state(vm_area->pages[i], NR_KERNEL_STACK_KB,
account * (PAGE_SIZE / 1024));
} else {
void *stack = task_stack_page(tsk);
/* All stack pages are in the same node. */
mod_lruvec_kmem_state(stack, NR_KERNEL_STACK_KB,
account * (THREAD_SIZE / 1024));
}
}
void exit_task_stack_account(struct task_struct *tsk)
{
account_kernel_stack(tsk, -1);
if (IS_ENABLED(CONFIG_VMAP_STACK)) {
struct vm_struct *vm_area;
int i;
vm_area = task_stack_vm_area(tsk);
for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++)
memcg_kmem_uncharge_page(vm_area->pages[i], 0);
}
}
static void release_task_stack(struct task_struct *tsk)
{
if (WARN_ON(READ_ONCE(tsk->__state) != TASK_DEAD))
return; /* Better to leak the stack than to free prematurely */
free_thread_stack(tsk);
}
#ifdef CONFIG_THREAD_INFO_IN_TASK
void put_task_stack(struct task_struct *tsk)
{
if (refcount_dec_and_test(&tsk->stack_refcount))
release_task_stack(tsk);
}
#endif
void free_task(struct task_struct *tsk)
{
#ifdef CONFIG_SECCOMP
WARN_ON_ONCE(tsk->seccomp.filter);
#endif
release_user_cpus_ptr(tsk);
scs_release(tsk);
#ifndef CONFIG_THREAD_INFO_IN_TASK
/*
* The task is finally done with both the stack and thread_info,
* so free both.
*/
release_task_stack(tsk);
#else
/*
* If the task had a separate stack allocation, it should be gone
* by now.
*/
WARN_ON_ONCE(refcount_read(&tsk->stack_refcount) != 0);
#endif
rt_mutex_debug_task_free(tsk);
ftrace_graph_exit_task(tsk);
arch_release_task_struct(tsk);
if (tsk->flags & PF_KTHREAD)
free_kthread_struct(tsk);
bpf_task_storage_free(tsk);
free_task_struct(tsk);
}
EXPORT_SYMBOL(free_task);
void dup_mm_exe_file(struct mm_struct *mm, struct mm_struct *oldmm)
{
struct file *exe_file;
exe_file = get_mm_exe_file(oldmm);
RCU_INIT_POINTER(mm->exe_file, exe_file);
/*
* We depend on the oldmm having properly denied write access to the
* exe_file already.
*/
if (exe_file && exe_file_deny_write_access(exe_file))
pr_warn_once("exe_file_deny_write_access() failed in %s\n", __func__);
}
#ifdef CONFIG_MMU
static inline int mm_alloc_pgd(struct mm_struct *mm)
{
mm->pgd = pgd_alloc(mm);
if (unlikely(!mm->pgd))
return -ENOMEM;
return 0;
}
static inline void mm_free_pgd(struct mm_struct *mm)
{
pgd_free(mm, mm->pgd);
}
#else
#define mm_alloc_pgd(mm) (0)
#define mm_free_pgd(mm)
#endif /* CONFIG_MMU */
#ifdef CONFIG_MM_ID
static DEFINE_IDA(mm_ida);
static inline int mm_alloc_id(struct mm_struct *mm)
{
int ret;
ret = ida_alloc_range(&mm_ida, MM_ID_MIN, MM_ID_MAX, GFP_KERNEL);
if (ret < 0)
return ret;
mm->mm_id = ret;
return 0;
}
static inline void mm_free_id(struct mm_struct *mm)
{
const mm_id_t id = mm->mm_id;
mm->mm_id = MM_ID_DUMMY;
if (id == MM_ID_DUMMY)
return;
if (WARN_ON_ONCE(id < MM_ID_MIN || id > MM_ID_MAX))
return;
ida_free(&mm_ida, id);
}
#else /* !CONFIG_MM_ID */
static inline int mm_alloc_id(struct mm_struct *mm) { return 0; }
static inline void mm_free_id(struct mm_struct *mm) {}
#endif /* CONFIG_MM_ID */
static void check_mm(struct mm_struct *mm)
{
int i;
BUILD_BUG_ON_MSG(ARRAY_SIZE(resident_page_types) != NR_MM_COUNTERS,
