Blame view
kernel/fork.c
41.3 KB
1da177e4c
|
1 2 3 4 5 6 7 8 9 10 11 12 |
/* * 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()' */ |
1da177e4c
|
13 14 15 |
#include <linux/slab.h> #include <linux/init.h> #include <linux/unistd.h> |
1da177e4c
|
16 17 18 |
#include <linux/module.h> #include <linux/vmalloc.h> #include <linux/completion.h> |
1da177e4c
|
19 20 21 22 |
#include <linux/personality.h> #include <linux/mempolicy.h> #include <linux/sem.h> #include <linux/file.h> |
9f3acc314
|
23 |
#include <linux/fdtable.h> |
da9cbc873
|
24 |
#include <linux/iocontext.h> |
1da177e4c
|
25 26 27 |
#include <linux/key.h> #include <linux/binfmts.h> #include <linux/mman.h> |
cddb8a5c1
|
28 |
#include <linux/mmu_notifier.h> |
1da177e4c
|
29 |
#include <linux/fs.h> |
ab516013a
|
30 |
#include <linux/nsproxy.h> |
c59ede7b7
|
31 |
#include <linux/capability.h> |
1da177e4c
|
32 |
#include <linux/cpu.h> |
b4f48b636
|
33 |
#include <linux/cgroup.h> |
1da177e4c
|
34 |
#include <linux/security.h> |
a1e78772d
|
35 |
#include <linux/hugetlb.h> |
1da177e4c
|
36 37 38 |
#include <linux/swap.h> #include <linux/syscalls.h> #include <linux/jiffies.h> |
09a05394f
|
39 |
#include <linux/tracehook.h> |
1da177e4c
|
40 |
#include <linux/futex.h> |
8141c7f3e
|
41 |
#include <linux/compat.h> |
7c3ab7381
|
42 |
#include <linux/task_io_accounting_ops.h> |
ab2af1f50
|
43 |
#include <linux/rcupdate.h> |
1da177e4c
|
44 45 46 |
#include <linux/ptrace.h> #include <linux/mount.h> #include <linux/audit.h> |
78fb74669
|
47 |
#include <linux/memcontrol.h> |
f201ae235
|
48 |
#include <linux/ftrace.h> |
1da177e4c
|
49 50 |
#include <linux/profile.h> #include <linux/rmap.h> |
f8af4da3b
|
51 |
#include <linux/ksm.h> |
1da177e4c
|
52 |
#include <linux/acct.h> |
8f0ab5147
|
53 |
#include <linux/tsacct_kern.h> |
9f46080c4
|
54 |
#include <linux/cn_proc.h> |
ba96a0c88
|
55 |
#include <linux/freezer.h> |
ca74e92b4
|
56 |
#include <linux/delayacct.h> |
ad4ecbcba
|
57 |
#include <linux/taskstats_kern.h> |
0a4254058
|
58 |
#include <linux/random.h> |
522ed7767
|
59 |
#include <linux/tty.h> |
6f4e64335
|
60 |
#include <linux/proc_fs.h> |
fd0928df9
|
61 |
#include <linux/blkdev.h> |
5ad4e53bd
|
62 |
#include <linux/fs_struct.h> |
7c9f8861e
|
63 |
#include <linux/magic.h> |
cdd6c482c
|
64 |
#include <linux/perf_event.h> |
42c4ab41a
|
65 |
#include <linux/posix-timers.h> |
8e7cac798
|
66 |
#include <linux/user-return-notifier.h> |
1da177e4c
|
67 68 69 70 71 72 73 |
#include <asm/pgtable.h> #include <asm/pgalloc.h> #include <asm/uaccess.h> #include <asm/mmu_context.h> #include <asm/cacheflush.h> #include <asm/tlbflush.h> |
ad8d75fff
|
74 |
#include <trace/events/sched.h> |
1da177e4c
|
75 76 77 78 79 80 81 82 83 |
/* * 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.. */ int max_threads; /* tunable limit on nr_threads */ DEFINE_PER_CPU(unsigned long, process_counts) = 0; |
c59923a15
|
84 |
__cacheline_aligned DEFINE_RWLOCK(tasklist_lock); /* outer */ |
db1466b3e
|
85 86 87 88 89 90 91 92 |
#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 */ |
1da177e4c
|
93 94 95 96 97 |
int nr_processes(void) { int cpu; int total = 0; |
1d5107509
|
98 |
for_each_possible_cpu(cpu) |
1da177e4c
|
99 100 101 102 103 104 105 106 |
total += per_cpu(process_counts, cpu); return total; } #ifndef __HAVE_ARCH_TASK_STRUCT_ALLOCATOR # define alloc_task_struct() kmem_cache_alloc(task_struct_cachep, GFP_KERNEL) # define free_task_struct(tsk) kmem_cache_free(task_struct_cachep, (tsk)) |
e18b890bb
|
107 |
static struct kmem_cache *task_struct_cachep; |
1da177e4c
|
108 |
#endif |
b69c49b78
|
109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 |
#ifndef __HAVE_ARCH_THREAD_INFO_ALLOCATOR static inline struct thread_info *alloc_thread_info(struct task_struct *tsk) { #ifdef CONFIG_DEBUG_STACK_USAGE gfp_t mask = GFP_KERNEL | __GFP_ZERO; #else gfp_t mask = GFP_KERNEL; #endif return (struct thread_info *)__get_free_pages(mask, THREAD_SIZE_ORDER); } static inline void free_thread_info(struct thread_info *ti) { free_pages((unsigned long)ti, THREAD_SIZE_ORDER); } #endif |
1da177e4c
|
125 |
/* SLAB cache for signal_struct structures (tsk->signal) */ |
e18b890bb
|
126 |
static struct kmem_cache *signal_cachep; |
1da177e4c
|
127 128 |
/* SLAB cache for sighand_struct structures (tsk->sighand) */ |
e18b890bb
|
129 |
struct kmem_cache *sighand_cachep; |
1da177e4c
|
130 131 |
/* SLAB cache for files_struct structures (tsk->files) */ |
e18b890bb
|
132 |
struct kmem_cache *files_cachep; |
1da177e4c
|
133 134 |
/* SLAB cache for fs_struct structures (tsk->fs) */ |
e18b890bb
|
135 |
struct kmem_cache *fs_cachep; |
1da177e4c
|
136 137 |
/* SLAB cache for vm_area_struct structures */ |
e18b890bb
|
138 |
struct kmem_cache *vm_area_cachep; |
1da177e4c
|
139 140 |
/* SLAB cache for mm_struct structures (tsk->mm) */ |
e18b890bb
|
141 |
static struct kmem_cache *mm_cachep; |
1da177e4c
|
142 |
|
c6a7f5728
|
143 144 145 146 147 148 |
static void account_kernel_stack(struct thread_info *ti, int account) { struct zone *zone = page_zone(virt_to_page(ti)); mod_zone_page_state(zone, NR_KERNEL_STACK, account); } |
1da177e4c
|
149 150 |
void free_task(struct task_struct *tsk) { |
3e26c149c
|
151 |
prop_local_destroy_single(&tsk->dirties); |
c6a7f5728
|
152 |
account_kernel_stack(tsk->stack, -1); |
f7e4217b0
|
153 |
free_thread_info(tsk->stack); |
23f78d4a0
|
154 |
rt_mutex_debug_task_free(tsk); |
fb52607af
|
155 |
ftrace_graph_exit_task(tsk); |
1da177e4c
|
156 157 158 |
free_task_struct(tsk); } EXPORT_SYMBOL(free_task); |
158d9ebd1
|
159 |
void __put_task_struct(struct task_struct *tsk) |
1da177e4c
|
160 |
{ |
270f722d4
|
161 |
WARN_ON(!tsk->exit_state); |
1da177e4c
|
162 163 |
WARN_ON(atomic_read(&tsk->usage)); WARN_ON(tsk == current); |
e0e817392
|
164 |
exit_creds(tsk); |
35df17c57
|
165 |
delayacct_tsk_free(tsk); |
1da177e4c
|
166 167 168 169 |
if (!profile_handoff_task(tsk)) free_task(tsk); } |
2adee9b30
|
170 171 172 173 174 175 176 |
/* * macro override instead of weak attribute alias, to workaround * gcc 4.1.0 and 4.1.1 bugs with weak attribute and empty functions. */ #ifndef arch_task_cache_init #define arch_task_cache_init() #endif |
61c4628b5
|
177 |
|
1da177e4c
|
178 179 180 181 182 183 184 185 186 |
void __init fork_init(unsigned long mempages) { #ifndef __HAVE_ARCH_TASK_STRUCT_ALLOCATOR #ifndef ARCH_MIN_TASKALIGN #define ARCH_MIN_TASKALIGN L1_CACHE_BYTES #endif /* create a slab on which task_structs can be allocated */ task_struct_cachep = kmem_cache_create("task_struct", sizeof(struct task_struct), |
2dff44052
|
187 |
ARCH_MIN_TASKALIGN, SLAB_PANIC | SLAB_NOTRACK, NULL); |
1da177e4c
|
188 |
#endif |
61c4628b5
|
189 190 |
/* do the arch specific task caches init */ arch_task_cache_init(); |
1da177e4c
|
191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 |
/* * The default maximum number of threads is set to a safe * value: the thread structures can take up at most half * of memory. */ max_threads = mempages / (8 * THREAD_SIZE / PAGE_SIZE); /* * we need to allow at least 20 threads to boot a system */ if(max_threads < 20) max_threads = 20; 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]; } |
