fork.c 66.4 KB
Newer Older
1
// SPDX-License-Identifier: GPL-2.0-only
2 3 4 5 6 7 8 9 10 11 12 13 14
/*
 *  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()'
 */

15
#include <linux/anon_inodes.h>
16
#include <linux/slab.h>
17 18 19 20 21 22 23 24 25
#include <linux/sched/autogroup.h>
#include <linux/sched/mm.h>
#include <linux/sched/coredump.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>
26
#include <linux/seq_file.h>
27
#include <linux/rtmutex.h>
28 29 30 31 32 33 34 35 36 37 38 39 40 41 42
#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/binfmts.h>
#include <linux/mman.h>
#include <linux/mmu_notifier.h>
43
#include <linux/hmm.h>
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
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/vmacache.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/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>
72
#include <linux/userfaultfd_k.h>
73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93
#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/random.h>
#include <linux/tty.h>
#include <linux/blkdev.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>
94
#include <linux/livepatch.h>
95
#include <linux/thread_info.h>
96
#include <linux/stackleak.h>
97 98 99

#include <asm/pgtable.h>
#include <asm/pgalloc.h>
100
#include <linux/uaccess.h>
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
#include <asm/mmu_context.h>
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>

#include <trace/events/sched.h>

#define CREATE_TRACE_POINTS
#include <trace/events/task.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.. */

126
static int max_threads;		/* tunable limit on nr_threads */
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

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)
{
}

#ifndef CONFIG_ARCH_TASK_STRUCT_ALLOCATOR
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);
}
#endif

#ifndef CONFIG_ARCH_THREAD_STACK_ALLOCATOR

/*
 * Allocate pages if THREAD_SIZE is >= PAGE_SIZE, otherwise use a
 * kmemcache based allocator.
 */
175 176 177 178 179 180 181 182 183
# if THREAD_SIZE >= PAGE_SIZE || defined(CONFIG_VMAP_STACK)

#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]);
184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201

static int free_vm_stack_cache(unsigned int cpu)
{
	struct vm_struct **cached_vm_stacks = per_cpu_ptr(cached_stacks, cpu);
	int i;

	for (i = 0; i < NR_CACHED_STACKS; i++) {
		struct vm_struct *vm_stack = cached_vm_stacks[i];

		if (!vm_stack)
			continue;

		vfree(vm_stack->addr);
		cached_vm_stacks[i] = NULL;
	}

	return 0;
}
202 203 204
#endif

static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node)
205
{
206 207 208 209 210
#ifdef CONFIG_VMAP_STACK
	void *stack;
	int i;

	for (i = 0; i < NR_CACHED_STACKS; i++) {
211 212 213
		struct vm_struct *s;

		s = this_cpu_xchg(cached_stacks[i], NULL);
214 215 216 217

		if (!s)
			continue;

218 219
		/* Clear stale pointers from reused stack. */
		memset(s->addr, 0, THREAD_SIZE);
220

221
		tsk->stack_vm_area = s;
222
		tsk->stack = s->addr;
223 224 225
		return s->addr;
	}

226 227 228 229 230
	/*
	 * Allocated stacks are cached and later reused by new threads,
	 * so memcg accounting is performed manually on assigning/releasing
	 * stacks to tasks. Drop __GFP_ACCOUNT.
	 */
231
	stack = __vmalloc_node_range(THREAD_SIZE, THREAD_ALIGN,
232
				     VMALLOC_START, VMALLOC_END,
233
				     THREADINFO_GFP & ~__GFP_ACCOUNT,
234 235 236 237 238 239 240 241
				     PAGE_KERNEL,
				     0, node, __builtin_return_address(0));

	/*
	 * 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.
	 */
242
	if (stack) {
243
		tsk->stack_vm_area = find_vm_area(stack);
244 245
		tsk->stack = stack;
	}
246 247
	return stack;
#else
248 249
	struct page *page = alloc_pages_node(node, THREADINFO_GFP,
					     THREAD_SIZE_ORDER);
250

251 252 253 254 255
	if (likely(page)) {
		tsk->stack = page_address(page);
		return tsk->stack;
	}
	return NULL;
256
#endif
257 258
}

259
static inline void free_thread_stack(struct task_struct *tsk)
260
{
261
#ifdef CONFIG_VMAP_STACK
262 263 264
	struct vm_struct *vm = task_stack_vm_area(tsk);

	if (vm) {
265 266
		int i;

267 268 269 270 271 272 273 274
		for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) {
			mod_memcg_page_state(vm->pages[i],
					     MEMCG_KERNEL_STACK_KB,
					     -(int)(PAGE_SIZE / 1024));

			memcg_kmem_uncharge(vm->pages[i], 0);
		}

275
		for (i = 0; i < NR_CACHED_STACKS; i++) {
276 277
			if (this_cpu_cmpxchg(cached_stacks[i],
					NULL, tsk->stack_vm_area) != NULL)
278 279 280 281 282
				continue;

			return;
		}

283
		vfree_atomic(tsk->stack);
284 285 286 287 288
		return;
	}
#endif

	__free_pages(virt_to_page(tsk->stack), THREAD_SIZE_ORDER);
289 290 291 292 293 294 295
}
# else
static struct kmem_cache *thread_stack_cache;

static unsigned long *alloc_thread_stack_node(struct task_struct *tsk,
						  int node)
{
296 297 298 299
	unsigned long *stack;
	stack = kmem_cache_alloc_node(thread_stack_cache, THREADINFO_GFP, node);
	tsk->stack = stack;
	return stack;
300 301
}

302
static void free_thread_stack(struct task_struct *tsk)
303
{
304
	kmem_cache_free(thread_stack_cache, tsk->stack);
305 306 307 308
}

void thread_stack_cache_init(void)
{
309 310 311
	thread_stack_cache = kmem_cache_create_usercopy("thread_stack",
					THREAD_SIZE, THREAD_SIZE, 0, 0,
					THREAD_SIZE, NULL);
312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329
	BUG_ON(thread_stack_cache == NULL);
}
# endif
#endif

/* 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 vm_area_struct structures */
330
static struct kmem_cache *vm_area_cachep;
331 332 333 334

/* SLAB cache for mm_struct structures (tsk->mm) */
static struct kmem_cache *mm_cachep;

335 336
struct vm_area_struct *vm_area_alloc(struct mm_struct *mm)
{
337
	struct vm_area_struct *vma;
338

339
	vma = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360
	if (vma)
		vma_init(vma, mm);
	return vma;
}

struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig)
{
	struct vm_area_struct *new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);

	if (new) {
		*new = *orig;
		INIT_LIST_HEAD(&new->anon_vma_chain);
	}
	return new;
}

void vm_area_free(struct vm_area_struct *vma)
{
	kmem_cache_free(vm_area_cachep, vma);
}

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
static void account_kernel_stack(struct task_struct *tsk, int account)
{
	void *stack = task_stack_page(tsk);
	struct vm_struct *vm = task_stack_vm_area(tsk);

	BUILD_BUG_ON(IS_ENABLED(CONFIG_VMAP_STACK) && PAGE_SIZE % 1024 != 0);

	if (vm) {
		int i;

		BUG_ON(vm->nr_pages != THREAD_SIZE / PAGE_SIZE);

		for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) {
			mod_zone_page_state(page_zone(vm->pages[i]),
					    NR_KERNEL_STACK_KB,
					    PAGE_SIZE / 1024 * account);
		}
	} else {
		/*
		 * All stack pages are in the same zone and belong to the
		 * same memcg.
		 */
		struct page *first_page = virt_to_page(stack);

		mod_zone_page_state(page_zone(first_page), NR_KERNEL_STACK_KB,
				    THREAD_SIZE / 1024 * account);

