inode.c

嵌入式系统设计与实例开发实验教材二源码 多线程应用程序设计 串行端口程序设计 AD接口实验 CAN总线通信实验 GPS通信实验 Linux内核移植与编译实验 IC卡读写实验 SD驱动使

/*
 * linux/fs/inode.c
 *
 * (C) 1997 Linus Torvalds
 */

#include <linux/config.h>
#include <linux/fs.h>
#include <linux/string.h>
#include <linux/mm.h>
#include <linux/dcache.h>
#include <linux/init.h>
#include <linux/quotaops.h>
#include <linux/slab.h>
#include <linux/cache.h>
#include <linux/swap.h>
#include <linux/swapctl.h>
#include <linux/prefetch.h>
#include <linux/locks.h>

/*
 * New inode.c implementation.
 *
 * This implementation has the basic premise of trying
 * to be extremely low-overhead and SMP-safe, yet be
 * simple enough to be "obviously correct".
 *
 * Famous last words.
 */

/* inode dynamic allocation 1999, Andrea Arcangeli <[e-mail]> */

/* #define INODE_PARANOIA 1 */
/* #define INODE_DEBUG 1 */

/*
 * Inode lookup is no longer as critical as it used to be:
 * most of the lookups are going to be through the dcache.
 */
#define I_HASHBITS	i_hash_shift
#define I_HASHMASK	i_hash_mask

static unsigned int i_hash_mask;
static unsigned int i_hash_shift;

/*
 * Each inode can be on two separate lists. One is
 * the hash list of the inode, used for lookups. The
 * other linked list is the "type" list:
 *  "in_use" - valid inode, i_count > 0, i_nlink > 0
 *  "dirty"  - as "in_use" but also dirty
 *  "unused" - valid inode, i_count = 0
 *
 * A "dirty" list is maintained for each super block,
 * allowing for low-overhead inode sync() operations.
 */

static LIST_HEAD(inode_in_use);
static LIST_HEAD(inode_unused);
static struct list_head *inode_hashtable;
static LIST_HEAD(anon_hash_chain); /* for inodes with NULL i_sb */

/*
 * A simple spinlock to protect the list manipulations.
 *
 * NOTE! You also have to own the lock if you change
 * the i_state of an inode while it is in use..
 */
static spinlock_t inode_lock = SPIN_LOCK_UNLOCKED;

/*
 * Statistics gathering..
 */
struct inodes_stat_t inodes_stat;

static kmem_cache_t * inode_cachep;

#define alloc_inode() \
	 ((struct inode *) kmem_cache_alloc(inode_cachep, SLAB_KERNEL))
static void destroy_inode(struct inode *inode) 
{
	if (inode_has_buffers(inode))
		BUG();
	kmem_cache_free(inode_cachep, (inode));
}


/*
 * These are initializations that only need to be done
 * once, because the fields are idempotent across use
 * of the inode, so let the slab aware of that.
 */
static void init_once(void * foo, kmem_cache_t * cachep, unsigned long flags)
{
	struct inode * inode = (struct inode *) foo;

	if ((flags & (SLAB_CTOR_VERIFY|SLAB_CTOR_CONSTRUCTOR)) ==
	    SLAB_CTOR_CONSTRUCTOR)
	{
		memset(inode, 0, sizeof(*inode));
		init_waitqueue_head(&inode->i_wait);
		INIT_LIST_HEAD(&inode->i_hash);
		INIT_LIST_HEAD(&inode->i_data.clean_pages);
		INIT_LIST_HEAD(&inode->i_data.dirty_pages);
		INIT_LIST_HEAD(&inode->i_data.locked_pages);
		INIT_LIST_HEAD(&inode->i_dentry);
		INIT_LIST_HEAD(&inode->i_dirty_buffers);
		INIT_LIST_HEAD(&inode->i_dirty_data_buffers);
		INIT_LIST_HEAD(&inode->i_devices);
		sema_init(&inode->i_sem, 1);
		sema_init(&inode->i_zombie, 1);
		spin_lock_init(&inode->i_data.i_shared_lock);
	}
}

/*
 * Put the inode on the super block's dirty list.
 *
 * CAREFUL! We mark it dirty unconditionally, but
 * move it onto the dirty list only if it is hashed.
 * If it was not hashed, it will never be added to
 * the dirty list even if it is later hashed, as it
 * will have been marked dirty already.
 *
 * In short, make sure you hash any inodes _before_
 * you start marking them dirty..
 */
 