"Please make sure 'struct resident_page_types[]' is updated as well");
for (i = 0; i < NR_MM_COUNTERS; i++) {
long x = percpu_counter_sum(&mm->rss_stat[i]);
if (unlikely(x)) {
pr_alert("BUG: Bad rss-counter state mm:%p type:%s val:%ld Comm:%s Pid:%d\n",
mm, resident_page_types[i], x,
current->comm,
task_pid_nr(current));
}
}
if (mm_pgtables_bytes(mm))
pr_alert("BUG: non-zero pgtables_bytes on freeing mm: %ld\n",
mm_pgtables_bytes(mm));
#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !defined(CONFIG_SPLIT_PMD_PTLOCKS)
VM_BUG_ON_MM(mm->pmd_huge_pte, mm);
#endif
}
#define allocate_mm() (kmem_cache_alloc(mm_cachep, GFP_KERNEL))
#define free_mm(mm) (kmem_cache_free(mm_cachep, (mm)))
static void do_check_lazy_tlb(void *arg)
{
struct mm_struct *mm = arg;
WARN_ON_ONCE(current->active_mm == mm);
}
static void do_shoot_lazy_tlb(void *arg)
{
struct mm_struct *mm = arg;
if (current->active_mm == mm) {
WARN_ON_ONCE(current->mm);
current->active_mm = &init_mm;
switch_mm(mm, &init_mm, current);
}
}
static void cleanup_lazy_tlbs(struct mm_struct *mm)
{
if (!IS_ENABLED(CONFIG_MMU_LAZY_TLB_SHOOTDOWN)) {
/*
* In this case, lazy tlb mms are refounted and would not reach
* __mmdrop until all CPUs have switched away and mmdrop()ed.
*/
return;
}
/*
* Lazy mm shootdown does not refcount "lazy tlb mm" usage, rather it
* requires lazy mm users to switch to another mm when the refcount
* drops to zero, before the mm is freed. This requires IPIs here to
* switch kernel threads to init_mm.
*
* archs that use IPIs to flush TLBs can piggy-back that lazy tlb mm
* switch with the final userspace teardown TLB flush which leaves the
* mm lazy on this CPU but no others, reducing the need for additional
* IPIs here. There are cases where a final IPI is still required here,
* such as the final mmdrop being performed on a different CPU than the
* one exiting, or kernel threads using the mm when userspace exits.
*
* IPI overheads have not found to be expensive, but they could be
* reduced in a number of possible ways, for example (roughly
* increasing order of complexity):
* - The last lazy reference created by exit_mm() could instead switch
* to init_mm, however it's probable this will run on the same CPU
* immediately afterwards, so this may not reduce IPIs much.
* - A batch of mms requiring IPIs could be gathered and freed at once.
* - CPUs store active_mm where it can be remotely checked without a
* lock, to filter out false-positives in the cpumask.
* - After mm_users or mm_count reaches zero, switching away from the
* mm could clear mm_cpumask to reduce some IPIs, perhaps together
* with some batching or delaying of the final IPIs.
* - A delayed freeing and RCU-like quiescing sequence based on mm
* switching to avoid IPIs completely.
*/
on_each_cpu_mask(mm_cpumask(mm), do_shoot_lazy_tlb, (void *)mm, 1);
if (IS_ENABLED(CONFIG_DEBUG_VM_SHOOT_LAZIES))
on_each_cpu(do_check_lazy_tlb, (void *)mm, 1);
}
/*
* Called when the last reference to the mm
* is dropped: either by a lazy thread or by
* mmput. Free the page directory and the mm.