388 389
		mod_memcg_page_state(first_page, MEMCG_KERNEL_STACK_KB,
				     account * (THREAD_SIZE / 1024));
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
static int memcg_charge_kernel_stack(struct task_struct *tsk)
{
#ifdef CONFIG_VMAP_STACK
	struct vm_struct *vm = task_stack_vm_area(tsk);
	int ret;

	if (vm) {
		int i;

		for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) {
			/*
			 * If memcg_kmem_charge() fails, page->mem_cgroup
			 * pointer is NULL, and both memcg_kmem_uncharge()
			 * and mod_memcg_page_state() in free_thread_stack()
			 * will ignore this page. So it's safe.
			 */
			ret = memcg_kmem_charge(vm->pages[i], GFP_KERNEL, 0);
			if (ret)
				return ret;

			mod_memcg_page_state(vm->pages[i],
					     MEMCG_KERNEL_STACK_KB,
					     PAGE_SIZE / 1024);
		}
	}
#endif
	return 0;
}

422
static void release_task_stack(struct task_struct *tsk)
423
{
424 425
	if (WARN_ON(tsk->state != TASK_DEAD))
		return;  /* Better to leak the stack than to free prematurely */
426

427 428 429 430 431 432 433
	account_kernel_stack(tsk, -1);
	free_thread_stack(tsk);
	tsk->stack = NULL;
#ifdef CONFIG_VMAP_STACK
	tsk->stack_vm_area = NULL;
#endif
}
434

435 436 437
#ifdef CONFIG_THREAD_INFO_IN_TASK
void put_task_stack(struct task_struct *tsk)
{
438
	if (refcount_dec_and_test(&tsk->stack_refcount))
439
		release_task_stack(tsk);
440
}
441
#endif
442 443 444

void free_task(struct task_struct *tsk)
{
445 446 447 448 449 450 451 452 453 454 455
#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.
	 */
456
	WARN_ON_ONCE(refcount_read(&tsk->stack_refcount) != 0);
457
#endif
458 459 460 461
	rt_mutex_debug_task_free(tsk);
	ftrace_graph_exit_task(tsk);
	put_seccomp_filter(tsk);
	arch_release_task_struct(tsk);
462 463
	if (tsk->flags & PF_KTHREAD)
		free_kthread_struct(tsk);
464 465 466 467
	free_task_struct(tsk);
}
EXPORT_SYMBOL(free_task);

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
#ifdef CONFIG_MMU
static __latent_entropy int dup_mmap(struct mm_struct *mm,
					struct mm_struct *oldmm)
{
	struct vm_area_struct *mpnt, *tmp, *prev, **pprev;
	struct rb_node **rb_link, *rb_parent;
	int retval;
	unsigned long charge;
	LIST_HEAD(uf);

	uprobe_start_dup_mmap();
	if (down_write_killable(&oldmm->mmap_sem)) {
		retval = -EINTR;
		goto fail_uprobe_end;
	}
	flush_cache_dup_mm(oldmm);
	uprobe_dup_mmap(oldmm, mm);
	/*
	 * Not linked in yet - no deadlock potential:
	 */
	down_write_nested(&mm->mmap_sem, SINGLE_DEPTH_NESTING);

	/* No ordering required: file already has been exposed. */
	RCU_INIT_POINTER(mm->exe_file, get_mm_exe_file(oldmm));

	mm->total_vm = oldmm->total_vm;
	mm->data_vm = oldmm->data_vm;
	mm->exec_vm = oldmm->exec_vm;
	mm->stack_vm = oldmm->stack_vm;

	rb_link = &mm->mm_rb.rb_node;
	rb_parent = NULL;
	pprev = &mm->mmap;
	retval = ksm_fork(mm, oldmm);
	if (retval)
		goto out;
	retval = khugepaged_fork(mm, oldmm);
	if (retval)
		goto out;

	prev = NULL;
	for (mpnt = oldmm->mmap; mpnt; mpnt = mpnt->vm_next) {
		struct file *file;

		if (mpnt->vm_flags & VM_DONTCOPY) {
			vm_stat_account(mm, mpnt->vm_flags, -vma_pages(mpnt));
			continue;
		}
		charge = 0;
517 518 519 520 521 522 523 524
		/*
		 * Don't duplicate many vmas if we've been oom-killed (for
		 * example)
		 */
		if (fatal_signal_pending(current)) {
			retval = -EINTR;
			goto out;
		}
525 526 527 528 529 530 531
		if (mpnt->vm_flags & VM_ACCOUNT) {
			unsigned long len = vma_pages(mpnt);

			if (security_vm_enough_memory_mm(oldmm, len)) /* sic */
				goto fail_nomem;
			charge = len;
		}
532
		tmp = vm_area_dup(mpnt);
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
		if (!tmp)
			goto fail_nomem;
		retval = vma_dup_policy(mpnt, tmp);
		if (retval)
			goto fail_nomem_policy;
		tmp->vm_mm = mm;
		retval = dup_userfaultfd(tmp, &uf);
		if (retval)
			goto fail_nomem_anon_vma_fork;
		if (tmp->vm_flags & VM_WIPEONFORK) {
			/* VM_WIPEONFORK gets a clean slate in the child. */
			tmp->anon_vma = NULL;
			if (anon_vma_prepare(tmp))
				goto fail_nomem_anon_vma_fork;
		} else if (anon_vma_fork(tmp, mpnt))
			goto fail_nomem_anon_vma_fork;
		tmp->vm_flags &= ~(VM_LOCKED | VM_LOCKONFAULT);
		tmp->vm_next = tmp->vm_prev = NULL;
		file = tmp->vm_file;
		if (file) {
			struct inode *inode = file_inode(file);
			struct address_space *mapping = file->f_mapping;

			get_file(file);
			if (tmp->vm_flags & VM_DENYWRITE)
				atomic_dec(&inode->i_writecount);
			i_mmap_lock_write(mapping);
			if (tmp->vm_flags & VM_SHARED)
				atomic_inc(&mapping->i_mmap_writable);
			flush_dcache_mmap_lock(mapping);
			/* insert tmp into the share list, just after mpnt */
			vma_interval_tree_insert_after(tmp, mpnt,
					&mapping->i_mmap);
			flush_dcache_mmap_unlock(mapping);
			i_mmap_unlock_write(mapping);
		}

		/*
		 * 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);

		/*
		 * Link in the new vma and copy the page table entries.
		 */
		*pprev = tmp;
		pprev = &tmp->vm_next;
		tmp->vm_prev = prev;
		prev = tmp;