/**
 *	__mark_inode_dirty -	internal function
 *	@inode: inode to mark
 *	@flags: what kind of dirty (i.e. I_DIRTY_SYNC)
 *	Mark an inode as dirty. Callers should use mark_inode_dirty or
 *  	mark_inode_dirty_sync.
 */
 
void __mark_inode_dirty(struct inode *inode, int flags)
{
	struct super_block * sb = inode->i_sb;

	if (!sb)
		return;

	/* Don't do this for I_DIRTY_PAGES - that doesn't actually dirty the inode itself */
	if (flags & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) {
		if (sb->s_op && sb->s_op->dirty_inode)
			sb->s_op->dirty_inode(inode);
	}

	/* avoid the locking if we can */
	if ((inode->i_state & flags) == flags)
		return;

	spin_lock(&inode_lock);
	if ((inode->i_state & flags) != flags) {
		inode->i_state |= flags;
		/* Only add valid (ie hashed) inodes to the dirty list */
		if (!(inode->i_state & I_LOCK) && !list_empty(&inode->i_hash)) {
			list_del(&inode->i_list);
			list_add(&inode->i_list, &sb->s_dirty);
		}
	}
	spin_unlock(&inode_lock);
}

static void __wait_on_inode(struct inode * inode)
{
	DECLARE_WAITQUEUE(wait, current);

	add_wait_queue(&inode->i_wait, &wait);
repeat:
	set_current_state(TASK_UNINTERRUPTIBLE);
	if (inode->i_state & I_LOCK) {
		schedule();
		goto repeat;
	}
	remove_wait_queue(&inode->i_wait, &wait);
	current->state = TASK_RUNNING;
}

static inline void wait_on_inode(struct inode *inode)
{
	if (inode->i_state & I_LOCK)
		__wait_on_inode(inode);
}


static inline void write_inode(struct inode *inode, int sync)
{
	if (inode->i_sb && inode->i_sb->s_op && inode->i_sb->s_op->write_inode && !is_bad_inode(inode))
		inode->i_sb->s_op->write_inode(inode, sync);
}

static inline void __iget(struct inode * inode)
{
	if (atomic_read(&inode->i_count)) {
		atomic_inc(&inode->i_count);
		return;
	}
	atomic_inc(&inode->i_count);
	if (!(inode->i_state & (I_DIRTY|I_LOCK))) {
		list_del(&inode->i_list);
		list_add(&inode->i_list, &inode_in_use);
	}
	inodes_stat.nr_unused--;
}

static inline void __sync_one(struct inode *inode, int sync)
{
	unsigned dirty;

	list_del(&inode->i_list);
	list_add(&inode->i_list, &inode->i_sb->s_locked_inodes);

	if (inode->i_state & I_LOCK)
		BUG();

	/* Set I_LOCK, reset I_DIRTY */
	dirty = inode->i_state & I_DIRTY;
	inode->i_state |= I_LOCK;
	inode->i_state &= ~I_DIRTY;
	spin_unlock(&inode_lock);

	filemap_fdatasync(inode->i_mapping);

	/* Don't write the inode if only I_DIRTY_PAGES was set */
	if (dirty & (I_DIRTY_SYNC | I_DIRTY_DATASYNC))
		write_inode(inode, sync);

	filemap_fdatawait(inode->i_mapping);

	spin_lock(&inode_lock);
	inode->i_state &= ~I_LOCK;
	if (!(inode->i_state & I_FREEING)) {
		struct list_head *to;
		if (inode->i_state & I_DIRTY)
			to = &inode->i_sb->s_dirty;
		else if (atomic_read(&inode->i_count))
			to = &inode_in_use;
		else
			to = &inode_unused;
		list_del(&inode->i_list);
		list_add(&inode->i_list, to);
	}
	wake_up(&inode->i_wait);
}

static inline void sync_one(struct inode *inode, int sync)
{
	if (inode->i_state & I_LOCK) {
		__iget(inode);
		spin_unlock(&inode_lock);
		__wait_on_inode(inode);
		iput(inode);
		spin_lock(&inode_lock);
	} else {
		__sync_one(inode, sync);
	}
}

static inline void sync_list(struct list_head *head)
{
	struct list_head * tmp;

	while ((tmp = head->prev) != head) 
		__sync_one(list_entry(tmp, struct inode, i_list), 0);
}