61c4628b5
|
209 210 211 212 213 214 |
int __attribute__((weak)) arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) { *dst = *src; return 0; } |
1da177e4c
|
215 216 217 218 |
static struct task_struct *dup_task_struct(struct task_struct *orig) { struct task_struct *tsk; struct thread_info *ti; |
7c9f8861e
|
219 |
unsigned long *stackend; |
3e26c149c
|
220 |
int err; |
1da177e4c
|
221 222 223 224 225 226 227 228 229 230 231 232 |
prepare_to_copy(orig); tsk = alloc_task_struct(); if (!tsk) return NULL; ti = alloc_thread_info(tsk); if (!ti) { free_task_struct(tsk); return NULL; } |
61c4628b5
|
233 234 235 |
err = arch_dup_task_struct(tsk, orig); if (err) goto out; |
f7e4217b0
|
236 |
tsk->stack = ti; |
3e26c149c
|
237 238 |
err = prop_local_init_single(&tsk->dirties); |
61c4628b5
|
239 240 |
if (err) goto out; |
3e26c149c
|
241 |
|
10ebffde3
|
242 |
setup_thread_stack(tsk, orig); |
8e7cac798
|
243 |
clear_user_return_notifier(tsk); |
7c9f8861e
|
244 245 |
stackend = end_of_stack(tsk); *stackend = STACK_END_MAGIC; /* for overflow detection */ |
1da177e4c
|
246 |
|
0a4254058
|
247 248 249 |
#ifdef CONFIG_CC_STACKPROTECTOR tsk->stack_canary = get_random_int(); #endif |
1da177e4c
|
250 251 |
/* One for us, one for whoever does the "release_task()" (usually parent) */ atomic_set(&tsk->usage,2); |
4b5d37ac0
|
252 |
atomic_set(&tsk->fs_excl, 0); |
6c5c93415
|
253 |
#ifdef CONFIG_BLK_DEV_IO_TRACE |
2056a782f
|
254 |
tsk->btrace_seq = 0; |
6c5c93415
|
255 |
#endif |
a0aa7f68a
|
256 |
tsk->splice_pipe = NULL; |
c6a7f5728
|
257 258 |
account_kernel_stack(ti, 1); |
1da177e4c
|
259 |
return tsk; |
61c4628b5
|
260 261 262 263 264 |
out: free_thread_info(ti); free_task_struct(tsk); return NULL; |
1da177e4c
|
265 266 267 |
} #ifdef CONFIG_MMU |
a39bc5169
|
268 |
static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) |
1da177e4c
|
269 |
{ |
fd3e42fcc
|
270 |
struct vm_area_struct *mpnt, *tmp, **pprev; |
1da177e4c
|
271 272 273 274 275 276 |
struct rb_node **rb_link, *rb_parent; int retval; unsigned long charge; struct mempolicy *pol; down_write(&oldmm->mmap_sem); |
ec8c0446b
|
277 |
flush_cache_dup_mm(oldmm); |
ad3394517
|
278 279 280 281 |
/* * Not linked in yet - no deadlock potential: */ down_write_nested(&mm->mmap_sem, SINGLE_DEPTH_NESTING); |
7ee782325
|
282 |
|
1da177e4c
|
283 284 285 286 |
mm->locked_vm = 0; mm->mmap = NULL; mm->mmap_cache = NULL; mm->free_area_cache = oldmm->mmap_base; |
1363c3cd8
|
287 |
mm->cached_hole_size = ~0UL; |
1da177e4c
|
288 |
mm->map_count = 0; |
948942445
|
289 |
cpumask_clear(mm_cpumask(mm)); |
1da177e4c
|
290 291 292 293 |
mm->mm_rb = RB_ROOT; rb_link = &mm->mm_rb.rb_node; rb_parent = NULL; pprev = &mm->mmap; |
f8af4da3b
|
294 295 296 |
retval = ksm_fork(mm, oldmm); if (retval) goto out; |
1da177e4c
|
297 |
|
fd3e42fcc
|
298 |
for (mpnt = oldmm->mmap; mpnt; mpnt = mpnt->vm_next) { |
1da177e4c
|
299 300 301 |
struct file *file; if (mpnt->vm_flags & VM_DONTCOPY) { |
3b6bfcdb1
|
302 303 |
long pages = vma_pages(mpnt); mm->total_vm -= pages; |
ab50b8ed8
|
304 |
vm_stat_account(mm, mpnt->vm_flags, mpnt->vm_file, |
3b6bfcdb1
|
305 |
-pages); |
1da177e4c
|
306 307 308 309 310 311 312 313 314 |
continue; } charge = 0; if (mpnt->vm_flags & VM_ACCOUNT) { unsigned int len = (mpnt->vm_end - mpnt->vm_start) >> PAGE_SHIFT; if (security_vm_enough_memory(len)) goto fail_nomem; charge = len; } |
e94b17660
|
315 |
tmp = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); |
1da177e4c
|
316 317 318 |
if (!tmp) goto fail_nomem; *tmp = *mpnt; |
5beb49305
|
319 |
INIT_LIST_HEAD(&tmp->anon_vma_chain); |
846a16bf0
|
320 |
pol = mpol_dup(vma_policy(mpnt)); |
1da177e4c
|
321 322 323 324 |
retval = PTR_ERR(pol); if (IS_ERR(pol)) goto fail_nomem_policy; vma_set_policy(tmp, pol); |
5beb49305
|
325 326 |
if (anon_vma_fork(tmp, mpnt)) goto fail_nomem_anon_vma_fork; |
1da177e4c
|
327 328 329 |
tmp->vm_flags &= ~VM_LOCKED; tmp->vm_mm = mm; tmp->vm_next = NULL; |
1da177e4c
|
330 331 |
file = tmp->vm_file; if (file) { |
f3a43f3f6
|
332 |
struct inode *inode = file->f_path.dentry->d_inode; |
b88ed2059
|
333 |
struct address_space *mapping = file->f_mapping; |
1da177e4c
|
334 335 336 |
get_file(file); if (tmp->vm_flags & VM_DENYWRITE) atomic_dec(&inode->i_writecount); |
b88ed2059
|
337 338 339 |
spin_lock(&mapping->i_mmap_lock); if (tmp->vm_flags & VM_SHARED) mapping->i_mmap_writable++; |
1da177e4c
|
340 |
tmp->vm_truncate_count = mpnt->vm_truncate_count; |
b88ed2059
|
341 342 |
flush_dcache_mmap_lock(mapping); /* insert tmp into the share list, just after mpnt */ |
1da177e4c
|
343 |
vma_prio_tree_add(tmp, mpnt); |
b88ed2059
|
344 345 |
flush_dcache_mmap_unlock(mapping); spin_unlock(&mapping->i_mmap_lock); |
1da177e4c
|
346 347 348 |
} /* |
a1e78772d
|
349 350 351 352 353 354 355 356 |
* Clear hugetlb-related page reserves for children. This only * affects MAP_PRIVATE mappings. Faults generated by the child * are not guaranteed to succeed, even if read-only */ if (is_vm_hugetlb_page(tmp)) reset_vma_resv_huge_pages(tmp); /* |
7ee782325
|
357 |
* Link in the new vma and copy the page table entries. |
1da177e4c
|
358 |
*/ |
1da177e4c
|
359 360 361 362 363 364 365 366 |
*pprev = tmp; pprev = &tmp->vm_next; __vma_link_rb(mm, tmp, rb_link, rb_parent); rb_link = &tmp->vm_rb.rb_right; rb_parent = &tmp->vm_rb; mm->map_count++; |
0b0db14c5
|
367 |
retval = copy_page_range(mm, oldmm, mpnt); |
1da177e4c
|
368 369 370 371 372 373 374 |
if (tmp->vm_ops && tmp->vm_ops->open) tmp->vm_ops->open(tmp); if (retval) goto out; } |
d6dd61c83
|
375 376 |
/* a new mm has just been created */ arch_dup_mmap(oldmm, mm); |
1da177e4c
|
377 |
retval = 0; |
1da177e4c
|
378 |
out: |
7ee782325
|
379 |
up_write(&mm->mmap_sem); |
fd3e42fcc
|
380 |
flush_tlb_mm(oldmm); |
1da177e4c
|
381 382 |
up_write(&oldmm->mmap_sem); return retval; |
5beb49305
|
383 384 |
fail_nomem_anon_vma_fork: mpol_put(pol); |
1da177e4c
|
385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 |
fail_nomem_policy: kmem_cache_free(vm_area_cachep, tmp); fail_nomem: retval = -ENOMEM; vm_unacct_memory(charge); goto out; } 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) { |
5e5419734
|
403 |
pgd_free(mm, mm->pgd); |
1da177e4c
|
404 405 406 407 408 409 |
} #else #define dup_mmap(mm, oldmm) (0) #define mm_alloc_pgd(mm) (0) #define mm_free_pgd(mm) #endif /* CONFIG_MMU */ |
23ff44402
|
410 |
__cacheline_aligned_in_smp DEFINE_SPINLOCK(mmlist_lock); |
1da177e4c
|
411 |
|
e94b17660
|
412 |
#define allocate_mm() (kmem_cache_alloc(mm_cachep, GFP_KERNEL)) |
1da177e4c
|
413 |
#define free_mm(mm) (kmem_cache_free(mm_cachep, (mm))) |
4cb0e11b1
|
414 415 416 417 418 419 420 421 422 423 424 |
static unsigned long default_dump_filter = MMF_DUMP_FILTER_DEFAULT; static int __init coredump_filter_setup(char *s) { default_dump_filter = (simple_strtoul(s, NULL, 0) << MMF_DUMP_FILTER_SHIFT) & MMF_DUMP_FILTER_MASK; return 1; } __setup("coredump_filter=", coredump_filter_setup); |
1da177e4c
|
425 |