		__vma_link_rb(mm, tmp, rb_link, rb_parent);
		rb_link = &tmp->vm_rb.rb_right;
		rb_parent = &tmp->vm_rb;

		mm->map_count++;
		if (!(tmp->vm_flags & VM_WIPEONFORK))
			retval = copy_page_range(mm, oldmm, mpnt);

		if (tmp->vm_ops && tmp->vm_ops->open)
			tmp->vm_ops->open(tmp);

		if (retval)
			goto out;
	}
	/* a new mm has just been created */
601
	retval = arch_dup_mmap(oldmm, mm);
602 603 604 605 606 607 608 609 610 611 612
out:
	up_write(&mm->mmap_sem);
	flush_tlb_mm(oldmm);
	up_write(&oldmm->mmap_sem);
	dup_userfaultfd_complete(&uf);
fail_uprobe_end:
	uprobe_end_dup_mmap();
	return retval;
fail_nomem_anon_vma_fork:
	mpol_put(vma_policy(tmp));
fail_nomem_policy:
613
	vm_area_free(tmp);
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
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)
{
	pgd_free(mm, mm->pgd);
}
#else
static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
{
	down_write(&oldmm->mmap_sem);
	RCU_INIT_POINTER(mm->exe_file, get_mm_exe_file(oldmm));
	up_write(&oldmm->mmap_sem);
	return 0;
}
#define mm_alloc_pgd(mm)	(0)
#define mm_free_pgd(mm)
#endif /* CONFIG_MMU */

static void check_mm(struct mm_struct *mm)
{
	int i;

	for (i = 0; i < NR_MM_COUNTERS; i++) {
		long x = atomic_long_read(&mm->rss_stat.count[i]);

		if (unlikely(x))
			printk(KERN_ALERT "BUG: Bad rss-counter state "
					  "mm:%p idx:%d val:%ld\n", mm, i, x);
	}

	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) && !USE_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)))

/*
 * 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);
676 677
	WARN_ON_ONCE(mm == current->mm);
	WARN_ON_ONCE(mm == current->active_mm);
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
	mm_free_pgd(mm);
	destroy_context(mm);
	hmm_mm_destroy(mm);
	mmu_notifier_mm_destroy(mm);
	check_mm(mm);
	put_user_ns(mm->user_ns);
	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);
	}
}

704 705 706 707
static inline void free_signal_struct(struct signal_struct *sig)
{
	taskstats_tgid_free(sig);
	sched_autogroup_exit(sig);
708 709 710 711 712 713
	/*
	 * __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);
714 715 716 717 718
	kmem_cache_free(signal_cachep, sig);
}

static inline void put_signal_struct(struct signal_struct *sig)
{
719
	if (refcount_dec_and_test(&sig->sigcnt))
720 721 722 723 724 725
		free_signal_struct(sig);
}

void __put_task_struct(struct task_struct *tsk)
{
	WARN_ON(!tsk->exit_state);
726
	WARN_ON(refcount_read(&tsk->usage));
727 728 729
	WARN_ON(tsk == current);

	cgroup_free(tsk);
730
	task_numa_free(tsk, true);
731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748
	security_task_free(tsk);
	exit_creds(tsk);
	delayacct_tsk_free(tsk);
	put_signal_struct(tsk->signal);

	if (!profile_handoff_task(tsk))
		free_task(tsk);
}
EXPORT_SYMBOL_GPL(__put_task_struct);

void __init __weak arch_task_cache_init(void) { }

/*
 * set_max_threads
 */
static void set_max_threads(unsigned int max_threads_suggested)
{
	u64 threads;
749
	unsigned long nr_pages = totalram_pages();
750 751 752 753 754

	/*
	 * The number of threads shall be limited such that the thread
	 * structures may only consume a small part of the available memory.
	 */
755
	if (fls64(nr_pages) + fls64(PAGE_SIZE) > 64)
756 757
		threads = MAX_THREADS;
	else
758
		threads = div64_u64((u64) nr_pages * (u64) PAGE_SIZE,
759 760 761 762 763 764 765 766 767 768 769 770 771
				    (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

772 773 774 775 776 777 778 779 780 781 782 783 784 785 786
static void 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);
}

787 788
void __init fork_init(void)
{
789
	int i;
790 791
#ifndef CONFIG_ARCH_TASK_STRUCT_ALLOCATOR
#ifndef ARCH_MIN_TASKALIGN
792
#define ARCH_MIN_TASKALIGN	0
793
#endif
794
	int align = max_t(int, L1_CACHE_BYTES, ARCH_MIN_TASKALIGN);
795
	unsigned long useroffset, usersize;
796

797
	/* create a slab on which task_structs can be allocated */
798 799
	task_struct_whitelist(&useroffset, &usersize);
	task_struct_cachep = kmem_cache_create_usercopy("task_struct",
800
			arch_task_struct_size, align,
801 802
			SLAB_PANIC|SLAB_ACCOUNT,
			useroffset, usersize, NULL);
803 804 805 806 807 808 809 810 811 812 813
#endif

	/* 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];
814 815 816 817

	for (i = 0; i < UCOUNT_COUNTS; i++) {
		init_user_ns.ucount_max[i] = max_threads/2;
	}
818 819 820 821 822

#ifdef CONFIG_VMAP_STACK
	cpuhp_setup_state(CPUHP_BP_PREPARE_DYN, "fork:vm_stack_cache",
			  NULL, free_vm_stack_cache);
#endif
823 824

	lockdep_init_task(&init_task);
825
	uprobes_init();
826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846
}

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;
	unsigned long *stack;
847
	struct vm_struct *stack_vm_area __maybe_unused;
848 849 850 851 852 853 854 855 856 857 858 859
	int err;

	if (node == NUMA_NO_NODE)
		node = tsk_fork_get_node(orig);
	tsk = alloc_task_struct_node(node);
	if (!tsk)
		return NULL;

	stack = alloc_thread_stack_node(tsk, node);
	if (!stack)
		goto free_tsk;

860 861 862
	if (memcg_charge_kernel_stack(tsk))
		goto free_stack;

863 864
	stack_vm_area = task_stack_vm_area(tsk);

865
	err = arch_dup_task_struct(tsk, orig);
866 867 868 869 870 871 872 873 874 875 876

	/*
	 * arch_dup_task_struct() clobbers the stack-related fields.  Make
	 * sure they're properly initialized before using any stack-related
	 * functions again.
	 */
	tsk->stack = stack;
#ifdef CONFIG_VMAP_STACK
	tsk->stack_vm_area = stack_vm_area;
#endif
#ifdef CONFIG_THREAD_INFO_IN_TASK
877
	refcount_set(&tsk->stack_refcount, 1);
878 879
#endif

880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897
	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);

898
#ifdef CONFIG_STACKPROTECTOR
899
	tsk->stack_canary = get_random_canary();
900 901 902 903 904 905
#endif

	/*
	 * One for us, one for whoever does the "release_task()" (usually
	 * parent)
	 */
906
	refcount_set(&tsk->usage, 2);
907 908 909 910 911 912 913
#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;

914
	account_kernel_stack(tsk, 1);
915 916 917

	kcov_task_init(tsk);

918 919 920 921
#ifdef CONFIG_FAULT_INJECTION
	tsk->fail_nth = 0;
#endif

922 923 924 925 926 927 928 929
#ifdef CONFIG_BLK_CGROUP
	tsk->throttle_queue = NULL;
	tsk->use_memdelay = 0;
#endif

#ifdef CONFIG_MEMCG
	tsk->active_memcg = NULL;
#endif
930 931 932
	return tsk;

free_stack:
933
	free_thread_stack(tsk);
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
free_tsk:
	free_task_struct(tsk);
	return NULL;
}

__cacheline_aligned_in_smp DEFINE_SPINLOCK(mmlist_lock);

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);

#include <linux/init_task.h>

static void mm_init_aio(struct mm_struct *mm)
{
#ifdef CONFIG_AIO
	spin_lock_init(&mm->ioctx_lock);
	mm->ioctx_table = NULL;
#endif
}

963 964 965 966 967 968 969 970 971
static __always_inline void mm_clear_owner(struct mm_struct *mm,
					   struct task_struct *p)
{
#ifdef CONFIG_MEMCG
	if (mm->owner == p)
		WRITE_ONCE(mm->owner, NULL);
#endif
}

