Release 4.15 kernel/fork.c

/*
 *  linux/kernel/fork.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 */

/*
 *  'fork.c' contains the help-routines for the 'fork' system call
 * (see also entry.S and others).
 * Fork is rather simple, once you get the hang of it, but the memory
 * management can be a bitch. See 'mm/memory.c': 'copy_page_range()'
 */

#include <linux/slab.h>
#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>
#include <linux/rtmutex.h>
#include <linux/init.h>
#include <linux/unistd.h>
#include <linux/module.h>
#include <linux/vmalloc.h>
#include <linux/completion.h>
#include <linux/personality.h>
#include <linux/mempolicy.h>
#include <linux/sem.h>
#include <linux/file.h>
#include <linux/fdtable.h>
#include <linux/iocontext.h>
#include <linux/key.h>
#include <linux/binfmts.h>
#include <linux/mman.h>
#include <linux/mmu_notifier.h>
#include <linux/hmm.h>
#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>
#include <linux/userfaultfd_k.h>
#include <linux/tsacct_kern.h>
#include <linux/cn_proc.h>
#include <linux/freezer.h>
#include <linux/delayacct.h>
#include <linux/taskstats_kern.h>
#include <linux/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>
#include <linux/livepatch.h>
#include <linux/thread_info.h>

#include <asm/pgtable.h>
#include <asm/pgalloc.h>
#include <linux/uaccess.h>
#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.. */


int max_threads;		
/* tunable limit on nr_threads */

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);
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Paul E. McKenney
14
100.00%
1
100.00%
Total
14
100.00%
1
100.00%


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;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Andrew Morton
30
96.77%
2
66.67%
Ian Campbell
1
3.23%
1
33.33%
Total
31
100.00%
3
100.00%



void __weak arch_release_task_struct(struct task_struct *tsk)
{
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Akinobu Mita
10
100.00%
1
100.00%
Total
10
100.00%
1
100.00%

#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);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Thomas Gleixner
18
81.82%
1
50.00%
Eric Dumazet
4
18.18%
1
50.00%
Total
22
100.00%
2
100.00%



static inline void free_task_struct(struct task_struct *tsk)
{
	kmem_cache_free(task_struct_cachep, tsk);
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Thomas Gleixner
15
78.95%
1
33.33%
David Mosberger-Tang
3
15.79%
1
33.33%
Christoph Lameter
1
5.26%
1
33.33%
Total
19
100.00%
3
100.00%

#endif



void __weak arch_release_thread_stack(unsigned long *stack)
{
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Thomas Gleixner
6
60.00%
1
50.00%
Linus Torvalds
4
40.00%
1
50.00%
Total
10
100.00%
2
100.00%

#ifndef CONFIG_ARCH_THREAD_STACK_ALLOCATOR

/*
 * Allocate pages if THREAD_SIZE is >= PAGE_SIZE, otherwise use a
 * kmemcache based allocator.
 */
# 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]);



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;
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Hoeun Ryu
74
100.00%
1
100.00%
Total
74
100.00%
1
100.00%

#endif



static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node)
{
#ifdef CONFIG_VMAP_STACK
	void *stack;
	int i;

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

		s = this_cpu_xchg(cached_stacks[i], NULL);

		if (!s)
			continue;

#ifdef CONFIG_DEBUG_KMEMLEAK
		/* Clear stale pointers from reused stack. */
		memset(s->addr, 0, THREAD_SIZE);
#endif
		tsk->stack_vm_area = s;
		return s->addr;
	}

	stack = __vmalloc_node_range(THREAD_SIZE, THREAD_ALIGN,
				     VMALLOC_START, VMALLOC_END,
				     THREADINFO_GFP,
				     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.
         */
	if (stack)
		tsk->stack_vm_area = find_vm_area(stack);
	return stack;
#else
	struct page *page = alloc_pages_node(node, THREADINFO_GFP,
					     THREAD_SIZE_ORDER);

	return page ? page_address(page) : NULL;
#endif
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Andrew Lutomirski
98
60.12%
2
20.00%
Eric Dumazet
20
12.27%
1
10.00%
Konstantin Khlebnikov
17
10.43%
1
10.00%
FUJITA Tomonori
15
9.20%
1
10.00%
Christoph Lameter
7
4.29%
1
10.00%
Linus Torvalds
3
1.84%
1
10.00%
Vladimir Davydov
2
1.23%
2
20.00%
Mark Rutland
1
0.61%
1
10.00%
Total
163
100.00%
10
100.00%