#include <linux/init_task.h> |
858f09930
|
426 427 428 429 430 431 432 |
static void mm_init_aio(struct mm_struct *mm) { #ifdef CONFIG_AIO spin_lock_init(&mm->ioctx_lock); INIT_HLIST_HEAD(&mm->ioctx_list); #endif } |
78fb74669
|
433 |
static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p) |
1da177e4c
|
434 435 436 437 438 |
{ atomic_set(&mm->mm_users, 1); atomic_set(&mm->mm_count, 1); init_rwsem(&mm->mmap_sem); INIT_LIST_HEAD(&mm->mmlist); |
f8af4da3b
|
439 440 |
mm->flags = (current->mm) ? (current->mm->flags & MMF_INIT_MASK) : default_dump_filter; |
999d9fc16
|
441 |
mm->core_state = NULL; |
1da177e4c
|
442 |
mm->nr_ptes = 0; |
d559db086
|
443 |
memset(&mm->rss_stat, 0, sizeof(mm->rss_stat)); |
1da177e4c
|
444 |
spin_lock_init(&mm->page_table_lock); |
1da177e4c
|
445 |
mm->free_area_cache = TASK_UNMAPPED_BASE; |
1363c3cd8
|
446 |
mm->cached_hole_size = ~0UL; |
858f09930
|
447 |
mm_init_aio(mm); |
cf475ad28
|
448 |
mm_init_owner(mm, p); |
1da177e4c
|
449 450 451 |
if (likely(!mm_alloc_pgd(mm))) { mm->def_flags = 0; |
cddb8a5c1
|
452 |
mmu_notifier_mm_init(mm); |
1da177e4c
|
453 454 |
return mm; } |
78fb74669
|
455 |
|
1da177e4c
|
456 457 458 459 460 461 462 463 464 465 466 467 468 469 |
free_mm(mm); return NULL; } /* * Allocate and initialize an mm_struct. */ struct mm_struct * mm_alloc(void) { struct mm_struct * mm; mm = allocate_mm(); if (mm) { memset(mm, 0, sizeof(*mm)); |
78fb74669
|
470 |
mm = mm_init(mm, current); |
1da177e4c
|
471 472 473 474 475 476 477 478 479 |
} return mm; } /* * 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. */ |
7ad5b3a50
|
480 |
void __mmdrop(struct mm_struct *mm) |
1da177e4c
|
481 482 483 484 |
{ BUG_ON(mm == &init_mm); mm_free_pgd(mm); destroy_context(mm); |
cddb8a5c1
|
485 |
mmu_notifier_mm_destroy(mm); |
1da177e4c
|
486 487 |
free_mm(mm); } |
6d4e4c4fc
|
488 |
EXPORT_SYMBOL_GPL(__mmdrop); |
1da177e4c
|
489 490 491 492 493 494 |
/* * Decrement the use count and release all resources for an mm. */ void mmput(struct mm_struct *mm) { |
0ae26f1b3
|
495 |
might_sleep(); |
1da177e4c
|
496 497 |
if (atomic_dec_and_test(&mm->mm_users)) { exit_aio(mm); |
1c2fb7a4c
|
498 |
ksm_exit(mm); |
1da177e4c
|
499 |
exit_mmap(mm); |
925d1c401
|
500 |
set_mm_exe_file(mm, NULL); |
1da177e4c
|
501 502 503 504 505 506 |
if (!list_empty(&mm->mmlist)) { spin_lock(&mmlist_lock); list_del(&mm->mmlist); spin_unlock(&mmlist_lock); } put_swap_token(mm); |
801460d0c
|
507 508 |
if (mm->binfmt) module_put(mm->binfmt->module); |
1da177e4c
|
509 510 511 512 513 514 515 516 |
mmdrop(mm); } } EXPORT_SYMBOL_GPL(mmput); /** * get_task_mm - acquire a reference to the task's mm * |
246bb0b1d
|
517 |
* Returns %NULL if the task has no mm. Checks PF_KTHREAD (meaning |
1da177e4c
|
518 519 520 521 522 523 524 525 526 527 528 529 |
* this kernel workthread has transiently adopted a user mm with use_mm, * to do its AIO) is not set and if so returns a reference to it, after * bumping up the use count. User must release the mm via mmput() * after use. Typically used by /proc and ptrace. */ struct mm_struct *get_task_mm(struct task_struct *task) { struct mm_struct *mm; task_lock(task); mm = task->mm; if (mm) { |
246bb0b1d
|
530 |
if (task->flags & PF_KTHREAD) |
1da177e4c
|
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 |
mm = NULL; else atomic_inc(&mm->mm_users); } task_unlock(task); return mm; } EXPORT_SYMBOL_GPL(get_task_mm); /* Please note the differences between mmput and mm_release. * mmput is called whenever we stop holding onto a mm_struct, * error success whatever. * * mm_release is called after a mm_struct has been removed * from the current process. * * This difference is important for error handling, when we * only half set up a mm_struct for a new process and need to restore * the old one. Because we mmput the new mm_struct before * restoring the old one. . . * Eric Biederman 10 January 1998 */ void mm_release(struct task_struct *tsk, struct mm_struct *mm) { struct completion *vfork_done = tsk->vfork_done; |
8141c7f3e
|
556 557 |
/* Get rid of any futexes when releasing the mm */ #ifdef CONFIG_FUTEX |
fc6b177de
|
558 |
if (unlikely(tsk->robust_list)) { |
8141c7f3e
|
559 |
exit_robust_list(tsk); |
fc6b177de
|
560 561 |
tsk->robust_list = NULL; } |
8141c7f3e
|
562 |
#ifdef CONFIG_COMPAT |
fc6b177de
|
563 |
if (unlikely(tsk->compat_robust_list)) { |
8141c7f3e
|
564 |
compat_exit_robust_list(tsk); |
fc6b177de
|
565 566 |
tsk->compat_robust_list = NULL; } |
8141c7f3e
|
567 |
#endif |
322a2c100
|
568 569 |
if (unlikely(!list_empty(&tsk->pi_state_list))) exit_pi_state_list(tsk); |
8141c7f3e
|
570 |
#endif |
1da177e4c
|
571 572 573 574 575 576 577 578 |
/* Get rid of any cached register state */ deactivate_mm(tsk, mm); /* notify parent sleeping on vfork() */ if (vfork_done) { tsk->vfork_done = NULL; complete(vfork_done); } |
fec1d0115
|
579 580 581 582 583 584 585 |
/* * If we're exiting normally, clear a user-space tid field if * requested. We leave this alone when dying by signal, to leave * the value intact in a core dump, and to save the unnecessary * trouble otherwise. Userland only wants this done for a sys_exit. */ |
9c8a8228d
|
586 587 588 589 590 591 592 593 594 595 596 |
if (tsk->clear_child_tid) { if (!(tsk->flags & PF_SIGNALED) && atomic_read(&mm->mm_users) > 1) { /* * We don't check the error code - if userspace has * not set up a proper pointer then tough luck. */ put_user(0, tsk->clear_child_tid); sys_futex(tsk->clear_child_tid, FUTEX_WAKE, 1, NULL, NULL, 0); } |
1da177e4c
|
597 |
tsk->clear_child_tid = NULL; |
1da177e4c
|
598 599 |
} } |
a0a7ec308
|
600 601 602 603 |
/* * Allocate a new mm structure and copy contents from the * mm structure of the passed in task structure. */ |
402b08622
|
604 |
struct mm_struct *dup_mm(struct task_struct *tsk) |
a0a7ec308
|
605 606 607 608 609 610 611 612 613 614 615 616 |
{ struct mm_struct *mm, *oldmm = current->mm; int err; if (!oldmm) return NULL; mm = allocate_mm(); if (!mm) goto fail_nomem; memcpy(mm, oldmm, sizeof(*mm)); |
7602bdf2f
|
617 618 619 |
/* Initializing for Swap token stuff */ mm->token_priority = 0; mm->last_interval = 0; |
78fb74669
|
620 |
if (!mm_init(mm, tsk)) |
a0a7ec308
|
621 622 623 624 |
goto fail_nomem; if (init_new_context(tsk, mm)) goto fail_nocontext; |
925d1c401
|
625 |
dup_mm_exe_file(oldmm, mm); |
a0a7ec308
|
626 627 628 629 630 631 |
err = dup_mmap(mm, oldmm); if (err) goto free_pt; mm->hiwater_rss = get_mm_rss(mm); mm->hiwater_vm = mm->total_vm; |
801460d0c
|
632 633 |
if (mm->binfmt && !try_module_get(mm->binfmt->module)) goto free_pt; |
a0a7ec308
|
634 635 636 |
return mm; free_pt: |
801460d0c
|
637 638 |
/* don't put binfmt in mmput, we haven't got module yet */ mm->binfmt = NULL; |
a0a7ec308
|
639 640 641 642 643 644 645 646 647 648 649 650 651 652 |
mmput(mm); fail_nomem: return NULL; fail_nocontext: /* * If init_new_context() failed, we cannot use mmput() to free the mm * because it calls destroy_context() */ mm_free_pgd(mm); free_mm(mm); return NULL; } |
1da177e4c
|
653 654 655 656 657 658 659 |