972 973 974 975 976 977 978
static void mm_init_owner(struct mm_struct *mm, struct task_struct *p)
{
#ifdef CONFIG_MEMCG
	mm->owner = p;
#endif
}

979 980 981 982 983 984 985
static void mm_init_uprobes_state(struct mm_struct *mm)
{
#ifdef CONFIG_UPROBES
	mm->uprobes_state.xol_area = NULL;
#endif
}

986 987
static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
	struct user_namespace *user_ns)
988 989 990 991 992 993 994 995 996
{
	mm->mmap = NULL;
	mm->mm_rb = RB_ROOT;
	mm->vmacache_seqnum = 0;
	atomic_set(&mm->mm_users, 1);
	atomic_set(&mm->mm_count, 1);
	init_rwsem(&mm->mmap_sem);
	INIT_LIST_HEAD(&mm->mmlist);
	mm->core_state = NULL;
997
	mm_pgtables_bytes_init(mm);
998 999
	mm->map_count = 0;
	mm->locked_vm = 0;
1000
	atomic64_set(&mm->pinned_vm, 0);
1001 1002
	memset(&mm->rss_stat, 0, sizeof(mm->rss_stat));
	spin_lock_init(&mm->page_table_lock);
1003
	spin_lock_init(&mm->arg_lock);
1004 1005 1006
	mm_init_cpumask(mm);
	mm_init_aio(mm);
	mm_init_owner(mm, p);
1007
	RCU_INIT_POINTER(mm->exe_file, NULL);
1008
	mmu_notifier_mm_init(mm);
1009
	hmm_mm_init(mm);
1010
	init_tlb_flush_pending(mm);
1011 1012 1013
#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS
	mm->pmd_huge_pte = NULL;
#endif
1014
	mm_init_uprobes_state(mm);
1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029

	if (current->mm) {
		mm->flags = current->mm->flags & MMF_INIT_MASK;
		mm->def_flags = current->mm->def_flags & VM_INIT_DEF_MASK;
	} else {
		mm->flags = default_dump_filter;
		mm->def_flags = 0;
	}

	if (mm_alloc_pgd(mm))
		goto fail_nopgd;

	if (init_new_context(p, mm))
		goto fail_nocontext;

1030
	mm->user_ns = get_user_ns(user_ns);
1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051
	return mm;

fail_nocontext:
	mm_free_pgd(mm);
fail_nopgd:
	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)
		return NULL;

	memset(mm, 0, sizeof(*mm));
1052
	return mm_init(mm, current, current_user_ns());
1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063
}

static inline void __mmput(struct mm_struct *mm)
{
	VM_BUG_ON(atomic_read(&mm->mm_users));

	uprobe_clear_state(mm);
	exit_aio(mm);
	ksm_exit(mm);
	khugepaged_exit(mm); /* must run before exit_mmap */
	exit_mmap(mm);
1064
	mm_put_huge_zero_page(mm);
1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090
	set_mm_exe_file(mm, NULL);
	if (!list_empty(&mm->mmlist)) {
		spin_lock(&mmlist_lock);
		list_del(&mm->mmlist);
		spin_unlock(&mmlist_lock);
	}
	if (mm->binfmt)
		module_put(mm->binfmt->module);
	mmdrop(mm);
}

/*
 * Decrement the use count and release all resources for an mm.
 */
void mmput(struct mm_struct *mm)
{
	might_sleep();

	if (atomic_dec_and_test(&mm->mm_users))
		__mmput(mm);
}
EXPORT_SYMBOL_GPL(mmput);

#ifdef CONFIG_MMU
static void mmput_async_fn(struct work_struct *work)
{
1091 1092 1093
	struct mm_struct *mm = container_of(work, struct mm_struct,
					    async_put_work);

1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195
	__mmput(mm);
}

void mmput_async(struct mm_struct *mm)
{
	if (atomic_dec_and_test(&mm->mm_users)) {
		INIT_WORK(&mm->async_put_work, mmput_async_fn);
		schedule_work(&mm->async_put_work);
	}
}
#endif

/**
 * set_mm_exe_file - change a reference to the mm's executable file
 *
 * This changes mm's executable file (shown as symlink /proc/[pid]/exe).
 *
 * Main users are mmput() and sys_execve(). Callers prevent concurrent
 * invocations: in mmput() nobody alive left, in execve task is single
 * threaded. sys_prctl(PR_SET_MM_MAP/EXE_FILE) also needs to set the
 * mm->exe_file, but does so without using set_mm_exe_file() in order
 * to do avoid the need for any locks.
 */
void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file)
{
	struct file *old_exe_file;

	/*
	 * It is safe to dereference the exe_file without RCU as
	 * this function is only called if nobody else can access
	 * this mm -- see comment above for justification.
	 */
	old_exe_file = rcu_dereference_raw(mm->exe_file);

	if (new_exe_file)
		get_file(new_exe_file);
	rcu_assign_pointer(mm->exe_file, new_exe_file);
	if (old_exe_file)
		fput(old_exe_file);
}

/**
 * get_mm_exe_file - acquire a reference to the mm's executable file
 *
 * Returns %NULL if mm has no associated executable file.
 * User must release file via fput().
 */
struct file *get_mm_exe_file(struct mm_struct *mm)
{
	struct file *exe_file;

	rcu_read_lock();
	exe_file = rcu_dereference(mm->exe_file);
	if (exe_file && !get_file_rcu(exe_file))
		exe_file = NULL;
	rcu_read_unlock();
	return exe_file;
}
EXPORT_SYMBOL(get_mm_exe_file);

/**
 * get_task_exe_file - acquire a reference to the task's executable file
 *
 * Returns %NULL if task's mm (if any) has no associated executable file or
 * this is a kernel thread with borrowed mm (see the comment above get_task_mm).
 * User must release file via fput().
 */
struct file *get_task_exe_file(struct task_struct *task)
{
	struct file *exe_file = NULL;
	struct mm_struct *mm;

	task_lock(task);
	mm = task->mm;
	if (mm) {
		if (!(task->flags & PF_KTHREAD))
			exe_file = get_mm_exe_file(mm);
	}
	task_unlock(task);
	return exe_file;
}
EXPORT_SYMBOL(get_task_exe_file);

/**
 * get_task_mm - acquire a reference to the task's mm
 *
 * Returns %NULL if the task has no mm.  Checks PF_KTHREAD (meaning
 * 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) {
		if (task->flags & PF_KTHREAD)
			mm = NULL;
		else
1196
			mmget(mm);
1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241
	}
	task_unlock(task);
	return mm;
}
EXPORT_SYMBOL_GPL(get_task_mm);

struct mm_struct *mm_access(struct task_struct *task, unsigned int mode)
{
	struct mm_struct *mm;
	int err;

	err =  mutex_lock_killable(&task->signal->cred_guard_mutex);
	if (err)
		return ERR_PTR(err);

	mm = get_task_mm(task);
	if (mm && mm != current->mm &&
			!ptrace_may_access(task, mode)) {
		mmput(mm);
		mm = ERR_PTR(-EACCES);
	}
	mutex_unlock(&task->signal->cred_guard_mutex);

	return mm;
}

static void complete_vfork_done(struct task_struct *tsk)
{
	struct completion *vfork;

	task_lock(tsk);
	vfork = tsk->vfork_done;
	if (likely(vfork)) {
		tsk->vfork_done = NULL;
		complete(vfork);
	}
	task_unlock(tsk);
}

static int wait_for_vfork_done(struct task_struct *child,
				struct completion *vfork)
{
	int killed;

	freezer_do_not_count();
1242
	cgroup_enter_frozen();
1243
	killed = wait_for_completion_killable(vfork);
1244
	cgroup_leave_frozen(false);
1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293
	freezer_count();

	if (killed) {
		task_lock(child);
		child->vfork_done = NULL;
		task_unlock(child);
	}

	put_task_struct(child);
	return killed;
}

/* 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)
{
	/* Get rid of any futexes when releasing the mm */
#ifdef CONFIG_FUTEX
	if (unlikely(tsk->robust_list)) {
		exit_robust_list(tsk);
		tsk->robust_list = NULL;
	}
#ifdef CONFIG_COMPAT
	if (unlikely(tsk->compat_robust_list)) {
		compat_exit_robust_list(tsk);
		tsk->compat_robust_list = NULL;
	}
#endif
	if (unlikely(!list_empty(&tsk->pi_state_list)))
		exit_pi_state_list(tsk);
#endif

	uprobe_free_utask(tsk);