*/
void __mmdrop(struct mm_struct *mm)
{
BUG_ON(mm == &init_mm);
WARN_ON_ONCE(mm == current->mm);
/* Ensure no CPUs are using this as their lazy tlb mm */
cleanup_lazy_tlbs(mm);
WARN_ON_ONCE(mm == current->active_mm);
mm_free_pgd(mm);
mm_free_id(mm);
destroy_context(mm);
mmu_notifier_subscriptions_destroy(mm);
check_mm(mm);
put_user_ns(mm->user_ns);
mm_pasid_drop(mm);
mm_destroy_cid(mm);
percpu_counter_destroy_many(mm->rss_stat, NR_MM_COUNTERS);
free_mm(mm);
}
EXPORT_SYMBOL_GPL(__mmdrop);
static void mmdrop_async_fn(struct work_struct *work)
{
struct mm_struct *mm;
mm = container_of(work, struct mm_struct, async_put_work);
__mmdrop(mm);
}
static void mmdrop_async(struct mm_struct *mm)
{
if (unlikely(atomic_dec_and_test(&mm->mm_count))) {
INIT_WORK(&mm->async_put_work, mmdrop_async_fn);
schedule_work(&mm->async_put_work);
}
}
static inline void free_signal_struct(struct signal_struct *sig)
{
taskstats_tgid_free(sig);
sched_autogroup_exit(sig);
/*
* __mmdrop is not safe to call from softirq context on x86 due to
* pgd_dtor so postpone it to the async context
*/
if (sig->oom_mm)
mmdrop_async(sig->oom_mm);
kmem_cache_free(signal_cachep, sig);
}
static inline void put_signal_struct(struct signal_struct *sig)
{
if (refcount_dec_and_test(&sig->sigcnt))
free_signal_struct(sig);
}
void __put_task_struct(struct task_struct *tsk)
{
WARN_ON(!tsk->exit_state);
WARN_ON(refcount_read(&tsk->usage));
WARN_ON(tsk == current);
unwind_task_free(tsk);
io_uring_free(tsk);
cgroup_task_free(tsk);
task_numa_free(tsk, true);
security_task_free(tsk);
exit_creds(tsk);
delayacct_tsk_free(tsk);
put_signal_struct(tsk->signal);
sched_core_free(tsk);
free_task(tsk);
}
EXPORT_SYMBOL_GPL(__put_task_struct);
void __put_task_struct_rcu_cb(struct rcu_head *rhp)
{
struct task_struct *task = container_of(rhp, struct task_struct, rcu);
__put_task_struct(task);
}
EXPORT_SYMBOL_GPL(__put_task_struct_rcu_cb);
void __init __weak arch_task_cache_init(void) { }
/*
* set_max_threads
*/
static void __init set_max_threads(unsigned int max_threads_suggested)
{
u64 threads;
unsigned long nr_pages = memblock_estimated_nr_free_pages();
/*
* The number of threads shall be limited such that the thread
* structures may only consume a small part of the available memory.
*/
if (fls64(nr_pages) + fls64(PAGE_SIZE) > 64)
threads = MAX_THREADS;
else
threads = div64_u64((u64) nr_pages * (u64) PAGE_SIZE,
(u64) THREAD_SIZE * 8UL);
if (threads > max_threads_suggested)
threads = max_threads_suggested;
max_threads = clamp_t(u64, threads, MIN_THREADS, MAX_THREADS);
}
#ifdef CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT
/* Initialized by the architecture: */
int arch_task_struct_size __read_mostly;
#endif
static void __init task_struct_whitelist(unsigned long *offset, unsigned long *size)
{
/* Fetch thread_struct whitelist for the architecture. */
arch_thread_struct_whitelist(offset, size);
/*
* Handle zero-sized whitelist or empty thread_struct, otherwise
* adjust offset to position of thread_struct in task_struct.
