fork.c

实现创建进程的fork函数的源代码

/*
 *  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/config.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/unistd.h>
#include <linux/smp_lock.h>
#include <linux/module.h>
#include <linux/vmalloc.h>
#include <linux/completion.h>
#include <linux/namespace.h>
#include <linux/personality.h>
#include <linux/mempolicy.h>
#include <linux/sem.h>
#include <linux/file.h>
#include <linux/binfmts.h>
#include <linux/mman.h>
#include <linux/fs.h>
#include <linux/cpu.h>
#include <linux/security.h>
#include <linux/syscalls.h>
#include <linux/jiffies.h>
#include <linux/futex.h>
#include <linux/ptrace.h>
#include <linux/mount.h>
#include <linux/audit.h>
#include <linux/rmap.h>

#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>

/* The idle threads do not count..
 * Protected by write_lock_irq(&tasklist_lock)
 */
int nr_threads;

int max_threads;
unsigned long total_forks;	/* Handle normal Linux uptimes. */

DEFINE_PER_CPU(unsigned long, process_counts) = 0;

rwlock_t tasklist_lock __cacheline_aligned = RW_LOCK_UNLOCKED;  /* outer */

EXPORT_SYMBOL(tasklist_lock);

int nr_processes(void)
{
	int cpu;
	int total = 0;

	for_each_online_cpu(cpu)
		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))
static kmem_cache_t *task_struct_cachep;
#endif

static void free_task(struct task_struct *tsk)
{
	free_thread_info(tsk->thread_info);
	free_task_struct(tsk);
}

void __put_task_struct(struct task_struct *tsk)
{
	WARN_ON(!(tsk->state & (TASK_DEAD | TASK_ZOMBIE)));
	WARN_ON(atomic_read(&tsk->usage));
	WARN_ON(tsk == current);

	if (unlikely(tsk->audit_context))
		audit_free(tsk);
	security_task_free(tsk);
	free_uid(tsk->user);
	put_group_info(tsk->group_info);
	free_task(tsk);
}

void fastcall add_wait_queue(wait_queue_head_t *q, wait_queue_t * wait)
{
	unsigned long flags;

	wait->flags &= ~WQ_FLAG_EXCLUSIVE;
	spin_lock_irqsave(&q->lock, flags);
	__add_wait_queue(q, wait);
	spin_unlock_irqrestore(&q->lock, flags);
}

EXPORT_SYMBOL(add_wait_queue);

void fastcall add_wait_queue_exclusive(wait_queue_head_t *q, wait_queue_t * wait)
{
	unsigned long flags;

	wait->flags |= WQ_FLAG_EXCLUSIVE;
	spin_lock_irqsave(&q->lock, flags);
	__add_wait_queue_tail(q, wait);
	spin_unlock_irqrestore(&q->lock, flags);
}

EXPORT_SYMBOL(add_wait_queue_exclusive);

void fastcall remove_wait_queue(wait_queue_head_t *q, wait_queue_t * wait)
{
	unsigned long flags;

	spin_lock_irqsave(&q->lock, flags);
	__remove_wait_queue(q, wait);
	spin_unlock_irqrestore(&q->lock, flags);
}

EXPORT_SYMBOL(remove_wait_queue);


/*
 * Note: we use "set_current_state()" _after_ the wait-queue add,
 * because we need a memory barrier there on SMP, so that any
 * wake-function that tests for the wait-queue being active
 * will be guaranteed to see waitqueue addition _or_ subsequent
 * tests in this thread will see the wakeup having taken place.
 *
 * The spin_unlock() itself is semi-permeable and only protects
 * one way (it only protects stuff inside the critical region and
 * stops them from bleeding out - it would still allow subsequent
 * loads to move into the the critical region).
 */
void fastcall prepare_to_wait(wait_queue_head_t *q, wait_queue_t *wait, int state)
{
	unsigned long flags;

	wait->flags &= ~WQ_FLAG_EXCLUSIVE;
	spin_lock_irqsave(&q->lock, flags);
	if (list_empty(&wait->task_list))
		__add_wait_queue(q, wait);
	set_current_state(state);
	spin_unlock_irqrestore(&q->lock, flags);
}

EXPORT_SYMBOL(prepare_to_wait);

void fastcall
prepare_to_wait_exclusive(wait_queue_head_t *q, wait_queue_t *wait, int state)
{
	unsigned long flags;

	wait->flags |= WQ_FLAG_EXCLUSIVE;
	spin_lock_irqsave(&q->lock, flags);
	if (list_empty(&wait->task_list))
		__add_wait_queue_tail(q, wait);
	set_current_state(state);
	spin_unlock_irqrestore(&q->lock, flags);
}

EXPORT_SYMBOL(prepare_to_wait_exclusive);

void fastcall finish_wait(wait_queue_head_t *q, wait_queue_t *wait)
{
	unsigned long flags;

	__set_current_state(TASK_RUNNING);
	/*
	 * We can check for list emptiness outside the lock
	 * IFF:
	 *  - we use the "careful" check that verifies both
	 *    the next and prev pointers, so that there cannot
	 *    be any half-pending updates in progress on other
	 *    CPU's that we haven't seen yet (and that might
	 *    still change the stack area.
	 * and
	 *  - all other users take the lock (ie we can only
	 *    have _one_ other CPU that looks at or modifies
	 *    the list).
	 */
	if (!list_empty_careful(&wait->task_list)) {
		spin_lock_irqsave(&q->lock, flags);
		list_del_init(&wait->task_list);
		spin_unlock_irqrestore(&q->lock, flags);
	}
}