static inline void free_thread_stack(struct task_struct *tsk)
{
#ifdef CONFIG_VMAP_STACK
	if (task_stack_vm_area(tsk)) {
		int i;

		for (i = 0; i < NR_CACHED_STACKS; i++) {
			if (this_cpu_cmpxchg(cached_stacks[i],
					NULL, tsk->stack_vm_area) != NULL)
				continue;

			return;
		}

		vfree_atomic(tsk->stack);
		return;
	}
#endif

	__free_pages(virt_to_page(tsk->stack), THREAD_SIZE_ORDER);
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Andrew Lutomirski
59
70.24%
3
37.50%
FUJITA Tomonori
12
14.29%
1
12.50%
Christoph Lameter
7
8.33%
1
12.50%
Vladimir Davydov
3
3.57%
1
12.50%
Linus Torvalds
2
2.38%
1
12.50%
Andrey Ryabinin
1
1.19%
1
12.50%
Total
84
100.00%
8
100.00%

# else

static struct kmem_cache *thread_stack_cache;



static unsigned long *alloc_thread_stack_node(struct task_struct *tsk,
						  int node)
{
	return kmem_cache_alloc_node(thread_stack_cache, THREADINFO_GFP, node);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Thomas Gleixner
22
84.62%
1
33.33%
Linus Torvalds
2
7.69%
1
33.33%
Michael Ellerman
2
7.69%
1
33.33%
Total
26
100.00%
3
100.00%



static void free_thread_stack(struct task_struct *tsk)
{
	kmem_cache_free(thread_stack_cache, tsk->stack);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Thomas Gleixner
12
60.00%
1
25.00%
Andrew Lutomirski
5
25.00%
1
25.00%
Linus Torvalds
2
10.00%
1
25.00%
Michael Ellerman
1
5.00%
1
25.00%
Total
20
100.00%
4
100.00%



void thread_stack_cache_init(void)
{
	thread_stack_cache = kmem_cache_create("thread_stack", THREAD_SIZE,
					      THREAD_SIZE, 0, NULL);
	BUG_ON(thread_stack_cache == NULL);
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Thomas Gleixner
25
86.21%
1
50.00%
Linus Torvalds
4
13.79%
1
50.00%
Total
29
100.00%
2
100.00%

# 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 */

struct kmem_cache *vm_area_cachep;

/* SLAB cache for mm_struct structures (tsk->mm) */

static struct kmem_cache *mm_cachep;



static void account_kernel_stack(struct task_struct *tsk, int account)
{
	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);
		}

		/* All stack pages belong to the same memcg. */
		mod_memcg_page_state(vm->pages[0], MEMCG_KERNEL_STACK_KB,
				     account * (THREAD_SIZE / 1024));
	} 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);

		mod_memcg_page_state(first_page, MEMCG_KERNEL_STACK_KB,
				     account * (THREAD_SIZE / 1024));
	}
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Andrew Lutomirski
143
83.63%
3
50.00%
Motohiro Kosaki
25
14.62%
1
16.67%
Johannes Weiner
2
1.17%
1
16.67%
Linus Torvalds
1
0.58%
1
16.67%
Total
171
100.00%
6
100.00%



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

	account_kernel_stack(tsk, -1);
	arch_release_thread_stack(tsk->stack);
	free_thread_stack(tsk);
	tsk->stack = NULL;
#ifdef CONFIG_VMAP_STACK
	tsk->stack_vm_area = NULL;
#endif
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Andrew Lutomirski
33
54.10%
2
33.33%
Ingo Molnar
12
19.67%
1
16.67%
Motohiro Kosaki
8
13.11%
1
16.67%
Akinobu Mita
6
9.84%
1
16.67%
Linus Torvalds
2
3.28%
1
16.67%
Total
61
100.00%
6
100.00%

#ifdef CONFIG_THREAD_INFO_IN_TASK


void put_task_stack(struct task_struct *tsk)
{
	if (atomic_dec_and_test(&tsk->stack_refcount))
		release_task_stack(tsk);
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Andrew Lutomirski
25
100.00%
1
100.00%
Total
25
100.00%
1
100.00%