	/* Get rid of any cached register state */
	deactivate_mm(tsk, mm);

	/*
1294 1295 1296
	 * Signal userspace if we're not exiting with a core dump
	 * because we want to leave the value intact for debugging
	 * purposes.
1297 1298
	 */
	if (tsk->clear_child_tid) {
1299
		if (!(tsk->signal->flags & SIGNAL_GROUP_COREDUMP) &&
1300 1301 1302 1303 1304 1305
		    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);
1306 1307
			do_futex(tsk->clear_child_tid, FUTEX_WAKE,
					1, NULL, NULL, 0, 0);
1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319
		}
		tsk->clear_child_tid = NULL;
	}

	/*
	 * All done, finally we can wake up parent and return this mm to him.
	 * Also kthread_stop() uses this completion for synchronization.
	 */
	if (tsk->vfork_done)
		complete_vfork_done(tsk);
}

1320 1321 1322 1323 1324 1325 1326 1327 1328
/**
 * dup_mm() - duplicates an existing mm structure
 * @tsk: the task_struct with which the new mm will be associated.
 * @oldmm: the mm to duplicate.
 *
 * Allocates a new mm structure and duplicates the provided @oldmm structure
 * content into it.
 *
 * Return: the duplicated mm or NULL on failure.
1329
 */
1330 1331
static struct mm_struct *dup_mm(struct task_struct *tsk,
				struct mm_struct *oldmm)
1332
{
1333
	struct mm_struct *mm;
1334 1335 1336 1337 1338 1339 1340 1341
	int err;

	mm = allocate_mm();
	if (!mm)
		goto fail_nomem;

	memcpy(mm, oldmm, sizeof(*mm));

1342
	if (!mm_init(mm, tsk, mm->user_ns))
1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359
		goto fail_nomem;

	err = dup_mmap(mm, oldmm);
	if (err)
		goto free_pt;

	mm->hiwater_rss = get_mm_rss(mm);
	mm->hiwater_vm = mm->total_vm;

	if (mm->binfmt && !try_module_get(mm->binfmt->module))
		goto free_pt;

	return mm;

free_pt:
	/* don't put binfmt in mmput, we haven't got module yet */
	mm->binfmt = NULL;
1360
	mm_init_owner(mm, NULL);
1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375
	mmput(mm);

fail_nomem:
	return NULL;
}

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;
#ifdef CONFIG_DETECT_HUNG_TASK
	tsk->last_switch_count = tsk->nvcsw + tsk->nivcsw;
1376
	tsk->last_switch_time = 0;
1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394
#endif

	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;

	/* initialize the new vmacache entries */
	vmacache_flush(tsk);

	if (clone_flags & CLONE_VM) {
1395
		mmget(oldmm);
1396 1397 1398 1399 1400
		mm = oldmm;
		goto good_mm;
	}

	retval = -ENOMEM;
1401
	mm = dup_mm(tsk, current->mm);
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 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491
	if (!mm)
		goto fail_nomem;

good_mm:
	tsk->mm = mm;
	tsk->active_mm = mm;
	return 0;

fail_nomem:
	return retval;
}

static int copy_fs(unsigned long clone_flags, struct task_struct *tsk)
{
	struct fs_struct *fs = current->fs;
	if (clone_flags & CLONE_FS) {
		/* tsk->fs is already what we want */
		spin_lock(&fs->lock);
		if (fs->in_exec) {
			spin_unlock(&fs->lock);
			return -EAGAIN;
		}
		fs->users++;
		spin_unlock(&fs->lock);
		return 0;
	}
	tsk->fs = copy_fs_struct(fs);
	if (!tsk->fs)
		return -ENOMEM;
	return 0;
}

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;
	}

	newf = dup_fd(oldf, &error);
	if (!newf)
		goto out;

	tsk->files = newf;
	error = 0;
out:
	return error;
}

static int copy_io(unsigned long clone_flags, struct task_struct *tsk)
{
#ifdef CONFIG_BLOCK
	struct io_context *ioc = current->io_context;
	struct io_context *new_ioc;

	if (!ioc)
		return 0;
	/*
	 * Share io context with parent, if CLONE_IO is set
	 */
	if (clone_flags & CLONE_IO) {
		ioc_task_link(ioc);
		tsk->io_context = ioc;
	} else if (ioprio_valid(ioc->ioprio)) {
		new_ioc = get_task_io_context(tsk, GFP_KERNEL, NUMA_NO_NODE);
		if (unlikely(!new_ioc))
			return -ENOMEM;

		new_ioc->ioprio = ioc->ioprio;
		put_io_context(new_ioc);
	}
#endif
	return 0;
}

static int copy_sighand(unsigned long clone_flags, struct task_struct *tsk)
{
	struct sighand_struct *sig;

	if (clone_flags & CLONE_SIGHAND) {
1492
		refcount_inc(&current->sighand->count);
1493 1494 1495 1496 1497 1498 1499
		return 0;
	}
	sig = kmem_cache_alloc(sighand_cachep, GFP_KERNEL);
	rcu_assign_pointer(tsk->sighand, sig);
	if (!sig)
		return -ENOMEM;

1500
	refcount_set(&sig->count, 1);
1501
	spin_lock_irq(&current->sighand->siglock);
1502
	memcpy(sig->action, current->sighand->action, sizeof(sig->action));
1503
	spin_unlock_irq(&current->sighand->siglock);
1504 1505 1506 1507 1508
	return 0;
}

void __cleanup_sighand(struct sighand_struct *sighand)
{
1509
	if (refcount_dec_and_test(&sighand->count)) {
1510 1511
		signalfd_cleanup(sighand);
		/*
1512
		 * sighand_cachep is SLAB_TYPESAFE_BY_RCU so we can free it
1513 1514 1515 1516 1517 1518
		 * without an RCU grace period, see __lock_task_sighand().
		 */
		kmem_cache_free(sighand_cachep, sighand);
	}
}

1519
#ifdef CONFIG_POSIX_TIMERS
1520 1521 1522 1523 1524 1525 1526 1527 1528
/*
 * Initialize POSIX timer handling for a thread group.
 */
static void posix_cpu_timers_init_group(struct signal_struct *sig)
{
	unsigned long cpu_limit;

	cpu_limit = READ_ONCE(sig->rlim[RLIMIT_CPU].rlim_cur);
	if (cpu_limit != RLIM_INFINITY) {
1529
		sig->cputime_expires.prof_exp = cpu_limit * NSEC_PER_SEC;
1530 1531 1532 1533 1534 1535 1536 1537
		sig->cputimer.running = true;
	}