static inline void wait_on_locked(struct list_head *head)
{
	struct list_head * tmp;
	while ((tmp = head->prev) != head) {
		struct inode *inode = list_entry(tmp, struct inode, i_list);
		__iget(inode);
		spin_unlock(&inode_lock);
		__wait_on_inode(inode);
		iput(inode);
		spin_lock(&inode_lock);
	}
}

static inline int try_to_sync_unused_list(struct list_head *head, int nr_inodes)
{
	struct list_head *tmp = head;
	struct inode *inode;

	while (nr_inodes && (tmp = tmp->prev) != head) {
		inode = list_entry(tmp, struct inode, i_list);

		if (!atomic_read(&inode->i_count)) {
			__sync_one(inode, 0);
			nr_inodes--;

			/* 
			 * __sync_one moved the inode to another list,
			 * so we have to start looking from the list head.
			 */
			tmp = head;
		}
	}

	return nr_inodes;
}

void sync_inodes_sb(struct super_block *sb)
{
	spin_lock(&inode_lock);
	while (!list_empty(&sb->s_dirty)||!list_empty(&sb->s_locked_inodes)) {
		sync_list(&sb->s_dirty);
		wait_on_locked(&sb->s_locked_inodes);
	}
	spin_unlock(&inode_lock);
}

/*
 * Note:
 * We don't need to grab a reference to superblock here. If it has non-empty
 * ->s_dirty it's hadn't been killed yet and kill_super() won't proceed
 * past sync_inodes_sb() until both ->s_dirty and ->s_locked_inodes are
 * empty. Since __sync_one() regains inode_lock before it finally moves
 * inode from superblock lists we are OK.
 */

void sync_unlocked_inodes(void)
{
	struct super_block * sb;
	spin_lock(&inode_lock);
	spin_lock(&sb_lock);
	sb = sb_entry(super_blocks.next);
	for (; sb != sb_entry(&super_blocks); sb = sb_entry(sb->s_list.next)) {
		if (!list_empty(&sb->s_dirty)) {
			spin_unlock(&sb_lock);
			sync_list(&sb->s_dirty);
			spin_lock(&sb_lock);
		}
	}
	spin_unlock(&sb_lock);
	spin_unlock(&inode_lock);
}

/*
 * Find a superblock with inodes that need to be synced
 */

static struct super_block *get_super_to_sync(void)
{
	struct list_head *p;
restart:
	spin_lock(&inode_lock);
	spin_lock(&sb_lock);
	list_for_each(p, &super_blocks) {
		struct super_block *s = list_entry(p,struct super_block,s_list);
		if (list_empty(&s->s_dirty) && list_empty(&s->s_locked_inodes))
			continue;
		s->s_count++;
		spin_unlock(&sb_lock);
		spin_unlock(&inode_lock);
		down_read(&s->s_umount);
		if (!s->s_root) {
			drop_super(s);
			goto restart;
		}
		return s;
	}
	spin_unlock(&sb_lock);
	spin_unlock(&inode_lock);
	return NULL;
}

/**
 *	sync_inodes
 *	@dev: device to sync the inodes from.
 *
 *	sync_inodes goes through the super block's dirty list, 
 *	writes them out, and puts them back on the normal list.
 */

void sync_inodes(kdev_t dev)
{
	struct super_block * s;

	/*
	 * Search the super_blocks array for the device(s) to sync.
	 */
	if (dev) {
		if ((s = get_super(dev)) != NULL) {
			sync_inodes_sb(s);
			drop_super(s);
		}
	} else {
		while ((s = get_super_to_sync()) != NULL) {
			sync_inodes_sb(s);
			drop_super(s);
		}
	}
}

static void try_to_sync_unused_inodes(void * arg)
{
	struct super_block * sb;
	int nr_inodes = inodes_stat.nr_unused;

	spin_lock(&inode_lock);
	spin_lock(&sb_lock);
	sb = sb_entry(super_blocks.next);
	for (; nr_inodes && sb != sb_entry(&super_blocks); sb = sb_entry(sb->s_list.next)) {
		if (list_empty(&sb->s_dirty))
			continue;
		spin_unlock(&sb_lock);
		nr_inodes = try_to_sync_unused_list(&sb->s_dirty, nr_inodes);
		spin_lock(&sb_lock);
	}
	spin_unlock(&sb_lock);
	spin_unlock(&inode_lock);
}