#endif



void free_task(struct task_struct *tsk)
{
#ifndef CONFIG_THREAD_INFO_IN_TASK
	/*
         * The task is finally done with both the stack and thread_info,
         * so free both.
         */
	release_task_stack(tsk);
#else
	/*
         * If the task had a separate stack allocation, it should be gone
         * by now.
         */
	WARN_ON_ONCE(atomic_read(&tsk->stack_refcount) != 0);
#endif
	rt_mutex_debug_task_free(tsk);
	ftrace_graph_exit_task(tsk);
	put_seccomp_filter(tsk);
	arch_release_task_struct(tsk);
	if (tsk->flags & PF_KTHREAD)
		free_kthread_struct(tsk);
	free_task_struct(tsk);
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Andrew Lutomirski
36
48.00%
1
11.11%
Oleg Nesterov
13
17.33%
1
11.11%
Ingo Molnar
10
13.33%
2
22.22%
Frédéric Weisbecker
5
6.67%
2
22.22%
Akinobu Mita
5
6.67%
1
11.11%
Will Drewry
5
6.67%
1
11.11%
David Mosberger-Tang
1
1.33%
1
11.11%
Total
75
100.00%
9
100.00%


EXPORT_SYMBOL(free_task);



static inline void free_signal_struct(struct signal_struct *sig)
{
	taskstats_tgid_free(sig);
	sched_autogroup_exit(sig);
	/*
         * __mmdrop is not safe to call from softirq context on x86 due to
         * pgd_dtor so postpone it to the async context
         */
	if (sig->oom_mm)
		mmdrop_async(sig->oom_mm);
	kmem_cache_free(signal_cachep, sig);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Oleg Nesterov
24
55.81%
2
40.00%
Michal Hocko
14
32.56%
2
40.00%
Mike Galbraith
5
11.63%
1
20.00%
Total
43
100.00%
5
100.00%



static inline void put_signal_struct(struct signal_struct *sig)
{
	if (atomic_dec_and_test(&sig->sigcnt))
		free_signal_struct(sig);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Oleg Nesterov
27
100.00%
1
100.00%
Total
27
100.00%
1
100.00%



void __put_task_struct(struct task_struct *tsk)
{
	WARN_ON(!tsk->exit_state);
	WARN_ON(atomic_read(&tsk->usage));
	WARN_ON(tsk == current);

	cgroup_free(tsk);
	task_numa_free(tsk);
	security_task_free(tsk);
	exit_creds(tsk);
	delayacct_tsk_free(tsk);
	put_signal_struct(tsk->signal);

	if (!profile_handoff_task(tsk))
		free_task(tsk);
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Linus Torvalds
35
43.21%
1
7.69%
John Levon
8
9.88%
1
7.69%
Oleg Nesterov
7
8.64%
1
7.69%
Shailabh Nagar
5
6.17%
1
7.69%
Tejun Heo
5
6.17%
1
7.69%
Kees Cook
5
6.17%
1
7.69%
Andrew Morton
5
6.17%
2
15.38%
Mike Galbraith
5
6.17%
1
7.69%
Christoph Hellwig
3
3.70%
1
7.69%
David Howells
1
1.23%
1
7.69%
David Mosberger-Tang
1
1.23%
1
7.69%
Ingo Molnar
1
1.23%
1
7.69%
Total
81
100.00%
13
100.00%


EXPORT_SYMBOL_GPL(__put_task_struct);



void __init __weak arch_task_cache_init(void) { }

Contributors
Person
Tokens
Prop
Commits
CommitProp
Thomas Gleixner
7
87.50%
1
50.00%
Suresh B. Siddha
1
12.50%
1
50.00%
Total
8
100.00%
2
100.00%

/*
 * set_max_threads
 */


static void set_max_threads(unsigned int max_threads_suggested)
{
	u64 threads;

	/*
         * The number of threads shall be limited such that the thread
         * structures may only consume a small part of the available memory.
         */
	if (fls64(totalram_pages) + fls64(PAGE_SIZE) > 64)
		threads = MAX_THREADS;
	else
		threads = div64_u64((u64) totalram_pages * (u64) PAGE_SIZE,
				    (u64) THREAD_SIZE * 8UL);

	if (threads > max_threads_suggested)
		threads = max_threads_suggested;

	max_threads = clamp_t(u64, threads, MIN_THREADS, MAX_THREADS);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Heinrich Schuchardt
78
100.00%
3
100.00%
Total
78
100.00%
3
100.00%

#ifdef CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT
/* Initialized by the architecture: */

int arch_task_struct_size __read_mostly;
#endif



void __init fork_init(void)
{
	int i;
#ifndef CONFIG_ARCH_TASK_STRUCT_ALLOCATOR
#ifndef ARCH_MIN_TASKALIGN

#define ARCH_MIN_TASKALIGN	0
#endif
	int align = max_t(int, L1_CACHE_BYTES, ARCH_MIN_TASKALIGN);