	/* The timer lists. */
	INIT_LIST_HEAD(&sig->cpu_timers[0]);
	INIT_LIST_HEAD(&sig->cpu_timers[1]);
	INIT_LIST_HEAD(&sig->cpu_timers[2]);
}
1538 1539 1540
#else
static inline void posix_cpu_timers_init_group(struct signal_struct *sig) { }
#endif
1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555

static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
{
	struct signal_struct *sig;

	if (clone_flags & CLONE_THREAD)
		return 0;

	sig = kmem_cache_zalloc(signal_cachep, GFP_KERNEL);
	tsk->signal = sig;
	if (!sig)
		return -ENOMEM;

	sig->nr_threads = 1;
	atomic_set(&sig->live, 1);
1556
	refcount_set(&sig->sigcnt, 1);
1557 1558 1559 1560 1561 1562 1563 1564

	/* list_add(thread_node, thread_head) without INIT_LIST_HEAD() */
	sig->thread_head = (struct list_head)LIST_HEAD_INIT(tsk->thread_node);
	tsk->thread_node = (struct list_head)LIST_HEAD_INIT(sig->thread_head);

	init_waitqueue_head(&sig->wait_chldexit);
	sig->curr_target = tsk;
	init_sigpending(&sig->shared_pending);
1565
	INIT_HLIST_HEAD(&sig->multiprocess);
1566 1567 1568
	seqlock_init(&sig->stats_lock);
	prev_cputime_init(&sig->prev_cputime);

1569 1570
#ifdef CONFIG_POSIX_TIMERS
	INIT_LIST_HEAD(&sig->posix_timers);
1571 1572
	hrtimer_init(&sig->real_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
	sig->real_timer.function = it_real_fn;
1573
#endif
1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635

	task_lock(current->group_leader);
	memcpy(sig->rlim, current->signal->rlim, sizeof sig->rlim);
	task_unlock(current->group_leader);

	posix_cpu_timers_init_group(sig);

	tty_audit_fork(sig);
	sched_autogroup_fork(sig);

	sig->oom_score_adj = current->signal->oom_score_adj;
	sig->oom_score_adj_min = current->signal->oom_score_adj_min;

	mutex_init(&sig->cred_guard_mutex);

	return 0;
}

static void copy_seccomp(struct task_struct *p)
{
#ifdef CONFIG_SECCOMP
	/*
	 * Must be called with sighand->lock held, which is common to
	 * all threads in the group. Holding cred_guard_mutex is not
	 * needed because this new task is not yet running and cannot
	 * be racing exec.
	 */
	assert_spin_locked(&current->sighand->siglock);

	/* Ref-count the new filter user, and assign it. */
	get_seccomp_filter(current);
	p->seccomp = current->seccomp;

	/*
	 * Explicitly enable no_new_privs here in case it got set
	 * between the task_struct being duplicated and holding the
	 * sighand lock. The seccomp state and nnp must be in sync.
	 */
	if (task_no_new_privs(current))
		task_set_no_new_privs(p);

	/*
	 * If the parent gained a seccomp mode after copying thread
	 * flags and between before we held the sighand lock, we have
	 * to manually enable the seccomp thread flag here.
	 */
	if (p->seccomp.mode != SECCOMP_MODE_DISABLED)
		set_tsk_thread_flag(p, TIF_SECCOMP);
#endif
}

SYSCALL_DEFINE1(set_tid_address, int __user *, tidptr)
{
	current->clear_child_tid = tidptr;

	return task_pid_vnr(current);
}

static void rt_mutex_init_task(struct task_struct *p)
{
	raw_spin_lock_init(&p->pi_lock);
#ifdef CONFIG_RT_MUTEXES
1636
	p->pi_waiters = RB_ROOT_CACHED;
1637
	p->pi_top_task = NULL;
1638 1639 1640 1641
	p->pi_blocked_on = NULL;
#endif
}

1642
#ifdef CONFIG_POSIX_TIMERS
1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654
/*
 * Initialize POSIX timer handling for a single task.
 */
static void posix_cpu_timers_init(struct task_struct *tsk)
{
	tsk->cputime_expires.prof_exp = 0;
	tsk->cputime_expires.virt_exp = 0;
	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]);
}
1655 1656 1657
#else
static inline void posix_cpu_timers_init(struct task_struct *tsk) { }
#endif
1658

1659 1660 1661 1662 1663 1664 1665 1666 1667
static inline void init_task_pid_links(struct task_struct *task)
{
	enum pid_type type;

	for (type = PIDTYPE_PID; type < PIDTYPE_MAX; ++type) {
		INIT_HLIST_NODE(&task->pid_links[type]);
	}
}

1668 1669 1670
static inline void
init_task_pid(struct task_struct *task, enum pid_type type, struct pid *pid)
{
1671 1672 1673 1674
	if (type == PIDTYPE_PID)
		task->thread_pid = pid;
	else
		task->signal->pids[type] = pid;
1675 1676
}

1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691
static inline void rcu_copy_process(struct task_struct *p)
{
#ifdef CONFIG_PREEMPT_RCU
	p->rcu_read_lock_nesting = 0;
	p->rcu_read_unlock_special.s = 0;
	p->rcu_blocked_node = NULL;
	INIT_LIST_HEAD(&p->rcu_node_entry);
#endif /* #ifdef CONFIG_PREEMPT_RCU */
#ifdef CONFIG_TASKS_RCU
	p->rcu_tasks_holdout = false;
	INIT_LIST_HEAD(&p->rcu_tasks_holdout_list);
	p->rcu_tasks_idle_cpu = -1;
#endif /* #ifdef CONFIG_TASKS_RCU */
}

1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733
static int pidfd_release(struct inode *inode, struct file *file)
{
	struct pid *pid = file->private_data;

	file->private_data = NULL;
	put_pid(pid);
	return 0;
}

#ifdef CONFIG_PROC_FS
static void pidfd_show_fdinfo(struct seq_file *m, struct file *f)
{
	struct pid_namespace *ns = proc_pid_ns(file_inode(m->file));
	struct pid *pid = f->private_data;

	seq_put_decimal_ull(m, "Pid:\t", pid_nr_ns(pid, ns));
	seq_putc(m, '\n');
}
#endif

const struct file_operations pidfd_fops = {
	.release = pidfd_release,
#ifdef CONFIG_PROC_FS
	.show_fdinfo = pidfd_show_fdinfo,
#endif
};

static void __delayed_free_task(struct rcu_head *rhp)
{
	struct task_struct *tsk = container_of(rhp, struct task_struct, rcu);

	free_task(tsk);
}

static __always_inline void delayed_free_task(struct task_struct *tsk)
{
	if (IS_ENABLED(CONFIG_MEMCG))
		call_rcu(&tsk->rcu, __delayed_free_task);
	else
		free_task(tsk);
}

1734 1735 1736 1737 1738 1739 1740 1741
/*
 * 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.
 */
1742 1743
static __latent_entropy struct task_struct *copy_process(
					unsigned long clone_flags,
1744 1745
					unsigned long stack_start,
					unsigned long stack_size,
1746
					int __user *parent_tidptr,
1747 1748 1749 1750 1751 1752
					int __user *child_tidptr,
					struct pid *pid,
					int trace,
					unsigned long tls,
					int node)
{
1753
	int pidfd = -1, retval;
1754
	struct task_struct *p;
1755
	struct multiprocess_signals delayed;
1756
	struct file *pidfile = NULL;
1757

1758 1759 1760 1761
	/*
	 * Don't allow sharing the root directory with processes in a different
	 * namespace
	 */
1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803
	if ((clone_flags & (CLONE_NEWNS|CLONE_FS)) == (CLONE_NEWNS|CLONE_FS))
		return ERR_PTR(-EINVAL);

	if ((clone_flags & (CLONE_NEWUSER|CLONE_FS)) == (CLONE_NEWUSER|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);