static int copy_mm(unsigned long clone_flags, struct task_struct * tsk) { struct mm_struct * mm, *oldmm; int retval; tsk->min_flt = tsk->maj_flt = 0; tsk->nvcsw = tsk->nivcsw = 0; |
17406b82d
|
660 661 662 |
#ifdef CONFIG_DETECT_HUNG_TASK tsk->last_switch_count = tsk->nvcsw + tsk->nivcsw; #endif |
1da177e4c
|
663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 |
tsk->mm = NULL; tsk->active_mm = NULL; /* * Are we cloning a kernel thread? * * We need to steal a active VM for that.. */ oldmm = current->mm; if (!oldmm) return 0; if (clone_flags & CLONE_VM) { atomic_inc(&oldmm->mm_users); mm = oldmm; |
1da177e4c
|
679 680 681 682 |
goto good_mm; } retval = -ENOMEM; |
a0a7ec308
|
683 |
mm = dup_mm(tsk); |
1da177e4c
|
684 685 |
if (!mm) goto fail_nomem; |
1da177e4c
|
686 |
good_mm: |
7602bdf2f
|
687 688 689 |
/* Initializing for Swap token stuff */ mm->token_priority = 0; mm->last_interval = 0; |
1da177e4c
|
690 691 692 |
tsk->mm = mm; tsk->active_mm = mm; return 0; |
1da177e4c
|
693 694 |
fail_nomem: return retval; |
1da177e4c
|
695 |
} |
a39bc5169
|
696 |
static int copy_fs(unsigned long clone_flags, struct task_struct *tsk) |
1da177e4c
|
697 |
{ |
498052bba
|
698 |
struct fs_struct *fs = current->fs; |
1da177e4c
|
699 |
if (clone_flags & CLONE_FS) { |
498052bba
|
700 701 702 703 704 705 706 707 |
/* tsk->fs is already what we want */ write_lock(&fs->lock); if (fs->in_exec) { write_unlock(&fs->lock); return -EAGAIN; } fs->users++; write_unlock(&fs->lock); |
1da177e4c
|
708 709 |
return 0; } |
498052bba
|
710 |
tsk->fs = copy_fs_struct(fs); |
1da177e4c
|
711 712 713 714 |
if (!tsk->fs) return -ENOMEM; return 0; } |
a016f3389
|
715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 |
static int copy_files(unsigned long clone_flags, struct task_struct * tsk) { struct files_struct *oldf, *newf; int error = 0; /* * A background process may not have any files ... */ oldf = current->files; if (!oldf) goto out; if (clone_flags & CLONE_FILES) { atomic_inc(&oldf->count); goto out; } |
a016f3389
|
731 732 733 734 735 736 737 738 739 |
newf = dup_fd(oldf, &error); if (!newf) goto out; tsk->files = newf; error = 0; out: return error; } |
fadad878c
|
740 |
static int copy_io(unsigned long clone_flags, struct task_struct *tsk) |
fd0928df9
|
741 742 743 744 745 746 |
{ #ifdef CONFIG_BLOCK struct io_context *ioc = current->io_context; if (!ioc) return 0; |
fadad878c
|
747 748 749 750 751 752 753 754 |
/* * Share io context with parent, if CLONE_IO is set */ if (clone_flags & CLONE_IO) { tsk->io_context = ioc_task_link(ioc); if (unlikely(!tsk->io_context)) return -ENOMEM; } else if (ioprio_valid(ioc->ioprio)) { |
fd0928df9
|
755 756 757 |
tsk->io_context = alloc_io_context(GFP_KERNEL, -1); if (unlikely(!tsk->io_context)) return -ENOMEM; |
fd0928df9
|
758 759 760 761 762 |
tsk->io_context->ioprio = ioc->ioprio; } #endif return 0; } |
a39bc5169
|
763 |
static int copy_sighand(unsigned long clone_flags, struct task_struct *tsk) |
1da177e4c
|
764 765 |
{ struct sighand_struct *sig; |
60348802e
|
766 |
if (clone_flags & CLONE_SIGHAND) { |
1da177e4c
|
767 768 769 770 |
atomic_inc(¤t->sighand->count); return 0; } sig = kmem_cache_alloc(sighand_cachep, GFP_KERNEL); |
e56d09031
|
771 |
rcu_assign_pointer(tsk->sighand, sig); |
1da177e4c
|
772 773 |
if (!sig) return -ENOMEM; |
1da177e4c
|
774 775 776 777 |
atomic_set(&sig->count, 1); memcpy(sig->action, current->sighand->action, sizeof(sig->action)); return 0; } |
a7e5328a0
|
778 |
void __cleanup_sighand(struct sighand_struct *sighand) |
c81addc9d
|
779 |
{ |
c81addc9d
|
780 781 782 |
if (atomic_dec_and_test(&sighand->count)) kmem_cache_free(sighand_cachep, sighand); } |
f06febc96
|
783 784 785 786 787 788 |
/* * Initialize POSIX timer handling for a thread group. */ static void posix_cpu_timers_init_group(struct signal_struct *sig) { |
78d7d407b
|
789 |
unsigned long cpu_limit; |
f06febc96
|
790 791 |
/* Thread group counters. */ thread_group_cputime_init(sig); |
78d7d407b
|
792 793 794 |
cpu_limit = ACCESS_ONCE(sig->rlim[RLIMIT_CPU].rlim_cur); if (cpu_limit != RLIM_INFINITY) { sig->cputime_expires.prof_exp = secs_to_cputime(cpu_limit); |
6279a751f
|
795 796 |
sig->cputimer.running = 1; } |
f06febc96
|
797 798 799 800 801 |
/* The timer lists. */ INIT_LIST_HEAD(&sig->cpu_timers[0]); INIT_LIST_HEAD(&sig->cpu_timers[1]); INIT_LIST_HEAD(&sig->cpu_timers[2]); } |
a39bc5169
|
802 |
static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) |
1da177e4c
|
803 804 |
{ struct signal_struct *sig; |
1da177e4c
|
805 |
|
4ab6c0833
|
806 |
if (clone_flags & CLONE_THREAD) |
490dea45d
|
807 |
return 0; |
490dea45d
|
808 |
|
a56704ef6
|
809 |
sig = kmem_cache_zalloc(signal_cachep, GFP_KERNEL); |
1da177e4c
|
810 811 812 |
tsk->signal = sig; if (!sig) return -ENOMEM; |
1da177e4c
|
813 814 815 |
atomic_set(&sig->count, 1); atomic_set(&sig->live, 1); init_waitqueue_head(&sig->wait_chldexit); |
b3bfa0cba
|
816 817 |
if (clone_flags & CLONE_NEWPID) sig->flags |= SIGNAL_UNKILLABLE; |
db51aeccd
|
818 |
sig->curr_target = tsk; |
1da177e4c
|
819 820 |
init_sigpending(&sig->shared_pending); INIT_LIST_HEAD(&sig->posix_timers); |
c9cb2e3d7
|
821 |
hrtimer_init(&sig->real_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); |
1da177e4c
|
822 |
sig->real_timer.function = it_real_fn; |
1da177e4c
|
823 |
|
1da177e4c
|
824 825 826 |
task_lock(current->group_leader); memcpy(sig->rlim, current->signal->rlim, sizeof sig->rlim); task_unlock(current->group_leader); |
6279a751f
|
827 |
posix_cpu_timers_init_group(sig); |
522ed7767
|
828 |
tty_audit_fork(sig); |
28b83c519
|
829 |
sig->oom_adj = current->signal->oom_adj; |
1da177e4c
|
830 831 |
return 0; } |
6b3934ef5
|
832 833 |
void __cleanup_signal(struct signal_struct *sig) { |
f06febc96
|
834 |
thread_group_cputime_free(sig); |
9c9f4ded9
|
835 |
tty_kref_put(sig->tty); |
6b3934ef5
|
836 837 |
kmem_cache_free(signal_cachep, sig); } |
a39bc5169
|
838 |
static void copy_flags(unsigned long clone_flags, struct task_struct *p) |
1da177e4c
|
839 840 |
{ unsigned long new_flags = p->flags; |
831441862
|
841 |
new_flags &= ~PF_SUPERPRIV; |
1da177e4c
|
842 |
new_flags |= PF_FORKNOEXEC; |
09a05394f
|
843 |
new_flags |= PF_STARTING; |
1da177e4c
|
844 |
p->flags = new_flags; |
2e1318956
|
845 |
clear_freeze_flag(p); |
1da177e4c
|
846 |
} |
17da2bd90
|
847 |
SYSCALL_DEFINE1(set_tid_address, int __user *, tidptr) |
1da177e4c
|
848 849 |
{ current->clear_child_tid = tidptr; |
b488893a3
|
850 |
return task_pid_vnr(current); |
1da177e4c
|
851 |
} |
a39bc5169
|
852 |
static void rt_mutex_init_task(struct task_struct *p) |
23f78d4a0
|
853 |
{ |
1d6154825
|
854 |
raw_spin_lock_init(&p->pi_lock); |
e29e175b0
|
855 |
#ifdef CONFIG_RT_MUTEXES |
1d6154825
|
856 |
plist_head_init_raw(&p->pi_waiters, &p->pi_lock); |
23f78d4a0
|
857 |
p->pi_blocked_on = NULL; |
23f78d4a0
|
858 859 |
#endif } |
cf475ad28
|
860 861 862 863 864 865 |
#ifdef CONFIG_MM_OWNER void mm_init_owner(struct mm_struct *mm, struct task_struct *p) { mm->owner = p; } #endif /* CONFIG_MM_OWNER */ |
1da177e4c
|
866 |
/* |
f06febc96
|
867 868 869 870 871 872 873 874 875 876 877 878 879 |