EXPORT_SYMBOL(finish_wait);

int autoremove_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key)
{
	int ret = default_wake_function(wait, mode, sync, key);

	if (ret)
		list_del_init(&wait->task_list);
	return ret;
}

EXPORT_SYMBOL(autoremove_wake_function);

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),
			ARCH_MIN_TASKALIGN, SLAB_PANIC, NULL, NULL);
#endif

	/*
	 * 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 / (THREAD_SIZE/PAGE_SIZE) / 8;
	/*
	 * we need to allow at least 20 threads to boot a system
	 */
	if(max_threads < 20)
		max_threads = 20;

	init_task.rlim[RLIMIT_NPROC].rlim_cur = max_threads/2;
	init_task.rlim[RLIMIT_NPROC].rlim_max = max_threads/2;
}

static struct task_struct *dup_task_struct(struct task_struct *orig)
{
	struct task_struct *tsk;
	struct thread_info *ti;

	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;
	}

	*ti = *orig->thread_info;
	*tsk = *orig;
	tsk->thread_info = ti;
	ti->task = tsk;

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

#ifdef CONFIG_MMU
static inline int dup_mmap(struct mm_struct * mm, struct mm_struct * oldmm)
{
	struct vm_area_struct * mpnt, *tmp, **pprev;
	struct rb_node **rb_link, *rb_parent;
	int retval;
	unsigned long charge;
	struct mempolicy *pol;

	down_write(&oldmm->mmap_sem);
	flush_cache_mm(current->mm);
	mm->locked_vm = 0;
	mm->mmap = NULL;
	mm->mmap_cache = NULL;
	mm->free_area_cache = TASK_UNMAPPED_BASE;
	mm->map_count = 0;
	mm->rss = 0;
	cpus_clear(mm->cpu_vm_mask);
	mm->mm_rb = RB_ROOT;
	rb_link = &mm->mm_rb.rb_node;
	rb_parent = NULL;
	pprev = &mm->mmap;

	/*
	 * Add it to the mmlist after the parent.
	 * Doing it this way means that we can order the list,
	 * and fork() won't mess up the ordering significantly.
	 * Add it first so that swapoff can see any swap entries.
	 */
	spin_lock(&mmlist_lock);
	list_add(&mm->mmlist, &current->mm->mmlist);
	mmlist_nr++;
	spin_unlock(&mmlist_lock);

	for (mpnt = current->mm->mmap ; mpnt ; mpnt = mpnt->vm_next) {
		struct file *file;

		if(mpnt->vm_flags & VM_DONTCOPY)
			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;
		}
		tmp = kmem_cache_alloc(vm_area_cachep, SLAB_KERNEL);
		if (!tmp)
			goto fail_nomem;
		*tmp = *mpnt;
		pol = mpol_copy(vma_policy(mpnt));
		retval = PTR_ERR(pol);
		if (IS_ERR(pol))
			goto fail_nomem_policy;
		vma_set_policy(tmp, pol);
		tmp->vm_flags &= ~VM_LOCKED;
		tmp->vm_mm = mm;
		tmp->vm_next = NULL;
		anon_vma_link(tmp);
		vma_prio_tree_init(tmp);
		file = tmp->vm_file;
		if (file) {
			struct inode *inode = file->f_dentry->d_inode;
			get_file(file);
			if (tmp->vm_flags & VM_DENYWRITE)
				atomic_dec(&inode->i_writecount);
      
			/* insert tmp into the share list, just after mpnt */
			spin_lock(&file->f_mapping->i_mmap_lock);
			flush_dcache_mmap_lock(file->f_mapping);
			vma_prio_tree_add(tmp, mpnt);
			flush_dcache_mmap_unlock(file->f_mapping);
			spin_unlock(&file->f_mapping->i_mmap_lock);
		}

		/*
		 * Link in the new vma and copy the page table entries:
		 * link in first so that swapoff can see swap entries,
		 * and try_to_unmap_one's find_vma find the new vma.
		 */
		spin_lock(&mm->page_table_lock);
		*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++;
		retval = copy_page_range(mm, current->mm, tmp);
		spin_unlock(&mm->page_table_lock);

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

		if (retval)
			goto out;
	}
	retval = 0;

out:
	flush_tlb_mm(current->mm);
	up_write(&oldmm->mmap_sem);
	return retval;
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)
{
	pgd_free(mm->pgd);
}
#else
#define dup_mmap(mm, oldmm)	(0)
#define mm_alloc_pgd(mm)	(0)
#define mm_free_pgd(mm)
#endif /* CONFIG_MMU */

spinlock_t mmlist_lock __cacheline_aligned_in_smp = SPIN_LOCK_UNLOCKED;
int mmlist_nr;

#define allocate_mm()	(kmem_cache_alloc(mm_cachep, SLAB_KERNEL))
#define free_mm(mm)	(kmem_cache_free(mm_cachep, (mm)))

#include <linux/init_task.h>

static struct mm_struct * mm_init(struct mm_struct * mm)
{
	atomic_set(&mm->mm_users, 1);
	atomic_set(&mm->mm_count, 1);
	init_rwsem(&mm->mmap_sem);
	mm->core_waiters = 0;
	mm->page_table_lock = SPIN_LOCK_UNLOCKED;
	mm->ioctx_list_lock = RW_LOCK_UNLOCKED;
	mm->ioctx_list = NULL;
	mm->default_kioctx = (struct kioctx)INIT_KIOCTX(mm->default_kioctx, *mm);
	mm->free_area_cache = TASK_UNMAPPED_BASE;

	if (likely(!mm_alloc_pgd(mm))) {
		mm->def_flags = 0;
		return mm;
	}
	free_mm(mm);
	return NULL;
}

/*
 * Allocate and initialize an mm_struct.
 */
struct mm_struct * mm_alloc(void)
{
	struct mm_struct * mm;