	/*
	 * 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);

	/*
	 * If the new process will be in a different pid or user namespace
	 * do not allow it to share a thread group with the forking task.
	 */
	if (clone_flags & CLONE_THREAD) {
		if ((clone_flags & (CLONE_NEWUSER | CLONE_NEWPID)) ||
		    (task_active_pid_ns(current) !=
				current->nsproxy->pid_ns_for_children))
			return ERR_PTR(-EINVAL);
	}

1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816
	if (clone_flags & CLONE_PIDFD) {
		/*
		 * - CLONE_PARENT_SETTID is useless for pidfds and also
		 *   parent_tidptr is used to return pidfds.
		 * - CLONE_DETACHED is blocked so that we can potentially
		 *   reuse it later for CLONE_PIDFD.
		 * - CLONE_THREAD is blocked until someone really needs it.
		 */
		if (clone_flags &
		    (CLONE_DETACHED | CLONE_PARENT_SETTID | CLONE_THREAD))
			return ERR_PTR(-EINVAL);
	}

1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834
	/*
	 * Force any signals received before this point to be delivered
	 * before the fork happens.  Collect up signals sent to multiple
	 * processes that happen during the fork and delay them so that
	 * they appear to happen after the fork.
	 */
	sigemptyset(&delayed.signal);
	INIT_HLIST_NODE(&delayed.node);

	spin_lock_irq(&current->sighand->siglock);
	if (!(clone_flags & CLONE_THREAD))
		hlist_add_head(&delayed.node, &current->signal->multiprocess);
	recalc_sigpending();
	spin_unlock_irq(&current->sighand->siglock);
	retval = -ERESTARTNOINTR;
	if (signal_pending(current))
		goto fork_out;

1835 1836 1837 1838 1839
	retval = -ENOMEM;
	p = dup_task_struct(current, node);
	if (!p)
		goto fork_out;

1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851
	/*
	 * This _must_ happen before we call free_task(), i.e. before we jump
	 * to any of the bad_fork_* labels. This is to avoid freeing
	 * p->set_child_tid which is (ab)used as a kthread's data pointer for
	 * kernel threads (PF_KTHREAD).
	 */
	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;

1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882
	ftrace_graph_init_task(p);

	rt_mutex_init_task(p);

#ifdef CONFIG_PROVE_LOCKING
	DEBUG_LOCKS_WARN_ON(!p->hardirqs_enabled);
	DEBUG_LOCKS_WARN_ON(!p->softirqs_enabled);
#endif
	retval = -EAGAIN;
	if (atomic_read(&p->real_cred->user->processes) >=
			task_rlimit(p, RLIMIT_NPROC)) {
		if (p->real_cred->user != INIT_USER &&
		    !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN))
			goto bad_fork_free;
	}
	current->flags &= ~PF_NPROC_EXCEEDED;

	retval = copy_creds(p, clone_flags);
	if (retval < 0)
		goto bad_fork_free;

	/*
	 * 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.
	 */
	retval = -EAGAIN;
	if (nr_threads >= max_threads)
		goto bad_fork_cleanup_count;

	delayacct_tsk_init(p);	/* Must remain after dup_task_struct() */
1883
	p->flags &= ~(PF_SUPERPRIV | PF_WQ_WORKER | PF_IDLE);
1884 1885 1886 1887 1888 1889 1890 1891 1892 1893
	p->flags |= PF_FORKNOEXEC;
	INIT_LIST_HEAD(&p->children);
	INIT_LIST_HEAD(&p->sibling);
	rcu_copy_process(p);
	p->vfork_done = NULL;
	spin_lock_init(&p->alloc_lock);

	init_sigpending(&p->pending);

	p->utime = p->stime = p->gtime = 0;
1894
#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME
1895
	p->utimescaled = p->stimescaled = 0;
1896
#endif
1897 1898 1899
	prev_cputime_init(&p->prev_cputime);

#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
1900 1901 1902
	seqcount_init(&p->vtime.seqcount);
	p->vtime.starttime = 0;
	p->vtime.state = VTIME_INACTIVE;
1903 1904 1905 1906 1907 1908 1909 1910
#endif

#if defined(SPLIT_RSS_COUNTING)
	memset(&p->rss_stat, 0, sizeof(p->rss_stat));
#endif

	p->default_timer_slack_ns = current->timer_slack_ns;

1911 1912 1913 1914
#ifdef CONFIG_PSI
	p->psi_flags = 0;
#endif

1915 1916 1917 1918 1919 1920
	task_io_accounting_init(&p->ioac);
	acct_clear_integrals(p);

	posix_cpu_timers_init(p);

	p->io_context = NULL;
1921
	audit_set_context(p, NULL);
1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957
	cgroup_fork(p);
#ifdef CONFIG_NUMA
	p->mempolicy = mpol_dup(p->mempolicy);
	if (IS_ERR(p->mempolicy)) {
		retval = PTR_ERR(p->mempolicy);
		p->mempolicy = NULL;
		goto bad_fork_cleanup_threadgroup_lock;
	}
#endif
#ifdef CONFIG_CPUSETS
	p->cpuset_mem_spread_rotor = NUMA_NO_NODE;
	p->cpuset_slab_spread_rotor = NUMA_NO_NODE;
	seqcount_init(&p->mems_allowed_seq);
#endif
#ifdef CONFIG_TRACE_IRQFLAGS
	p->irq_events = 0;
	p->hardirqs_enabled = 0;
	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

	p->pagefault_disabled = 0;

#ifdef CONFIG_LOCKDEP
	p->lockdep_depth = 0; /* no locks held yet */
	p->curr_chain_key = 0;
	p->lockdep_recursion = 0;
1958
	lockdep_init_task(p);
1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981
#endif

#ifdef CONFIG_DEBUG_MUTEXES
	p->blocked_on = NULL; /* not blocked yet */
#endif
#ifdef CONFIG_BCACHE
	p->sequential_io	= 0;
	p->sequential_io_avg	= 0;
#endif

	/* Perform scheduler related setup. Assign this task to a CPU. */
	retval = sched_fork(clone_flags, p);
	if (retval)
		goto bad_fork_cleanup_policy;

	retval = perf_event_init_task(p);
	if (retval)
		goto bad_fork_cleanup_policy;
	retval = audit_alloc(p);
	if (retval)
		goto bad_fork_cleanup_perf;
	/* copy all the process information */
	shm_init_task(p);
1982
	retval = security_task_alloc(p, clone_flags);
1983 1984
	if (retval)
		goto bad_fork_cleanup_audit;
1985 1986 1987
	retval = copy_semundo(clone_flags, p);
	if (retval)
		goto bad_fork_cleanup_security;
1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012
	retval = copy_files(clone_flags, p);
	if (retval)
		goto bad_fork_cleanup_semundo;
	retval = copy_fs(clone_flags, p);
	if (retval)
		goto bad_fork_cleanup_files;
	retval = copy_sighand(clone_flags, p);
	if (retval)
		goto bad_fork_cleanup_fs;
	retval = copy_signal(clone_flags, p);
	if (retval)
		goto bad_fork_cleanup_sighand;
	retval = copy_mm(clone_flags, p);
	if (retval)
		goto bad_fork_cleanup_signal;
	retval = copy_namespaces(clone_flags, p);
	if (retval)
		goto bad_fork_cleanup_mm;
	retval = copy_io(clone_flags, p);
	if (retval)
		goto bad_fork_cleanup_namespaces;
	retval = copy_thread_tls(clone_flags, stack_start, stack_size, p, tls);
	if (retval)
		goto bad_fork_cleanup_io;