* Initialize POSIX timer handling for a single task. */ static void posix_cpu_timers_init(struct task_struct *tsk) { tsk->cputime_expires.prof_exp = cputime_zero; tsk->cputime_expires.virt_exp = cputime_zero; tsk->cputime_expires.sched_exp = 0; INIT_LIST_HEAD(&tsk->cpu_timers[0]); INIT_LIST_HEAD(&tsk->cpu_timers[1]); INIT_LIST_HEAD(&tsk->cpu_timers[2]); } /* |
1da177e4c
|
880 881 882 883 884 885 886 |
* This creates a new process as a copy of the old one, * but does not actually start it yet. * * It copies the registers, and all the appropriate * parts of the process environment (as per the clone * flags). The actual kick-off is left to the caller. */ |
36c8b5868
|
887 888 889 890 |
static struct task_struct *copy_process(unsigned long clone_flags, unsigned long stack_start, struct pt_regs *regs, unsigned long stack_size, |
36c8b5868
|
891 |
int __user *child_tidptr, |
09a05394f
|
892 893 |
struct pid *pid, int trace) |
1da177e4c
|
894 895 |
{ int retval; |
a24efe62d
|
896 |
struct task_struct *p; |
b4f48b636
|
897 |
int cgroup_callbacks_done = 0; |
1da177e4c
|
898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 |
if ((clone_flags & (CLONE_NEWNS|CLONE_FS)) == (CLONE_NEWNS|CLONE_FS)) return ERR_PTR(-EINVAL); /* * Thread groups must share signals as well, and detached threads * can only be started up within the thread group. */ if ((clone_flags & CLONE_THREAD) && !(clone_flags & CLONE_SIGHAND)) return ERR_PTR(-EINVAL); /* * Shared signal handlers imply shared VM. By way of the above, * thread groups also imply shared VM. Blocking this case allows * for various simplifications in other code. */ if ((clone_flags & CLONE_SIGHAND) && !(clone_flags & CLONE_VM)) return ERR_PTR(-EINVAL); |
123be07b0
|
916 917 918 919 920 921 922 923 924 |
/* * Siblings of global init remain as zombies on exit since they are * not reaped by their parent (swapper). To solve this and to avoid * multi-rooted process trees, prevent global and container-inits * from creating siblings. */ if ((clone_flags & CLONE_PARENT) && current->signal->flags & SIGNAL_UNKILLABLE) return ERR_PTR(-EINVAL); |
1da177e4c
|
925 926 927 928 929 930 931 932 |
retval = security_task_create(clone_flags); if (retval) goto fork_out; retval = -ENOMEM; p = dup_task_struct(current); if (!p) goto fork_out; |
f7e8b616e
|
933 |
ftrace_graph_init_task(p); |
bea493a03
|
934 |
rt_mutex_init_task(p); |
d12c1a379
|
935 |
#ifdef CONFIG_PROVE_LOCKING |
de30a2b35
|
936 937 938 |
DEBUG_LOCKS_WARN_ON(!p->hardirqs_enabled); DEBUG_LOCKS_WARN_ON(!p->softirqs_enabled); #endif |
1da177e4c
|
939 |
retval = -EAGAIN; |
3b11a1dec
|
940 |
if (atomic_read(&p->real_cred->user->processes) >= |
78d7d407b
|
941 |
task_rlimit(p, RLIMIT_NPROC)) { |
1da177e4c
|
942 |
if (!capable(CAP_SYS_ADMIN) && !capable(CAP_SYS_RESOURCE) && |
18b6e0414
|
943 |
p->real_cred->user != INIT_USER) |
1da177e4c
|
944 945 |
goto bad_fork_free; } |
f1752eec6
|
946 947 948 |
retval = copy_creds(p, clone_flags); if (retval < 0) goto bad_fork_free; |
1da177e4c
|
949 950 951 952 953 954 |
/* * If multiple threads are within copy_process(), then this check * triggers too late. This doesn't hurt, the check is only there * to stop root fork bombs. */ |
04ec93fe9
|
955 |
retval = -EAGAIN; |
1da177e4c
|
956 957 |
if (nr_threads >= max_threads) goto bad_fork_cleanup_count; |
a1261f546
|
958 |
if (!try_module_get(task_thread_info(p)->exec_domain->module)) |
1da177e4c
|
959 |
goto bad_fork_cleanup_count; |
1da177e4c
|
960 |
p->did_exec = 0; |
ca74e92b4
|
961 |
delayacct_tsk_init(p); /* Must remain after dup_task_struct() */ |
1da177e4c
|
962 |
copy_flags(clone_flags, p); |
1da177e4c
|
963 964 |
INIT_LIST_HEAD(&p->children); INIT_LIST_HEAD(&p->sibling); |
f41d911f8
|
965 |
rcu_copy_process(p); |
1da177e4c
|
966 967 |
p->vfork_done = NULL; spin_lock_init(&p->alloc_lock); |
1da177e4c
|
968 |
|
1da177e4c
|
969 970 971 972 |
init_sigpending(&p->pending); p->utime = cputime_zero; p->stime = cputime_zero; |
9ac52315d
|
973 |
p->gtime = cputime_zero; |
c66f08be7
|
974 975 |
p->utimescaled = cputime_zero; p->stimescaled = cputime_zero; |
d99ca3b97
|
976 |
#ifndef CONFIG_VIRT_CPU_ACCOUNTING |
73a2bcb0e
|
977 |
p->prev_utime = cputime_zero; |
9301899be
|
978 |
p->prev_stime = cputime_zero; |
d99ca3b97
|
979 |
#endif |
a3a2e76c7
|
980 981 982 |
#if defined(SPLIT_RSS_COUNTING) memset(&p->rss_stat, 0, sizeof(p->rss_stat)); #endif |
172ba844a
|
983 |
|
6976675d9
|
984 |
p->default_timer_slack_ns = current->timer_slack_ns; |
5995477ab
|
985 |
task_io_accounting_init(&p->ioac); |
1da177e4c
|
986 |
acct_clear_integrals(p); |
f06febc96
|
987 |
posix_cpu_timers_init(p); |
1da177e4c
|
988 989 990 |
p->lock_depth = -1; /* -1 = no lock */ do_posix_clock_monotonic_gettime(&p->start_time); |
924b42d5a
|
991 992 |
p->real_start_time = p->start_time; monotonic_to_bootbased(&p->real_start_time); |
1da177e4c
|
993 |
p->io_context = NULL; |
1da177e4c
|
994 |
p->audit_context = NULL; |
b4f48b636
|
995 |
cgroup_fork(p); |
1da177e4c
|
996 |
#ifdef CONFIG_NUMA |
846a16bf0
|
997 |
p->mempolicy = mpol_dup(p->mempolicy); |
1da177e4c
|
998 999 1000 |
if (IS_ERR(p->mempolicy)) { retval = PTR_ERR(p->mempolicy); p->mempolicy = NULL; |
b4f48b636
|
1001 |
goto bad_fork_cleanup_cgroup; |
1da177e4c
|
1002 |
} |
c61afb181
|
1003 |
mpol_fix_fork_child_flag(p); |
1da177e4c
|
1004 |
#endif |
de30a2b35
|
1005 1006 |
#ifdef CONFIG_TRACE_IRQFLAGS p->irq_events = 0; |
b36e4758d
|
1007 1008 1009 |
#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW p->hardirqs_enabled = 1; #else |
de30a2b35
|
1010 |
p->hardirqs_enabled = 0; |
b36e4758d
|
1011 |
#endif |
de30a2b35
|
1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 |
p->hardirq_enable_ip = 0; p->hardirq_enable_event = 0; p->hardirq_disable_ip = _THIS_IP_; p->hardirq_disable_event = 0; p->softirqs_enabled = 1; p->softirq_enable_ip = _THIS_IP_; p->softirq_enable_event = 0; p->softirq_disable_ip = 0; p->softirq_disable_event = 0; p->hardirq_context = 0; p->softirq_context = 0; #endif |
fbb9ce953
|
1024 1025 1026 1027 1028 |
#ifdef CONFIG_LOCKDEP p->lockdep_depth = 0; /* no locks held yet */ p->curr_chain_key = 0; p->lockdep_recursion = 0; #endif |
1da177e4c
|
1029 |
|
408894ee4
|
1030 1031 1032 |
#ifdef CONFIG_DEBUG_MUTEXES p->blocked_on = NULL; /* not blocked yet */ #endif |
569b846df
|
1033 1034 1035 1036 |
#ifdef CONFIG_CGROUP_MEM_RES_CTLR p->memcg_batch.do_batch = 0; p->memcg_batch.memcg = NULL; #endif |
0f4814065
|
1037 1038 |
p->bts = NULL; |
408894ee4
|
1039 |
|
d899bf7b5
|
1040 |
p->stack_start = stack_start; |
3c90e6e99
|
1041 1042 |
/* Perform scheduler related setup. Assign this task to a CPU. */ sched_fork(p, clone_flags); |
6ab423e0e
|
1043 |
|
cdd6c482c
|
1044 |
retval = perf_event_init_task(p); |
6ab423e0e
|
1045 1046 |
if (retval) goto bad_fork_cleanup_policy; |
3c90e6e99
|
1047 |
|
1da177e4c
|
1048 |
if ((retval = audit_alloc(p))) |
f1752eec6
|
1049 |
goto bad_fork_cleanup_policy; |
1da177e4c
|
1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 |