*/
if (unlikely(*size == 0))
*offset = 0;
else
*offset += offsetof(struct task_struct, thread);
}
void __init fork_init(void)
{
int i;
#ifndef ARCH_MIN_TASKALIGN
#define ARCH_MIN_TASKALIGN 0
#endif
int align = max_t(int, L1_CACHE_BYTES, ARCH_MIN_TASKALIGN);
unsigned long useroffset, usersize;
/* create a slab on which task_structs can be allocated */
task_struct_whitelist(&useroffset, &usersize);
task_struct_cachep = kmem_cache_create_usercopy("task_struct",
arch_task_struct_size, align,
SLAB_PANIC|SLAB_ACCOUNT,
useroffset, usersize, NULL);
/* do the arch specific task caches init */
arch_task_cache_init();
set_max_threads(MAX_THREADS);
init_task.signal->rlim[RLIMIT_NPROC].rlim_cur = max_threads/2;
init_task.signal->rlim[RLIMIT_NPROC].rlim_max = max_threads/2;
init_task.signal->rlim[RLIMIT_SIGPENDING] =
init_task.signal->rlim[RLIMIT_NPROC];
for (i = 0; i < UCOUNT_COUNTS; i++)
init_user_ns.ucount_max[i] = max_threads/2;
set_userns_rlimit_max(&init_user_ns, UCOUNT_RLIMIT_NPROC, RLIM_INFINITY);
set_userns_rlimit_max(&init_user_ns, UCOUNT_RLIMIT_MSGQUEUE, RLIM_INFINITY);
set_userns_rlimit_max(&init_user_ns, UCOUNT_RLIMIT_SIGPENDING, RLIM_INFINITY);
set_userns_rlimit_max(&init_user_ns, UCOUNT_RLIMIT_MEMLOCK, RLIM_INFINITY);
#ifdef CONFIG_VMAP_STACK
cpuhp_setup_state(CPUHP_BP_PREPARE_DYN, "fork:vm_stack_cache",
NULL, free_vm_stack_cache);
#endif
scs_init();
lockdep_init_task(&init_task);
uprobes_init();
}
int __weak arch_dup_task_struct(struct task_struct *dst,
struct task_struct *src)
{
*dst = *src;
return 0;
}
void set_task_stack_end_magic(struct task_struct *tsk)
{
unsigned long *stackend;
stackend = end_of_stack(tsk);
*stackend = STACK_END_MAGIC; /* for overflow detection */
}
static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
{
struct task_struct *tsk;
int err;
if (node == NUMA_NO_NODE)
node = tsk_fork_get_node(orig);
tsk = alloc_task_struct_node(node);
if (!tsk)
return NULL;
err = arch_dup_task_struct(tsk, orig);
if (err)
goto free_tsk;
err = alloc_thread_stack_node(tsk, node);
if (err)
goto free_tsk;
#ifdef CONFIG_THREAD_INFO_IN_TASK
refcount_set(&tsk->stack_refcount, 1);
#endif
account_kernel_stack(tsk, 1);
err = scs_prepare(tsk, node);
if (err)
goto free_stack;
#ifdef CONFIG_SECCOMP
/*
* We must handle setting up seccomp filters once we're under
* the sighand lock in case orig has changed between now and
* then. Until then, filter must be NULL to avoid messing up
* the usage counts on the error path calling free_task.
*/
tsk->seccomp.filter = NULL;
#endif
setup_thread_stack(tsk, orig);
clear_user_return_notifier(tsk);
clear_tsk_need_resched(tsk);
set_task_stack_end_magic(tsk);
clear_syscall_work_syscall_user_dispatch(tsk);
#ifdef CONFIG_STACKPROTECTOR
tsk->stack_canary = get_random_canary();
#endif
if (orig->cpus_ptr == &orig->cpus_mask)
tsk->cpus_ptr = &tsk->cpus_mask;
dup_user_cpus_ptr(tsk, orig, node);
/*
* One for the user space visible state that goes away when reaped.
* One for the scheduler.
*/
refcount_set(&tsk->rcu_users, 2);
/* One for the rcu users */
refcount_set(&tsk->usage, 1);
#ifdef CONFIG_BLK_DEV_IO_TRACE
tsk->btrace_seq = 0;
#endif
tsk->splice_pipe = NULL;
tsk->task_frag.page = NULL;
tsk->wake_q.next = NULL;
tsk->worker_private = NULL;
kcov_task_init(tsk);
kmsan_task_create(tsk);
kmap_local_fork(tsk);
#ifdef CONFIG_FAULT_INJECTION
tsk->fail_nth = 0;
#endif
#ifdef CONFIG_BLK_CGROUP
tsk->throttle_disk = NULL;
tsk->use_memdelay = 0;
#endif
#ifdef CONFIG_ARCH_HAS_CPU_PASID
tsk->pasid_activated = 0;
#endif
#ifdef CONFIG_MEMCG
tsk->active_memcg = NULL;
#endif
#ifdef CONFIG_X86_BUS_LOCK_DETECT
tsk->reported_split_lock = 0;
#endif
#ifdef CONFIG_SCHED_MM_CID