	/* create a slab on which task_structs can be allocated */
	task_struct_cachep = kmem_cache_create("task_struct",
			arch_task_struct_size, align,
			SLAB_PANIC|SLAB_ACCOUNT, NULL);
#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];

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

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

	lockdep_init_task(&init_task);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Linus Torvalds (pre-git)
34
21.25%
5
19.23%
Eric W. Biedermann
28
17.50%
3
11.54%
Roland McGrath
22
13.75%
2
7.69%
Hoeun Ryu
16
10.00%
1
3.85%
Peter Zijlstra
14
8.75%
2
7.69%
David Howells
13
8.12%
1
3.85%
Andrew Morton
9
5.62%
2
7.69%
Byungchul Park
6
3.75%
1
3.85%
Heinrich Schuchardt
5
3.12%
2
7.69%
Suresh B. Siddha
4
2.50%
1
3.85%
David Mosberger-Tang
4
2.50%
1
3.85%
Vegard Nossum
1
0.62%
1
3.85%
Thomas Gleixner
1
0.62%
1
3.85%
Alan Cox
1
0.62%
1
3.85%
Ingo Molnar
1
0.62%
1
3.85%
Vladimir Davydov
1
0.62%
1
3.85%
Total
160
100.00%
26
100.00%



int __weak arch_dup_task_struct(struct task_struct *dst,
					       struct task_struct *src)
{
	*dst = *src;
	return 0;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Suresh B. Siddha
17
68.00%
1
50.00%
Gideon Israel Dsouza
8
32.00%
1
50.00%
Total
25
100.00%
2
100.00%



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 */
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Aaron Tomlin
28
100.00%
1
100.00%
Total
28
100.00%
1
100.00%



static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
{
	struct task_struct *tsk;
	unsigned long *stack;
	struct vm_struct *stack_vm_area;
	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;

	stack_vm_area = task_stack_vm_area(tsk);

	err = arch_dup_task_struct(tsk, orig);

	/*
         * 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
	atomic_set(&tsk->stack_refcount, 1);
#endif

	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);

#ifdef CONFIG_CC_STACKPROTECTOR
	tsk->stack_canary = get_random_canary();
#endif

	/*
         * One for us, one for whoever does the "release_task()" (usually
         * parent)
         */
	atomic_set(&tsk->usage, 2);
#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;

	account_kernel_stack(tsk, 1);

	kcov_task_init(tsk);

#ifdef CONFIG_FAULT_INJECTION
	tsk->fail_nth = 0;
#endif

	return tsk;

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

Contributors
Person
Tokens
Prop
Commits
CommitProp
David Howells
52
19.26%
1
3.03%
Andrew Lutomirski
47
17.41%
2
6.06%
Eric Dumazet
19
7.04%
4
12.12%
Suresh B. Siddha
18
6.67%
1
3.03%
Dmitriy Vyukov
16
5.93%
2
6.06%
Kees Cook
14
5.19%
1
3.03%
Andi Kleen
13
4.81%
1
3.03%
Jens Axboe
12
4.44%
2
6.06%
Arjan van de Ven
11
4.07%
1
3.03%
Linus Torvalds
10
3.70%
2
6.06%
Sebastian Andrzej Siewior
8
2.96%
1
3.03%
Andrew Morton
6
2.22%
1
3.03%
Motohiro Kosaki
6
2.22%
1
3.03%
Mike Galbraith
5
1.85%
1
3.03%
Akinobu Mita
5
1.85%
1
3.03%
Alexey Dobriyan
5
1.85%
1
3.03%
Al Viro
5
1.85%
1
3.03%
Avi Kivity
5
1.85%
1
3.03%
Eric Sandeen
4
1.48%
1
3.03%
Ingo Molnar
2
0.74%
1
3.03%
David Mosberger-Tang
2
0.74%
1
3.03%
Peter Zijlstra
1
0.37%
1
3.03%
Aaron Tomlin
1
0.37%
1
3.03%
Rik Van Riel
1
0.37%
1
3.03%
Stephen Rothwell
1
0.37%
1
3.03%
Daniel Rebelo de Oliveira
1
0.37%
1
3.03%
Total
270
100.00%
33
100.00%

#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;
		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;
		}
		tmp = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
		if (!tmp)
			goto fail_nomem;
		*tmp = *mpnt;
		INIT_LIST_HEAD(&tmp->anon_vma_chain);
		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 */
	retval = arch_dup_mmap(oldmm, mm);
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)