/* copy all the process information */ if ((retval = copy_semundo(clone_flags, p))) goto bad_fork_cleanup_audit; if ((retval = copy_files(clone_flags, p))) goto bad_fork_cleanup_semundo; if ((retval = copy_fs(clone_flags, p))) goto bad_fork_cleanup_files; if ((retval = copy_sighand(clone_flags, p))) goto bad_fork_cleanup_fs; if ((retval = copy_signal(clone_flags, p))) goto bad_fork_cleanup_sighand; if ((retval = copy_mm(clone_flags, p))) goto bad_fork_cleanup_signal; |
ab516013a
|
1063 |
if ((retval = copy_namespaces(clone_flags, p))) |
d84f4f992
|
1064 |
goto bad_fork_cleanup_mm; |
fadad878c
|
1065 |
if ((retval = copy_io(clone_flags, p))) |
fd0928df9
|
1066 |
goto bad_fork_cleanup_namespaces; |
6f2c55b84
|
1067 |
retval = copy_thread(clone_flags, stack_start, stack_size, p, regs); |
1da177e4c
|
1068 |
if (retval) |
fd0928df9
|
1069 |
goto bad_fork_cleanup_io; |
1da177e4c
|
1070 |
|
425fb2b4b
|
1071 1072 |
if (pid != &init_struct_pid) { retval = -ENOMEM; |
61bce0f13
|
1073 |
pid = alloc_pid(p->nsproxy->pid_ns); |
425fb2b4b
|
1074 |
if (!pid) |
fd0928df9
|
1075 |
goto bad_fork_cleanup_io; |
6f4e64335
|
1076 1077 |
if (clone_flags & CLONE_NEWPID) { |
61bce0f13
|
1078 |
retval = pid_ns_prepare_proc(p->nsproxy->pid_ns); |
6f4e64335
|
1079 1080 1081 |
if (retval < 0) goto bad_fork_free_pid; } |
425fb2b4b
|
1082 1083 1084 1085 1086 1087 |
} p->pid = pid_nr(pid); p->tgid = p->pid; if (clone_flags & CLONE_THREAD) p->tgid = current->tgid; |
e885dcde7
|
1088 1089 1090 |
if (current->nsproxy != p->nsproxy) { retval = ns_cgroup_clone(p, pid); if (retval) |
f7e8b616e
|
1091 |
goto bad_fork_free_pid; |
e885dcde7
|
1092 |
} |
1da177e4c
|
1093 1094 1095 1096 1097 |
p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? child_tidptr : NULL; /* * Clear TID on mm_release()? */ p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? child_tidptr: NULL; |
42b2dd0a0
|
1098 |
#ifdef CONFIG_FUTEX |
8f17d3a50
|
1099 1100 1101 1102 |
p->robust_list = NULL; #ifdef CONFIG_COMPAT p->compat_robust_list = NULL; #endif |
c87e2837b
|
1103 1104 |
INIT_LIST_HEAD(&p->pi_state_list); p->pi_state_cache = NULL; |
42b2dd0a0
|
1105 |
#endif |
1da177e4c
|
1106 |
/* |
f9a3879ab
|
1107 1108 1109 1110 1111 1112 |
* sigaltstack should be cleared when sharing the same VM */ if ((clone_flags & (CLONE_VM|CLONE_VFORK)) == CLONE_VM) p->sas_ss_sp = p->sas_ss_size = 0; /* |
6580807da
|
1113 1114 |
* Syscall tracing and stepping should be turned off in the * child regardless of CLONE_PTRACE. |
1da177e4c
|
1115 |
*/ |
6580807da
|
1116 |
user_disable_single_step(p); |
1da177e4c
|
1117 |
clear_tsk_thread_flag(p, TIF_SYSCALL_TRACE); |
ed75e8d58
|
1118 1119 1120 |
#ifdef TIF_SYSCALL_EMU clear_tsk_thread_flag(p, TIF_SYSCALL_EMU); #endif |
9745512ce
|
1121 |
clear_all_latency_tracing(p); |
1da177e4c
|
1122 |
|
1da177e4c
|
1123 1124 1125 1126 |
/* ok, now we should be set up.. */ p->exit_signal = (clone_flags & CLONE_THREAD) ? -1 : (clone_flags & CSIGNAL); p->pdeath_signal = 0; p->exit_state = 0; |
1da177e4c
|
1127 1128 1129 1130 1131 |
/* * Ok, make it visible to the rest of the system. * We dont wake it up yet. */ p->group_leader = p; |
47e65328a
|
1132 |
INIT_LIST_HEAD(&p->thread_group); |
1da177e4c
|
1133 |
|
b4f48b636
|
1134 1135 1136 1137 1138 |
/* Now that the task is set up, run cgroup callbacks if * necessary. We need to run them before the task is visible * on the tasklist. */ cgroup_fork_callbacks(p); cgroup_callbacks_done = 1; |
1da177e4c
|
1139 1140 |
/* Need tasklist lock for parent etc handling! */ write_lock_irq(&tasklist_lock); |
1da177e4c
|
1141 |
/* CLONE_PARENT re-uses the old parent */ |
2d5516cbb
|
1142 |
if (clone_flags & (CLONE_PARENT|CLONE_THREAD)) { |
1da177e4c
|
1143 |
p->real_parent = current->real_parent; |
2d5516cbb
|
1144 1145 |
p->parent_exec_id = current->parent_exec_id; } else { |
1da177e4c
|
1146 |
p->real_parent = current; |
2d5516cbb
|
1147 1148 |
p->parent_exec_id = current->self_exec_id; } |
1da177e4c
|
1149 |
|
3f17da699
|
1150 |
spin_lock(¤t->sighand->siglock); |
4a2c7a783
|
1151 1152 1153 1154 1155 1156 1157 1158 1159 |
/* * Process group and session signals need to be delivered to just the * parent before the fork or both the parent and the child after the * fork. Restart if a signal comes in before we add the new process to * it's process group. * A fatal signal pending means that current will exit, so the new * thread can't slip out of an OOM kill (or normal SIGKILL). */ |
23ff44402
|
1160 |
recalc_sigpending(); |
4a2c7a783
|
1161 1162 1163 1164 |
if (signal_pending(current)) { spin_unlock(¤t->sighand->siglock); write_unlock_irq(&tasklist_lock); retval = -ERESTARTNOINTR; |
f7e8b616e
|
1165 |
goto bad_fork_free_pid; |
4a2c7a783
|
1166 |
} |
1da177e4c
|
1167 |
if (clone_flags & CLONE_THREAD) { |
4ab6c0833
|
1168 1169 |
atomic_inc(¤t->signal->count); atomic_inc(¤t->signal->live); |
1da177e4c
|
1170 |
p->group_leader = current->group_leader; |
47e65328a
|
1171 |
list_add_tail_rcu(&p->thread_group, &p->group_leader->thread_group); |
1da177e4c
|
1172 |
} |
73b9ebfe1
|
1173 |
if (likely(p->pid)) { |
09a05394f
|
1174 |
tracehook_finish_clone(p, clone_flags, trace); |
73b9ebfe1
|
1175 1176 |
if (thread_group_leader(p)) { |
5cd17569f
|
1177 |
if (clone_flags & CLONE_NEWPID) |
30e49c263
|
1178 |
p->nsproxy->pid_ns->child_reaper = p; |
73b9ebfe1
|
1179 |
|
fea9d1755
|
1180 |
p->signal->leader_pid = pid; |
9c9f4ded9
|
1181 1182 |
tty_kref_put(p->signal->tty); p->signal->tty = tty_kref_get(current->signal->tty); |
5cd17569f
|
1183 1184 |
attach_pid(p, PIDTYPE_PGID, task_pgrp(current)); attach_pid(p, PIDTYPE_SID, task_session(current)); |
9cd80bbb0
|
1185 |
list_add_tail(&p->sibling, &p->real_parent->children); |
5e85d4abe
|
1186 |
list_add_tail_rcu(&p->tasks, &init_task.tasks); |
1da177e4c
|
1187 |
__get_cpu_var(process_counts)++; |
73b9ebfe1
|
1188 |
} |
85868995d
|
1189 |
attach_pid(p, PIDTYPE_PID, pid); |
73b9ebfe1
|
1190 |
nr_threads++; |
1da177e4c
|
1191 |
} |
1da177e4c
|
1192 |
total_forks++; |
3f17da699
|
1193 |
spin_unlock(¤t->sighand->siglock); |
1da177e4c
|
1194 |
write_unlock_irq(&tasklist_lock); |
c13cf856c
|
1195 |
proc_fork_connector(p); |
817929ec2
|
1196 |
cgroup_post_fork(p); |
cdd6c482c
|
1197 |
perf_event_fork(p); |
1da177e4c
|
1198 |
return p; |
425fb2b4b
|
1199 1200 1201 |
bad_fork_free_pid: if (pid != &init_struct_pid) free_pid(pid); |
fd0928df9
|
1202 |
bad_fork_cleanup_io: |
b69f22920
|
1203 1204 |
if (p->io_context) exit_io_context(p); |
ab516013a
|
1205 |
bad_fork_cleanup_namespaces: |
444f378b2
|
1206 |
exit_task_namespaces(p); |
1da177e4c
|
1207 1208 1209 1210 |
bad_fork_cleanup_mm: if (p->mm) mmput(p->mm); bad_fork_cleanup_signal: |
4ab6c0833
|
1211 1212 |
if (!(clone_flags & CLONE_THREAD)) __cleanup_signal(p->signal); |
1da177e4c
|
1213 |
bad_fork_cleanup_sighand: |
a7e5328a0
|
1214 |
__cleanup_sighand(p->sighand); |
1da177e4c
|
1215 1216 1217 1218 1219 1220 1221 1222 |
bad_fork_cleanup_fs: exit_fs(p); /* blocking */ bad_fork_cleanup_files: exit_files(p); /* blocking */ bad_fork_cleanup_semundo: exit_sem(p); bad_fork_cleanup_audit: audit_free(p); |
1da177e4c
|