2013 2014
	stackleak_task_init(p);

2015 2016 2017 2018 2019 2020 2021 2022
	if (pid != &init_struct_pid) {
		pid = alloc_pid(p->nsproxy->pid_ns_for_children);
		if (IS_ERR(pid)) {
			retval = PTR_ERR(pid);
			goto bad_fork_cleanup_thread;
		}
	}

2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048
	/*
	 * This has to happen after we've potentially unshared the file
	 * descriptor table (so that the pidfd doesn't leak into the child
	 * if the fd table isn't shared).
	 */
	if (clone_flags & CLONE_PIDFD) {
		retval = get_unused_fd_flags(O_RDWR | O_CLOEXEC);
		if (retval < 0)
			goto bad_fork_free_pid;

		pidfd = retval;

		pidfile = anon_inode_getfile("[pidfd]", &pidfd_fops, pid,
					      O_RDWR | O_CLOEXEC);
		if (IS_ERR(pidfile)) {
			put_unused_fd(pidfd);
			retval = PTR_ERR(pidfile);
			goto bad_fork_free_pid;
		}
		get_pid(pid);	/* held by pidfile now */

		retval = put_user(pidfd, parent_tidptr);
		if (retval)
			goto bad_fork_put_pidfd;
	}

2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074
#ifdef CONFIG_BLOCK
	p->plug = NULL;
#endif
#ifdef CONFIG_FUTEX
	p->robust_list = NULL;
#ifdef CONFIG_COMPAT
	p->compat_robust_list = NULL;
#endif
	INIT_LIST_HEAD(&p->pi_state_list);
	p->pi_state_cache = NULL;
#endif
	/*
	 * sigaltstack should be cleared when sharing the same VM
	 */
	if ((clone_flags & (CLONE_VM|CLONE_VFORK)) == CLONE_VM)
		sas_ss_reset(p);

	/*
	 * Syscall tracing and stepping should be turned off in the
	 * child regardless of CLONE_PTRACE.
	 */
	user_disable_single_step(p);
	clear_tsk_thread_flag(p, TIF_SYSCALL_TRACE);
#ifdef TIF_SYSCALL_EMU
	clear_tsk_thread_flag(p, TIF_SYSCALL_EMU);
#endif
2075
	clear_tsk_latency_tracing(p);
2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099

	/* ok, now we should be set up.. */
	p->pid = pid_nr(pid);
	if (clone_flags & CLONE_THREAD) {
		p->exit_signal = -1;
		p->group_leader = current->group_leader;
		p->tgid = current->tgid;
	} else {
		if (clone_flags & CLONE_PARENT)
			p->exit_signal = current->group_leader->exit_signal;
		else
			p->exit_signal = (clone_flags & CSIGNAL);
		p->group_leader = p;
		p->tgid = p->pid;
	}

	p->nr_dirtied = 0;
	p->nr_dirtied_pause = 128 >> (PAGE_SHIFT - 10);
	p->dirty_paused_when = 0;

	p->pdeath_signal = 0;
	INIT_LIST_HEAD(&p->thread_group);
	p->task_works = NULL;

2100
	cgroup_threadgroup_change_begin(current);
2101 2102 2103 2104 2105 2106 2107 2108
	/*
	 * Ensure that the cgroup subsystem policies allow the new process to be
	 * forked. It should be noted the the new process's css_set can be changed
	 * between here and cgroup_post_fork() if an organisation operation is in
	 * progress.
	 */
	retval = cgroup_can_fork(p);
	if (retval)
2109
		goto bad_fork_cgroup_threadgroup_change_end;
2110

2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121
	/*
	 * From this point on we must avoid any synchronous user-space
	 * communication until we take the tasklist-lock. In particular, we do
	 * not want user-space to be able to predict the process start-time by
	 * stalling fork(2) after we recorded the start_time but before it is
	 * visible to the system.
	 */

	p->start_time = ktime_get_ns();
	p->real_start_time = ktime_get_boot_ns();

2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136
	/*
	 * Make it visible to the rest of the system, but dont wake it up yet.
	 * Need tasklist lock for parent etc handling!
	 */
	write_lock_irq(&tasklist_lock);

	/* CLONE_PARENT re-uses the old parent */
	if (clone_flags & (CLONE_PARENT|CLONE_THREAD)) {
		p->real_parent = current->real_parent;
		p->parent_exec_id = current->parent_exec_id;
	} else {
		p->real_parent = current;
		p->parent_exec_id = current->self_exec_id;
	}

2137 2138
	klp_copy_process(p);

2139 2140 2141 2142 2143 2144 2145 2146
	spin_lock(&current->sighand->siglock);

	/*
	 * Copy seccomp details explicitly here, in case they were changed
	 * before holding sighand lock.
	 */
	copy_seccomp(p);

2147 2148
	rseq_fork(p, clone_flags);

2149
	/* Don't start children in a dying pid namespace */
2150
	if (unlikely(!(ns_of_pid(pid)->pid_allocated & PIDNS_ADDING))) {
2151 2152 2153
		retval = -ENOMEM;
		goto bad_fork_cancel_cgroup;
	}
2154

2155 2156 2157 2158 2159 2160
	/* Let kill terminate clone/fork in the middle */
	if (fatal_signal_pending(current)) {
		retval = -EINTR;
		goto bad_fork_cancel_cgroup;
	}

2161 2162 2163
	/* past the last point of failure */
	if (pidfile)
		fd_install(pidfd, pidfile);
2164 2165

	init_task_pid_links(p);
2166 2167 2168 2169 2170
	if (likely(p->pid)) {
		ptrace_init_task(p, (clone_flags & CLONE_PTRACE) || trace);

		init_task_pid(p, PIDTYPE_PID, pid);
		if (thread_group_leader(p)) {
2171
			init_task_pid(p, PIDTYPE_TGID, pid);
2172 2173 2174 2175 2176 2177 2178
			init_task_pid(p, PIDTYPE_PGID, task_pgrp(current));
			init_task_pid(p, PIDTYPE_SID, task_session(current));

			if (is_child_reaper(pid)) {
				ns_of_pid(pid)->child_reaper = p;
				p->signal->flags |= SIGNAL_UNKILLABLE;
			}
2179
			p->signal->shared_pending.signal = delayed.signal;
2180
			p->signal->tty = tty_kref_get(current->signal->tty);
2181 2182 2183 2184 2185 2186 2187
			/*
			 * Inherit has_child_subreaper flag under the same
			 * tasklist_lock with adding child to the process tree
			 * for propagate_has_child_subreaper optimization.
			 */
			p->signal->has_child_subreaper = p->real_parent->signal->has_child_subreaper ||
							 p->real_parent->signal->is_child_subreaper;
2188 2189
			list_add_tail(&p->sibling, &p->real_parent->children);
			list_add_tail_rcu(&p->tasks, &init_task.tasks);
2190
			attach_pid(p, PIDTYPE_TGID);
2191 2192 2193 2194 2195 2196
			attach_pid(p, PIDTYPE_PGID);
			attach_pid(p, PIDTYPE_SID);
			__this_cpu_inc(process_counts);
		} else {
			current->signal->nr_threads++;
			atomic_inc(&current->signal->live);
2197
			refcount_inc(&current->signal->sigcnt);
2198
			task_join_group_stop(p);
Lorenzo Faletra's avatar