1223 |
bad_fork_cleanup_policy: |
cdd6c482c
|
1224 |
perf_event_free_task(p); |
1da177e4c
|
1225 |
#ifdef CONFIG_NUMA |
f0be3d32b
|
1226 |
mpol_put(p->mempolicy); |
b4f48b636
|
1227 |
bad_fork_cleanup_cgroup: |
1da177e4c
|
1228 |
#endif |
b4f48b636
|
1229 |
cgroup_exit(p, cgroup_callbacks_done); |
35df17c57
|
1230 |
delayacct_tsk_free(p); |
a1261f546
|
1231 |
module_put(task_thread_info(p)->exec_domain->module); |
1da177e4c
|
1232 |
bad_fork_cleanup_count: |
d84f4f992
|
1233 |
atomic_dec(&p->cred->user->processes); |
e0e817392
|
1234 |
exit_creds(p); |
1da177e4c
|
1235 1236 |
bad_fork_free: free_task(p); |
fe7d37d1f
|
1237 1238 |
fork_out: return ERR_PTR(retval); |
1da177e4c
|
1239 |
} |
6b2fb3c65
|
1240 |
noinline struct pt_regs * __cpuinit __attribute__((weak)) idle_regs(struct pt_regs *regs) |
1da177e4c
|
1241 1242 1243 1244 |
{ memset(regs, 0, sizeof(struct pt_regs)); return regs; } |
9abcf40b1
|
1245 |
struct task_struct * __cpuinit fork_idle(int cpu) |
1da177e4c
|
1246 |
{ |
36c8b5868
|
1247 |
struct task_struct *task; |
1da177e4c
|
1248 |
struct pt_regs regs; |
30e49c263
|
1249 |
task = copy_process(CLONE_VM, 0, idle_regs(®s), 0, NULL, |
09a05394f
|
1250 |
&init_struct_pid, 0); |
753ca4f31
|
1251 1252 |
if (!IS_ERR(task)) init_idle(task, cpu); |
73b9ebfe1
|
1253 |
|
1da177e4c
|
1254 1255 |
return task; } |
1da177e4c
|
1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 |
/* * Ok, this is the main fork-routine. * * It copies the process, and if successful kick-starts * it and waits for it to finish using the VM if required. */ long do_fork(unsigned long clone_flags, unsigned long stack_start, struct pt_regs *regs, unsigned long stack_size, int __user *parent_tidptr, int __user *child_tidptr) { struct task_struct *p; int trace = 0; |
92476d7fc
|
1271 |
long nr; |
1da177e4c
|
1272 |
|
bdff746a3
|
1273 |
/* |
18b6e0414
|
1274 1275 1276 1277 1278 1279 1280 1281 1282 |
* Do some preliminary argument and permissions checking before we * actually start allocating stuff */ if (clone_flags & CLONE_NEWUSER) { if (clone_flags & CLONE_THREAD) return -EINVAL; /* hopefully this check will go away when userns support is * complete */ |
7657d9049
|
1283 1284 |
if (!capable(CAP_SYS_ADMIN) || !capable(CAP_SETUID) || !capable(CAP_SETGID)) |
18b6e0414
|
1285 1286 1287 1288 |
return -EPERM; } /* |
bdff746a3
|
1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 |
* We hope to recycle these flags after 2.6.26 */ if (unlikely(clone_flags & CLONE_STOPPED)) { static int __read_mostly count = 100; if (count > 0 && printk_ratelimit()) { char comm[TASK_COMM_LEN]; count--; printk(KERN_INFO "fork(): process `%s' used deprecated " "clone flags 0x%lx ", get_task_comm(comm, current), clone_flags & CLONE_STOPPED); } } |
09a05394f
|
1305 1306 1307 1308 1309 |
/* * When called from kernel_thread, don't do user tracing stuff. */ if (likely(user_mode(regs))) trace = tracehook_prepare_clone(clone_flags); |
1da177e4c
|
1310 |
|
a6f5e0637
|
1311 |
p = copy_process(clone_flags, stack_start, regs, stack_size, |
09a05394f
|
1312 |
child_tidptr, NULL, trace); |
1da177e4c
|
1313 1314 1315 1316 1317 1318 |
/* * Do this prior waking up the new thread - the thread pointer * might get invalid after that point, if the thread exits quickly. */ if (!IS_ERR(p)) { struct completion vfork; |
0a16b6075
|
1319 |
trace_sched_process_fork(current, p); |
6c5f3e7b4
|
1320 |
nr = task_pid_vnr(p); |
30e49c263
|
1321 1322 1323 |
if (clone_flags & CLONE_PARENT_SETTID) put_user(nr, parent_tidptr); |
a6f5e0637
|
1324 |
|
1da177e4c
|
1325 1326 1327 1328 |
if (clone_flags & CLONE_VFORK) { p->vfork_done = &vfork; init_completion(&vfork); } |
a64e64944
|
1329 |
audit_finish_fork(p); |
087eb4370
|
1330 |
tracehook_report_clone(regs, clone_flags, nr, p); |
09a05394f
|
1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 |
/* * We set PF_STARTING at creation in case tracing wants to * use this to distinguish a fully live task from one that * hasn't gotten to tracehook_report_clone() yet. Now we * clear it and set the child going. */ p->flags &= ~PF_STARTING; if (unlikely(clone_flags & CLONE_STOPPED)) { |
1da177e4c
|
1341 1342 1343 1344 1345 |
/* * We'll start up with an immediate SIGSTOP. */ sigaddset(&p->pending.signal, SIGSTOP); set_tsk_thread_flag(p, TIF_SIGPENDING); |
d9ae90ac4
|
1346 |
__set_task_state(p, TASK_STOPPED); |
09a05394f
|
1347 1348 |
} else { wake_up_new_task(p, clone_flags); |
1da177e4c
|
1349 |
} |
09a05394f
|
1350 1351 |
tracehook_report_clone_complete(trace, regs, clone_flags, nr, p); |
1da177e4c
|
1352 |
if (clone_flags & CLONE_VFORK) { |
ba96a0c88
|
1353 |
freezer_do_not_count(); |
1da177e4c
|
1354 |
wait_for_completion(&vfork); |
ba96a0c88
|
1355 |
freezer_count(); |
daded34be
|
1356 |
tracehook_report_vfork_done(p, nr); |
1da177e4c
|
1357 1358 |
} } else { |
92476d7fc
|
1359 |
nr = PTR_ERR(p); |
1da177e4c
|
1360 |
} |
92476d7fc
|
1361 |
return nr; |
1da177e4c
|
1362 |
} |
5fd63b308
|
1363 1364 1365 |
#ifndef ARCH_MIN_MMSTRUCT_ALIGN #define ARCH_MIN_MMSTRUCT_ALIGN 0 #endif |
51cc50685
|
1366 |
static void sighand_ctor(void *data) |
aa1757f90
|
1367 1368 |
{ struct sighand_struct *sighand = data; |
a35afb830
|
1369 |
spin_lock_init(&sighand->siglock); |
b8fceee17
|
1370 |
init_waitqueue_head(&sighand->signalfd_wqh); |
aa1757f90
|
1371 |
} |
1da177e4c
|
1372 1373 1374 1375 |
void __init proc_caches_init(void) { sighand_cachep = kmem_cache_create("sighand_cache", sizeof(struct sighand_struct), 0, |
2dff44052
|
1376 1377 |
SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_DESTROY_BY_RCU| SLAB_NOTRACK, sighand_ctor); |
1da177e4c
|
1378 1379 |
signal_cachep = kmem_cache_create("signal_cache", sizeof(struct signal_struct), 0, |
2dff44052
|
1380 |
SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL); |
20c2df83d
|
1381 |
files_cachep = kmem_cache_create("files_cache", |
1da177e4c
|
1382 |
sizeof(struct files_struct), 0, |
2dff44052
|
1383 |
SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL); |
20c2df83d
|
1384 |
fs_cachep = kmem_cache_create("fs_cache", |
1da177e4c
|
1385 |
sizeof(struct fs_struct), 0, |
2dff44052
|
1386 |
SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL); |
1da177e4c
|
1387 |
mm_cachep = kmem_cache_create("mm_struct", |
5fd63b308
|
1388 |
sizeof(struct mm_struct), ARCH_MIN_MMSTRUCT_ALIGN, |
2dff44052
|
1389 |
SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL); |
33e5d7697
|
1390 |
vm_area_cachep = KMEM_CACHE(vm_area_struct, SLAB_PANIC); |
8feae1311
|
1391 |
mmap_init(); |
1da177e4c
|
1392 |
} |
cf2e340f4
|
1393 |
|
cf2e340f4
|
1394 1395 1396 1397 |
/* * Check constraints on flags passed to the unshare system call and * force unsharing of additional process context as appropriate. */ |
a39bc5169
|
1398 |
static void check_unshare_flags(unsigned long *flags_ptr) |
cf2e340f4
|
1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 |
{ /* * If unsharing a thread from a thread group, must also * unshare vm. */ if (*flags_ptr & CLONE_THREAD) *flags_ptr |= CLONE_VM; /* * If unsharing vm, must also unshare signal handlers. */ if (*flags_ptr & CLONE_VM) *flags_ptr |= CLONE_SIGHAND; /* * If unsharing signal handlers and the task was created * using CLONE_THREAD, then must unshare the thread */ if ((*flags_ptr & CLONE_SIGHAND) && (atomic_read(¤t->signal->count) > 1)) *flags_ptr |= CLONE_THREAD; /* * If unsharing namespace, must also unshare filesystem information. */ if (*flags_ptr & CLONE_NEWNS) *flags_ptr |= CLONE_FS; } /* * Unsharing of tasks created with CLONE_THREAD is not supported yet */ static int unshare_thread(unsigned long unshare_flags) { if (unshare_flags & CLONE_THREAD) return -EINVAL; return 0; } /* |
99d1419d9
|
1440 |
* Unshare the filesystem structure if it is being shared |
cf2e340f4
|
1441 1442 1443 1444 |
*/ static int unshare_fs(unsigned long unshare_flags, struct fs_struct **new_fsp) { struct fs_struct *fs = current->fs; |
498052bba
|
1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 |
if (!(unshare_flags & CLONE_FS) || !fs) return 0; /* don't need lock here; in the worst case we'll do useless copy */ if (fs->users == 1) return 0; *new_fsp = copy_fs_struct(fs); if (!*new_fsp) return -ENOMEM; |
cf2e340f4
|
1455 1456 1457 1458 1459 |
return 0; } /* |
dae3c5a0b
|
1460 |
* Unsharing of sighand is not supported yet |
cf2e340f4
|
1461 1462 1463 1464 |
*/ static int unshare_sighand(unsigned long unshare_flags, struct sighand_struct **new_sighp) { struct sighand_struct *sigh = current->sighand; |
dae3c5a0b
|
1465 |
if ((unshare_flags & CLONE_SIGHAND) && atomic_read(&sigh->count) > 1) |
cf2e340f4
|
1466 1467 1468 1469 1470 1471 |
return -EINVAL; else return 0; } /* |
a0a7ec308
|
1472 |
* Unshare vm if it is being shared |
cf2e340f4
|
1473 1474 1475 1476 1477 1478 |
*/ static int unshare_vm(unsigned long unshare_flags, struct mm_struct **new_mmp) { struct mm_struct *mm = current->mm; if ((unshare_flags & CLONE_VM) && |
a0a7ec308
|
1479 |
(mm && atomic_read(&mm->mm_users) > 1)) { |
2d61b8677
|
1480 |
return -EINVAL; |
a0a7ec308
|
1481 |
} |
cf2e340f4
|
1482 1483 |
return 0; |
cf2e340f4
|
1484 1485 1486 |
} /* |
a016f3389
|
1487 |
* Unshare file descriptor table if it is being shared |
cf2e340f4
|
1488 1489 1490 1491 |
*/ static int unshare_fd(unsigned long unshare_flags, struct files_struct **new_fdp) { struct files_struct *fd = current->files; |
a016f3389
|
1492 |
int error = 0; |
cf2e340f4
|
1493 1494 |
if ((unshare_flags & CLONE_FILES) && |
a016f3389
|
1495 1496 1497 1498 1499 |
(fd && atomic_read(&fd->count) > 1)) { *new_fdp = dup_fd(fd, &error); if (!*new_fdp) return error; } |
cf2e340f4
|
1500 1501 1502 1503 1504 |
return 0; } /* |
cf2e340f4
|
1505 1506 1507 1508 1509 1510 1511 |
* unshare allows a process to 'unshare' part of the process * context which was originally shared using clone. copy_* * functions used by do_fork() cannot be used here directly * because they modify an inactive task_struct that is being * constructed. Here we are modifying the current, active, * task_struct. */ |
6559eed8c
|
1512 |
SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags) |
cf2e340f4
|
1513 1514 1515 |
{ int err = 0; struct fs_struct *fs, *new_fs = NULL; |
dae3c5a0b
|
1516 |
struct sighand_struct *new_sigh = NULL; |
cf2e340f4
|
1517 1518 |
struct mm_struct *mm, *new_mm = NULL, *active_mm = NULL; struct files_struct *fd, *new_fd = NULL; |
cf7b708c8
|
1519 |
struct nsproxy *new_nsproxy = NULL; |
9edff4ab1
|
1520 |
int do_sysvsem = 0; |
cf2e340f4
|
1521 1522 |
check_unshare_flags(&unshare_flags); |
06f9d4f94
|
1523 1524 1525 |
/* Return -EINVAL for all unsupported flags */ err = -EINVAL; if (unshare_flags & ~(CLONE_THREAD|CLONE_FS|CLONE_NEWNS|CLONE_SIGHAND| |
25b21cb2f
|
1526 |
CLONE_VM|CLONE_FILES|CLONE_SYSVSEM| |
18b6e0414
|
1527 |
CLONE_NEWUTS|CLONE_NEWIPC|CLONE_NEWNET)) |
06f9d4f94
|
1528 |
goto bad_unshare_out; |
6013f67fc
|
1529 1530 1531 1532 1533 1534 |
/* * CLONE_NEWIPC must also detach from the undolist: after switching * to a new ipc namespace, the semaphore arrays from the old * namespace are unreachable. */ if (unshare_flags & (CLONE_NEWIPC|CLONE_SYSVSEM)) |
9edff4ab1
|
1535 |
do_sysvsem = 1; |
cf2e340f4
|
1536 1537 1538 1539 |
if ((err = unshare_thread(unshare_flags))) goto bad_unshare_out; if ((err = unshare_fs(unshare_flags, &new_fs))) goto bad_unshare_cleanup_thread; |
cf2e340f4
|
1540 |
if ((err = unshare_sighand(unshare_flags, &new_sigh))) |
e3222c4ec
|
1541 |
goto bad_unshare_cleanup_fs; |
cf2e340f4
|
1542 1543 1544 1545 |
if ((err = unshare_vm(unshare_flags, &new_mm))) goto bad_unshare_cleanup_sigh; if ((err = unshare_fd(unshare_flags, &new_fd))) goto bad_unshare_cleanup_vm; |
e3222c4ec
|
1546 1547 |
if ((err = unshare_nsproxy_namespaces(unshare_flags, &new_nsproxy, new_fs))) |
9edff4ab1
|
1548 |
goto bad_unshare_cleanup_fd; |
c0b2fc316
|
1549 |
|
9edff4ab1
|
1550 1551 1552 1553 1554 1555 1556 |
if (new_fs || new_mm || new_fd || do_sysvsem || new_nsproxy) { if (do_sysvsem) { /* * CLONE_SYSVSEM is equivalent to sys_exit(). */ exit_sem(current); } |
ab516013a
|
1557 |
|
c0b2fc316
|
1558 |
if (new_nsproxy) { |
cf7b708c8
|
1559 1560 |
switch_task_namespaces(current, new_nsproxy); new_nsproxy = NULL; |
c0b2fc316
|
1561 |
} |
cf2e340f4
|
1562 |
|
cf7b708c8
|
1563 |
task_lock(current); |
cf2e340f4
|
1564 1565 |
if (new_fs) { fs = current->fs; |
498052bba
|
1566 |
write_lock(&fs->lock); |
cf2e340f4
|
1567 |
current->fs = new_fs; |
498052bba
|
1568 1569 1570 1571 1572 |
if (--fs->users) new_fs = NULL; else new_fs = fs; write_unlock(&fs->lock); |
cf2e340f4
|
1573 |
} |
cf2e340f4
|
1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 |
if (new_mm) { mm = current->mm; active_mm = current->active_mm; current->mm = new_mm; current->active_mm = new_mm; activate_mm(active_mm, new_mm); new_mm = mm; } if (new_fd) { fd = current->files; current->files = new_fd; new_fd = fd; } task_unlock(current); } |
c0b2fc316
|
1591 |
if (new_nsproxy) |
444f378b2
|
1592 |
put_nsproxy(new_nsproxy); |
c0b2fc316
|
1593 |
|
cf2e340f4
|
1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 |
bad_unshare_cleanup_fd: if (new_fd) put_files_struct(new_fd); bad_unshare_cleanup_vm: if (new_mm) mmput(new_mm); bad_unshare_cleanup_sigh: if (new_sigh) if (atomic_dec_and_test(&new_sigh->count)) kmem_cache_free(sighand_cachep, new_sigh); |
cf2e340f4
|
1606 1607 |
bad_unshare_cleanup_fs: if (new_fs) |
498052bba
|
1608 |
free_fs_struct(new_fs); |
cf2e340f4
|
1609 1610 1611 1612 1613 |
bad_unshare_cleanup_thread: bad_unshare_out: return err; } |
3b1253880
|
1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 |
/* * Helper to unshare the files of the current task. * We don't want to expose copy_files internals to * the exec layer of the kernel. */ int unshare_files(struct files_struct **displaced) { struct task_struct *task = current; |
50704516f
|
1624 |
struct files_struct *copy = NULL; |
3b1253880
|
1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 |
int error; error = unshare_fd(CLONE_FILES, ©); if (error || !copy) { *displaced = NULL; return error; } *displaced = task->files; task_lock(task); task->files = copy; task_unlock(task); return 0; } |